ftopal/huggingface-models-raw · Datasets at Hugging Face

pipeline_tag stringclasses 48 values	library_name stringclasses 205 values	text stringlengths 0 18.3M	metadata stringlengths 2 1.07B	id stringlengths 5 122	last_modified null	tags sequencelengths 1 1.84k	sha null	created_at stringlengths 25 25
automatic-speech-recognition	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper-bs-cs-train-aug-test-aug2 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_11_0 dataset. It achieves the following results on the evaluation set: - Loss: 0.6875 - Wer: 54.1533 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Wer \| \|:-------------:\|:------:\|:----:\|:---------------:\|:-------:\| \| 0.6476 \| 1.4440 \| 1000 \| 0.8181 \| 63.1377 \| \| 0.4531 \| 2.8881 \| 2000 \| 0.7081 \| 56.8700 \| \| 0.3048 \| 4.3321 \| 3000 \| 0.6906 \| 54.5125 \| \| 0.2841 \| 5.7762 \| 4000 \| 0.6875 \| 54.1533 \| ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["common_voice_11_0"], "metrics": ["wer"], "base_model": "openai/whisper-base", "model-index": [{"name": "whisper-bs-cs-train-aug-test-aug2", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "common_voice_11_0", "type": "common_voice_11_0", "config": "cs", "split": "None", "args": "cs"}, "metrics": [{"type": "wer", "value": 54.15331344163259, "name": "Wer"}]}]}]}	LadislavVasina1/whisper-bs-cs-train-aug-test-aug2	null	[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:common_voice_11_0", "base_model:openai/whisper-base", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:28:56+00:00
null	null		{}	mselek/results	null	[ "safetensors", "region:us" ]	null	2024-04-29T22:29:20+00:00
null	null		{}	ivykopal/mlqa_en_prompt_100k	null	[ "region:us" ]	null	2024-04-29T22:29:56+00:00
text-classification	transformers		{}	JibreelGG/railisfinetune	null	[ "transformers", "safetensors", "deberta-v2", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:30:29+00:00
null	null		{}	Mirgan/fine-tune-blip2-cxr-8bits	null	[ "region:us" ]	null	2024-04-29T22:30:41+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H4ac-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H4ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5598 - F1 Score: 0.7325 - Accuracy: 0.7323 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6448 \| 0.93 \| 200 \| 0.5977 \| 0.6750 \| 0.6774 \| \| 0.5934 \| 1.87 \| 400 \| 0.5784 \| 0.7057 \| 0.7067 \| \| 0.5712 \| 2.8 \| 600 \| 0.5560 \| 0.7261 \| 0.7258 \| \| 0.5629 \| 3.74 \| 800 \| 0.5547 \| 0.7249 \| 0.7249 \| \| 0.5589 \| 4.67 \| 1000 \| 0.5502 \| 0.7271 \| 0.7270 \| \| 0.5499 \| 5.61 \| 1200 \| 0.5559 \| 0.7240 \| 0.7246 \| \| 0.551 \| 6.54 \| 1400 \| 0.5597 \| 0.7173 \| 0.7185 \| \| 0.5402 \| 7.48 \| 1600 \| 0.5439 \| 0.7349 \| 0.7346 \| \| 0.5464 \| 8.41 \| 1800 \| 0.5390 \| 0.7361 \| 0.7358 \| \| 0.5401 \| 9.35 \| 2000 \| 0.5496 \| 0.7384 \| 0.7387 \| \| 0.5357 \| 10.28 \| 2200 \| 0.5373 \| 0.7401 \| 0.7399 \| \| 0.5386 \| 11.21 \| 2400 \| 0.5427 \| 0.7357 \| 0.7358 \| \| 0.5311 \| 12.15 \| 2600 \| 0.5496 \| 0.7340 \| 0.7346 \| \| 0.5302 \| 13.08 \| 2800 \| 0.5625 \| 0.7271 \| 0.7284 \| \| 0.5322 \| 14.02 \| 3000 \| 0.5350 \| 0.7446 \| 0.7443 \| \| 0.5288 \| 14.95 \| 3200 \| 0.5383 \| 0.7443 \| 0.7443 \| \| 0.5242 \| 15.89 \| 3400 \| 0.5460 \| 0.7360 \| 0.7364 \| \| 0.5243 \| 16.82 \| 3600 \| 0.5364 \| 0.7473 \| 0.7472 \| \| 0.5272 \| 17.76 \| 3800 \| 0.5465 \| 0.7388 \| 0.7393 \| \| 0.5226 \| 18.69 \| 4000 \| 0.5353 \| 0.7442 \| 0.7440 \| \| 0.5204 \| 19.63 \| 4200 \| 0.5360 \| 0.7433 \| 0.7434 \| \| 0.5203 \| 20.56 \| 4400 \| 0.5290 \| 0.7466 \| 0.7463 \| \| 0.5176 \| 21.5 \| 4600 \| 0.5557 \| 0.7321 \| 0.7334 \| \| 0.5193 \| 22.43 \| 4800 \| 0.5312 \| 0.7449 \| 0.7446 \| \| 0.5161 \| 23.36 \| 5000 \| 0.5463 \| 0.7391 \| 0.7396 \| \| 0.5177 \| 24.3 \| 5200 \| 0.5280 \| 0.7440 \| 0.7437 \| \| 0.5157 \| 25.23 \| 5400 \| 0.5303 \| 0.7484 \| 0.7481 \| \| 0.5148 \| 26.17 \| 5600 \| 0.5290 \| 0.7446 \| 0.7443 \| \| 0.5149 \| 27.1 \| 5800 \| 0.5310 \| 0.7478 \| 0.7475 \| \| 0.5096 \| 28.04 \| 6000 \| 0.5305 \| 0.7481 \| 0.7478 \| \| 0.5144 \| 28.97 \| 6200 \| 0.5411 \| 0.7469 \| 0.7472 \| \| 0.5114 \| 29.91 \| 6400 \| 0.5305 \| 0.7472 \| 0.7469 \| \| 0.5123 \| 30.84 \| 6600 \| 0.5431 \| 0.7453 \| 0.7457 \| \| 0.5094 \| 31.78 \| 6800 \| 0.5307 \| 0.7487 \| 0.7484 \| \| 0.51 \| 32.71 \| 7000 \| 0.5292 \| 0.7487 \| 0.7484 \| \| 0.5084 \| 33.64 \| 7200 \| 0.5346 \| 0.7492 \| 0.7493 \| \| 0.5087 \| 34.58 \| 7400 \| 0.5309 \| 0.7515 \| 0.7513 \| \| 0.5094 \| 35.51 \| 7600 \| 0.5279 \| 0.7510 \| 0.7507 \| \| 0.5048 \| 36.45 \| 7800 \| 0.5297 \| 0.7490 \| 0.7487 \| \| 0.5106 \| 37.38 \| 8000 \| 0.5368 \| 0.7487 \| 0.7487 \| \| 0.5045 \| 38.32 \| 8200 \| 0.5312 \| 0.7521 \| 0.7519 \| \| 0.5049 \| 39.25 \| 8400 \| 0.5283 \| 0.7507 \| 0.7504 \| \| 0.5081 \| 40.19 \| 8600 \| 0.5302 \| 0.7478 \| 0.7475 \| \| 0.5065 \| 41.12 \| 8800 \| 0.5312 \| 0.7500 \| 0.7499 \| \| 0.5065 \| 42.06 \| 9000 \| 0.5302 \| 0.7510 \| 0.7507 \| \| 0.5065 \| 42.99 \| 9200 \| 0.5344 \| 0.7508 \| 0.7507 \| \| 0.5066 \| 43.93 \| 9400 \| 0.5328 \| 0.7511 \| 0.7510 \| \| 0.5042 \| 44.86 \| 9600 \| 0.5297 \| 0.7498 \| 0.7496 \| \| 0.5028 \| 45.79 \| 9800 \| 0.5307 \| 0.7501 \| 0.7499 \| \| 0.5057 \| 46.73 \| 10000 \| 0.5316 \| 0.7515 \| 0.7513 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H4ac-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H4ac-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:33:10+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3) dataset. It achieves the following results on the evaluation set: - Loss: 0.3581 - F1 Score: 0.8804 - Accuracy: 0.8804 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4331 \| 2.13 \| 200 \| 0.3621 \| 0.8516 \| 0.8517 \| \| 0.2958 \| 4.26 \| 400 \| 0.3346 \| 0.8684 \| 0.8684 \| \| 0.2657 \| 6.38 \| 600 \| 0.3485 \| 0.8597 \| 0.8597 \| \| 0.2523 \| 8.51 \| 800 \| 0.3201 \| 0.8731 \| 0.8731 \| \| 0.2368 \| 10.64 \| 1000 \| 0.3464 \| 0.8653 \| 0.8657 \| \| 0.2238 \| 12.77 \| 1200 \| 0.3192 \| 0.8771 \| 0.8771 \| \| 0.2103 \| 14.89 \| 1400 \| 0.3609 \| 0.8567 \| 0.8570 \| \| 0.1988 \| 17.02 \| 1600 \| 0.3454 \| 0.8771 \| 0.8771 \| \| 0.185 \| 19.15 \| 1800 \| 0.3556 \| 0.8764 \| 0.8764 \| \| 0.1694 \| 21.28 \| 2000 \| 0.3875 \| 0.8736 \| 0.8737 \| \| 0.1635 \| 23.4 \| 2200 \| 0.3822 \| 0.8731 \| 0.8731 \| \| 0.1469 \| 25.53 \| 2400 \| 0.3999 \| 0.8804 \| 0.8804 \| \| 0.1385 \| 27.66 \| 2600 \| 0.4115 \| 0.8677 \| 0.8677 \| \| 0.1288 \| 29.79 \| 2800 \| 0.4386 \| 0.8634 \| 0.8637 \| \| 0.1228 \| 31.91 \| 3000 \| 0.4146 \| 0.8643 \| 0.8644 \| \| 0.1082 \| 34.04 \| 3200 \| 0.4470 \| 0.8670 \| 0.8671 \| \| 0.103 \| 36.17 \| 3400 \| 0.4991 \| 0.8519 \| 0.8524 \| \| 0.0932 \| 38.3 \| 3600 \| 0.5066 \| 0.8657 \| 0.8657 \| \| 0.0896 \| 40.43 \| 3800 \| 0.5448 \| 0.8640 \| 0.8644 \| \| 0.0826 \| 42.55 \| 4000 \| 0.6343 \| 0.8518 \| 0.8524 \| \| 0.0738 \| 44.68 \| 4200 \| 0.5258 \| 0.8710 \| 0.8711 \| \| 0.072 \| 46.81 \| 4400 \| 0.5121 \| 0.8711 \| 0.8711 \| \| 0.0696 \| 48.94 \| 4600 \| 0.5634 \| 0.8683 \| 0.8684 \| \| 0.0647 \| 51.06 \| 4800 \| 0.5905 \| 0.8643 \| 0.8644 \| \| 0.0609 \| 53.19 \| 5000 \| 0.6529 \| 0.8588 \| 0.8591 \| \| 0.0559 \| 55.32 \| 5200 \| 0.5790 \| 0.8751 \| 0.8751 \| \| 0.0521 \| 57.45 \| 5400 \| 0.6104 \| 0.8716 \| 0.8717 \| \| 0.0484 \| 59.57 \| 5600 \| 0.6275 \| 0.8723 \| 0.8724 \| \| 0.048 \| 61.7 \| 5800 \| 0.6447 \| 0.8622 \| 0.8624 \| \| 0.0437 \| 63.83 \| 6000 \| 0.7093 \| 0.8578 \| 0.8584 \| \| 0.0476 \| 65.96 \| 6200 \| 0.6825 \| 0.8702 \| 0.8704 \| \| 0.0394 \| 68.09 \| 6400 \| 0.6768 \| 0.8690 \| 0.8691 \| \| 0.0404 \| 70.21 \| 6600 \| 0.6940 \| 0.8702 \| 0.8704 \| \| 0.0373 \| 72.34 \| 6800 \| 0.6746 \| 0.8751 \| 0.8751 \| \| 0.0381 \| 74.47 \| 7000 \| 0.7295 \| 0.8607 \| 0.8611 \| \| 0.0348 \| 76.6 \| 7200 \| 0.7110 \| 0.8757 \| 0.8758 \| \| 0.0318 \| 78.72 \| 7400 \| 0.7322 \| 0.8703 \| 0.8704 \| \| 0.029 \| 80.85 \| 7600 \| 0.8020 \| 0.8642 \| 0.8644 \| \| 0.0314 \| 82.98 \| 7800 \| 0.7269 \| 0.8737 \| 0.8737 \| \| 0.0283 \| 85.11 \| 8000 \| 0.7380 \| 0.8737 \| 0.8737 \| \| 0.0272 \| 87.23 \| 8200 \| 0.7716 \| 0.8710 \| 0.8711 \| \| 0.0237 \| 89.36 \| 8400 \| 0.8220 \| 0.8777 \| 0.8778 \| \| 0.0273 \| 91.49 \| 8600 \| 0.7853 \| 0.8716 \| 0.8717 \| \| 0.0255 \| 93.62 \| 8800 \| 0.8045 \| 0.8737 \| 0.8737 \| \| 0.0252 \| 95.74 \| 9000 \| 0.8016 \| 0.8723 \| 0.8724 \| \| 0.0233 \| 97.87 \| 9200 \| 0.8163 \| 0.8675 \| 0.8677 \| \| 0.023 \| 100.0 \| 9400 \| 0.8253 \| 0.8683 \| 0.8684 \| \| 0.022 \| 102.13 \| 9600 \| 0.8238 \| 0.8723 \| 0.8724 \| \| 0.0206 \| 104.26 \| 9800 \| 0.8230 \| 0.8703 \| 0.8704 \| \| 0.0221 \| 106.38 \| 10000 \| 0.8229 \| 0.8703 \| 0.8704 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:33:10+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/6my36hg	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T22:33:26+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H4ac-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H4ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5616 - F1 Score: 0.7387 - Accuracy: 0.7384 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6227 \| 0.93 \| 200 \| 0.5658 \| 0.7100 \| 0.7097 \| \| 0.5654 \| 1.87 \| 400 \| 0.5636 \| 0.7194 \| 0.7208 \| \| 0.5489 \| 2.8 \| 600 \| 0.5446 \| 0.7351 \| 0.7349 \| \| 0.5409 \| 3.74 \| 800 \| 0.5364 \| 0.7366 \| 0.7364 \| \| 0.5353 \| 4.67 \| 1000 \| 0.5306 \| 0.7455 \| 0.7452 \| \| 0.5263 \| 5.61 \| 1200 \| 0.5509 \| 0.7324 \| 0.7337 \| \| 0.5267 \| 6.54 \| 1400 \| 0.5441 \| 0.7394 \| 0.7399 \| \| 0.5118 \| 7.48 \| 1600 \| 0.5292 \| 0.7451 \| 0.7449 \| \| 0.5188 \| 8.41 \| 1800 \| 0.5248 \| 0.7472 \| 0.7469 \| \| 0.511 \| 9.35 \| 2000 \| 0.5281 \| 0.7466 \| 0.7463 \| \| 0.5056 \| 10.28 \| 2200 \| 0.5246 \| 0.7455 \| 0.7457 \| \| 0.5067 \| 11.21 \| 2400 \| 0.5307 \| 0.7456 \| 0.7457 \| \| 0.4972 \| 12.15 \| 2600 \| 0.5389 \| 0.7455 \| 0.7457 \| \| 0.4958 \| 13.08 \| 2800 \| 0.5385 \| 0.7460 \| 0.7457 \| \| 0.4972 \| 14.02 \| 3000 \| 0.5267 \| 0.7516 \| 0.7513 \| \| 0.4929 \| 14.95 \| 3200 \| 0.5233 \| 0.7519 \| 0.7516 \| \| 0.4863 \| 15.89 \| 3400 \| 0.5245 \| 0.7516 \| 0.7513 \| \| 0.4842 \| 16.82 \| 3600 \| 0.5337 \| 0.7439 \| 0.7437 \| \| 0.4867 \| 17.76 \| 3800 \| 0.5509 \| 0.7396 \| 0.7408 \| \| 0.48 \| 18.69 \| 4000 \| 0.5238 \| 0.7542 \| 0.7540 \| \| 0.4795 \| 19.63 \| 4200 \| 0.5206 \| 0.7551 \| 0.7548 \| \| 0.4768 \| 20.56 \| 4400 \| 0.5198 \| 0.7481 \| 0.7478 \| \| 0.4728 \| 21.5 \| 4600 \| 0.5364 \| 0.7488 \| 0.7490 \| \| 0.4729 \| 22.43 \| 4800 \| 0.5249 \| 0.7520 \| 0.7519 \| \| 0.469 \| 23.36 \| 5000 \| 0.5293 \| 0.7569 \| 0.7566 \| \| 0.4714 \| 24.3 \| 5200 \| 0.5234 \| 0.7568 \| 0.7566 \| \| 0.4658 \| 25.23 \| 5400 \| 0.5253 \| 0.7538 \| 0.7537 \| \| 0.4627 \| 26.17 \| 5600 \| 0.5303 \| 0.7448 \| 0.7449 \| \| 0.4634 \| 27.1 \| 5800 \| 0.5301 \| 0.7495 \| 0.7493 \| \| 0.4572 \| 28.04 \| 6000 \| 0.5336 \| 0.7560 \| 0.7557 \| \| 0.4611 \| 28.97 \| 6200 \| 0.5301 \| 0.7557 \| 0.7554 \| \| 0.4555 \| 29.91 \| 6400 \| 0.5358 \| 0.7499 \| 0.7496 \| \| 0.4568 \| 30.84 \| 6600 \| 0.5380 \| 0.7554 \| 0.7551 \| \| 0.456 \| 31.78 \| 6800 \| 0.5299 \| 0.7571 \| 0.7569 \| \| 0.4513 \| 32.71 \| 7000 \| 0.5298 \| 0.7529 \| 0.7528 \| \| 0.4524 \| 33.64 \| 7200 \| 0.5345 \| 0.7511 \| 0.7510 \| \| 0.4495 \| 34.58 \| 7400 \| 0.5313 \| 0.7571 \| 0.7569 \| \| 0.4496 \| 35.51 \| 7600 \| 0.5316 \| 0.7542 \| 0.7540 \| \| 0.4455 \| 36.45 \| 7800 \| 0.5359 \| 0.7604 \| 0.7601 \| \| 0.4474 \| 37.38 \| 8000 \| 0.5407 \| 0.7571 \| 0.7569 \| \| 0.4471 \| 38.32 \| 8200 \| 0.5328 \| 0.7595 \| 0.7592 \| \| 0.447 \| 39.25 \| 8400 \| 0.5322 \| 0.7532 \| 0.7531 \| \| 0.4458 \| 40.19 \| 8600 \| 0.5372 \| 0.7566 \| 0.7563 \| \| 0.4447 \| 41.12 \| 8800 \| 0.5381 \| 0.7575 \| 0.7572 \| \| 0.4407 \| 42.06 \| 9000 \| 0.5391 \| 0.7572 \| 0.7569 \| \| 0.4416 \| 42.99 \| 9200 \| 0.5400 \| 0.7598 \| 0.7595 \| \| 0.4411 \| 43.93 \| 9400 \| 0.5382 \| 0.7589 \| 0.7587 \| \| 0.4396 \| 44.86 \| 9600 \| 0.5373 \| 0.7574 \| 0.7572 \| \| 0.4371 \| 45.79 \| 9800 \| 0.5380 \| 0.7574 \| 0.7572 \| \| 0.4429 \| 46.73 \| 10000 \| 0.5382 \| 0.7610 \| 0.7607 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H4ac-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H4ac-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:33:30+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H4ac-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H4ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5538 - F1 Score: 0.7389 - Accuracy: 0.7390 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6081 \| 0.93 \| 200 \| 0.5518 \| 0.7247 \| 0.7243 \| \| 0.5526 \| 1.87 \| 400 \| 0.5545 \| 0.7313 \| 0.7326 \| \| 0.535 \| 2.8 \| 600 \| 0.5285 \| 0.7443 \| 0.7440 \| \| 0.5242 \| 3.74 \| 800 \| 0.5270 \| 0.7443 \| 0.7440 \| \| 0.5169 \| 4.67 \| 1000 \| 0.5219 \| 0.7459 \| 0.7457 \| \| 0.5062 \| 5.61 \| 1200 \| 0.5342 \| 0.7413 \| 0.7416 \| \| 0.5035 \| 6.54 \| 1400 \| 0.5216 \| 0.7489 \| 0.7487 \| \| 0.4892 \| 7.48 \| 1600 \| 0.5246 \| 0.7481 \| 0.7478 \| \| 0.4923 \| 8.41 \| 1800 \| 0.5181 \| 0.7452 \| 0.7449 \| \| 0.4809 \| 9.35 \| 2000 \| 0.5245 \| 0.7486 \| 0.7487 \| \| 0.4739 \| 10.28 \| 2200 \| 0.5253 \| 0.7489 \| 0.7487 \| \| 0.4697 \| 11.21 \| 2400 \| 0.5379 \| 0.7391 \| 0.7396 \| \| 0.4613 \| 12.15 \| 2600 \| 0.5365 \| 0.7481 \| 0.7478 \| \| 0.4538 \| 13.08 \| 2800 \| 0.5499 \| 0.7410 \| 0.7411 \| \| 0.4548 \| 14.02 \| 3000 \| 0.5488 \| 0.7512 \| 0.7516 \| \| 0.4436 \| 14.95 \| 3200 \| 0.5493 \| 0.7460 \| 0.7457 \| \| 0.435 \| 15.89 \| 3400 \| 0.5366 \| 0.7544 \| 0.7545 \| \| 0.429 \| 16.82 \| 3600 \| 0.5443 \| 0.7417 \| 0.7416 \| \| 0.4287 \| 17.76 \| 3800 \| 0.5782 \| 0.7348 \| 0.7358 \| \| 0.4189 \| 18.69 \| 4000 \| 0.5448 \| 0.7533 \| 0.7531 \| \| 0.4162 \| 19.63 \| 4200 \| 0.5436 \| 0.7433 \| 0.7431 \| \| 0.4075 \| 20.56 \| 4400 \| 0.5440 \| 0.7493 \| 0.7493 \| \| 0.3997 \| 21.5 \| 4600 \| 0.5583 \| 0.7519 \| 0.7516 \| \| 0.3933 \| 22.43 \| 4800 \| 0.5815 \| 0.7442 \| 0.7446 \| \| 0.393 \| 23.36 \| 5000 \| 0.5817 \| 0.7490 \| 0.7487 \| \| 0.3883 \| 24.3 \| 5200 \| 0.5909 \| 0.7499 \| 0.7496 \| \| 0.3812 \| 25.23 \| 5400 \| 0.5716 \| 0.7493 \| 0.7490 \| \| 0.3746 \| 26.17 \| 5600 \| 0.5996 \| 0.7464 \| 0.7463 \| \| 0.3707 \| 27.1 \| 5800 \| 0.5904 \| 0.7422 \| 0.7419 \| \| 0.3625 \| 28.04 \| 6000 \| 0.5976 \| 0.7505 \| 0.7504 \| \| 0.3631 \| 28.97 \| 6200 \| 0.5873 \| 0.7443 \| 0.7440 \| \| 0.3572 \| 29.91 \| 6400 \| 0.6049 \| 0.7383 \| 0.7381 \| \| 0.356 \| 30.84 \| 6600 \| 0.5934 \| 0.7442 \| 0.7440 \| \| 0.3527 \| 31.78 \| 6800 \| 0.5961 \| 0.7450 \| 0.7452 \| \| 0.3467 \| 32.71 \| 7000 \| 0.6047 \| 0.7436 \| 0.7434 \| \| 0.3442 \| 33.64 \| 7200 \| 0.6134 \| 0.7407 \| 0.7405 \| \| 0.34 \| 34.58 \| 7400 \| 0.6167 \| 0.7477 \| 0.7475 \| \| 0.3383 \| 35.51 \| 7600 \| 0.5981 \| 0.7407 \| 0.7405 \| \| 0.3291 \| 36.45 \| 7800 \| 0.6243 \| 0.7434 \| 0.7431 \| \| 0.3274 \| 37.38 \| 8000 \| 0.6363 \| 0.7437 \| 0.7434 \| \| 0.3272 \| 38.32 \| 8200 \| 0.6318 \| 0.7364 \| 0.7364 \| \| 0.3254 \| 39.25 \| 8400 \| 0.6307 \| 0.7409 \| 0.7408 \| \| 0.324 \| 40.19 \| 8600 \| 0.6369 \| 0.7428 \| 0.7425 \| \| 0.3238 \| 41.12 \| 8800 \| 0.6378 \| 0.7453 \| 0.7452 \| \| 0.3152 \| 42.06 \| 9000 \| 0.6401 \| 0.7458 \| 0.7457 \| \| 0.3168 \| 42.99 \| 9200 \| 0.6474 \| 0.7425 \| 0.7422 \| \| 0.3152 \| 43.93 \| 9400 \| 0.6440 \| 0.7404 \| 0.7402 \| \| 0.3136 \| 44.86 \| 9600 \| 0.6442 \| 0.7400 \| 0.7399 \| \| 0.3101 \| 45.79 \| 9800 \| 0.6478 \| 0.7450 \| 0.7449 \| \| 0.3182 \| 46.73 \| 10000 \| 0.6442 \| 0.7439 \| 0.7437 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H4ac-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H4ac-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:33:30+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K79me3-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K79me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K79me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4351 - F1 Score: 0.8097 - Accuracy: 0.8096 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5289 \| 1.1 \| 200 \| 0.4655 \| 0.7962 \| 0.7961 \| \| 0.4736 \| 2.21 \| 400 \| 0.4711 \| 0.7904 \| 0.7926 \| \| 0.4658 \| 3.31 \| 600 \| 0.4509 \| 0.8034 \| 0.8044 \| \| 0.4533 \| 4.42 \| 800 \| 0.4448 \| 0.8066 \| 0.8076 \| \| 0.4528 \| 5.52 \| 1000 \| 0.4530 \| 0.7972 \| 0.7992 \| \| 0.4433 \| 6.63 \| 1200 \| 0.4542 \| 0.8020 \| 0.8041 \| \| 0.4454 \| 7.73 \| 1400 \| 0.4403 \| 0.8083 \| 0.8096 \| \| 0.439 \| 8.84 \| 1600 \| 0.4545 \| 0.8003 \| 0.8027 \| \| 0.4355 \| 9.94 \| 1800 \| 0.4351 \| 0.8177 \| 0.8176 \| \| 0.4344 \| 11.05 \| 2000 \| 0.4376 \| 0.8087 \| 0.8100 \| \| 0.4338 \| 12.15 \| 2200 \| 0.4301 \| 0.8167 \| 0.8169 \| \| 0.4272 \| 13.26 \| 2400 \| 0.4300 \| 0.8168 \| 0.8173 \| \| 0.4274 \| 14.36 \| 2600 \| 0.4305 \| 0.8138 \| 0.8141 \| \| 0.4282 \| 15.47 \| 2800 \| 0.4323 \| 0.8138 \| 0.8148 \| \| 0.4228 \| 16.57 \| 3000 \| 0.4306 \| 0.8184 \| 0.8183 \| \| 0.4252 \| 17.68 \| 3200 \| 0.4266 \| 0.8161 \| 0.8162 \| \| 0.4178 \| 18.78 \| 3400 \| 0.4305 \| 0.8170 \| 0.8176 \| \| 0.4178 \| 19.89 \| 3600 \| 0.4257 \| 0.8165 \| 0.8169 \| \| 0.418 \| 20.99 \| 3800 \| 0.4340 \| 0.8162 \| 0.8169 \| \| 0.4157 \| 22.1 \| 4000 \| 0.4258 \| 0.8159 \| 0.8166 \| \| 0.4149 \| 23.2 \| 4200 \| 0.4268 \| 0.8176 \| 0.8180 \| \| 0.4158 \| 24.31 \| 4400 \| 0.4398 \| 0.8099 \| 0.8117 \| \| 0.4075 \| 25.41 \| 4600 \| 0.4275 \| 0.8176 \| 0.8180 \| \| 0.4134 \| 26.52 \| 4800 \| 0.4275 \| 0.8130 \| 0.8135 \| \| 0.4144 \| 27.62 \| 5000 \| 0.4281 \| 0.8160 \| 0.8169 \| \| 0.406 \| 28.73 \| 5200 \| 0.4276 \| 0.8117 \| 0.8124 \| \| 0.4059 \| 29.83 \| 5400 \| 0.4247 \| 0.8151 \| 0.8155 \| \| 0.4056 \| 30.94 \| 5600 \| 0.4279 \| 0.8113 \| 0.8117 \| \| 0.4063 \| 32.04 \| 5800 \| 0.4252 \| 0.8153 \| 0.8155 \| \| 0.4043 \| 33.15 \| 6000 \| 0.4262 \| 0.8153 \| 0.8159 \| \| 0.4057 \| 34.25 \| 6200 \| 0.4269 \| 0.8130 \| 0.8135 \| \| 0.4015 \| 35.36 \| 6400 \| 0.4291 \| 0.8160 \| 0.8166 \| \| 0.4067 \| 36.46 \| 6600 \| 0.4256 \| 0.8128 \| 0.8131 \| \| 0.4048 \| 37.57 \| 6800 \| 0.4282 \| 0.8121 \| 0.8128 \| \| 0.4019 \| 38.67 \| 7000 \| 0.4293 \| 0.8166 \| 0.8173 \| \| 0.4011 \| 39.78 \| 7200 \| 0.4268 \| 0.8141 \| 0.8145 \| \| 0.4029 \| 40.88 \| 7400 \| 0.4259 \| 0.8148 \| 0.8152 \| \| 0.402 \| 41.99 \| 7600 \| 0.4275 \| 0.8130 \| 0.8135 \| \| 0.3994 \| 43.09 \| 7800 \| 0.4304 \| 0.8147 \| 0.8152 \| \| 0.3999 \| 44.2 \| 8000 \| 0.4306 \| 0.8117 \| 0.8124 \| \| 0.3982 \| 45.3 \| 8200 \| 0.4267 \| 0.8145 \| 0.8148 \| \| 0.3986 \| 46.41 \| 8400 \| 0.4283 \| 0.8130 \| 0.8135 \| \| 0.4009 \| 47.51 \| 8600 \| 0.4303 \| 0.8151 \| 0.8159 \| \| 0.3988 \| 48.62 \| 8800 \| 0.4304 \| 0.8117 \| 0.8124 \| \| 0.3943 \| 49.72 \| 9000 \| 0.4295 \| 0.8115 \| 0.8121 \| \| 0.4009 \| 50.83 \| 9200 \| 0.4309 \| 0.8133 \| 0.8141 \| \| 0.3995 \| 51.93 \| 9400 \| 0.4287 \| 0.8111 \| 0.8117 \| \| 0.3994 \| 53.04 \| 9600 \| 0.4285 \| 0.8118 \| 0.8124 \| \| 0.396 \| 54.14 \| 9800 \| 0.4284 \| 0.8122 \| 0.8128 \| \| 0.3996 \| 55.25 \| 10000 \| 0.4297 \| 0.8121 \| 0.8128 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K79me3-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K79me3-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:34:39+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K79me3-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K79me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K79me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4277 - F1 Score: 0.8227 - Accuracy: 0.8228 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5134 \| 1.1 \| 200 \| 0.4604 \| 0.7997 \| 0.7996 \| \| 0.4626 \| 2.21 \| 400 \| 0.4493 \| 0.8046 \| 0.8055 \| \| 0.4525 \| 3.31 \| 600 \| 0.4420 \| 0.8109 \| 0.8121 \| \| 0.4366 \| 4.42 \| 800 \| 0.4367 \| 0.8125 \| 0.8135 \| \| 0.4308 \| 5.52 \| 1000 \| 0.4315 \| 0.8173 \| 0.8180 \| \| 0.4207 \| 6.63 \| 1200 \| 0.4432 \| 0.8085 \| 0.8100 \| \| 0.4219 \| 7.73 \| 1400 \| 0.4409 \| 0.8097 \| 0.8117 \| \| 0.4137 \| 8.84 \| 1600 \| 0.4629 \| 0.8007 \| 0.8037 \| \| 0.4086 \| 9.94 \| 1800 \| 0.4282 \| 0.8169 \| 0.8169 \| \| 0.406 \| 11.05 \| 2000 \| 0.4322 \| 0.8110 \| 0.8114 \| \| 0.4041 \| 12.15 \| 2200 \| 0.4259 \| 0.8238 \| 0.8239 \| \| 0.3954 \| 13.26 \| 2400 \| 0.4300 \| 0.8175 \| 0.8176 \| \| 0.3953 \| 14.36 \| 2600 \| 0.4303 \| 0.8187 \| 0.8190 \| \| 0.3954 \| 15.47 \| 2800 \| 0.4260 \| 0.8200 \| 0.8204 \| \| 0.3866 \| 16.57 \| 3000 \| 0.4336 \| 0.8125 \| 0.8124 \| \| 0.3886 \| 17.68 \| 3200 \| 0.4279 \| 0.8199 \| 0.8200 \| \| 0.3812 \| 18.78 \| 3400 \| 0.4385 \| 0.8130 \| 0.8141 \| \| 0.3792 \| 19.89 \| 3600 \| 0.4264 \| 0.8219 \| 0.8221 \| \| 0.3803 \| 20.99 \| 3800 \| 0.4366 \| 0.8119 \| 0.8124 \| \| 0.3765 \| 22.1 \| 4000 \| 0.4298 \| 0.8173 \| 0.8173 \| \| 0.3751 \| 23.2 \| 4200 \| 0.4333 \| 0.8198 \| 0.8200 \| \| 0.3722 \| 24.31 \| 4400 \| 0.4384 \| 0.8153 \| 0.8162 \| \| 0.3634 \| 25.41 \| 4600 \| 0.4442 \| 0.8175 \| 0.8173 \| \| 0.3699 \| 26.52 \| 4800 \| 0.4434 \| 0.8137 \| 0.8141 \| \| 0.3687 \| 27.62 \| 5000 \| 0.4336 \| 0.8183 \| 0.8190 \| \| 0.3593 \| 28.73 \| 5200 \| 0.4379 \| 0.8138 \| 0.8141 \| \| 0.3587 \| 29.83 \| 5400 \| 0.4383 \| 0.8136 \| 0.8135 \| \| 0.3577 \| 30.94 \| 5600 \| 0.4391 \| 0.8185 \| 0.8187 \| \| 0.3565 \| 32.04 \| 5800 \| 0.4402 \| 0.8117 \| 0.8117 \| \| 0.3555 \| 33.15 \| 6000 \| 0.4377 \| 0.8184 \| 0.8190 \| \| 0.3528 \| 34.25 \| 6200 \| 0.4452 \| 0.8170 \| 0.8169 \| \| 0.3509 \| 35.36 \| 6400 \| 0.4499 \| 0.8194 \| 0.8204 \| \| 0.3554 \| 36.46 \| 6600 \| 0.4392 \| 0.8191 \| 0.8193 \| \| 0.3481 \| 37.57 \| 6800 \| 0.4417 \| 0.8178 \| 0.8183 \| \| 0.3451 \| 38.67 \| 7000 \| 0.4459 \| 0.8158 \| 0.8166 \| \| 0.3469 \| 39.78 \| 7200 \| 0.4445 \| 0.8145 \| 0.8148 \| \| 0.3453 \| 40.88 \| 7400 \| 0.4445 \| 0.8146 \| 0.8145 \| \| 0.3446 \| 41.99 \| 7600 \| 0.4428 \| 0.8157 \| 0.8159 \| \| 0.3417 \| 43.09 \| 7800 \| 0.4512 \| 0.8163 \| 0.8166 \| \| 0.3413 \| 44.2 \| 8000 \| 0.4491 \| 0.8176 \| 0.8183 \| \| 0.339 \| 45.3 \| 8200 \| 0.4521 \| 0.8126 \| 0.8128 \| \| 0.3387 \| 46.41 \| 8400 \| 0.4507 \| 0.8190 \| 0.8193 \| \| 0.3376 \| 47.51 \| 8600 \| 0.4561 \| 0.8173 \| 0.8180 \| \| 0.3382 \| 48.62 \| 8800 \| 0.4509 \| 0.8175 \| 0.8180 \| \| 0.3321 \| 49.72 \| 9000 \| 0.4498 \| 0.8166 \| 0.8169 \| \| 0.3391 \| 50.83 \| 9200 \| 0.4521 \| 0.8167 \| 0.8176 \| \| 0.3369 \| 51.93 \| 9400 \| 0.4501 \| 0.8155 \| 0.8159 \| \| 0.3331 \| 53.04 \| 9600 \| 0.4511 \| 0.8160 \| 0.8162 \| \| 0.3326 \| 54.14 \| 9800 \| 0.4519 \| 0.8163 \| 0.8166 \| \| 0.3354 \| 55.25 \| 10000 \| 0.4527 \| 0.8162 \| 0.8166 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K79me3-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K79me3-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:35:07+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K79me3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K79me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K79me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4507 - F1 Score: 0.8194 - Accuracy: 0.8197 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5034 \| 1.1 \| 200 \| 0.4527 \| 0.8016 \| 0.8017 \| \| 0.4532 \| 2.21 \| 400 \| 0.4417 \| 0.8117 \| 0.8124 \| \| 0.4401 \| 3.31 \| 600 \| 0.4337 \| 0.8079 \| 0.8086 \| \| 0.4227 \| 4.42 \| 800 \| 0.4331 \| 0.8155 \| 0.8162 \| \| 0.4155 \| 5.52 \| 1000 \| 0.4300 \| 0.8146 \| 0.8159 \| \| 0.4046 \| 6.63 \| 1200 \| 0.4488 \| 0.8063 \| 0.8083 \| \| 0.402 \| 7.73 \| 1400 \| 0.4522 \| 0.8022 \| 0.8051 \| \| 0.3905 \| 8.84 \| 1600 \| 0.4595 \| 0.8018 \| 0.8044 \| \| 0.3818 \| 9.94 \| 1800 \| 0.4344 \| 0.8173 \| 0.8173 \| \| 0.3747 \| 11.05 \| 2000 \| 0.4403 \| 0.8127 \| 0.8131 \| \| 0.3694 \| 12.15 \| 2200 \| 0.4358 \| 0.8202 \| 0.8211 \| \| 0.3559 \| 13.26 \| 2400 \| 0.4452 \| 0.8150 \| 0.8155 \| \| 0.3534 \| 14.36 \| 2600 \| 0.4384 \| 0.8150 \| 0.8155 \| \| 0.3474 \| 15.47 \| 2800 \| 0.4431 \| 0.8185 \| 0.8190 \| \| 0.3327 \| 16.57 \| 3000 \| 0.4609 \| 0.8108 \| 0.8107 \| \| 0.3349 \| 17.68 \| 3200 \| 0.4437 \| 0.8203 \| 0.8204 \| \| 0.3188 \| 18.78 \| 3400 \| 0.4701 \| 0.8065 \| 0.8079 \| \| 0.3131 \| 19.89 \| 3600 \| 0.4559 \| 0.8171 \| 0.8176 \| \| 0.3114 \| 20.99 \| 3800 \| 0.4827 \| 0.8121 \| 0.8124 \| \| 0.3021 \| 22.1 \| 4000 \| 0.4816 \| 0.8199 \| 0.8197 \| \| 0.2955 \| 23.2 \| 4200 \| 0.4813 \| 0.8139 \| 0.8141 \| \| 0.2872 \| 24.31 \| 4400 \| 0.4862 \| 0.8123 \| 0.8128 \| \| 0.2768 \| 25.41 \| 4600 \| 0.4948 \| 0.8153 \| 0.8152 \| \| 0.2785 \| 26.52 \| 4800 \| 0.5160 \| 0.8091 \| 0.8096 \| \| 0.2734 \| 27.62 \| 5000 \| 0.5076 \| 0.8075 \| 0.8086 \| \| 0.2618 \| 28.73 \| 5200 \| 0.5060 \| 0.8116 \| 0.8121 \| \| 0.2563 \| 29.83 \| 5400 \| 0.5171 \| 0.8074 \| 0.8076 \| \| 0.2494 \| 30.94 \| 5600 \| 0.5232 \| 0.8151 \| 0.8155 \| \| 0.2449 \| 32.04 \| 5800 \| 0.5446 \| 0.8069 \| 0.8069 \| \| 0.2451 \| 33.15 \| 6000 \| 0.5403 \| 0.8110 \| 0.8114 \| \| 0.2342 \| 34.25 \| 6200 \| 0.5469 \| 0.8121 \| 0.8121 \| \| 0.2335 \| 35.36 \| 6400 \| 0.5858 \| 0.8135 \| 0.8141 \| \| 0.233 \| 36.46 \| 6600 \| 0.5532 \| 0.8067 \| 0.8076 \| \| 0.2238 \| 37.57 \| 6800 \| 0.5736 \| 0.8126 \| 0.8128 \| \| 0.2204 \| 38.67 \| 7000 \| 0.5773 \| 0.8036 \| 0.8044 \| \| 0.2164 \| 39.78 \| 7200 \| 0.5784 \| 0.8148 \| 0.8152 \| \| 0.2121 \| 40.88 \| 7400 \| 0.5757 \| 0.8088 \| 0.8089 \| \| 0.2092 \| 41.99 \| 7600 \| 0.5637 \| 0.8097 \| 0.8096 \| \| 0.2088 \| 43.09 \| 7800 \| 0.5988 \| 0.8014 \| 0.8020 \| \| 0.2005 \| 44.2 \| 8000 \| 0.6101 \| 0.8042 \| 0.8048 \| \| 0.1994 \| 45.3 \| 8200 \| 0.6062 \| 0.8106 \| 0.8107 \| \| 0.1976 \| 46.41 \| 8400 \| 0.6074 \| 0.8042 \| 0.8044 \| \| 0.1959 \| 47.51 \| 8600 \| 0.6235 \| 0.8058 \| 0.8069 \| \| 0.1972 \| 48.62 \| 8800 \| 0.6036 \| 0.8073 \| 0.8076 \| \| 0.188 \| 49.72 \| 9000 \| 0.6267 \| 0.8074 \| 0.8079 \| \| 0.1939 \| 50.83 \| 9200 \| 0.6132 \| 0.8069 \| 0.8076 \| \| 0.1887 \| 51.93 \| 9400 \| 0.6256 \| 0.8103 \| 0.8107 \| \| 0.186 \| 53.04 \| 9600 \| 0.6270 \| 0.8066 \| 0.8069 \| \| 0.1811 \| 54.14 \| 9800 \| 0.6349 \| 0.8071 \| 0.8076 \| \| 0.185 \| 55.25 \| 10000 \| 0.6333 \| 0.8061 \| 0.8065 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K79me3-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K79me3-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:35:33+00:00
null	null		{}	Amr-h/final	null	[ "region:us" ]	null	2024-04-29T22:39:32+00:00
question-answering	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distil_final This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.5805 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 10 - eval_batch_size: 10 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 40 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 4 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 5.0926 \| 0.32 \| 10 \| 3.9348 \| \| 3.9237 \| 0.64 \| 20 \| 4.0141 \| \| 3.8084 \| 0.96 \| 30 \| 3.8194 \| \| 3.6561 \| 1.28 \| 40 \| 3.6860 \| \| 3.4836 \| 1.6 \| 50 \| 3.6023 \| \| 3.5731 \| 1.92 \| 60 \| 3.5904 \| \| 3.497 \| 2.24 \| 70 \| 3.6435 \| \| 3.34 \| 2.56 \| 80 \| 3.5359 \| \| 3.2943 \| 2.88 \| 90 \| 3.6003 \| \| 3.0902 \| 3.2 \| 100 \| 3.6634 \| \| 3.1061 \| 3.52 \| 110 \| 3.6059 \| \| 3.1395 \| 3.84 \| 120 \| 3.5805 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"language": ["ar"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-cased", "model-index": [{"name": "distil_final", "results": []}]}	gp-tar4/QA_FineTuned_DistilBert-based-uncased	null	[ "transformers", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "ar", "base_model:distilbert-base-cased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:40:54+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	BotoxBernd/SQL-Generation-mistral-7B-v0.2	null	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T22:41:02+00:00
null	null		{}	omarezz/xlm-roberta-base	null	[ "region:us" ]	null	2024-04-29T22:42:04+00:00
reinforcement-learning	null	# Q-Learning Agent playing1 FrozenLake-v1 This is a trained model of a Q-Learning agent playing FrozenLake-v1 . ## Usage ```python model = load_from_hub(repo_id="whiskeyriot/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```	{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}	whiskeyriot/q-FrozenLake-v1-4x4-noSlippery	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	null	2024-04-29T22:42:23+00:00
text-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # sentiment-analysis-model-trained This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3513 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 0.425 \| 1.0 \| 157 \| 0.3631 \| \| 0.2844 \| 2.0 \| 314 \| 0.3368 \| \| 0.2199 \| 3.0 \| 471 \| 0.3513 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "sentiment-analysis-model-trained", "results": []}]}	Lasghar/sentiment-analysis-model-trained	null	[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:43:23+00:00
reinforcement-learning	null	# Q-Learning Agent playing1 Taxi-v3 This is a trained model of a Q-Learning agent playing Taxi-v3 . ## Usage ```python model = load_from_hub(repo_id="whiskeyriot/Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```	{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.32 +/- 2.70", "name": "mean_reward", "verified": false}]}]}]}	whiskeyriot/Taxi-v3	null	[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	null	2024-04-29T22:46:18+00:00
feature-extraction	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	stvhuang/rcr-run-5pqr6lwp-90396-master-0_20240402T105012-ep40	null	[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:46:39+00:00
null	null		{}	Proodby/myke	null	[ "region:us" ]	null	2024-04-29T22:46:59+00:00
text-classification	transformers		{}	anonyiv/elastic_zero	null	[ "transformers", "pytorch", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:48:01+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me1-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me1) dataset. It achieves the following results on the evaluation set: - Loss: 0.5145 - F1 Score: 0.7700 - Accuracy: 0.7715 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6129 \| 1.01 \| 200 \| 0.5906 \| 0.7080 \| 0.7099 \| \| 0.5808 \| 2.02 \| 400 \| 0.5710 \| 0.7214 \| 0.7229 \| \| 0.5606 \| 3.03 \| 600 \| 0.5566 \| 0.7353 \| 0.7377 \| \| 0.5538 \| 4.04 \| 800 \| 0.5553 \| 0.7423 \| 0.7440 \| \| 0.5474 \| 5.05 \| 1000 \| 0.5473 \| 0.7448 \| 0.7462 \| \| 0.5419 \| 6.06 \| 1200 \| 0.5525 \| 0.7387 \| 0.7415 \| \| 0.5389 \| 7.07 \| 1400 \| 0.5477 \| 0.7421 \| 0.7443 \| \| 0.5381 \| 8.08 \| 1600 \| 0.5469 \| 0.7424 \| 0.7453 \| \| 0.534 \| 9.09 \| 1800 \| 0.5430 \| 0.7469 \| 0.7491 \| \| 0.5321 \| 10.1 \| 2000 \| 0.5386 \| 0.7500 \| 0.7513 \| \| 0.5303 \| 11.11 \| 2200 \| 0.5439 \| 0.7467 \| 0.7491 \| \| 0.5279 \| 12.12 \| 2400 \| 0.5388 \| 0.7526 \| 0.7538 \| \| 0.5277 \| 13.13 \| 2600 \| 0.5393 \| 0.7519 \| 0.7541 \| \| 0.5268 \| 14.14 \| 2800 \| 0.5382 \| 0.7477 \| 0.75 \| \| 0.5229 \| 15.15 \| 3000 \| 0.5414 \| 0.7474 \| 0.75 \| \| 0.5235 \| 16.16 \| 3200 \| 0.5433 \| 0.7384 \| 0.7424 \| \| 0.5193 \| 17.17 \| 3400 \| 0.5434 \| 0.7472 \| 0.7494 \| \| 0.5213 \| 18.18 \| 3600 \| 0.5320 \| 0.7540 \| 0.7554 \| \| 0.5185 \| 19.19 \| 3800 \| 0.5358 \| 0.7521 \| 0.7541 \| \| 0.5195 \| 20.2 \| 4000 \| 0.5344 \| 0.7550 \| 0.7569 \| \| 0.516 \| 21.21 \| 4200 \| 0.5442 \| 0.7406 \| 0.7443 \| \| 0.5165 \| 22.22 \| 4400 \| 0.5367 \| 0.7521 \| 0.7538 \| \| 0.5113 \| 23.23 \| 4600 \| 0.5398 \| 0.7462 \| 0.7491 \| \| 0.5195 \| 24.24 \| 4800 \| 0.5364 \| 0.7438 \| 0.7468 \| \| 0.5121 \| 25.25 \| 5000 \| 0.5343 \| 0.7585 \| 0.7598 \| \| 0.5162 \| 26.26 \| 5200 \| 0.5339 \| 0.7591 \| 0.7598 \| \| 0.5104 \| 27.27 \| 5400 \| 0.5334 \| 0.7561 \| 0.7579 \| \| 0.5132 \| 28.28 \| 5600 \| 0.5323 \| 0.7594 \| 0.7604 \| \| 0.5128 \| 29.29 \| 5800 \| 0.5433 \| 0.7392 \| 0.7434 \| \| 0.5101 \| 30.3 \| 6000 \| 0.5337 \| 0.7549 \| 0.7566 \| \| 0.5088 \| 31.31 \| 6200 \| 0.5344 \| 0.7555 \| 0.7576 \| \| 0.5132 \| 32.32 \| 6400 \| 0.5380 \| 0.7446 \| 0.7481 \| \| 0.5097 \| 33.33 \| 6600 \| 0.5341 \| 0.7544 \| 0.7569 \| \| 0.507 \| 34.34 \| 6800 \| 0.5344 \| 0.7501 \| 0.7528 \| \| 0.5048 \| 35.35 \| 7000 \| 0.5326 \| 0.7567 \| 0.7585 \| \| 0.5099 \| 36.36 \| 7200 \| 0.5301 \| 0.7533 \| 0.7557 \| \| 0.5063 \| 37.37 \| 7400 \| 0.5306 \| 0.7553 \| 0.7573 \| \| 0.5083 \| 38.38 \| 7600 \| 0.5299 \| 0.7612 \| 0.7623 \| \| 0.505 \| 39.39 \| 7800 \| 0.5321 \| 0.7600 \| 0.7614 \| \| 0.5075 \| 40.4 \| 8000 \| 0.5328 \| 0.7590 \| 0.7607 \| \| 0.5045 \| 41.41 \| 8200 \| 0.5327 \| 0.7517 \| 0.7541 \| \| 0.5077 \| 42.42 \| 8400 \| 0.5326 \| 0.7531 \| 0.7557 \| \| 0.5038 \| 43.43 \| 8600 \| 0.5328 \| 0.7550 \| 0.7569 \| \| 0.5064 \| 44.44 \| 8800 \| 0.5310 \| 0.7548 \| 0.7569 \| \| 0.5039 \| 45.45 \| 9000 \| 0.5317 \| 0.7586 \| 0.7604 \| \| 0.5033 \| 46.46 \| 9200 \| 0.5324 \| 0.7554 \| 0.7573 \| \| 0.5099 \| 47.47 \| 9400 \| 0.5319 \| 0.7527 \| 0.7551 \| \| 0.4981 \| 48.48 \| 9600 \| 0.5336 \| 0.7544 \| 0.7566 \| \| 0.5105 \| 49.49 \| 9800 \| 0.5320 \| 0.7540 \| 0.7563 \| \| 0.5029 \| 50.51 \| 10000 \| 0.5319 \| 0.7552 \| 0.7573 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K4me1-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K4me1-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:48:07+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me1-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me1) dataset. It achieves the following results on the evaluation set: - Loss: 0.5125 - F1 Score: 0.7706 - Accuracy: 0.7718 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5982 \| 1.01 \| 200 \| 0.5654 \| 0.7301 \| 0.7330 \| \| 0.5551 \| 2.02 \| 400 \| 0.5492 \| 0.7420 \| 0.7440 \| \| 0.5392 \| 3.03 \| 600 \| 0.5380 \| 0.7479 \| 0.75 \| \| 0.5345 \| 4.04 \| 800 \| 0.5385 \| 0.7526 \| 0.7547 \| \| 0.529 \| 5.05 \| 1000 \| 0.5344 \| 0.7544 \| 0.7551 \| \| 0.5243 \| 6.06 \| 1200 \| 0.5372 \| 0.7488 \| 0.7522 \| \| 0.5191 \| 7.07 \| 1400 \| 0.5333 \| 0.7585 \| 0.7604 \| \| 0.5178 \| 8.08 \| 1600 \| 0.5328 \| 0.7511 \| 0.7544 \| \| 0.5128 \| 9.09 \| 1800 \| 0.5297 \| 0.7546 \| 0.7569 \| \| 0.5089 \| 10.1 \| 2000 \| 0.5259 \| 0.7585 \| 0.7604 \| \| 0.5053 \| 11.11 \| 2200 \| 0.5379 \| 0.7533 \| 0.7563 \| \| 0.5042 \| 12.12 \| 2400 \| 0.5200 \| 0.7612 \| 0.7623 \| \| 0.5019 \| 13.13 \| 2600 \| 0.5268 \| 0.7594 \| 0.7620 \| \| 0.5001 \| 14.14 \| 2800 \| 0.5279 \| 0.7578 \| 0.7598 \| \| 0.4947 \| 15.15 \| 3000 \| 0.5261 \| 0.7634 \| 0.7652 \| \| 0.4925 \| 16.16 \| 3200 \| 0.5263 \| 0.7536 \| 0.7569 \| \| 0.4888 \| 17.17 \| 3400 \| 0.5357 \| 0.7612 \| 0.7633 \| \| 0.4898 \| 18.18 \| 3600 \| 0.5193 \| 0.7684 \| 0.7693 \| \| 0.4855 \| 19.19 \| 3800 \| 0.5196 \| 0.7645 \| 0.7664 \| \| 0.4825 \| 20.2 \| 4000 \| 0.5256 \| 0.7599 \| 0.7620 \| \| 0.4789 \| 21.21 \| 4200 \| 0.5371 \| 0.7516 \| 0.7544 \| \| 0.4789 \| 22.22 \| 4400 \| 0.5328 \| 0.7631 \| 0.7645 \| \| 0.4724 \| 23.23 \| 4600 \| 0.5290 \| 0.7638 \| 0.7664 \| \| 0.4777 \| 24.24 \| 4800 \| 0.5440 \| 0.7471 \| 0.7513 \| \| 0.4722 \| 25.25 \| 5000 \| 0.5276 \| 0.7675 \| 0.7680 \| \| 0.4738 \| 26.26 \| 5200 \| 0.5291 \| 0.7667 \| 0.7670 \| \| 0.4669 \| 27.27 \| 5400 \| 0.5323 \| 0.7569 \| 0.7595 \| \| 0.4683 \| 28.28 \| 5600 \| 0.5283 \| 0.7668 \| 0.7677 \| \| 0.4676 \| 29.29 \| 5800 \| 0.5398 \| 0.7453 \| 0.7503 \| \| 0.4605 \| 30.3 \| 6000 \| 0.5328 \| 0.7637 \| 0.7652 \| \| 0.4614 \| 31.31 \| 6200 \| 0.5288 \| 0.7652 \| 0.7664 \| \| 0.4637 \| 32.32 \| 6400 \| 0.5363 \| 0.7584 \| 0.7610 \| \| 0.4596 \| 33.33 \| 6600 \| 0.5352 \| 0.7614 \| 0.7636 \| \| 0.4573 \| 34.34 \| 6800 \| 0.5317 \| 0.7526 \| 0.7554 \| \| 0.452 \| 35.35 \| 7000 \| 0.5339 \| 0.7676 \| 0.7689 \| \| 0.4567 \| 36.36 \| 7200 \| 0.5331 \| 0.7545 \| 0.7566 \| \| 0.4518 \| 37.37 \| 7400 \| 0.5350 \| 0.7576 \| 0.7595 \| \| 0.4552 \| 38.38 \| 7600 \| 0.5343 \| 0.7667 \| 0.7677 \| \| 0.4514 \| 39.39 \| 7800 \| 0.5345 \| 0.7664 \| 0.7674 \| \| 0.4501 \| 40.4 \| 8000 \| 0.5313 \| 0.7645 \| 0.7661 \| \| 0.4458 \| 41.41 \| 8200 \| 0.5369 \| 0.7595 \| 0.7617 \| \| 0.45 \| 42.42 \| 8400 \| 0.5406 \| 0.7575 \| 0.7601 \| \| 0.4461 \| 43.43 \| 8600 \| 0.5367 \| 0.7619 \| 0.7636 \| \| 0.4474 \| 44.44 \| 8800 \| 0.5383 \| 0.7578 \| 0.7601 \| \| 0.4458 \| 45.45 \| 9000 \| 0.5349 \| 0.7610 \| 0.7626 \| \| 0.4421 \| 46.46 \| 9200 \| 0.5379 \| 0.7632 \| 0.7645 \| \| 0.4511 \| 47.47 \| 9400 \| 0.5360 \| 0.7594 \| 0.7617 \| \| 0.4383 \| 48.48 \| 9600 \| 0.5399 \| 0.7586 \| 0.7604 \| \| 0.4526 \| 49.49 \| 9800 \| 0.5357 \| 0.7584 \| 0.7604 \| \| 0.4403 \| 50.51 \| 10000 \| 0.5365 \| 0.7590 \| 0.7607 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K4me1-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K4me1-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:48:31+00:00
text-to-image	diffusers	--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### vesttieandtux2 Dreambooth model trained by enriq3 with TheLastBen's fast-DreamBooth notebook	{}	enriq3/vesttieandtux2	null	[ "diffusers", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]	null	2024-04-29T22:48:50+00:00
text-generation	transformers		{"license": "mit"}	multitensor/mistral-mllm	null	[ "transformers", "safetensors", "mistral", "text-generation", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T22:50:31+00:00
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GPT2_DocBot_SonatafyAI_V3 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.8062 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 3.0191 \| 1.0 \| 9715 \| 2.9325 \| \| 2.8082 \| 2.0 \| 19430 \| 2.8542 \| \| 2.7173 \| 3.0 \| 29145 \| 2.8198 \| \| 2.6473 \| 4.0 \| 38860 \| 2.8052 \| \| 2.5881 \| 5.0 \| 48575 \| 2.8062 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "gpt2", "model-index": [{"name": "GPT2_DocBot_SonatafyAI_V3", "results": []}]}	ajtamayoh/GPT2_DocBot_SonatafyAI_V3	null	[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T22:51:22+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K4me1-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me1) dataset. It achieves the following results on the evaluation set: - Loss: 0.5161 - F1 Score: 0.7724 - Accuracy: 0.7737 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5877 \| 1.01 \| 200 \| 0.5568 \| 0.7362 \| 0.7371 \| \| 0.5454 \| 2.02 \| 400 \| 0.5428 \| 0.7537 \| 0.7551 \| \| 0.5301 \| 3.03 \| 600 \| 0.5330 \| 0.7531 \| 0.7551 \| \| 0.5235 \| 4.04 \| 800 \| 0.5309 \| 0.7550 \| 0.7569 \| \| 0.5161 \| 5.05 \| 1000 \| 0.5291 \| 0.7614 \| 0.7620 \| \| 0.5091 \| 6.06 \| 1200 \| 0.5340 \| 0.7516 \| 0.7547 \| \| 0.5021 \| 7.07 \| 1400 \| 0.5320 \| 0.7621 \| 0.7639 \| \| 0.4978 \| 8.08 \| 1600 \| 0.5250 \| 0.7573 \| 0.7601 \| \| 0.4895 \| 9.09 \| 1800 \| 0.5259 \| 0.7564 \| 0.7585 \| \| 0.4836 \| 10.1 \| 2000 \| 0.5275 \| 0.7603 \| 0.7623 \| \| 0.4758 \| 11.11 \| 2200 \| 0.5495 \| 0.7519 \| 0.7560 \| \| 0.4737 \| 12.12 \| 2400 \| 0.5267 \| 0.7643 \| 0.7652 \| \| 0.4664 \| 13.13 \| 2600 \| 0.5384 \| 0.7562 \| 0.7592 \| \| 0.4617 \| 14.14 \| 2800 \| 0.5470 \| 0.7586 \| 0.7604 \| \| 0.4528 \| 15.15 \| 3000 \| 0.5355 \| 0.7634 \| 0.7648 \| \| 0.4503 \| 16.16 \| 3200 \| 0.5305 \| 0.7510 \| 0.7528 \| \| 0.4392 \| 17.17 \| 3400 \| 0.5566 \| 0.7610 \| 0.7623 \| \| 0.4383 \| 18.18 \| 3600 \| 0.5509 \| 0.7597 \| 0.7607 \| \| 0.4284 \| 19.19 \| 3800 \| 0.5471 \| 0.7619 \| 0.7633 \| \| 0.4237 \| 20.2 \| 4000 \| 0.5406 \| 0.7567 \| 0.7582 \| \| 0.4158 \| 21.21 \| 4200 \| 0.5632 \| 0.7517 \| 0.7535 \| \| 0.4111 \| 22.22 \| 4400 \| 0.5720 \| 0.7610 \| 0.7620 \| \| 0.4002 \| 23.23 \| 4600 \| 0.5655 \| 0.7642 \| 0.7652 \| \| 0.4017 \| 24.24 \| 4800 \| 0.6035 \| 0.7490 \| 0.7528 \| \| 0.3928 \| 25.25 \| 5000 \| 0.5774 \| 0.7634 \| 0.7633 \| \| 0.3912 \| 26.26 \| 5200 \| 0.5868 \| 0.7538 \| 0.7541 \| \| 0.3819 \| 27.27 \| 5400 \| 0.5887 \| 0.7534 \| 0.7560 \| \| 0.3795 \| 28.28 \| 5600 \| 0.5987 \| 0.7552 \| 0.7566 \| \| 0.375 \| 29.29 \| 5800 \| 0.6025 \| 0.7398 \| 0.7434 \| \| 0.3644 \| 30.3 \| 6000 \| 0.6111 \| 0.7570 \| 0.7579 \| \| 0.3623 \| 31.31 \| 6200 \| 0.6112 \| 0.7471 \| 0.7472 \| \| 0.3611 \| 32.32 \| 6400 \| 0.6075 \| 0.7440 \| 0.7453 \| \| 0.3553 \| 33.33 \| 6600 \| 0.6100 \| 0.7562 \| 0.7573 \| \| 0.3497 \| 34.34 \| 6800 \| 0.6096 \| 0.7477 \| 0.7481 \| \| 0.3425 \| 35.35 \| 7000 \| 0.6285 \| 0.7562 \| 0.7566 \| \| 0.3459 \| 36.36 \| 7200 \| 0.6170 \| 0.7446 \| 0.7456 \| \| 0.3369 \| 37.37 \| 7400 \| 0.6361 \| 0.7525 \| 0.7532 \| \| 0.3344 \| 38.38 \| 7600 \| 0.6405 \| 0.7440 \| 0.7443 \| \| 0.3369 \| 39.39 \| 7800 \| 0.6419 \| 0.7560 \| 0.7563 \| \| 0.3275 \| 40.4 \| 8000 \| 0.6409 \| 0.7496 \| 0.7513 \| \| 0.3256 \| 41.41 \| 8200 \| 0.6481 \| 0.7481 \| 0.7491 \| \| 0.3283 \| 42.42 \| 8400 \| 0.6509 \| 0.7439 \| 0.7453 \| \| 0.3202 \| 43.43 \| 8600 \| 0.6656 \| 0.7404 \| 0.7415 \| \| 0.3193 \| 44.44 \| 8800 \| 0.6546 \| 0.7465 \| 0.7475 \| \| 0.3157 \| 45.45 \| 9000 \| 0.6614 \| 0.7500 \| 0.7509 \| \| 0.3144 \| 46.46 \| 9200 \| 0.6641 \| 0.7460 \| 0.7465 \| \| 0.3173 \| 47.47 \| 9400 \| 0.6623 \| 0.7419 \| 0.7427 \| \| 0.3066 \| 48.48 \| 9600 \| 0.6763 \| 0.7433 \| 0.7443 \| \| 0.3191 \| 49.49 \| 9800 \| 0.6665 \| 0.7427 \| 0.7437 \| \| 0.3091 \| 50.51 \| 10000 \| 0.6692 \| 0.7426 \| 0.7434 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K4me1-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K4me1-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T22:51:42+00:00
null	null		{}	ldm0612/gpt2-wikitext2	null	[ "region:us" ]	null	2024-04-29T22:52:25+00:00
question-answering	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-squad This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.2149 \| 1.0 \| 5533 \| 1.1802 \| \| 0.9459 \| 2.0 \| 11066 \| 1.1161 \| \| 0.7596 \| 3.0 \| 16599 \| 1.1599 \| ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-squad", "results": []}]}	ahmad01010101/distilbert-base-uncased-finetuned-squad	null	[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:53:10+00:00
text-generation	transformers	An updated version of the previous model. In this one, I have not yet found any problems with word duplication. 02.05.24 Model updates, new versions are in the v1.1 branch. Link to original model and script: - openlynn/Llama-3-Soliloquy-8B-v1.5-64k: https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v1.5-64k - FantasiaFoundry/GGUF-Quantization-Script: https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script	{"language": ["en"], "license": "cc-by-nc-sa-4.0", "library_name": "transformers", "tags": ["llama", "text-generation-inference"], "pipeline_tag": "text-generation"}	SolidSnacke/Llama-3-Soliloquy-8B-v1.5-64k-i-GGUF	null	[ "transformers", "gguf", "llama", "text-generation-inference", "text-generation", "en", "license:cc-by-nc-sa-4.0", "endpoints_compatible", "region:us" ]	null	2024-04-29T22:53:28+00:00
null	null	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # O0428HMA2 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0559 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.6301 \| 0.09 \| 10 \| 0.1786 \| \| 0.1808 \| 0.18 \| 20 \| 0.1584 \| \| 0.151 \| 0.27 \| 30 \| 0.1656 \| \| 0.1571 \| 0.36 \| 40 \| 0.1538 \| \| 0.1506 \| 0.45 \| 50 \| 0.1473 \| \| 0.1503 \| 0.54 \| 60 \| 0.1472 \| \| 0.1495 \| 0.63 \| 70 \| 0.1470 \| \| 0.1494 \| 0.73 \| 80 \| 0.1533 \| \| 0.1454 \| 0.82 \| 90 \| 0.1454 \| \| 0.2027 \| 0.91 \| 100 \| 0.3378 \| \| 0.6197 \| 1.0 \| 110 \| 0.1547 \| \| 0.1558 \| 1.09 \| 120 \| 0.1495 \| \| 0.151 \| 1.18 \| 130 \| 0.2320 \| \| 0.1812 \| 1.27 \| 140 \| 0.1292 \| \| 0.1265 \| 1.36 \| 150 \| 0.0858 \| \| 0.0775 \| 1.45 \| 160 \| 0.0811 \| \| 1.561 \| 1.54 \| 170 \| 3.8411 \| \| 0.6605 \| 1.63 \| 180 \| 0.0889 \| \| 0.9093 \| 1.72 \| 190 \| 0.1577 \| \| 0.1072 \| 1.81 \| 200 \| 0.1386 \| \| 0.3511 \| 1.9 \| 210 \| 0.0862 \| \| 0.0683 \| 1.99 \| 220 \| 0.0609 \| \| 0.0628 \| 2.08 \| 230 \| 0.0583 \| \| 0.0574 \| 2.18 \| 240 \| 0.0583 \| \| 0.0576 \| 2.27 \| 250 \| 0.0589 \| \| 0.064 \| 2.36 \| 260 \| 0.0615 \| \| 0.0555 \| 2.45 \| 270 \| 0.0571 \| \| 0.0548 \| 2.54 \| 280 \| 0.0564 \| \| 0.0563 \| 2.63 \| 290 \| 0.0577 \| \| 0.0583 \| 2.72 \| 300 \| 0.0558 \| \| 0.058 \| 2.81 \| 310 \| 0.0555 \| \| 0.0589 \| 2.9 \| 320 \| 0.0558 \| \| 0.0621 \| 2.99 \| 330 \| 0.0559 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA2", "results": []}]}	Litzy619/O0428HMA2	null	[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]	null	2024-04-29T22:53:54+00:00
null	null	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # O0428HMA3 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0534 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.516 \| 0.09 \| 10 \| 0.1675 \| \| 0.1635 \| 0.18 \| 20 \| 0.1582 \| \| 0.1494 \| 0.27 \| 30 \| 0.1521 \| \| 0.1524 \| 0.36 \| 40 \| 0.1511 \| \| 0.1511 \| 0.45 \| 50 \| 0.1465 \| \| 0.1533 \| 0.54 \| 60 \| 0.1502 \| \| 0.149 \| 0.63 \| 70 \| 0.1473 \| \| 0.1503 \| 0.73 \| 80 \| 0.1592 \| \| 0.1487 \| 0.82 \| 90 \| 0.1494 \| \| 0.1474 \| 0.91 \| 100 \| 0.1475 \| \| 0.1331 \| 1.0 \| 110 \| 0.2279 \| \| 0.3556 \| 1.09 \| 120 \| 0.1260 \| \| 0.2269 \| 1.18 \| 130 \| 0.1110 \| \| 0.1173 \| 1.27 \| 140 \| 0.0777 \| \| 0.1209 \| 1.36 \| 150 \| 0.0818 \| \| 0.0771 \| 1.45 \| 160 \| 0.0822 \| \| 0.0701 \| 1.54 \| 170 \| 0.0583 \| \| 0.0641 \| 1.63 \| 180 \| 0.0579 \| \| 0.0638 \| 1.72 \| 190 \| 0.0560 \| \| 0.0564 \| 1.81 \| 200 \| 0.0569 \| \| 0.058 \| 1.9 \| 210 \| 0.0603 \| \| 0.059 \| 1.99 \| 220 \| 0.0548 \| \| 0.0576 \| 2.08 \| 230 \| 0.0548 \| \| 0.0532 \| 2.18 \| 240 \| 0.0565 \| \| 0.0549 \| 2.27 \| 250 \| 0.0574 \| \| 0.0586 \| 2.36 \| 260 \| 0.0561 \| \| 0.0537 \| 2.45 \| 270 \| 0.0543 \| \| 0.0522 \| 2.54 \| 280 \| 0.0545 \| \| 0.0541 \| 2.63 \| 290 \| 0.0556 \| \| 0.055 \| 2.72 \| 300 \| 0.0532 \| \| 0.0556 \| 2.81 \| 310 \| 0.0531 \| \| 0.0563 \| 2.9 \| 320 \| 0.0533 \| \| 0.0579 \| 2.99 \| 330 \| 0.0534 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA3", "results": []}]}	Litzy619/O0428HMA3	null	[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]	null	2024-04-29T22:54:01+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	cilantro9246/tlvmpdp	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T22:56:25+00:00
text2text-generation	peft	## llama-2-13b-code-alpaca [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) Trained for 3 epochs on `theblackcat102/evol-codealpaca-v1` dataset, scored decent on locally run perplexity at 4.36. ## Axolotl config used ```yaml base_model: NousResearch/Llama-2-13b-hf base_model_config: NousResearch/Llama-2-13b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer push_dataset_to_hub: hub_model_id: load_in_8bit: false load_in_4bit: true strict: false datasets: - path: theblackcat102/evol-codealpaca-v1 type: alpaca dataset_prepared_path: last_run_prepared val_set_size: 0.01 output_dir: ./checkpoints/llama-2-13b-qlora adapter: qlora lora_model_dir: sequence_len: 4096 max_packed_sequence_len: 4096 lora_r: 32 lora_alpha: 16 lora_dropout: 0.05 lora_target_modules: lora_target_linear: true lora_fan_in_fan_out: wandb_project: wandb_watch: wandb_run_id: wandb_log_model: gradient_accumulation_steps: 2 micro_batch_size: 2 num_epochs: 3 optimizer: paged_adamw_32bit lr_scheduler: cosine learning_rate: 0.0001 train_on_inputs: false group_by_length: true bf16: true fp16: false tf32: true gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: true flash_attention: warmup_steps: 10 eval_steps: 50 save_steps: debug: deepspeed: weight_decay: 0.0 fsdp: fsdp_config: special_tokens: bos_token: "<s>" eos_token: "</s>" unk_token: "<unk>" ``` And then merged with Axolotl via: ``` accelerate launch scripts/finetune.py configs/your_config.yml --merge_lora --lora_model_dir="./completed-model" --load_in_8bit=False --load_in_4bit=False ``` ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.5.0.dev0	{"language": ["en"], "license": "cc-by-nc-4.0", "library_name": "peft", "datasets": ["theblackcat102/evol-codealpaca-v1"], "pipeline_tag": "text2text-generation"}	DTang161/ModelMergingCode	null	[ "peft", "pytorch", "llama", "text2text-generation", "en", "dataset:theblackcat102/evol-codealpaca-v1", "license:cc-by-nc-4.0", "region:us" ]	null	2024-04-29T22:56:37+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	Quac/Indian-Edu-SFT-llama-3-8B	null	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-29T22:58:50+00:00
text-generation	transformers	# Llama-3-8B-Ultra-Instruct This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). Hello everyone this is Dampf, creator of the Destroyer series! looks around Oh, now I'm on Elinas' HF account. As you can see, I'm quite the traveler! This time, I'm introducing you to 8B-Ultra-Instruct. It is a small general purpose model that combines the most powerful instruct models with enticing roleplaying models. It will introduce better RAG capabilities in the form of Bagel to Llama 3 8B Instruct as well as German multilanguage, higher general intelligence and vision support. A model focused on Biology adds knowledge in the medical field. As for roleplay, it features two of the hottest models right now. Those are known to be high quality and for being uncensored. So this model might put out harmful responses. We are not responsible for what you do with this model and please take everything the model says with a huge grain of salt. Lastly, you might notice I'm conversative with the weight values in the final merge. This is because I believe L8B Instruct is a very dense model that's already great and doesn't need a lot more data. So instead of reaching the weight value of 1 in a ties merge, I'm only using a total of 0,65. This is to preserve Llama Instruct's intelligence and knowledge, while adding a little bit of the aforementioned models as salt in the soup. A huge thank you for all the creators of the datasets. Those include Undi95, Jon Durbin, Aaditya, VAGOsolutions, Teknium, Camel and many more. They deserve all the credit. And of course, thank you Elinas for providing the compute. ## Quants [GGUF](https://huggingface.co/bartowski/Llama-3-8B-Ultra-Instruct-GGUF) [exllama2](https://huggingface.co/bartowski/Llama-3-8B-Ultra-Instruct-exl2) ## Merge Details ### Merge Method This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Undi95/Meta-Llama-3-8B-Instruct-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-Instruct-hf) as a base. ### Models Merged The following models were included in the merge: * llama-3-8B-ultra-instruct/InstructPart * llama-3-8B-ultra-instruct/RPPart ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B parameters: weight: 0.4 - model: Undi95/Llama-3-LewdPlay-8B-evo parameters: weight: 0.5 - model: jondurbin/bagel-8b-v1.0 parameters: weight: 0.1 merge_method: dare_ties dtype: bfloat16 base_model: Undi95/Meta-Llama-3-8B-hf name: RPPart --- models: - model: Weyaxi/Einstein-v6.1-Llama3-8B parameters: weight: 0.6 - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct parameters: weight: 0.3 - model: aaditya/OpenBioLLM-Llama3-8B parameters: weight: 0.1 merge_method: dare_ties base_model: Undi95/Meta-Llama-3-8B-hf dtype: bfloat16 name: InstructPart --- models: - model: RPPart parameters: weight: 0.39 - model: InstructPart parameters: weight: 0.26 merge_method: dare_ties base_model: Undi95/Meta-Llama-3-8B-Instruct-hf dtype: bfloat16 name: Llama-3-8B-Ultra-Instruct ``` ### Chat Template (Llama 3 Official) ``` <\|begin_of_text\|><\|start_header_id\|>system<\|end_header_id\|> {system_prompt}<\|eot_id\|><\|start_header_id\|>user<\|end_header_id\|> {input}<\|eot_id\|><\|start_header_id\|>assistant<\|end_header_id\|> {output}<\|eot_id\|> ``` ### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_elinas__Llama-3-8B-Ultra-Instruct) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|69.11\| \|AI2 Reasoning Challenge (25-Shot)\|64.59\| \|HellaSwag (10-Shot) \|81.63\| \|MMLU (5-Shot) \|68.32\| \|TruthfulQA (0-shot) \|52.80\| \|Winogrande (5-shot) \|76.95\| \|GSM8k (5-shot) \|70.36\|	{"license": "llama3", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["Undi95/Meta-Llama-3-8B-Instruct-hf"]}	elinas/Llama-3-8B-Ultra-Instruct	null	[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "arxiv:2306.01708", "base_model:Undi95/Meta-Llama-3-8B-Instruct-hf", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T23:00:11+00:00
text2text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # mbart-large-50-bcoqa This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.0137 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:-----:\|:---------------:\| \| 1.8791 \| 0.1 \| 3500 \| 1.7917 \| \| 1.579 \| 0.2 \| 7000 \| 1.4741 \| \| 1.4918 \| 0.3 \| 10500 \| 1.4246 \| \| 1.422 \| 0.4 \| 14000 \| 1.3369 \| \| 1.4088 \| 0.5 \| 17500 \| 1.3064 \| \| 1.3245 \| 0.61 \| 21000 \| 1.2566 \| \| 1.3205 \| 0.71 \| 24500 \| 1.2274 \| \| 1.3168 \| 0.81 \| 28000 \| 1.2052 \| \| 1.2256 \| 0.91 \| 31500 \| 1.1630 \| \| 1.0668 \| 1.01 \| 35000 \| 1.1543 \| \| 1.0185 \| 1.11 \| 38500 \| 1.1391 \| \| 0.9521 \| 1.21 \| 42000 \| 1.1076 \| \| 0.9467 \| 1.31 \| 45500 \| 1.1316 \| \| 1.0128 \| 1.41 \| 49000 \| 1.0849 \| \| 0.9948 \| 1.51 \| 52500 \| 1.0619 \| \| 0.9601 \| 1.61 \| 56000 \| 1.0489 \| \| 0.9479 \| 1.72 \| 59500 \| 1.0353 \| \| 0.9046 \| 1.82 \| 63000 \| 1.0212 \| \| 0.8924 \| 1.92 \| 66500 \| 1.0137 \| ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.16.1 - Tokenizers 0.15.1	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "facebook/mbart-large-50", "model-index": [{"name": "mbart-large-50-bcoqa", "results": []}]}	arbitropy/mbart-large-50-bcoqa	null	[ "transformers", "safetensors", "mbart", "text2text-generation", "generated_from_trainer", "base_model:facebook/mbart-large-50", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:00:29+00:00
null	null		{}	abaral7/test-model	null	[ "region:us" ]	null	2024-04-29T23:00:32+00:00
reinforcement-learning	null	# Reinforce Agent playing CartPole-v1 This is a trained model of a Reinforce agent playing CartPole-v1 . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction	{"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-CartPole-v1", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "CartPole-v1", "type": "CartPole-v1"}, "metrics": [{"type": "mean_reward", "value": "500.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}	haytamelouarrat/Reinforce-CartPole-v1	null	[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]	null	2024-04-29T23:01:28+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # norllm-ai-normistral-7b-align-scan This model is a fine-tuned version of [data/norllm-ai-normistral-7b-sft-qlora](https://huggingface.co/data/norllm-ai-normistral-7b-sft-qlora) on the hugodk-sch/aftonposten_title_prefs dataset. It achieves the following results on the evaluation set: - Loss: 0.9294 - Rewards/chosen: -0.0900 - Rewards/rejected: -0.1614 - Rewards/accuracies: 0.6009 - Rewards/margins: 0.0715 - Logps/rejected: -35.5053 - Logps/chosen: -31.7323 - Logits/rejected: -2.8259 - Logits/chosen: -2.8279 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Rewards/chosen \| Rewards/rejected \| Rewards/accuracies \| Rewards/margins \| Logps/rejected \| Logps/chosen \| Logits/rejected \| Logits/chosen \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------------:\|:----------------:\|:------------------:\|:---------------:\|:--------------:\|:------------:\|:---------------:\|:-------------:\| \| 0.9239 \| 0.26 \| 100 \| 0.9661 \| -0.0010 \| -0.0351 \| 0.6013 \| 0.0342 \| -34.8738 \| -31.2872 \| -2.8027 \| -2.8055 \| \| 0.8146 \| 0.52 \| 200 \| 0.9363 \| -0.0747 \| -0.1389 \| 0.6184 \| 0.0641 \| -35.3925 \| -31.6561 \| -2.8206 \| -2.8233 \| \| 0.7173 \| 0.78 \| 300 \| 0.9279 \| -0.0837 \| -0.1567 \| 0.6125 \| 0.0730 \| -35.4817 \| -31.7010 \| -2.8247 \| -2.8267 \| ### Framework versions - PEFT 0.10.0 - Transformers 4.39.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.1	{"library_name": "peft", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer"], "datasets": ["hugodk-sch/aftonposten_title_prefs"], "base_model": "NorLLM-AI/NorMistral-7B", "model-index": [{"name": "norllm-ai-normistral-7b-align-scan", "results": []}]}	hugodk-sch/norllm-ai-normistral-7b-align-scan	null	[ "peft", "safetensors", "mistral", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "dataset:hugodk-sch/aftonposten_title_prefs", "base_model:NorLLM-AI/NorMistral-7B", "4-bit", "region:us" ]	null	2024-04-29T23:03:36+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/i604il5	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T23:03:51+00:00
text-classification	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	profoz/parent_malicious_model	null	[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:04:03+00:00
null	null		{}	viwonrecord/SEOKYOUNG	null	[ "region:us" ]	null	2024-04-29T23:04:36+00:00
null	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	tsharish/Mistral-7B-Inst-v0.2-pubmed-1k_adapter	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:05:41+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K36me3-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K36me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K36me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4546 - F1 Score: 0.7974 - Accuracy: 0.7999 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5656 \| 0.92 \| 200 \| 0.5396 \| 0.7434 \| 0.7457 \| \| 0.5164 \| 1.83 \| 400 \| 0.5221 \| 0.7582 \| 0.7612 \| \| 0.5001 \| 2.75 \| 600 \| 0.5085 \| 0.7683 \| 0.7704 \| \| 0.5011 \| 3.67 \| 800 \| 0.5027 \| 0.7739 \| 0.7755 \| \| 0.4857 \| 4.59 \| 1000 \| 0.5024 \| 0.7777 \| 0.7798 \| \| 0.4814 \| 5.5 \| 1200 \| 0.4862 \| 0.7825 \| 0.7841 \| \| 0.4782 \| 6.42 \| 1400 \| 0.4814 \| 0.7861 \| 0.7870 \| \| 0.4754 \| 7.34 \| 1600 \| 0.4872 \| 0.7820 \| 0.7838 \| \| 0.4679 \| 8.26 \| 1800 \| 0.4855 \| 0.7847 \| 0.7864 \| \| 0.4729 \| 9.17 \| 2000 \| 0.4816 \| 0.7823 \| 0.7841 \| \| 0.4679 \| 10.09 \| 2200 \| 0.4951 \| 0.7783 \| 0.7818 \| \| 0.4659 \| 11.01 \| 2400 \| 0.4760 \| 0.7862 \| 0.7884 \| \| 0.4629 \| 11.93 \| 2600 \| 0.4728 \| 0.7873 \| 0.7893 \| \| 0.4618 \| 12.84 \| 2800 \| 0.4770 \| 0.7858 \| 0.7881 \| \| 0.4592 \| 13.76 \| 3000 \| 0.4802 \| 0.7799 \| 0.7830 \| \| 0.4559 \| 14.68 \| 3200 \| 0.4697 \| 0.7912 \| 0.7927 \| \| 0.4619 \| 15.6 \| 3400 \| 0.4723 \| 0.7879 \| 0.7904 \| \| 0.4572 \| 16.51 \| 3600 \| 0.4736 \| 0.7902 \| 0.7921 \| \| 0.4566 \| 17.43 \| 3800 \| 0.4626 \| 0.7949 \| 0.7962 \| \| 0.452 \| 18.35 \| 4000 \| 0.4754 \| 0.7908 \| 0.7927 \| \| 0.4551 \| 19.27 \| 4200 \| 0.4720 \| 0.7925 \| 0.7942 \| \| 0.4531 \| 20.18 \| 4400 \| 0.4777 \| 0.7867 \| 0.7893 \| \| 0.4486 \| 21.1 \| 4600 \| 0.4705 \| 0.7942 \| 0.7959 \| \| 0.4512 \| 22.02 \| 4800 \| 0.4709 \| 0.7949 \| 0.7967 \| \| 0.4486 \| 22.94 \| 5000 \| 0.4632 \| 0.7940 \| 0.7959 \| \| 0.4471 \| 23.85 \| 5200 \| 0.4673 \| 0.7938 \| 0.7959 \| \| 0.4488 \| 24.77 \| 5400 \| 0.4783 \| 0.7864 \| 0.7893 \| \| 0.4494 \| 25.69 \| 5600 \| 0.4688 \| 0.7929 \| 0.7950 \| \| 0.4467 \| 26.61 \| 5800 \| 0.4678 \| 0.7921 \| 0.7939 \| \| 0.4447 \| 27.52 \| 6000 \| 0.4729 \| 0.7913 \| 0.7936 \| \| 0.4447 \| 28.44 \| 6200 \| 0.4641 \| 0.7954 \| 0.7973 \| \| 0.4436 \| 29.36 \| 6400 \| 0.4725 \| 0.7898 \| 0.7924 \| \| 0.4471 \| 30.28 \| 6600 \| 0.4697 \| 0.7907 \| 0.7933 \| \| 0.4433 \| 31.19 \| 6800 \| 0.4655 \| 0.7958 \| 0.7973 \| \| 0.4454 \| 32.11 \| 7000 \| 0.4664 \| 0.7942 \| 0.7962 \| \| 0.4421 \| 33.03 \| 7200 \| 0.4682 \| 0.7950 \| 0.7970 \| \| 0.4413 \| 33.94 \| 7400 \| 0.4713 \| 0.7938 \| 0.7959 \| \| 0.4415 \| 34.86 \| 7600 \| 0.4680 \| 0.7949 \| 0.7970 \| \| 0.4415 \| 35.78 \| 7800 \| 0.4643 \| 0.7959 \| 0.7976 \| \| 0.4391 \| 36.7 \| 8000 \| 0.4634 \| 0.7993 \| 0.8010 \| \| 0.4413 \| 37.61 \| 8200 \| 0.4719 \| 0.7868 \| 0.7899 \| \| 0.4385 \| 38.53 \| 8400 \| 0.4648 \| 0.7963 \| 0.7982 \| \| 0.441 \| 39.45 \| 8600 \| 0.4686 \| 0.7938 \| 0.7962 \| \| 0.4356 \| 40.37 \| 8800 \| 0.4725 \| 0.7931 \| 0.7956 \| \| 0.4439 \| 41.28 \| 9000 \| 0.4677 \| 0.7911 \| 0.7936 \| \| 0.4384 \| 42.2 \| 9200 \| 0.4648 \| 0.7970 \| 0.7990 \| \| 0.4367 \| 43.12 \| 9400 \| 0.4663 \| 0.7969 \| 0.7990 \| \| 0.4372 \| 44.04 \| 9600 \| 0.4668 \| 0.7938 \| 0.7962 \| \| 0.4404 \| 44.95 \| 9800 \| 0.4687 \| 0.7907 \| 0.7933 \| \| 0.4395 \| 45.87 \| 10000 \| 0.4666 \| 0.7935 \| 0.7959 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K36me3-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K36me3-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:05:51+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K36me3-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K36me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K36me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4506 - F1 Score: 0.8122 - Accuracy: 0.8142 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5504 \| 0.92 \| 200 \| 0.5331 \| 0.7489 \| 0.7526 \| \| 0.4958 \| 1.83 \| 400 \| 0.4990 \| 0.7734 \| 0.7758 \| \| 0.4776 \| 2.75 \| 600 \| 0.4796 \| 0.7878 \| 0.7890 \| \| 0.4802 \| 3.67 \| 800 \| 0.4811 \| 0.7896 \| 0.7910 \| \| 0.4638 \| 4.59 \| 1000 \| 0.4874 \| 0.7864 \| 0.7884 \| \| 0.4582 \| 5.5 \| 1200 \| 0.4710 \| 0.7903 \| 0.7921 \| \| 0.4563 \| 6.42 \| 1400 \| 0.4680 \| 0.7967 \| 0.7979 \| \| 0.4515 \| 7.34 \| 1600 \| 0.4721 \| 0.7926 \| 0.7947 \| \| 0.4448 \| 8.26 \| 1800 \| 0.4736 \| 0.7919 \| 0.7939 \| \| 0.4466 \| 9.17 \| 2000 \| 0.4668 \| 0.7929 \| 0.7947 \| \| 0.4413 \| 10.09 \| 2200 \| 0.4890 \| 0.7760 \| 0.7801 \| \| 0.4395 \| 11.01 \| 2400 \| 0.4614 \| 0.7961 \| 0.7982 \| \| 0.4358 \| 11.93 \| 2600 \| 0.4567 \| 0.7996 \| 0.7999 \| \| 0.4341 \| 12.84 \| 2800 \| 0.4737 \| 0.7850 \| 0.7884 \| \| 0.4284 \| 13.76 \| 3000 \| 0.4900 \| 0.7771 \| 0.7818 \| \| 0.4245 \| 14.68 \| 3200 \| 0.4666 \| 0.7990 \| 0.8007 \| \| 0.4283 \| 15.6 \| 3400 \| 0.4565 \| 0.7968 \| 0.7985 \| \| 0.4248 \| 16.51 \| 3600 \| 0.4838 \| 0.7919 \| 0.7947 \| \| 0.4213 \| 17.43 \| 3800 \| 0.4729 \| 0.7910 \| 0.7930 \| \| 0.4166 \| 18.35 \| 4000 \| 0.4621 \| 0.7989 \| 0.8005 \| \| 0.4202 \| 19.27 \| 4200 \| 0.4710 \| 0.7998 \| 0.8019 \| \| 0.4144 \| 20.18 \| 4400 \| 0.4801 \| 0.7969 \| 0.7990 \| \| 0.4117 \| 21.1 \| 4600 \| 0.4672 \| 0.7976 \| 0.7993 \| \| 0.412 \| 22.02 \| 4800 \| 0.4626 \| 0.7988 \| 0.8002 \| \| 0.4095 \| 22.94 \| 5000 \| 0.4661 \| 0.7939 \| 0.7964 \| \| 0.4051 \| 23.85 \| 5200 \| 0.4695 \| 0.7977 \| 0.8002 \| \| 0.4061 \| 24.77 \| 5400 \| 0.4818 \| 0.7946 \| 0.7976 \| \| 0.4053 \| 25.69 \| 5600 \| 0.4660 \| 0.7944 \| 0.7970 \| \| 0.402 \| 26.61 \| 5800 \| 0.4649 \| 0.7991 \| 0.8010 \| \| 0.4013 \| 27.52 \| 6000 \| 0.4767 \| 0.7982 \| 0.8002 \| \| 0.4011 \| 28.44 \| 6200 \| 0.4698 \| 0.7990 \| 0.8010 \| \| 0.3956 \| 29.36 \| 6400 \| 0.4683 \| 0.7978 \| 0.7996 \| \| 0.3991 \| 30.28 \| 6600 \| 0.4720 \| 0.7946 \| 0.7970 \| \| 0.3962 \| 31.19 \| 6800 \| 0.4673 \| 0.7972 \| 0.7987 \| \| 0.3956 \| 32.11 \| 7000 \| 0.4702 \| 0.7955 \| 0.7976 \| \| 0.3907 \| 33.03 \| 7200 \| 0.4693 \| 0.7994 \| 0.8010 \| \| 0.3915 \| 33.94 \| 7400 \| 0.4673 \| 0.8019 \| 0.8036 \| \| 0.3891 \| 34.86 \| 7600 \| 0.4668 \| 0.7936 \| 0.7956 \| \| 0.3901 \| 35.78 \| 7800 \| 0.4653 \| 0.8013 \| 0.8028 \| \| 0.3869 \| 36.7 \| 8000 \| 0.4635 \| 0.7971 \| 0.7987 \| \| 0.3884 \| 37.61 \| 8200 \| 0.4734 \| 0.7921 \| 0.7947 \| \| 0.3871 \| 38.53 \| 8400 \| 0.4749 \| 0.7965 \| 0.7987 \| \| 0.3866 \| 39.45 \| 8600 \| 0.4737 \| 0.7956 \| 0.7979 \| \| 0.382 \| 40.37 \| 8800 \| 0.4798 \| 0.7923 \| 0.7950 \| \| 0.3897 \| 41.28 \| 9000 \| 0.4740 \| 0.7940 \| 0.7964 \| \| 0.3849 \| 42.2 \| 9200 \| 0.4700 \| 0.7988 \| 0.8007 \| \| 0.3798 \| 43.12 \| 9400 \| 0.4709 \| 0.8012 \| 0.8030 \| \| 0.3836 \| 44.04 \| 9600 \| 0.4731 \| 0.7948 \| 0.7970 \| \| 0.3853 \| 44.95 \| 9800 \| 0.4738 \| 0.7926 \| 0.7950 \| \| 0.3825 \| 45.87 \| 10000 \| 0.4714 \| 0.7954 \| 0.7976 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K36me3-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K36me3-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:06:44+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # EstigiaxLlama This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - training_steps: 250 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "model-index": [{"name": "EstigiaxLlama", "results": []}]}	franciscobdl/EstigiaxLlama	null	[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "region:us" ]	null	2024-04-29T23:06:57+00:00
null	null	# DDPO trained model num_epochs=20 train_gradient_accumulation_steps=1 sample_num_steps=30 sample_batch_size=8 train_batch_size=8 sample_num_batches_per_epoch=32 based off of stabilityai/stable-diffusion-2-base and then trained off of None	{}	jlbaker361/ddpo-runway-image_reward-hard	null	[ "region:us" ]	null	2024-04-29T23:07:08+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_0-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.5838 - F1 Score: 0.7160 - Accuracy: 0.7173 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6482 \| 3.92 \| 200 \| 0.6103 \| 0.6555 \| 0.6568 \| \| 0.6062 \| 7.84 \| 400 \| 0.5965 \| 0.6803 \| 0.6815 \| \| 0.586 \| 11.76 \| 600 \| 0.5813 \| 0.7025 \| 0.7025 \| \| 0.5673 \| 15.69 \| 800 \| 0.5669 \| 0.7085 \| 0.7086 \| \| 0.5496 \| 19.61 \| 1000 \| 0.5569 \| 0.7037 \| 0.7037 \| \| 0.5443 \| 23.53 \| 1200 \| 0.5889 \| 0.6842 \| 0.7 \| \| 0.5318 \| 27.45 \| 1400 \| 0.5531 \| 0.7074 \| 0.7086 \| \| 0.5218 \| 31.37 \| 1600 \| 0.5475 \| 0.7014 \| 0.7025 \| \| 0.5177 \| 35.29 \| 1800 \| 0.5485 \| 0.7118 \| 0.7136 \| \| 0.509 \| 39.22 \| 2000 \| 0.5474 \| 0.7077 \| 0.7086 \| \| 0.4993 \| 43.14 \| 2200 \| 0.5541 \| 0.7135 \| 0.7136 \| \| 0.498 \| 47.06 \| 2400 \| 0.5485 \| 0.7184 \| 0.7198 \| \| 0.489 \| 50.98 \| 2600 \| 0.5472 \| 0.7232 \| 0.7235 \| \| 0.4855 \| 54.9 \| 2800 \| 0.5571 \| 0.7221 \| 0.7247 \| \| 0.4809 \| 58.82 \| 3000 \| 0.5488 \| 0.7223 \| 0.7235 \| \| 0.4769 \| 62.75 \| 3200 \| 0.5472 \| 0.7271 \| 0.7284 \| \| 0.4725 \| 66.67 \| 3400 \| 0.5468 \| 0.7231 \| 0.7247 \| \| 0.4707 \| 70.59 \| 3600 \| 0.5473 \| 0.7304 \| 0.7309 \| \| 0.4655 \| 74.51 \| 3800 \| 0.5513 \| 0.7182 \| 0.7198 \| \| 0.4618 \| 78.43 \| 4000 \| 0.5527 \| 0.7220 \| 0.7235 \| \| 0.4595 \| 82.35 \| 4200 \| 0.5566 \| 0.7179 \| 0.7198 \| \| 0.4552 \| 86.27 \| 4400 \| 0.5566 \| 0.7222 \| 0.7235 \| \| 0.458 \| 90.2 \| 4600 \| 0.5572 \| 0.7256 \| 0.7284 \| \| 0.4487 \| 94.12 \| 4800 \| 0.5584 \| 0.7275 \| 0.7284 \| \| 0.4455 \| 98.04 \| 5000 \| 0.5558 \| 0.7234 \| 0.7259 \| \| 0.4448 \| 101.96 \| 5200 \| 0.5549 \| 0.7363 \| 0.7370 \| \| 0.4422 \| 105.88 \| 5400 \| 0.5603 \| 0.7352 \| 0.7358 \| \| 0.4409 \| 109.8 \| 5600 \| 0.5538 \| 0.7365 \| 0.7370 \| \| 0.4368 \| 113.73 \| 5800 \| 0.5603 \| 0.7331 \| 0.7346 \| \| 0.4361 \| 117.65 \| 6000 \| 0.5619 \| 0.7330 \| 0.7333 \| \| 0.435 \| 121.57 \| 6200 \| 0.5559 \| 0.7341 \| 0.7346 \| \| 0.4359 \| 125.49 \| 6400 \| 0.5572 \| 0.7353 \| 0.7358 \| \| 0.4331 \| 129.41 \| 6600 \| 0.5565 \| 0.7329 \| 0.7333 \| \| 0.4265 \| 133.33 \| 6800 \| 0.5595 \| 0.7336 \| 0.7346 \| \| 0.4229 \| 137.25 \| 7000 \| 0.5584 \| 0.7325 \| 0.7333 \| \| 0.4269 \| 141.18 \| 7200 \| 0.5566 \| 0.7337 \| 0.7346 \| \| 0.4269 \| 145.1 \| 7400 \| 0.5559 \| 0.7403 \| 0.7407 \| \| 0.4196 \| 149.02 \| 7600 \| 0.5587 \| 0.7291 \| 0.7296 \| \| 0.424 \| 152.94 \| 7800 \| 0.5528 \| 0.7399 \| 0.7407 \| \| 0.4209 \| 156.86 \| 8000 \| 0.5550 \| 0.7394 \| 0.7407 \| \| 0.4165 \| 160.78 \| 8200 \| 0.5611 \| 0.7363 \| 0.7370 \| \| 0.4225 \| 164.71 \| 8400 \| 0.5544 \| 0.7352 \| 0.7358 \| \| 0.42 \| 168.63 \| 8600 \| 0.5522 \| 0.7396 \| 0.7407 \| \| 0.423 \| 172.55 \| 8800 \| 0.5522 \| 0.7385 \| 0.7395 \| \| 0.4151 \| 176.47 \| 9000 \| 0.5579 \| 0.7360 \| 0.7370 \| \| 0.4165 \| 180.39 \| 9200 \| 0.5567 \| 0.7361 \| 0.7370 \| \| 0.4214 \| 184.31 \| 9400 \| 0.5547 \| 0.7387 \| 0.7395 \| \| 0.4189 \| 188.24 \| 9600 \| 0.5555 \| 0.7354 \| 0.7358 \| \| 0.4162 \| 192.16 \| 9800 \| 0.5562 \| 0.7351 \| 0.7358 \| \| 0.4175 \| 196.08 \| 10000 \| 0.5562 \| 0.7362 \| 0.7370 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_0-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_0-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:07:22+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_EMP_H3K36me3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K36me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K36me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4544 - F1 Score: 0.8013 - Accuracy: 0.8013 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5415 \| 0.92 \| 200 \| 0.5369 \| 0.7565 \| 0.7600 \| \| 0.4848 \| 1.83 \| 400 \| 0.4846 \| 0.7811 \| 0.7830 \| \| 0.4678 \| 2.75 \| 600 \| 0.4677 \| 0.7976 \| 0.7985 \| \| 0.4676 \| 3.67 \| 800 \| 0.4715 \| 0.7944 \| 0.7953 \| \| 0.4499 \| 4.59 \| 1000 \| 0.4752 \| 0.7949 \| 0.7967 \| \| 0.4422 \| 5.5 \| 1200 \| 0.4607 \| 0.7963 \| 0.7982 \| \| 0.4387 \| 6.42 \| 1400 \| 0.4631 \| 0.8020 \| 0.8030 \| \| 0.4329 \| 7.34 \| 1600 \| 0.4669 \| 0.7911 \| 0.7936 \| \| 0.4217 \| 8.26 \| 1800 \| 0.4607 \| 0.7959 \| 0.7973 \| \| 0.4214 \| 9.17 \| 2000 \| 0.4591 \| 0.7964 \| 0.7985 \| \| 0.4128 \| 10.09 \| 2200 \| 0.4746 \| 0.7934 \| 0.7959 \| \| 0.4078 \| 11.01 \| 2400 \| 0.4535 \| 0.8014 \| 0.8025 \| \| 0.4002 \| 11.93 \| 2600 \| 0.4550 \| 0.8050 \| 0.8050 \| \| 0.3953 \| 12.84 \| 2800 \| 0.4655 \| 0.7979 \| 0.7996 \| \| 0.3854 \| 13.76 \| 3000 \| 0.4848 \| 0.7817 \| 0.7858 \| \| 0.3825 \| 14.68 \| 3200 \| 0.4719 \| 0.8012 \| 0.8030 \| \| 0.3812 \| 15.6 \| 3400 \| 0.4811 \| 0.7886 \| 0.7916 \| \| 0.3745 \| 16.51 \| 3600 \| 0.5227 \| 0.7785 \| 0.7838 \| \| 0.3679 \| 17.43 \| 3800 \| 0.4944 \| 0.7971 \| 0.7987 \| \| 0.3607 \| 18.35 \| 4000 \| 0.4810 \| 0.7982 \| 0.7990 \| \| 0.3586 \| 19.27 \| 4200 \| 0.5204 \| 0.7968 \| 0.7993 \| \| 0.3532 \| 20.18 \| 4400 \| 0.5151 \| 0.7945 \| 0.7970 \| \| 0.3457 \| 21.1 \| 4600 \| 0.4889 \| 0.7978 \| 0.7990 \| \| 0.3435 \| 22.02 \| 4800 \| 0.4771 \| 0.7962 \| 0.7973 \| \| 0.3379 \| 22.94 \| 5000 \| 0.5006 \| 0.7940 \| 0.7959 \| \| 0.3304 \| 23.85 \| 5200 \| 0.5199 \| 0.7876 \| 0.7904 \| \| 0.3279 \| 24.77 \| 5400 \| 0.5228 \| 0.7874 \| 0.7896 \| \| 0.3238 \| 25.69 \| 5600 \| 0.5171 \| 0.7918 \| 0.7939 \| \| 0.3179 \| 26.61 \| 5800 \| 0.5140 \| 0.7967 \| 0.7987 \| \| 0.3127 \| 27.52 \| 6000 \| 0.5424 \| 0.7949 \| 0.7970 \| \| 0.3124 \| 28.44 \| 6200 \| 0.5512 \| 0.7862 \| 0.7893 \| \| 0.3046 \| 29.36 \| 6400 \| 0.5430 \| 0.7854 \| 0.7878 \| \| 0.3039 \| 30.28 \| 6600 \| 0.5411 \| 0.7874 \| 0.7899 \| \| 0.3009 \| 31.19 \| 6800 \| 0.5338 \| 0.7890 \| 0.7901 \| \| 0.2949 \| 32.11 \| 7000 \| 0.5609 \| 0.7855 \| 0.7881 \| \| 0.2938 \| 33.03 \| 7200 \| 0.5325 \| 0.7896 \| 0.7910 \| \| 0.2878 \| 33.94 \| 7400 \| 0.5406 \| 0.7907 \| 0.7924 \| \| 0.284 \| 34.86 \| 7600 \| 0.5429 \| 0.7931 \| 0.7944 \| \| 0.2824 \| 35.78 \| 7800 \| 0.5504 \| 0.7892 \| 0.7907 \| \| 0.2831 \| 36.7 \| 8000 \| 0.5466 \| 0.7912 \| 0.7927 \| \| 0.2769 \| 37.61 \| 8200 \| 0.5762 \| 0.7871 \| 0.7896 \| \| 0.2747 \| 38.53 \| 8400 \| 0.5852 \| 0.7925 \| 0.7947 \| \| 0.2751 \| 39.45 \| 8600 \| 0.5643 \| 0.7889 \| 0.7907 \| \| 0.2674 \| 40.37 \| 8800 \| 0.5814 \| 0.7896 \| 0.7919 \| \| 0.2734 \| 41.28 \| 9000 \| 0.5793 \| 0.7860 \| 0.7881 \| \| 0.271 \| 42.2 \| 9200 \| 0.5699 \| 0.7864 \| 0.7881 \| \| 0.2653 \| 43.12 \| 9400 \| 0.5777 \| 0.7911 \| 0.7927 \| \| 0.2709 \| 44.04 \| 9600 \| 0.5768 \| 0.7886 \| 0.7907 \| \| 0.2665 \| 44.95 \| 9800 \| 0.5772 \| 0.7878 \| 0.7899 \| \| 0.2623 \| 45.87 \| 10000 \| 0.5772 \| 0.7901 \| 0.7919 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K36me3-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_EMP_H3K36me3-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:07:32+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_0-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.9978 - F1 Score: 0.7109 - Accuracy: 0.7123 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.633 \| 3.92 \| 200 \| 0.5934 \| 0.6860 \| 0.6864 \| \| 0.5677 \| 7.84 \| 400 \| 0.5685 \| 0.7048 \| 0.7049 \| \| 0.5361 \| 11.76 \| 600 \| 0.5605 \| 0.7028 \| 0.7037 \| \| 0.5105 \| 15.69 \| 800 \| 0.5610 \| 0.7119 \| 0.7173 \| \| 0.4955 \| 19.61 \| 1000 \| 0.5529 \| 0.7156 \| 0.7173 \| \| 0.4773 \| 23.53 \| 1200 \| 0.5698 \| 0.7154 \| 0.7210 \| \| 0.4592 \| 27.45 \| 1400 \| 0.5672 \| 0.7154 \| 0.7160 \| \| 0.4423 \| 31.37 \| 1600 \| 0.5890 \| 0.7197 \| 0.7198 \| \| 0.432 \| 35.29 \| 1800 \| 0.6112 \| 0.7136 \| 0.7136 \| \| 0.4143 \| 39.22 \| 2000 \| 0.5904 \| 0.7079 \| 0.7099 \| \| 0.3994 \| 43.14 \| 2200 \| 0.6026 \| 0.7237 \| 0.7247 \| \| 0.391 \| 47.06 \| 2400 \| 0.6136 \| 0.7210 \| 0.7210 \| \| 0.3717 \| 50.98 \| 2600 \| 0.6466 \| 0.7134 \| 0.7136 \| \| 0.3604 \| 54.9 \| 2800 \| 0.6392 \| 0.7119 \| 0.7160 \| \| 0.3494 \| 58.82 \| 3000 \| 0.6471 \| 0.7185 \| 0.7185 \| \| 0.3341 \| 62.75 \| 3200 \| 0.6738 \| 0.7052 \| 0.7062 \| \| 0.3228 \| 66.67 \| 3400 \| 0.6589 \| 0.7185 \| 0.7185 \| \| 0.3203 \| 70.59 \| 3600 \| 0.7133 \| 0.7173 \| 0.7173 \| \| 0.3072 \| 74.51 \| 3800 \| 0.6876 \| 0.7073 \| 0.7086 \| \| 0.2972 \| 78.43 \| 4000 \| 0.7309 \| 0.7121 \| 0.7123 \| \| 0.2928 \| 82.35 \| 4200 \| 0.7412 \| 0.7223 \| 0.7222 \| \| 0.2885 \| 86.27 \| 4400 \| 0.7442 \| 0.7106 \| 0.7111 \| \| 0.2813 \| 90.2 \| 4600 \| 0.7384 \| 0.7156 \| 0.7160 \| \| 0.2693 \| 94.12 \| 4800 \| 0.7672 \| 0.7169 \| 0.7173 \| \| 0.2601 \| 98.04 \| 5000 \| 0.7531 \| 0.7219 \| 0.7222 \| \| 0.258 \| 101.96 \| 5200 \| 0.7722 \| 0.7134 \| 0.7136 \| \| 0.2492 \| 105.88 \| 5400 \| 0.8086 \| 0.7222 \| 0.7222 \| \| 0.2447 \| 109.8 \| 5600 \| 0.7982 \| 0.7073 \| 0.7074 \| \| 0.2375 \| 113.73 \| 5800 \| 0.8282 \| 0.7242 \| 0.7247 \| \| 0.2341 \| 117.65 \| 6000 \| 0.8704 \| 0.7148 \| 0.7148 \| \| 0.2313 \| 121.57 \| 6200 \| 0.8546 \| 0.7099 \| 0.7099 \| \| 0.223 \| 125.49 \| 6400 \| 0.8760 \| 0.7222 \| 0.7222 \| \| 0.222 \| 129.41 \| 6600 \| 0.8714 \| 0.7223 \| 0.7222 \| \| 0.2156 \| 133.33 \| 6800 \| 0.8522 \| 0.7294 \| 0.7296 \| \| 0.2116 \| 137.25 \| 7000 \| 0.8889 \| 0.7173 \| 0.7173 \| \| 0.2097 \| 141.18 \| 7200 \| 0.8858 \| 0.7256 \| 0.7259 \| \| 0.2085 \| 145.1 \| 7400 \| 0.8835 \| 0.7260 \| 0.7259 \| \| 0.2022 \| 149.02 \| 7600 \| 0.8739 \| 0.7269 \| 0.7272 \| \| 0.1994 \| 152.94 \| 7800 \| 0.9251 \| 0.7173 \| 0.7173 \| \| 0.1981 \| 156.86 \| 8000 \| 0.9022 \| 0.7307 \| 0.7309 \| \| 0.1976 \| 160.78 \| 8200 \| 0.9101 \| 0.7223 \| 0.7222 \| \| 0.1966 \| 164.71 \| 8400 \| 0.9368 \| 0.7247 \| 0.7247 \| \| 0.19 \| 168.63 \| 8600 \| 0.9489 \| 0.7222 \| 0.7222 \| \| 0.1955 \| 172.55 \| 8800 \| 0.9325 \| 0.7173 \| 0.7173 \| \| 0.1897 \| 176.47 \| 9000 \| 0.9419 \| 0.7222 \| 0.7222 \| \| 0.1864 \| 180.39 \| 9200 \| 0.9354 \| 0.7246 \| 0.7247 \| \| 0.1898 \| 184.31 \| 9400 \| 0.9424 \| 0.7259 \| 0.7259 \| \| 0.1855 \| 188.24 \| 9600 \| 0.9451 \| 0.7284 \| 0.7284 \| \| 0.1815 \| 192.16 \| 9800 \| 0.9510 \| 0.7222 \| 0.7222 \| \| 0.1892 \| 196.08 \| 10000 \| 0.9462 \| 0.7246 \| 0.7247 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_0-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_0-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:07:34+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_0-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_0) dataset. It achieves the following results on the evaluation set: - Loss: 1.1630 - F1 Score: 0.7037 - Accuracy: 0.7074 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6177 \| 3.92 \| 200 \| 0.5794 \| 0.6873 \| 0.6889 \| \| 0.5329 \| 7.84 \| 400 \| 0.5571 \| 0.7145 \| 0.7148 \| \| 0.4923 \| 11.76 \| 600 \| 0.5716 \| 0.7201 \| 0.7210 \| \| 0.4452 \| 15.69 \| 800 \| 0.5815 \| 0.7267 \| 0.7296 \| \| 0.4103 \| 19.61 \| 1000 \| 0.6009 \| 0.7256 \| 0.7272 \| \| 0.3683 \| 23.53 \| 1200 \| 0.7288 \| 0.7136 \| 0.7136 \| \| 0.3379 \| 27.45 \| 1400 \| 0.7234 \| 0.7280 \| 0.7284 \| \| 0.2982 \| 31.37 \| 1600 \| 0.8047 \| 0.7189 \| 0.7198 \| \| 0.276 \| 35.29 \| 1800 \| 0.8438 \| 0.7198 \| 0.7198 \| \| 0.2419 \| 39.22 \| 2000 \| 0.8574 \| 0.7049 \| 0.7049 \| \| 0.2209 \| 43.14 \| 2200 \| 0.8520 \| 0.7148 \| 0.7148 \| \| 0.1996 \| 47.06 \| 2400 \| 0.9748 \| 0.7197 \| 0.7198 \| \| 0.1742 \| 50.98 \| 2600 \| 0.9773 \| 0.7121 \| 0.7123 \| \| 0.1596 \| 54.9 \| 2800 \| 0.9787 \| 0.7433 \| 0.7444 \| \| 0.1483 \| 58.82 \| 3000 \| 1.0219 \| 0.7260 \| 0.7259 \| \| 0.1329 \| 62.75 \| 3200 \| 1.0687 \| 0.7286 \| 0.7296 \| \| 0.1201 \| 66.67 \| 3400 \| 1.0622 \| 0.7197 \| 0.7210 \| \| 0.1203 \| 70.59 \| 3600 \| 1.1993 \| 0.7194 \| 0.7198 \| \| 0.1079 \| 74.51 \| 3800 \| 1.1788 \| 0.7153 \| 0.7160 \| \| 0.0994 \| 78.43 \| 4000 \| 1.2685 \| 0.7269 \| 0.7272 \| \| 0.0961 \| 82.35 \| 4200 \| 1.2230 \| 0.7172 \| 0.7173 \| \| 0.0964 \| 86.27 \| 4400 \| 1.2038 \| 0.7209 \| 0.7210 \| \| 0.0872 \| 90.2 \| 4600 \| 1.2811 \| 0.7297 \| 0.7296 \| \| 0.0816 \| 94.12 \| 4800 \| 1.3154 \| 0.7234 \| 0.7235 \| \| 0.0789 \| 98.04 \| 5000 \| 1.3489 \| 0.7210 \| 0.7210 \| \| 0.0766 \| 101.96 \| 5200 \| 1.3078 \| 0.7272 \| 0.7272 \| \| 0.0687 \| 105.88 \| 5400 \| 1.3756 \| 0.7197 \| 0.7198 \| \| 0.0631 \| 109.8 \| 5600 \| 1.4372 \| 0.7233 \| 0.7235 \| \| 0.0645 \| 113.73 \| 5800 \| 1.4055 \| 0.7260 \| 0.7259 \| \| 0.0615 \| 117.65 \| 6000 \| 1.3889 \| 0.7223 \| 0.7222 \| \| 0.0591 \| 121.57 \| 6200 \| 1.4774 \| 0.7180 \| 0.7185 \| \| 0.0566 \| 125.49 \| 6400 \| 1.5159 \| 0.7195 \| 0.7198 \| \| 0.0525 \| 129.41 \| 6600 \| 1.5330 \| 0.7172 \| 0.7173 \| \| 0.053 \| 133.33 \| 6800 \| 1.5570 \| 0.7244 \| 0.7247 \| \| 0.0528 \| 137.25 \| 7000 \| 1.5276 \| 0.7222 \| 0.7222 \| \| 0.0487 \| 141.18 \| 7200 \| 1.5118 \| 0.7296 \| 0.7296 \| \| 0.0471 \| 145.1 \| 7400 \| 1.5333 \| 0.7210 \| 0.7210 \| \| 0.0479 \| 149.02 \| 7600 \| 1.5198 \| 0.7271 \| 0.7272 \| \| 0.0431 \| 152.94 \| 7800 \| 1.5453 \| 0.7197 \| 0.7198 \| \| 0.0442 \| 156.86 \| 8000 \| 1.5638 \| 0.7296 \| 0.7296 \| \| 0.0426 \| 160.78 \| 8200 \| 1.5832 \| 0.7222 \| 0.7222 \| \| 0.0392 \| 164.71 \| 8400 \| 1.6342 \| 0.7209 \| 0.7210 \| \| 0.0373 \| 168.63 \| 8600 \| 1.6430 \| 0.7219 \| 0.7222 \| \| 0.0388 \| 172.55 \| 8800 \| 1.6083 \| 0.7284 \| 0.7284 \| \| 0.0365 \| 176.47 \| 9000 \| 1.6100 \| 0.7196 \| 0.7198 \| \| 0.0368 \| 180.39 \| 9200 \| 1.6320 \| 0.7296 \| 0.7296 \| \| 0.0388 \| 184.31 \| 9400 \| 1.6367 \| 0.7259 \| 0.7259 \| \| 0.0381 \| 188.24 \| 9600 \| 1.6066 \| 0.7246 \| 0.7247 \| \| 0.0333 \| 192.16 \| 9800 \| 1.6421 \| 0.7271 \| 0.7272 \| \| 0.0348 \| 196.08 \| 10000 \| 1.6420 \| 0.7233 \| 0.7235 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_0-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_0-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:08:18+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_1-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.2519 - F1 Score: 0.8867 - Accuracy: 0.8867 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4803 \| 0.47 \| 200 \| 0.3522 \| 0.8435 \| 0.8437 \| \| 0.3667 \| 0.95 \| 400 \| 0.3135 \| 0.8613 \| 0.8614 \| \| 0.3353 \| 1.42 \| 600 \| 0.3008 \| 0.8680 \| 0.8681 \| \| 0.3373 \| 1.9 \| 800 \| 0.2901 \| 0.8708 \| 0.8709 \| \| 0.3169 \| 2.37 \| 1000 \| 0.2873 \| 0.8730 \| 0.8731 \| \| 0.3145 \| 2.84 \| 1200 \| 0.2840 \| 0.8760 \| 0.8762 \| \| 0.3044 \| 3.32 \| 1400 \| 0.2825 \| 0.8752 \| 0.8752 \| \| 0.3106 \| 3.79 \| 1600 \| 0.2766 \| 0.8777 \| 0.8777 \| \| 0.3023 \| 4.27 \| 1800 \| 0.2744 \| 0.8825 \| 0.8827 \| \| 0.2985 \| 4.74 \| 2000 \| 0.2720 \| 0.8822 \| 0.8823 \| \| 0.298 \| 5.21 \| 2200 \| 0.2778 \| 0.8775 \| 0.8780 \| \| 0.2964 \| 5.69 \| 2400 \| 0.2721 \| 0.8812 \| 0.8812 \| \| 0.2887 \| 6.16 \| 2600 \| 0.2656 \| 0.8853 \| 0.8854 \| \| 0.2872 \| 6.64 \| 2800 \| 0.2630 \| 0.8875 \| 0.8876 \| \| 0.2908 \| 7.11 \| 3000 \| 0.2635 \| 0.8866 \| 0.8866 \| \| 0.2861 \| 7.58 \| 3200 \| 0.2734 \| 0.8809 \| 0.8809 \| \| 0.2832 \| 8.06 \| 3400 \| 0.2589 \| 0.8885 \| 0.8887 \| \| 0.2781 \| 8.53 \| 3600 \| 0.2621 \| 0.8881 \| 0.8881 \| \| 0.282 \| 9.0 \| 3800 \| 0.2568 \| 0.8895 \| 0.8895 \| \| 0.275 \| 9.48 \| 4000 \| 0.2567 \| 0.8894 \| 0.8895 \| \| 0.2776 \| 9.95 \| 4200 \| 0.2528 \| 0.8923 \| 0.8924 \| \| 0.2707 \| 10.43 \| 4400 \| 0.2533 \| 0.8934 \| 0.8934 \| \| 0.2728 \| 10.9 \| 4600 \| 0.2537 \| 0.8909 \| 0.8909 \| \| 0.2639 \| 11.37 \| 4800 \| 0.2552 \| 0.8904 \| 0.8904 \| \| 0.2747 \| 11.85 \| 5000 \| 0.2487 \| 0.8938 \| 0.8938 \| \| 0.2663 \| 12.32 \| 5200 \| 0.2543 \| 0.8900 \| 0.8900 \| \| 0.2672 \| 12.8 \| 5400 \| 0.2518 \| 0.8928 \| 0.8928 \| \| 0.2726 \| 13.27 \| 5600 \| 0.2460 \| 0.8931 \| 0.8931 \| \| 0.2636 \| 13.74 \| 5800 \| 0.2459 \| 0.8950 \| 0.8950 \| \| 0.2654 \| 14.22 \| 6000 \| 0.2490 \| 0.8936 \| 0.8936 \| \| 0.2609 \| 14.69 \| 6200 \| 0.2465 \| 0.8944 \| 0.8944 \| \| 0.2652 \| 15.17 \| 6400 \| 0.2537 \| 0.8916 \| 0.8916 \| \| 0.264 \| 15.64 \| 6600 \| 0.2448 \| 0.8956 \| 0.8956 \| \| 0.2598 \| 16.11 \| 6800 \| 0.2424 \| 0.8944 \| 0.8944 \| \| 0.2616 \| 16.59 \| 7000 \| 0.2428 \| 0.8941 \| 0.8941 \| \| 0.2581 \| 17.06 \| 7200 \| 0.2438 \| 0.8953 \| 0.8953 \| \| 0.263 \| 17.54 \| 7400 \| 0.2485 \| 0.8929 \| 0.8930 \| \| 0.2603 \| 18.01 \| 7600 \| 0.2417 \| 0.8962 \| 0.8962 \| \| 0.254 \| 18.48 \| 7800 \| 0.2438 \| 0.8971 \| 0.8971 \| \| 0.262 \| 18.96 \| 8000 \| 0.2416 \| 0.8959 \| 0.8959 \| \| 0.2571 \| 19.43 \| 8200 \| 0.2421 \| 0.8956 \| 0.8956 \| \| 0.2592 \| 19.91 \| 8400 \| 0.2406 \| 0.8950 \| 0.8950 \| \| 0.2624 \| 20.38 \| 8600 \| 0.2420 \| 0.8959 \| 0.8959 \| \| 0.2557 \| 20.85 \| 8800 \| 0.2401 \| 0.8947 \| 0.8947 \| \| 0.2553 \| 21.33 \| 9000 \| 0.2421 \| 0.8961 \| 0.8961 \| \| 0.2558 \| 21.8 \| 9200 \| 0.2433 \| 0.8962 \| 0.8962 \| \| 0.2579 \| 22.27 \| 9400 \| 0.2421 \| 0.8962 \| 0.8962 \| \| 0.252 \| 22.75 \| 9600 \| 0.2411 \| 0.8965 \| 0.8965 \| \| 0.2553 \| 23.22 \| 9800 \| 0.2416 \| 0.8962 \| 0.8962 \| \| 0.2589 \| 23.7 \| 10000 \| 0.2420 \| 0.8958 \| 0.8958 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_1-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_1-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:08:45+00:00
text-generation	null	## Exllama v2 Quantizations of NPC-LLM-3_8B Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</a> for quantization. <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b> Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions. Conversion was done using the default calibration dataset. Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6. Original model: https://huggingface.co/Gigax/NPC-LLM-3_8B <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/8_0">8.0 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/6_5">6.5 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/5_0">5.0 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/4_25">4.25 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/3_5">3.5 bits per weight</a> ## Download instructions With git: ```shell git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2 ``` With huggingface hub (credit to TheBloke for instructions): ```shell pip3 install huggingface-hub ``` To download the `main` (only useful if you only care about measurement.json) branch to a folder called `NPC-LLM-3_8B-exl2`: ```shell mkdir NPC-LLM-3_8B-exl2 huggingface-cli download bartowski/NPC-LLM-3_8B-exl2 --local-dir NPC-LLM-3_8B-exl2 --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: Linux: ```shell mkdir NPC-LLM-3_8B-exl2-6_5 huggingface-cli download bartowski/NPC-LLM-3_8B-exl2 --revision 6_5 --local-dir NPC-LLM-3_8B-exl2-6_5 --local-dir-use-symlinks False ``` Windows (which apparently doesn't like _ in folders sometimes?): ```shell mkdir NPC-LLM-3_8B-exl2-6.5 huggingface-cli download bartowski/NPC-LLM-3_8B-exl2 --revision 6_5 --local-dir NPC-LLM-3_8B-exl2-6.5 --local-dir-use-symlinks False ```	{"language": ["en"], "license": "mit", "quantized_by": "bartowski", "pipeline_tag": "text-generation"}	bartowski/NPC-LLM-3_8B-exl2	null	[ "text-generation", "en", "license:mit", "region:us" ]	null	2024-04-29T23:09:15+00:00
null	null		{"license": "openrail"}	martinvdv05/FNaF-SB	null	[ "license:openrail", "region:us" ]	null	2024-04-29T23:09:51+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	franciscobdl/EstigiaxTinyLlama	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T23:14:24+00:00
text-generation	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # 0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2 This model is a fine-tuned version of [ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1](https://huggingface.co/ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2	{"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1", "model-index": [{"name": "0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2", "results": []}]}	ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T23:14:50+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	Shaleen123/llama3-code-4bit	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-04-29T23:15:32+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_1-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.2345 - F1 Score: 0.8950 - Accuracy: 0.8950 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4305 \| 0.47 \| 200 \| 0.3166 \| 0.8587 \| 0.8587 \| \| 0.333 \| 0.95 \| 400 \| 0.2954 \| 0.8715 \| 0.8715 \| \| 0.3115 \| 1.42 \| 600 \| 0.2770 \| 0.8795 \| 0.8796 \| \| 0.3138 \| 1.9 \| 800 \| 0.2689 \| 0.8823 \| 0.8824 \| \| 0.2915 \| 2.37 \| 1000 \| 0.2645 \| 0.8836 \| 0.8836 \| \| 0.2865 \| 2.84 \| 1200 \| 0.2562 \| 0.8895 \| 0.8895 \| \| 0.2717 \| 3.32 \| 1400 \| 0.2552 \| 0.8886 \| 0.8887 \| \| 0.2773 \| 3.79 \| 1600 \| 0.2578 \| 0.8873 \| 0.8873 \| \| 0.2664 \| 4.27 \| 1800 \| 0.2410 \| 0.8973 \| 0.8973 \| \| 0.2631 \| 4.74 \| 2000 \| 0.2383 \| 0.8956 \| 0.8956 \| \| 0.2598 \| 5.21 \| 2200 \| 0.2403 \| 0.8946 \| 0.8949 \| \| 0.2573 \| 5.69 \| 2400 \| 0.2484 \| 0.8910 \| 0.8910 \| \| 0.2487 \| 6.16 \| 2600 \| 0.2318 \| 0.9008 \| 0.9008 \| \| 0.2484 \| 6.64 \| 2800 \| 0.2346 \| 0.8992 \| 0.8992 \| \| 0.2522 \| 7.11 \| 3000 \| 0.2354 \| 0.8978 \| 0.8979 \| \| 0.2451 \| 7.58 \| 3200 \| 0.2470 \| 0.8949 \| 0.8949 \| \| 0.2448 \| 8.06 \| 3400 \| 0.2279 \| 0.9005 \| 0.9005 \| \| 0.2396 \| 8.53 \| 3600 \| 0.2414 \| 0.8962 \| 0.8962 \| \| 0.245 \| 9.0 \| 3800 \| 0.2314 \| 0.8996 \| 0.8996 \| \| 0.2386 \| 9.48 \| 4000 \| 0.2270 \| 0.8998 \| 0.8998 \| \| 0.2397 \| 9.95 \| 4200 \| 0.2290 \| 0.8993 \| 0.8993 \| \| 0.2334 \| 10.43 \| 4400 \| 0.2300 \| 0.9017 \| 0.9017 \| \| 0.2339 \| 10.9 \| 4600 \| 0.2333 \| 0.8989 \| 0.8989 \| \| 0.2282 \| 11.37 \| 4800 \| 0.2327 \| 0.9009 \| 0.9010 \| \| 0.2385 \| 11.85 \| 5000 \| 0.2271 \| 0.9021 \| 0.9021 \| \| 0.2322 \| 12.32 \| 5200 \| 0.2314 \| 0.8987 \| 0.8987 \| \| 0.2331 \| 12.8 \| 5400 \| 0.2334 \| 0.8993 \| 0.8993 \| \| 0.2331 \| 13.27 \| 5600 \| 0.2239 \| 0.9008 \| 0.9008 \| \| 0.2281 \| 13.74 \| 5800 \| 0.2244 \| 0.9021 \| 0.9021 \| \| 0.2304 \| 14.22 \| 6000 \| 0.2344 \| 0.8996 \| 0.8996 \| \| 0.2264 \| 14.69 \| 6200 \| 0.2260 \| 0.9033 \| 0.9033 \| \| 0.2287 \| 15.17 \| 6400 \| 0.2348 \| 0.8989 \| 0.8989 \| \| 0.2287 \| 15.64 \| 6600 \| 0.2262 \| 0.9002 \| 0.9002 \| \| 0.2223 \| 16.11 \| 6800 \| 0.2227 \| 0.9018 \| 0.9019 \| \| 0.2241 \| 16.59 \| 7000 \| 0.2269 \| 0.9018 \| 0.9019 \| \| 0.2261 \| 17.06 \| 7200 \| 0.2250 \| 0.9023 \| 0.9023 \| \| 0.2244 \| 17.54 \| 7400 \| 0.2284 \| 0.9016 \| 0.9016 \| \| 0.2244 \| 18.01 \| 7600 \| 0.2225 \| 0.9023 \| 0.9023 \| \| 0.2187 \| 18.48 \| 7800 \| 0.2273 \| 0.9017 \| 0.9017 \| \| 0.2256 \| 18.96 \| 8000 \| 0.2212 \| 0.9030 \| 0.9030 \| \| 0.2214 \| 19.43 \| 8200 \| 0.2252 \| 0.9024 \| 0.9024 \| \| 0.2247 \| 19.91 \| 8400 \| 0.2218 \| 0.9030 \| 0.9030 \| \| 0.2237 \| 20.38 \| 8600 \| 0.2243 \| 0.9020 \| 0.9020 \| \| 0.2217 \| 20.85 \| 8800 \| 0.2215 \| 0.9041 \| 0.9041 \| \| 0.2185 \| 21.33 \| 9000 \| 0.2262 \| 0.9015 \| 0.9016 \| \| 0.2178 \| 21.8 \| 9200 \| 0.2272 \| 0.9010 \| 0.9010 \| \| 0.2216 \| 22.27 \| 9400 \| 0.2249 \| 0.9023 \| 0.9023 \| \| 0.2157 \| 22.75 \| 9600 \| 0.2225 \| 0.9033 \| 0.9033 \| \| 0.2174 \| 23.22 \| 9800 \| 0.2245 \| 0.9027 \| 0.9027 \| \| 0.2222 \| 23.7 \| 10000 \| 0.2247 \| 0.9016 \| 0.9016 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_1-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_1-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:17:46+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_1-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.2318 - F1 Score: 0.9017 - Accuracy: 0.9017 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4117 \| 0.47 \| 200 \| 0.3138 \| 0.8630 \| 0.8632 \| \| 0.3169 \| 0.95 \| 400 \| 0.2770 \| 0.8805 \| 0.8805 \| \| 0.2909 \| 1.42 \| 600 \| 0.2570 \| 0.8890 \| 0.8891 \| \| 0.2872 \| 1.9 \| 800 \| 0.2507 \| 0.8895 \| 0.8895 \| \| 0.2663 \| 2.37 \| 1000 \| 0.2452 \| 0.8930 \| 0.8930 \| \| 0.2604 \| 2.84 \| 1200 \| 0.2369 \| 0.8961 \| 0.8961 \| \| 0.2471 \| 3.32 \| 1400 \| 0.2436 \| 0.8959 \| 0.8959 \| \| 0.2551 \| 3.79 \| 1600 \| 0.2381 \| 0.8980 \| 0.8980 \| \| 0.2457 \| 4.27 \| 1800 \| 0.2311 \| 0.9013 \| 0.9013 \| \| 0.2457 \| 4.74 \| 2000 \| 0.2325 \| 0.8979 \| 0.8980 \| \| 0.241 \| 5.21 \| 2200 \| 0.2374 \| 0.8974 \| 0.8977 \| \| 0.2418 \| 5.69 \| 2400 \| 0.2369 \| 0.8972 \| 0.8973 \| \| 0.2321 \| 6.16 \| 2600 \| 0.2238 \| 0.9021 \| 0.9021 \| \| 0.2322 \| 6.64 \| 2800 \| 0.2251 \| 0.9036 \| 0.9036 \| \| 0.2345 \| 7.11 \| 3000 \| 0.2356 \| 0.8987 \| 0.8987 \| \| 0.2276 \| 7.58 \| 3200 \| 0.2362 \| 0.8975 \| 0.8976 \| \| 0.2289 \| 8.06 \| 3400 \| 0.2231 \| 0.9024 \| 0.9024 \| \| 0.2203 \| 8.53 \| 3600 \| 0.2283 \| 0.9007 \| 0.9007 \| \| 0.2273 \| 9.0 \| 3800 \| 0.2271 \| 0.9041 \| 0.9041 \| \| 0.2192 \| 9.48 \| 4000 \| 0.2194 \| 0.9049 \| 0.9050 \| \| 0.2205 \| 9.95 \| 4200 \| 0.2202 \| 0.9035 \| 0.9035 \| \| 0.2139 \| 10.43 \| 4400 \| 0.2266 \| 0.9020 \| 0.9020 \| \| 0.2155 \| 10.9 \| 4600 \| 0.2237 \| 0.9029 \| 0.9029 \| \| 0.2068 \| 11.37 \| 4800 \| 0.2238 \| 0.9023 \| 0.9023 \| \| 0.2198 \| 11.85 \| 5000 \| 0.2209 \| 0.9050 \| 0.9050 \| \| 0.212 \| 12.32 \| 5200 \| 0.2236 \| 0.9024 \| 0.9024 \| \| 0.2112 \| 12.8 \| 5400 \| 0.2301 \| 0.9020 \| 0.9020 \| \| 0.2099 \| 13.27 \| 5600 \| 0.2196 \| 0.9039 \| 0.9039 \| \| 0.2048 \| 13.74 \| 5800 \| 0.2204 \| 0.9027 \| 0.9027 \| \| 0.2068 \| 14.22 \| 6000 \| 0.2324 \| 0.8996 \| 0.8996 \| \| 0.2049 \| 14.69 \| 6200 \| 0.2193 \| 0.9064 \| 0.9064 \| \| 0.2065 \| 15.17 \| 6400 \| 0.2255 \| 0.9026 \| 0.9026 \| \| 0.2041 \| 15.64 \| 6600 \| 0.2215 \| 0.9050 \| 0.9050 \| \| 0.1999 \| 16.11 \| 6800 \| 0.2212 \| 0.9067 \| 0.9067 \| \| 0.1997 \| 16.59 \| 7000 \| 0.2217 \| 0.9041 \| 0.9041 \| \| 0.2026 \| 17.06 \| 7200 \| 0.2225 \| 0.9048 \| 0.9048 \| \| 0.1981 \| 17.54 \| 7400 \| 0.2236 \| 0.9050 \| 0.9050 \| \| 0.1987 \| 18.01 \| 7600 \| 0.2184 \| 0.9051 \| 0.9051 \| \| 0.1928 \| 18.48 \| 7800 \| 0.2236 \| 0.9027 \| 0.9027 \| \| 0.1982 \| 18.96 \| 8000 \| 0.2169 \| 0.9061 \| 0.9062 \| \| 0.1921 \| 19.43 \| 8200 \| 0.2213 \| 0.9060 \| 0.9060 \| \| 0.1988 \| 19.91 \| 8400 \| 0.2193 \| 0.9063 \| 0.9063 \| \| 0.1946 \| 20.38 \| 8600 \| 0.2241 \| 0.9050 \| 0.9050 \| \| 0.1945 \| 20.85 \| 8800 \| 0.2202 \| 0.9042 \| 0.9042 \| \| 0.1901 \| 21.33 \| 9000 \| 0.2246 \| 0.9035 \| 0.9035 \| \| 0.1891 \| 21.8 \| 9200 \| 0.2254 \| 0.9038 \| 0.9038 \| \| 0.1912 \| 22.27 \| 9400 \| 0.2207 \| 0.9047 \| 0.9047 \| \| 0.1873 \| 22.75 \| 9600 \| 0.2218 \| 0.9041 \| 0.9041 \| \| 0.1879 \| 23.22 \| 9800 \| 0.2225 \| 0.9045 \| 0.9045 \| \| 0.1929 \| 23.7 \| 10000 \| 0.2227 \| 0.9044 \| 0.9044 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_1-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_1-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:17:52+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_4-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.5700 - F1 Score: 0.6988 - Accuracy: 0.6989 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6556 \| 1.69 \| 200 \| 0.6362 \| 0.6178 \| 0.6235 \| \| 0.6313 \| 3.39 \| 400 \| 0.6152 \| 0.6557 \| 0.6564 \| \| 0.6176 \| 5.08 \| 600 \| 0.6042 \| 0.6498 \| 0.6511 \| \| 0.6046 \| 6.78 \| 800 \| 0.5874 \| 0.6737 \| 0.6739 \| \| 0.595 \| 8.47 \| 1000 \| 0.5771 \| 0.6888 \| 0.6888 \| \| 0.5855 \| 10.17 \| 1200 \| 0.5765 \| 0.6882 \| 0.6888 \| \| 0.5789 \| 11.86 \| 1400 \| 0.5677 \| 0.6989 \| 0.6989 \| \| 0.5756 \| 13.56 \| 1600 \| 0.5644 \| 0.6990 \| 0.6989 \| \| 0.5721 \| 15.25 \| 1800 \| 0.5621 \| 0.7069 \| 0.7074 \| \| 0.5682 \| 16.95 \| 2000 \| 0.5675 \| 0.6970 \| 0.6989 \| \| 0.5671 \| 18.64 \| 2200 \| 0.5605 \| 0.7053 \| 0.7058 \| \| 0.5625 \| 20.34 \| 2400 \| 0.5544 \| 0.7128 \| 0.7127 \| \| 0.5624 \| 22.03 \| 2600 \| 0.5772 \| 0.6856 \| 0.6904 \| \| 0.5555 \| 23.73 \| 2800 \| 0.5542 \| 0.7122 \| 0.7122 \| \| 0.555 \| 25.42 \| 3000 \| 0.5544 \| 0.7175 \| 0.7175 \| \| 0.5525 \| 27.12 \| 3200 \| 0.5617 \| 0.7028 \| 0.7047 \| \| 0.5494 \| 28.81 \| 3400 \| 0.5533 \| 0.7141 \| 0.7143 \| \| 0.5464 \| 30.51 \| 3600 \| 0.5561 \| 0.7165 \| 0.7164 \| \| 0.5487 \| 32.2 \| 3800 \| 0.5546 \| 0.7123 \| 0.7127 \| \| 0.5452 \| 33.9 \| 4000 \| 0.5589 \| 0.7040 \| 0.7053 \| \| 0.5421 \| 35.59 \| 4200 \| 0.5630 \| 0.7076 \| 0.7090 \| \| 0.5438 \| 37.29 \| 4400 \| 0.5570 \| 0.7118 \| 0.7127 \| \| 0.5432 \| 38.98 \| 4600 \| 0.5532 \| 0.7146 \| 0.7148 \| \| 0.539 \| 40.68 \| 4800 \| 0.5671 \| 0.6973 \| 0.6999 \| \| 0.5387 \| 42.37 \| 5000 \| 0.5582 \| 0.7127 \| 0.7132 \| \| 0.5412 \| 44.07 \| 5200 \| 0.5535 \| 0.7179 \| 0.7180 \| \| 0.5391 \| 45.76 \| 5400 \| 0.5527 \| 0.7105 \| 0.7106 \| \| 0.534 \| 47.46 \| 5600 \| 0.5526 \| 0.7106 \| 0.7106 \| \| 0.5347 \| 49.15 \| 5800 \| 0.5577 \| 0.7122 \| 0.7132 \| \| 0.5351 \| 50.85 \| 6000 \| 0.5569 \| 0.7097 \| 0.7106 \| \| 0.5332 \| 52.54 \| 6200 \| 0.5517 \| 0.7112 \| 0.7111 \| \| 0.528 \| 54.24 \| 6400 \| 0.5515 \| 0.7132 \| 0.7132 \| \| 0.5348 \| 55.93 \| 6600 \| 0.5490 \| 0.7149 \| 0.7148 \| \| 0.5287 \| 57.63 \| 6800 \| 0.5500 \| 0.7192 \| 0.7191 \| \| 0.5285 \| 59.32 \| 7000 \| 0.5563 \| 0.7120 \| 0.7127 \| \| 0.5287 \| 61.02 \| 7200 \| 0.5522 \| 0.7137 \| 0.7138 \| \| 0.5309 \| 62.71 \| 7400 \| 0.5497 \| 0.7159 \| 0.7159 \| \| 0.528 \| 64.41 \| 7600 \| 0.5514 \| 0.7111 \| 0.7111 \| \| 0.5321 \| 66.1 \| 7800 \| 0.5503 \| 0.7143 \| 0.7143 \| \| 0.5279 \| 67.8 \| 8000 \| 0.5502 \| 0.7148 \| 0.7148 \| \| 0.5282 \| 69.49 \| 8200 \| 0.5491 \| 0.7159 \| 0.7159 \| \| 0.5267 \| 71.19 \| 8400 \| 0.5513 \| 0.7148 \| 0.7148 \| \| 0.5247 \| 72.88 \| 8600 \| 0.5498 \| 0.7138 \| 0.7138 \| \| 0.5226 \| 74.58 \| 8800 \| 0.5513 \| 0.7163 \| 0.7164 \| \| 0.5262 \| 76.27 \| 9000 \| 0.5518 \| 0.7158 \| 0.7159 \| \| 0.5232 \| 77.97 \| 9200 \| 0.5512 \| 0.7158 \| 0.7159 \| \| 0.5215 \| 79.66 \| 9400 \| 0.5506 \| 0.7154 \| 0.7153 \| \| 0.5269 \| 81.36 \| 9600 \| 0.5503 \| 0.7143 \| 0.7143 \| \| 0.5241 \| 83.05 \| 9800 \| 0.5504 \| 0.7148 \| 0.7148 \| \| 0.5238 \| 84.75 \| 10000 \| 0.5508 \| 0.7126 \| 0.7127 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_4-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_4-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:18:40+00:00
null	null		{"license": "apache-2.0"}	razqr1911/trained1	null	[ "safetensors", "license:apache-2.0", "region:us" ]	null	2024-04-29T23:18:47+00:00
null	null		{}	josiahgottfried/amtibot_pegasus_pbt_1	null	[ "region:us" ]	null	2024-04-29T23:19:19+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_4-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.5910 - F1 Score: 0.7116 - Accuracy: 0.7116 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6436 \| 1.69 \| 200 \| 0.6117 \| 0.6527 \| 0.6543 \| \| 0.6093 \| 3.39 \| 400 \| 0.6026 \| 0.6510 \| 0.6591 \| \| 0.5868 \| 5.08 \| 600 \| 0.5730 \| 0.6979 \| 0.6978 \| \| 0.572 \| 6.78 \| 800 \| 0.5650 \| 0.7006 \| 0.7010 \| \| 0.5645 \| 8.47 \| 1000 \| 0.5782 \| 0.6926 \| 0.6962 \| \| 0.5518 \| 10.17 \| 1200 \| 0.5679 \| 0.7036 \| 0.7037 \| \| 0.5462 \| 11.86 \| 1400 \| 0.5613 \| 0.7027 \| 0.7026 \| \| 0.5379 \| 13.56 \| 1600 \| 0.5660 \| 0.7046 \| 0.7047 \| \| 0.5352 \| 15.25 \| 1800 \| 0.5611 \| 0.7085 \| 0.7090 \| \| 0.5297 \| 16.95 \| 2000 \| 0.5727 \| 0.6963 \| 0.6989 \| \| 0.5244 \| 18.64 \| 2200 \| 0.5860 \| 0.6914 \| 0.6946 \| \| 0.5203 \| 20.34 \| 2400 \| 0.5614 \| 0.7110 \| 0.7111 \| \| 0.5162 \| 22.03 \| 2600 \| 0.5711 \| 0.7024 \| 0.7037 \| \| 0.5072 \| 23.73 \| 2800 \| 0.5593 \| 0.7111 \| 0.7111 \| \| 0.5028 \| 25.42 \| 3000 \| 0.5651 \| 0.7133 \| 0.7138 \| \| 0.4981 \| 27.12 \| 3200 \| 0.5684 \| 0.7101 \| 0.7100 \| \| 0.4913 \| 28.81 \| 3400 \| 0.5699 \| 0.7090 \| 0.7090 \| \| 0.4847 \| 30.51 \| 3600 \| 0.5746 \| 0.7106 \| 0.7106 \| \| 0.4872 \| 32.2 \| 3800 \| 0.5799 \| 0.7156 \| 0.7159 \| \| 0.4819 \| 33.9 \| 4000 \| 0.5789 \| 0.7079 \| 0.7079 \| \| 0.4739 \| 35.59 \| 4200 \| 0.5968 \| 0.7004 \| 0.7010 \| \| 0.4774 \| 37.29 \| 4400 \| 0.5751 \| 0.7128 \| 0.7127 \| \| 0.4731 \| 38.98 \| 4600 \| 0.5734 \| 0.7175 \| 0.7175 \| \| 0.4652 \| 40.68 \| 4800 \| 0.6021 \| 0.7014 \| 0.7021 \| \| 0.4623 \| 42.37 \| 5000 \| 0.5976 \| 0.7149 \| 0.7148 \| \| 0.4604 \| 44.07 \| 5200 \| 0.6079 \| 0.7095 \| 0.7095 \| \| 0.4607 \| 45.76 \| 5400 \| 0.5911 \| 0.7133 \| 0.7132 \| \| 0.4509 \| 47.46 \| 5600 \| 0.6176 \| 0.7146 \| 0.7148 \| \| 0.4536 \| 49.15 \| 5800 \| 0.6003 \| 0.7096 \| 0.7095 \| \| 0.4478 \| 50.85 \| 6000 \| 0.5923 \| 0.7123 \| 0.7122 \| \| 0.445 \| 52.54 \| 6200 \| 0.6070 \| 0.7148 \| 0.7148 \| \| 0.4381 \| 54.24 \| 6400 \| 0.6022 \| 0.7139 \| 0.7138 \| \| 0.4456 \| 55.93 \| 6600 \| 0.5996 \| 0.7096 \| 0.7095 \| \| 0.4369 \| 57.63 \| 6800 \| 0.6064 \| 0.7139 \| 0.7138 \| \| 0.4353 \| 59.32 \| 7000 \| 0.6163 \| 0.7082 \| 0.7084 \| \| 0.4355 \| 61.02 \| 7200 \| 0.6118 \| 0.7106 \| 0.7106 \| \| 0.4355 \| 62.71 \| 7400 \| 0.6045 \| 0.7143 \| 0.7143 \| \| 0.4311 \| 64.41 \| 7600 \| 0.6077 \| 0.7038 \| 0.7037 \| \| 0.434 \| 66.1 \| 7800 \| 0.6098 \| 0.7064 \| 0.7063 \| \| 0.4284 \| 67.8 \| 8000 \| 0.6108 \| 0.7075 \| 0.7074 \| \| 0.4268 \| 69.49 \| 8200 \| 0.6117 \| 0.7038 \| 0.7037 \| \| 0.427 \| 71.19 \| 8400 \| 0.6174 \| 0.7084 \| 0.7084 \| \| 0.4242 \| 72.88 \| 8600 \| 0.6175 \| 0.7101 \| 0.7100 \| \| 0.4192 \| 74.58 \| 8800 \| 0.6206 \| 0.7090 \| 0.7090 \| \| 0.4201 \| 76.27 \| 9000 \| 0.6232 \| 0.7038 \| 0.7037 \| \| 0.4184 \| 77.97 \| 9200 \| 0.6243 \| 0.7038 \| 0.7037 \| \| 0.4182 \| 79.66 \| 9400 \| 0.6232 \| 0.7068 \| 0.7069 \| \| 0.4214 \| 81.36 \| 9600 \| 0.6223 \| 0.7064 \| 0.7063 \| \| 0.4217 \| 83.05 \| 9800 \| 0.6208 \| 0.7048 \| 0.7047 \| \| 0.4147 \| 84.75 \| 10000 \| 0.6218 \| 0.7053 \| 0.7053 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_4-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_4-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:20:03+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"license": "apache-2.0", "library_name": "transformers"}	Shaleen123/llama3-code-8bit	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]	null	2024-04-29T23:20:15+00:00
null	peft	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.10.0	{"library_name": "peft", "base_model": "mistralai/Mistral-7B-Instruct-v0.1"}	Akshay24/mistral7b_finetuned_tijori	null	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.1", "region:us" ]	null	2024-04-29T23:21:03+00:00
text-generation	gguf	# Megac4ai-command-r-plus-gguf These are quantized GGUF versions of [nitky/Megac4ai-command-r-plus](https://huggingface.co/nitky/Megac4ai-command-r-plus). Please check the original model for license and more details. ## Results for non-English languages (Japanese) \| Model \| Output Quality \| Notes \| \|-------\|----------------\|-------\| \| Megac4ai-command-r-plus-IQ3_XS.gguf \| Poor \| \| \| Megac4ai-command-r-plus-IQ4_XS.gguf \| Average \| \| \| Megac4ai-command-r-plus-Q4_K_M.gguf \| Good \| recommended \| \| Megac4ai-command-r-plus-Q5_K_M.gguf \| Good \| \| \| Megac4ai-command-r-plus-Q6_K.gguf \| Excellent \| recommended \| \| Megac4ai-command-r-plus-Q8_0.gguf \| Excellent \| \|	{"language": ["en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar"], "license": "cc-by-nc-4.0", "library_name": "gguf", "tags": ["mergekit", "merge"], "base_model": ["CohereForAI/c4ai-command-r-plus"], "pipeline_tag": "text-generation"}	nitky/Megac4ai-command-r-plus-gguf	null	[ "gguf", "mergekit", "merge", "text-generation", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "base_model:CohereForAI/c4ai-command-r-plus", "license:cc-by-nc-4.0", "region:us" ]	null	2024-04-29T23:22:35+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_4-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.6491 - F1 Score: 0.7024 - Accuracy: 0.7026 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.6347 \| 1.69 \| 200 \| 0.5944 \| 0.6853 \| 0.6872 \| \| 0.5914 \| 3.39 \| 400 \| 0.5758 \| 0.6823 \| 0.6835 \| \| 0.5678 \| 5.08 \| 600 \| 0.5639 \| 0.7058 \| 0.7063 \| \| 0.5493 \| 6.78 \| 800 \| 0.5648 \| 0.6908 \| 0.6930 \| \| 0.5397 \| 8.47 \| 1000 \| 0.5903 \| 0.6786 \| 0.6840 \| \| 0.5174 \| 10.17 \| 1200 \| 0.5686 \| 0.7030 \| 0.7031 \| \| 0.5081 \| 11.86 \| 1400 \| 0.5634 \| 0.7069 \| 0.7069 \| \| 0.4907 \| 13.56 \| 1600 \| 0.5732 \| 0.7088 \| 0.7090 \| \| 0.4796 \| 15.25 \| 1800 \| 0.5734 \| 0.7091 \| 0.7090 \| \| 0.4654 \| 16.95 \| 2000 \| 0.5799 \| 0.6984 \| 0.6994 \| \| 0.4539 \| 18.64 \| 2200 \| 0.5960 \| 0.7091 \| 0.7100 \| \| 0.4417 \| 20.34 \| 2400 \| 0.5979 \| 0.7099 \| 0.7100 \| \| 0.4265 \| 22.03 \| 2600 \| 0.6262 \| 0.7141 \| 0.7148 \| \| 0.413 \| 23.73 \| 2800 \| 0.6192 \| 0.7169 \| 0.7169 \| \| 0.4037 \| 25.42 \| 3000 \| 0.6166 \| 0.7123 \| 0.7143 \| \| 0.3919 \| 27.12 \| 3200 \| 0.6586 \| 0.7169 \| 0.7169 \| \| 0.3788 \| 28.81 \| 3400 \| 0.6822 \| 0.7117 \| 0.7116 \| \| 0.3654 \| 30.51 \| 3600 \| 0.6812 \| 0.7043 \| 0.7042 \| \| 0.3593 \| 32.2 \| 3800 \| 0.7320 \| 0.6999 \| 0.6999 \| \| 0.3521 \| 33.9 \| 4000 \| 0.7206 \| 0.7081 \| 0.7084 \| \| 0.3371 \| 35.59 \| 4200 \| 0.7422 \| 0.7042 \| 0.7042 \| \| 0.3343 \| 37.29 \| 4400 \| 0.7608 \| 0.7135 \| 0.7143 \| \| 0.325 \| 38.98 \| 4600 \| 0.7313 \| 0.7006 \| 0.7005 \| \| 0.3108 \| 40.68 \| 4800 \| 0.8242 \| 0.7102 \| 0.7111 \| \| 0.3039 \| 42.37 \| 5000 \| 0.7951 \| 0.7101 \| 0.7100 \| \| 0.298 \| 44.07 \| 5200 \| 0.8027 \| 0.7073 \| 0.7074 \| \| 0.2907 \| 45.76 \| 5400 \| 0.8170 \| 0.7106 \| 0.7106 \| \| 0.2814 \| 47.46 \| 5600 \| 0.8783 \| 0.7108 \| 0.7111 \| \| 0.279 \| 49.15 \| 5800 \| 0.8531 \| 0.7032 \| 0.7031 \| \| 0.2682 \| 50.85 \| 6000 \| 0.8655 \| 0.6935 \| 0.6936 \| \| 0.2638 \| 52.54 \| 6200 \| 0.8895 \| 0.7065 \| 0.7069 \| \| 0.2617 \| 54.24 \| 6400 \| 0.8833 \| 0.7026 \| 0.7026 \| \| 0.2607 \| 55.93 \| 6600 \| 0.9108 \| 0.7068 \| 0.7069 \| \| 0.2497 \| 57.63 \| 6800 \| 0.9018 \| 0.7032 \| 0.7031 \| \| 0.2518 \| 59.32 \| 7000 \| 0.9166 \| 0.7011 \| 0.7010 \| \| 0.2444 \| 61.02 \| 7200 \| 0.9175 \| 0.6969 \| 0.6968 \| \| 0.2427 \| 62.71 \| 7400 \| 0.9294 \| 0.7014 \| 0.7021 \| \| 0.2342 \| 64.41 \| 7600 \| 0.9125 \| 0.7000 \| 0.7005 \| \| 0.2369 \| 66.1 \| 7800 \| 0.9295 \| 0.7013 \| 0.7015 \| \| 0.2257 \| 67.8 \| 8000 \| 0.9363 \| 0.6979 \| 0.6978 \| \| 0.2262 \| 69.49 \| 8200 \| 0.9430 \| 0.7040 \| 0.7042 \| \| 0.2225 \| 71.19 \| 8400 \| 0.9627 \| 0.6944 \| 0.6952 \| \| 0.2198 \| 72.88 \| 8600 \| 0.9913 \| 0.7027 \| 0.7031 \| \| 0.2147 \| 74.58 \| 8800 \| 0.9746 \| 0.7008 \| 0.7015 \| \| 0.2155 \| 76.27 \| 9000 \| 0.9829 \| 0.7052 \| 0.7053 \| \| 0.2148 \| 77.97 \| 9200 \| 0.9758 \| 0.7068 \| 0.7069 \| \| 0.2141 \| 79.66 \| 9400 \| 0.9774 \| 0.6985 \| 0.6989 \| \| 0.215 \| 81.36 \| 9600 \| 0.9752 \| 0.7052 \| 0.7053 \| \| 0.2111 \| 83.05 \| 9800 \| 0.9817 \| 0.7041 \| 0.7042 \| \| 0.2071 \| 84.75 \| 10000 \| 0.9847 \| 0.7019 \| 0.7021 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_4-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_4-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:23:23+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	cilantro9246/q95707u	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T23:23:27+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_3-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4306 - F1 Score: 0.8158 - Accuracy: 0.8159 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5969 \| 13.33 \| 200 \| 0.5095 \| 0.7362 \| 0.7364 \| \| 0.4907 \| 26.67 \| 400 \| 0.4640 \| 0.7696 \| 0.7699 \| \| 0.3987 \| 40.0 \| 600 \| 0.4348 \| 0.8196 \| 0.8201 \| \| 0.3349 \| 53.33 \| 800 \| 0.4285 \| 0.8282 \| 0.8285 \| \| 0.301 \| 66.67 \| 1000 \| 0.4091 \| 0.8365 \| 0.8368 \| \| 0.2727 \| 80.0 \| 1200 \| 0.4314 \| 0.8117 \| 0.8117 \| \| 0.2517 \| 93.33 \| 1400 \| 0.4056 \| 0.8324 \| 0.8326 \| \| 0.2328 \| 106.67 \| 1600 \| 0.4287 \| 0.8283 \| 0.8285 \| \| 0.2151 \| 120.0 \| 1800 \| 0.4352 \| 0.8362 \| 0.8368 \| \| 0.2034 \| 133.33 \| 2000 \| 0.4598 \| 0.8201 \| 0.8201 \| \| 0.1953 \| 146.67 \| 2200 \| 0.4749 \| 0.8235 \| 0.8243 \| \| 0.1799 \| 160.0 \| 2400 \| 0.4859 \| 0.8200 \| 0.8201 \| \| 0.1712 \| 173.33 \| 2600 \| 0.5180 \| 0.8158 \| 0.8159 \| \| 0.1635 \| 186.67 \| 2800 \| 0.5094 \| 0.8197 \| 0.8201 \| \| 0.1573 \| 200.0 \| 3000 \| 0.5249 \| 0.8112 \| 0.8117 \| \| 0.1504 \| 213.33 \| 3200 \| 0.5275 \| 0.8201 \| 0.8201 \| \| 0.1409 \| 226.67 \| 3400 \| 0.5598 \| 0.8116 \| 0.8117 \| \| 0.1362 \| 240.0 \| 3600 \| 0.5883 \| 0.8117 \| 0.8117 \| \| 0.1333 \| 253.33 \| 3800 \| 0.5897 \| 0.8116 \| 0.8117 \| \| 0.1271 \| 266.67 \| 4000 \| 0.5970 \| 0.8032 \| 0.8033 \| \| 0.1185 \| 280.0 \| 4200 \| 0.6158 \| 0.8159 \| 0.8159 \| \| 0.1194 \| 293.33 \| 4400 \| 0.6234 \| 0.8155 \| 0.8159 \| \| 0.1168 \| 306.67 \| 4600 \| 0.6237 \| 0.8032 \| 0.8033 \| \| 0.1139 \| 320.0 \| 4800 \| 0.6394 \| 0.8156 \| 0.8159 \| \| 0.1085 \| 333.33 \| 5000 \| 0.6447 \| 0.8032 \| 0.8033 \| \| 0.1127 \| 346.67 \| 5200 \| 0.6333 \| 0.8074 \| 0.8075 \| \| 0.103 \| 360.0 \| 5400 \| 0.6719 \| 0.8033 \| 0.8033 \| \| 0.1051 \| 373.33 \| 5600 \| 0.6635 \| 0.8073 \| 0.8075 \| \| 0.1009 \| 386.67 \| 5800 \| 0.6677 \| 0.7990 \| 0.7992 \| \| 0.0949 \| 400.0 \| 6000 \| 0.7129 \| 0.8072 \| 0.8075 \| \| 0.1017 \| 413.33 \| 6200 \| 0.6686 \| 0.7988 \| 0.7992 \| \| 0.0955 \| 426.67 \| 6400 \| 0.6848 \| 0.8073 \| 0.8075 \| \| 0.0904 \| 440.0 \| 6600 \| 0.7276 \| 0.8115 \| 0.8117 \| \| 0.093 \| 453.33 \| 6800 \| 0.7003 \| 0.8032 \| 0.8033 \| \| 0.0887 \| 466.67 \| 7000 \| 0.7550 \| 0.8156 \| 0.8159 \| \| 0.0863 \| 480.0 \| 7200 \| 0.7110 \| 0.8074 \| 0.8075 \| \| 0.0893 \| 493.33 \| 7400 \| 0.7272 \| 0.8032 \| 0.8033 \| \| 0.0882 \| 506.67 \| 7600 \| 0.7284 \| 0.8032 \| 0.8033 \| \| 0.0839 \| 520.0 \| 7800 \| 0.7471 \| 0.8073 \| 0.8075 \| \| 0.086 \| 533.33 \| 8000 \| 0.7495 \| 0.8032 \| 0.8033 \| \| 0.0863 \| 546.67 \| 8200 \| 0.7395 \| 0.8032 \| 0.8033 \| \| 0.084 \| 560.0 \| 8400 \| 0.7449 \| 0.8032 \| 0.8033 \| \| 0.0826 \| 573.33 \| 8600 \| 0.7441 \| 0.8032 \| 0.8033 \| \| 0.0826 \| 586.67 \| 8800 \| 0.7596 \| 0.7990 \| 0.7992 \| \| 0.0824 \| 600.0 \| 9000 \| 0.7508 \| 0.8074 \| 0.8075 \| \| 0.079 \| 613.33 \| 9200 \| 0.7753 \| 0.7990 \| 0.7992 \| \| 0.078 \| 626.67 \| 9400 \| 0.7688 \| 0.8074 \| 0.8075 \| \| 0.0819 \| 640.0 \| 9600 \| 0.7613 \| 0.8074 \| 0.8075 \| \| 0.0839 \| 653.33 \| 9800 \| 0.7621 \| 0.8032 \| 0.8033 \| \| 0.0791 \| 666.67 \| 10000 \| 0.7611 \| 0.8074 \| 0.8075 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_3-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_3-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:23:51+00:00
null	null	# Smaug-72B-v0.1-GGUF - Original model: [Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1) <!-- description start --> ## Description This repo contains GGUF format model files for [Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1). <!-- description end --> <!-- README_GGUF.md-about-gguf start --> ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration. * [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications * [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling. * [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration. * [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection. * [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use. * [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server. * [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents. <!-- README_GGUF.md-about-gguf end --> <!-- compatibility_gguf start --> ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw. </details> <!-- compatibility_gguf end --> <!-- README_GGUF.md-how-to-download start --> ## How to download GGUF files Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: LiteLLMs/Smaug-72B-v0.1-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='Q4_Kgguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install huggingface_hub[hf_transfer] ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details> <!-- README_GGUF.md-how-to-download end --> <!-- README_GGUF.md-how-to-run start --> ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m Q4_0/Q4_0-00001-of-00009.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 8192` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./Q4_0/Q4_0-00001-of-00009.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<PROMPT>", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./Q4_0/Q4_0-00001-of-00009.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers) <!-- README_GGUF.md-how-to-run end --> <!-- footer end --> <!-- original-model-card start --> # Original model card: Smaug-72B-v0.1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/e4u8VYfDBh11u60rFYJHF.png) Smaug arrives! We recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%. Smaug-72B is finetuned directly from [moreh/MoMo-72B-lora-1.8.7-DPO](https://huggingface.co/moreh/MoMo-72B-lora-1.8.7-DPO) and is ultimately based on [Qwen-72B](https://huggingface.co/Qwen/Qwen-72B). We created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228. We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases. Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode. Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions. We believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models. With the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space! ### Evaluation Results \| Average \| ARC \| HellaSwag \| MMLU \| TruthfulQA \| Winogrande \| GSM8K \| \| - \| \| - \| -- \| \| 80.48 \| 76.02 \| 89.27 \| 77.15 \| 76.67 \| 85.08 \| 78.70 \| #### MT-Bench We ran MT-Bench with the llama-2 conversation template and the system prompt set to the Qwen system prompt. We got the following results in single model mode: \| First Turn \| Second Turn \| Average \| \| -- \| - \| \| 8.18 \| 7.34 \| 7.76 \| The bottom of the card includes some sample responses from the model. We have selected responses that have high and low scores from the GPT-4 judge. ### Contamination Results We generate our contamination numbers using https://github.com/swj0419/detect-pretrain-code-contamination/tree/master, with Llama7B as our reference model. Smaug-72B has the following results: \| ARC \| TruthfulQA \| GSM8K \| \| - \| - \| -- \| \| 0.20 \| 0.39 \| 1.00 \| Note that GSM8K often scores very highly on this contamination suite - we verified this by also running Llama-2-70B: \| ARC \| TruthfulQA \| GSM8K \| \| - \| ----- \| \| 0.22 \| 0.51 \| 0.89 \| ### Sample MT Bench results #### Example 1 Question Imagine you are writing a blog post comparing two popular smartphone models. Develop an outline for the blog post, including key points and subheadings to effectively compare and contrast the features, performance, and user experience of the two models. Please answer in fewer than 200 words. Response Outline: 1. Introduction to the two smartphone models being compared (mention brand names and models) 2. Design and Build Quality - Comparison of dimensions, weight, materials used, and overall aesthetic appeal - Water and dust resistance, if applicable 3. Display and Screen Quality - Comparison of screen technology (OLED, IPS LCD, etc.) - Display resolution, refresh rate, and brightness levels 4. Performance and Hardware - Processor, RAM, and storage configurations - Comparison of benchmark scores (e.g., AnTuTu, Geekbench) 5. Camera System and Image Quality - Comparison of primary, ultra-wide, telephoto, and macro lenses (if available) - Comparison of low-light performance and image processing capabilities 6. Battery Life and Charging - Battery capacity and estimated usage time - Charging technologies (wired, wireless, fast charging, reverse charging) 7. Software and User Experience - Comparison of operating systems (iOS vs. Android) and their features - User interface, customization options, and app ecosystem 8. Additional Features and Extras - Comparison of biometric authentication (fingerprint, face unlock, etc.) - Additional features like NFC, 5G connectivity, and audio quality 9. Pricing and Value for Money - Comparison of retail prices and current offers - Assessment of overall value considering the features and performance 10. Conclusion and recommendation for potential buyers based on their preferences #### Example 2 Question In a survey conducted at a local high school, preferences for a new school color were measured: 58% of students liked the color blue, 45% preferred green, and 22% liked both colors. If we randomly pick a student from the school, what's the probability that they would like neither blue nor green? Answer To find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color. From the given information, we know: - 58% like blue - 45% prefer green - 22% like both colors To find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green: - 58% (blue) + 45% (green) - 22% (both) = 83% Now, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%: - 100% - 83% = 17% So, the probability that a randomly picked student would like neither blue nor green is 17%. #### Example 3 Question Implement a program to find the common elements in two arrays without using any extra data structures. Answer Finding common elements in two arrays without using extra data structures can be achieved by using a simple algorithm. Here's a Python implementation of this problem: ```python def find_common_elements(arr1, arr2): common_elements = [] for num1 in arr1: if num1 in arr2 and num1 not in common_elements: common_elements.append(num1) return common_elements # Example usage: array1 = [1, 2, 3, 4, 5] array2 = [4, 5, 6, 7, 8] print(find_common_elements(array1, array2)) # Output: [4, 5] ``` This program iterates through the elements of the first array (arr1) and checks if each element is present in the second array (arr2). If it is, and the element hasn't been added to the common_elements list yet, it is appended. The function then returns the list of common elements. #### Example 4 Question Identify the named entities (people, organizations, locations) mentioned in the given news article. Please generate a JSON dictionary that lists the named entities in three separate groups based on their entity types. The key is the type of entity and the value is a list of strings. Yesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to build a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing electric vehicles and battery packs for both companies, creating thousands of job opportunities in the region. Emerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure, makes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe and contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will, benefit the auto industry's transition to e-mobility. Answer ``` { "people": ["Adamson Emerson", "Dieter Zetsche", "Herbert Diess"], "organizations": ["Faraday", "Daimler AG", "Volkswagen"], "locations": ["Berlin", "Europe"] } ``` ### Citation Please cite the paper if you use data, model, or method in this repo. ``` @article{pal2024smaug, title={Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive}, author={Pal, Arka and Karkhanis, Deep and Dooley, Samuel and Roberts, Manley and Naidu, Siddartha and White, Colin}, journal={arXiv preprint arXiv:2402.13228}, year={2024} } ``` <!-- original-model-card end -->	{"license": "other", "tags": ["GGUF"], "base_model": "moreh/MoMo-72B-lora-1.8.7-DPO", "license_name": "tongyi-qianwen-license-agreement", "license_link": "https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT", "quantized_by": "andrijdavid"}	LiteLLMs/Smaug-72B-v0.1-GGUF	null	[ "GGUF", "arxiv:2402.13228", "base_model:moreh/MoMo-72B-lora-1.8.7-DPO", "license:other", "region:us" ]	null	2024-04-29T23:25:46+00:00
null	null		{}	webnizam/llama3-8b-unintended-consequences-gguf	null	[ "gguf", "region:us" ]	null	2024-04-29T23:27:21+00:00
null	null		{}	ShenaoZhang/0.0_3iters_bs256_nodpo_full6w_iter_2	null	[ "region:us" ]	null	2024-04-29T23:27:28+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_3-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.8517 - F1 Score: 0.8452 - Accuracy: 0.8452 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5452 \| 13.33 \| 200 \| 0.4368 \| 0.7950 \| 0.7950 \| \| 0.3383 \| 26.67 \| 400 \| 0.4173 \| 0.8281 \| 0.8285 \| \| 0.2546 \| 40.0 \| 600 \| 0.4703 \| 0.8368 \| 0.8368 \| \| 0.198 \| 53.33 \| 800 \| 0.5257 \| 0.8321 \| 0.8326 \| \| 0.1583 \| 66.67 \| 1000 \| 0.5990 \| 0.8276 \| 0.8285 \| \| 0.1327 \| 80.0 \| 1200 \| 0.7110 \| 0.8158 \| 0.8159 \| \| 0.1138 \| 93.33 \| 1400 \| 0.6432 \| 0.8158 \| 0.8159 \| \| 0.0975 \| 106.67 \| 1600 \| 0.6860 \| 0.8325 \| 0.8326 \| \| 0.0802 \| 120.0 \| 1800 \| 0.8088 \| 0.8197 \| 0.8201 \| \| 0.0723 \| 133.33 \| 2000 \| 0.8668 \| 0.8242 \| 0.8243 \| \| 0.0653 \| 146.67 \| 2200 \| 0.9054 \| 0.8158 \| 0.8159 \| \| 0.0587 \| 160.0 \| 2400 \| 0.9065 \| 0.8201 \| 0.8201 \| \| 0.0486 \| 173.33 \| 2600 \| 1.0048 \| 0.8200 \| 0.8201 \| \| 0.0509 \| 186.67 \| 2800 \| 0.9290 \| 0.8408 \| 0.8410 \| \| 0.0456 \| 200.0 \| 3000 \| 0.9976 \| 0.8159 \| 0.8159 \| \| 0.0418 \| 213.33 \| 3200 \| 0.9689 \| 0.8159 \| 0.8159 \| \| 0.037 \| 226.67 \| 3400 \| 1.0219 \| 0.8281 \| 0.8285 \| \| 0.0371 \| 240.0 \| 3600 \| 1.0860 \| 0.8200 \| 0.8201 \| \| 0.034 \| 253.33 \| 3800 \| 1.0840 \| 0.8074 \| 0.8075 \| \| 0.0314 \| 266.67 \| 4000 \| 1.1107 \| 0.8200 \| 0.8201 \| \| 0.0291 \| 280.0 \| 4200 \| 1.1084 \| 0.7990 \| 0.7992 \| \| 0.0274 \| 293.33 \| 4400 \| 1.1196 \| 0.8153 \| 0.8159 \| \| 0.0263 \| 306.67 \| 4600 \| 1.1009 \| 0.8117 \| 0.8117 \| \| 0.0261 \| 320.0 \| 4800 \| 1.1459 \| 0.8074 \| 0.8075 \| \| 0.0239 \| 333.33 \| 5000 \| 1.1017 \| 0.8159 \| 0.8159 \| \| 0.0218 \| 346.67 \| 5200 \| 1.1290 \| 0.8199 \| 0.8201 \| \| 0.0194 \| 360.0 \| 5400 \| 1.2031 \| 0.8240 \| 0.8243 \| \| 0.0194 \| 373.33 \| 5600 \| 1.2167 \| 0.8155 \| 0.8159 \| \| 0.019 \| 386.67 \| 5800 \| 1.1979 \| 0.8241 \| 0.8243 \| \| 0.0177 \| 400.0 \| 6000 \| 1.2198 \| 0.8074 \| 0.8075 \| \| 0.0185 \| 413.33 \| 6200 \| 1.1752 \| 0.8199 \| 0.8201 \| \| 0.0181 \| 426.67 \| 6400 \| 1.1793 \| 0.8242 \| 0.8243 \| \| 0.0146 \| 440.0 \| 6600 \| 1.2931 \| 0.8115 \| 0.8117 \| \| 0.0157 \| 453.33 \| 6800 \| 1.2946 \| 0.8159 \| 0.8159 \| \| 0.017 \| 466.67 \| 7000 \| 1.3000 \| 0.8201 \| 0.8201 \| \| 0.0135 \| 480.0 \| 7200 \| 1.2510 \| 0.8201 \| 0.8201 \| \| 0.0141 \| 493.33 \| 7400 \| 1.2736 \| 0.8201 \| 0.8201 \| \| 0.0127 \| 506.67 \| 7600 \| 1.2899 \| 0.8200 \| 0.8201 \| \| 0.0134 \| 520.0 \| 7800 \| 1.3283 \| 0.8241 \| 0.8243 \| \| 0.0129 \| 533.33 \| 8000 \| 1.3425 \| 0.8197 \| 0.8201 \| \| 0.0131 \| 546.67 \| 8200 \| 1.2405 \| 0.8282 \| 0.8285 \| \| 0.0121 \| 560.0 \| 8400 \| 1.2794 \| 0.8117 \| 0.8117 \| \| 0.0109 \| 573.33 \| 8600 \| 1.3451 \| 0.8283 \| 0.8285 \| \| 0.0116 \| 586.67 \| 8800 \| 1.3675 \| 0.8159 \| 0.8159 \| \| 0.0122 \| 600.0 \| 9000 \| 1.3784 \| 0.8075 \| 0.8075 \| \| 0.0109 \| 613.33 \| 9200 \| 1.3744 \| 0.8200 \| 0.8201 \| \| 0.0103 \| 626.67 \| 9400 \| 1.4141 \| 0.8200 \| 0.8201 \| \| 0.0106 \| 640.0 \| 9600 \| 1.3886 \| 0.8117 \| 0.8117 \| \| 0.0113 \| 653.33 \| 9800 \| 1.3747 \| 0.8200 \| 0.8201 \| \| 0.0102 \| 666.67 \| 10000 \| 1.3772 \| 0.8158 \| 0.8159 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_3-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_3-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:27:30+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	lunarsylph/stablecell_v53	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:27:44+00:00
null	null		{}	curtisxu/mergeLlama-7b-Instruct-hf-quantized-peft-2	null	[ "region:us" ]	null	2024-04-29T23:28:01+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.8282 - F1 Score: 0.8534 - Accuracy: 0.8536 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.4872 \| 13.33 \| 200 \| 0.4103 \| 0.8241 \| 0.8243 \| \| 0.2478 \| 26.67 \| 400 \| 0.4459 \| 0.8197 \| 0.8201 \| \| 0.1554 \| 40.0 \| 600 \| 0.5680 \| 0.7990 \| 0.7992 \| \| 0.102 \| 53.33 \| 800 \| 0.6341 \| 0.8403 \| 0.8410 \| \| 0.0669 \| 66.67 \| 1000 \| 0.7863 \| 0.8192 \| 0.8201 \| \| 0.0475 \| 80.0 \| 1200 \| 0.9739 \| 0.8065 \| 0.8075 \| \| 0.0433 \| 93.33 \| 1400 \| 0.8721 \| 0.8282 \| 0.8285 \| \| 0.0332 \| 106.67 \| 1600 \| 0.8710 \| 0.8449 \| 0.8452 \| \| 0.0255 \| 120.0 \| 1800 \| 1.0873 \| 0.8072 \| 0.8075 \| \| 0.0244 \| 133.33 \| 2000 \| 1.0687 \| 0.7988 \| 0.7992 \| \| 0.02 \| 146.67 \| 2200 \| 1.1529 \| 0.8281 \| 0.8285 \| \| 0.0161 \| 160.0 \| 2400 \| 1.1772 \| 0.8284 \| 0.8285 \| \| 0.0165 \| 173.33 \| 2600 \| 1.2462 \| 0.8276 \| 0.8285 \| \| 0.0144 \| 186.67 \| 2800 \| 1.1893 \| 0.8115 \| 0.8117 \| \| 0.0125 \| 200.0 \| 3000 \| 1.2388 \| 0.8067 \| 0.8075 \| \| 0.0109 \| 213.33 \| 3200 \| 1.3548 \| 0.8073 \| 0.8075 \| \| 0.0109 \| 226.67 \| 3400 \| 1.2163 \| 0.7907 \| 0.7908 \| \| 0.0112 \| 240.0 \| 3600 \| 1.1475 \| 0.8117 \| 0.8117 \| \| 0.0109 \| 253.33 \| 3800 \| 1.3809 \| 0.8065 \| 0.8075 \| \| 0.0086 \| 266.67 \| 4000 \| 1.3586 \| 0.8072 \| 0.8075 \| \| 0.0062 \| 280.0 \| 4200 \| 1.3622 \| 0.8031 \| 0.8033 \| \| 0.0087 \| 293.33 \| 4400 \| 1.2448 \| 0.8071 \| 0.8075 \| \| 0.0072 \| 306.67 \| 4600 \| 1.4332 \| 0.8028 \| 0.8033 \| \| 0.0065 \| 320.0 \| 4800 \| 1.3601 \| 0.7947 \| 0.7950 \| \| 0.0071 \| 333.33 \| 5000 \| 1.5165 \| 0.7978 \| 0.7992 \| \| 0.0049 \| 346.67 \| 5200 \| 1.4562 \| 0.8026 \| 0.8033 \| \| 0.0048 \| 360.0 \| 5400 \| 1.5191 \| 0.7988 \| 0.7992 \| \| 0.0053 \| 373.33 \| 5600 \| 1.4817 \| 0.8196 \| 0.8201 \| \| 0.0041 \| 386.67 \| 5800 \| 1.6016 \| 0.7949 \| 0.7950 \| \| 0.0044 \| 400.0 \| 6000 \| 1.5036 \| 0.8153 \| 0.8159 \| \| 0.0052 \| 413.33 \| 6200 \| 1.5273 \| 0.8075 \| 0.8075 \| \| 0.0041 \| 426.67 \| 6400 \| 1.4759 \| 0.8028 \| 0.8033 \| \| 0.0023 \| 440.0 \| 6600 \| 1.5729 \| 0.8031 \| 0.8033 \| \| 0.0028 \| 453.33 \| 6800 \| 1.6576 \| 0.8155 \| 0.8159 \| \| 0.0043 \| 466.67 \| 7000 \| 1.6210 \| 0.8157 \| 0.8159 \| \| 0.003 \| 480.0 \| 7200 \| 1.5857 \| 0.7992 \| 0.7992 \| \| 0.0036 \| 493.33 \| 7400 \| 1.6029 \| 0.8149 \| 0.8159 \| \| 0.0024 \| 506.67 \| 7600 \| 1.5662 \| 0.8114 \| 0.8117 \| \| 0.0023 \| 520.0 \| 7800 \| 1.6867 \| 0.8028 \| 0.8033 \| \| 0.0032 \| 533.33 \| 8000 \| 1.5723 \| 0.8030 \| 0.8033 \| \| 0.0024 \| 546.67 \| 8200 \| 1.6106 \| 0.8116 \| 0.8117 \| \| 0.0023 \| 560.0 \| 8400 \| 1.6233 \| 0.7903 \| 0.7908 \| \| 0.0021 \| 573.33 \| 8600 \| 1.5936 \| 0.8030 \| 0.8033 \| \| 0.0021 \| 586.67 \| 8800 \| 1.5612 \| 0.8116 \| 0.8117 \| \| 0.0017 \| 600.0 \| 9000 \| 1.6127 \| 0.8157 \| 0.8159 \| \| 0.002 \| 613.33 \| 9200 \| 1.6056 \| 0.8156 \| 0.8159 \| \| 0.0011 \| 626.67 \| 9400 \| 1.6240 \| 0.8032 \| 0.8033 \| \| 0.0015 \| 640.0 \| 9600 \| 1.6482 \| 0.8031 \| 0.8033 \| \| 0.0018 \| 653.33 \| 9800 \| 1.6421 \| 0.8031 \| 0.8033 \| \| 0.003 \| 666.67 \| 10000 \| 1.6413 \| 0.8031 \| 0.8033 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_3-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_3-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:28:26+00:00
null	transformers	## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> static quants of https://huggingface.co/Hugosh71/Llama-3-8B-Eden <!-- provided-files --> weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) \| Link \| Type \| Size/GB \| Notes \| \|:-----\|:-----\|--------:\|:------\| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q2_K.gguf) \| Q2_K \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_XS.gguf) \| IQ3_XS \| 3.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_S.gguf) \| Q3_K_S \| 3.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_S.gguf) \| IQ3_S \| 3.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_M.gguf) \| IQ3_M \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_M.gguf) \| Q3_K_M \| 4.1 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_L.gguf) \| Q3_K_L \| 4.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ4_XS.gguf) \| IQ4_XS \| 4.6 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q4_K_S.gguf) \| Q4_K_S \| 4.8 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q4_K_M.gguf) \| Q4_K_M \| 5.0 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q5_K_S.gguf) \| Q5_K_S \| 5.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q5_K_M.gguf) \| Q5_K_M \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q6_K.gguf) \| Q6_K \| 6.7 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q8_0.gguf) \| Q8_0 \| 8.6 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.f16.gguf) \| f16 \| 16.2 \| 16 bpw, overkill \| Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->	{"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "Hugosh71/Llama-3-8B-Eden", "quantized_by": "mradermacher"}	mradermacher/Llama-3-8B-Eden-GGUF	null	[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "sft", "en", "base_model:Hugosh71/Llama-3-8B-Eden", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:28:57+00:00
text-generation	transformers	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]	{"library_name": "transformers", "tags": []}	shallow6414/7aeerbr	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-04-29T23:29:15+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_2-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4898 - F1 Score: 0.8627 - Accuracy: 0.8628 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.3798 \| 9.52 \| 200 \| 0.2814 \| 0.8688 \| 0.8689 \| \| 0.2589 \| 19.05 \| 400 \| 0.2488 \| 0.9024 \| 0.9024 \| \| 0.2158 \| 28.57 \| 600 \| 0.2361 \| 0.9238 \| 0.9238 \| \| 0.177 \| 38.1 \| 800 \| 0.2305 \| 0.9237 \| 0.9238 \| \| 0.1469 \| 47.62 \| 1000 \| 0.2415 \| 0.9084 \| 0.9085 \| \| 0.1237 \| 57.14 \| 1200 \| 0.3192 \| 0.9053 \| 0.9055 \| \| 0.0998 \| 66.67 \| 1400 \| 0.3660 \| 0.9113 \| 0.9116 \| \| 0.0845 \| 76.19 \| 1600 \| 0.3451 \| 0.9084 \| 0.9085 \| \| 0.0732 \| 85.71 \| 1800 \| 0.3503 \| 0.9145 \| 0.9146 \| \| 0.0638 \| 95.24 \| 2000 \| 0.4203 \| 0.8960 \| 0.8963 \| \| 0.056 \| 104.76 \| 2200 \| 0.4481 \| 0.9144 \| 0.9146 \| \| 0.0522 \| 114.29 \| 2400 \| 0.3994 \| 0.9175 \| 0.9177 \| \| 0.048 \| 123.81 \| 2600 \| 0.4189 \| 0.9114 \| 0.9116 \| \| 0.0435 \| 133.33 \| 2800 \| 0.4454 \| 0.8989 \| 0.8994 \| \| 0.04 \| 142.86 \| 3000 \| 0.4346 \| 0.9267 \| 0.9268 \| \| 0.0379 \| 152.38 \| 3200 \| 0.4681 \| 0.9082 \| 0.9085 \| \| 0.0321 \| 161.9 \| 3400 \| 0.4259 \| 0.9143 \| 0.9146 \| \| 0.0318 \| 171.43 \| 3600 \| 0.3744 \| 0.9207 \| 0.9207 \| \| 0.0299 \| 180.95 \| 3800 \| 0.3893 \| 0.9207 \| 0.9207 \| \| 0.0251 \| 190.48 \| 4000 \| 0.4827 \| 0.9143 \| 0.9146 \| \| 0.0249 \| 200.0 \| 4200 \| 0.5806 \| 0.8957 \| 0.8963 \| \| 0.0222 \| 209.52 \| 4400 \| 0.5559 \| 0.9113 \| 0.9116 \| \| 0.0226 \| 219.05 \| 4600 \| 0.4151 \| 0.9175 \| 0.9177 \| \| 0.0216 \| 228.57 \| 4800 \| 0.4778 \| 0.9174 \| 0.9177 \| \| 0.0202 \| 238.1 \| 5000 \| 0.4794 \| 0.9144 \| 0.9146 \| \| 0.0188 \| 247.62 \| 5200 \| 0.5111 \| 0.9020 \| 0.9024 \| \| 0.0182 \| 257.14 \| 5400 \| 0.4998 \| 0.9021 \| 0.9024 \| \| 0.0152 \| 266.67 \| 5600 \| 0.4815 \| 0.9176 \| 0.9177 \| \| 0.0151 \| 276.19 \| 5800 \| 0.5486 \| 0.9082 \| 0.9085 \| \| 0.0164 \| 285.71 \| 6000 \| 0.5131 \| 0.9113 \| 0.9116 \| \| 0.014 \| 295.24 \| 6200 \| 0.5049 \| 0.9206 \| 0.9207 \| \| 0.0144 \| 304.76 \| 6400 \| 0.4674 \| 0.9083 \| 0.9085 \| \| 0.0147 \| 314.29 \| 6600 \| 0.6490 \| 0.8896 \| 0.8902 \| \| 0.0143 \| 323.81 \| 6800 \| 0.4780 \| 0.9237 \| 0.9238 \| \| 0.0137 \| 333.33 \| 7000 \| 0.5217 \| 0.9082 \| 0.9085 \| \| 0.0133 \| 342.86 \| 7200 \| 0.4700 \| 0.9175 \| 0.9177 \| \| 0.0134 \| 352.38 \| 7400 \| 0.5702 \| 0.9051 \| 0.9055 \| \| 0.0116 \| 361.9 \| 7600 \| 0.5374 \| 0.9020 \| 0.9024 \| \| 0.0104 \| 371.43 \| 7800 \| 0.5493 \| 0.8989 \| 0.8994 \| \| 0.013 \| 380.95 \| 8000 \| 0.4950 \| 0.9083 \| 0.9085 \| \| 0.0114 \| 390.48 \| 8200 \| 0.5291 \| 0.9021 \| 0.9024 \| \| 0.0104 \| 400.0 \| 8400 \| 0.5530 \| 0.8958 \| 0.8963 \| \| 0.009 \| 409.52 \| 8600 \| 0.5151 \| 0.9145 \| 0.9146 \| \| 0.0092 \| 419.05 \| 8800 \| 0.5606 \| 0.9082 \| 0.9085 \| \| 0.0087 \| 428.57 \| 9000 \| 0.6063 \| 0.9020 \| 0.9024 \| \| 0.0097 \| 438.1 \| 9200 \| 0.5208 \| 0.9237 \| 0.9238 \| \| 0.0099 \| 447.62 \| 9400 \| 0.5650 \| 0.9113 \| 0.9116 \| \| 0.008 \| 457.14 \| 9600 \| 0.5689 \| 0.9082 \| 0.9085 \| \| 0.009 \| 466.67 \| 9800 \| 0.5718 \| 0.9051 \| 0.9055 \| \| 0.0091 \| 476.19 \| 10000 \| 0.5701 \| 0.9051 \| 0.9055 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_2-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_2-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:29:29+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_2-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.2431 - F1 Score: 0.8933 - Accuracy: 0.8933 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.431 \| 9.52 \| 200 \| 0.3091 \| 0.8352 \| 0.8354 \| \| 0.3042 \| 19.05 \| 400 \| 0.2854 \| 0.8655 \| 0.8659 \| \| 0.2832 \| 28.57 \| 600 \| 0.2640 \| 0.8720 \| 0.8720 \| \| 0.2619 \| 38.1 \| 800 \| 0.2485 \| 0.8902 \| 0.8902 \| \| 0.245 \| 47.62 \| 1000 \| 0.2347 \| 0.8932 \| 0.8933 \| \| 0.2316 \| 57.14 \| 1200 \| 0.2357 \| 0.8963 \| 0.8963 \| \| 0.2161 \| 66.67 \| 1400 \| 0.2363 \| 0.8994 \| 0.8994 \| \| 0.204 \| 76.19 \| 1600 \| 0.2410 \| 0.9054 \| 0.9055 \| \| 0.194 \| 85.71 \| 1800 \| 0.2328 \| 0.9085 \| 0.9085 \| \| 0.1781 \| 95.24 \| 2000 \| 0.2349 \| 0.8994 \| 0.8994 \| \| 0.1696 \| 104.76 \| 2200 \| 0.2507 \| 0.9022 \| 0.9024 \| \| 0.1603 \| 114.29 \| 2400 \| 0.2369 \| 0.9085 \| 0.9085 \| \| 0.156 \| 123.81 \| 2600 \| 0.2406 \| 0.9085 \| 0.9085 \| \| 0.1474 \| 133.33 \| 2800 \| 0.2660 \| 0.8992 \| 0.8994 \| \| 0.1385 \| 142.86 \| 3000 \| 0.2323 \| 0.8963 \| 0.8963 \| \| 0.1378 \| 152.38 \| 3200 \| 0.2642 \| 0.9023 \| 0.9024 \| \| 0.1302 \| 161.9 \| 3400 \| 0.2688 \| 0.9024 \| 0.9024 \| \| 0.1226 \| 171.43 \| 3600 \| 0.2931 \| 0.9054 \| 0.9055 \| \| 0.1199 \| 180.95 \| 3800 \| 0.2706 \| 0.8963 \| 0.8963 \| \| 0.1126 \| 190.48 \| 4000 \| 0.2766 \| 0.8994 \| 0.8994 \| \| 0.1098 \| 200.0 \| 4200 \| 0.3117 \| 0.8961 \| 0.8963 \| \| 0.1067 \| 209.52 \| 4400 \| 0.3084 \| 0.8993 \| 0.8994 \| \| 0.1055 \| 219.05 \| 4600 \| 0.2736 \| 0.8963 \| 0.8963 \| \| 0.102 \| 228.57 \| 4800 \| 0.2974 \| 0.8993 \| 0.8994 \| \| 0.1018 \| 238.1 \| 5000 \| 0.3201 \| 0.8900 \| 0.8902 \| \| 0.0941 \| 247.62 \| 5200 \| 0.3076 \| 0.8993 \| 0.8994 \| \| 0.0952 \| 257.14 \| 5400 \| 0.3099 \| 0.8962 \| 0.8963 \| \| 0.0956 \| 266.67 \| 5600 \| 0.3151 \| 0.9023 \| 0.9024 \| \| 0.0901 \| 276.19 \| 5800 \| 0.3250 \| 0.8993 \| 0.8994 \| \| 0.0912 \| 285.71 \| 6000 \| 0.3075 \| 0.8963 \| 0.8963 \| \| 0.0847 \| 295.24 \| 6200 \| 0.3183 \| 0.8902 \| 0.8902 \| \| 0.0869 \| 304.76 \| 6400 \| 0.3248 \| 0.8993 \| 0.8994 \| \| 0.0844 \| 314.29 \| 6600 \| 0.3260 \| 0.8962 \| 0.8963 \| \| 0.083 \| 323.81 \| 6800 \| 0.3201 \| 0.8993 \| 0.8994 \| \| 0.0838 \| 333.33 \| 7000 \| 0.3342 \| 0.8962 \| 0.8963 \| \| 0.0833 \| 342.86 \| 7200 \| 0.3211 \| 0.8993 \| 0.8994 \| \| 0.0784 \| 352.38 \| 7400 \| 0.3228 \| 0.8963 \| 0.8963 \| \| 0.0794 \| 361.9 \| 7600 \| 0.3261 \| 0.8932 \| 0.8933 \| \| 0.0738 \| 371.43 \| 7800 \| 0.3553 \| 0.8901 \| 0.8902 \| \| 0.0785 \| 380.95 \| 8000 \| 0.3454 \| 0.8932 \| 0.8933 \| \| 0.0733 \| 390.48 \| 8200 \| 0.3383 \| 0.8993 \| 0.8994 \| \| 0.0715 \| 400.0 \| 8400 \| 0.3430 \| 0.8962 \| 0.8963 \| \| 0.0717 \| 409.52 \| 8600 \| 0.3406 \| 0.8963 \| 0.8963 \| \| 0.071 \| 419.05 \| 8800 \| 0.3436 \| 0.8993 \| 0.8994 \| \| 0.0727 \| 428.57 \| 9000 \| 0.3576 \| 0.8962 \| 0.8963 \| \| 0.0699 \| 438.1 \| 9200 \| 0.3441 \| 0.8963 \| 0.8963 \| \| 0.0693 \| 447.62 \| 9400 \| 0.3590 \| 0.8993 \| 0.8994 \| \| 0.0699 \| 457.14 \| 9600 \| 0.3587 \| 0.8993 \| 0.8994 \| \| 0.0689 \| 466.67 \| 9800 \| 0.3608 \| 0.8993 \| 0.8994 \| \| 0.0706 \| 476.19 \| 10000 \| 0.3599 \| 0.8993 \| 0.8994 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_2-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_2-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:29:29+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_mouse_2-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.5170 - F1 Score: 0.8719 - Accuracy: 0.8720 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:------:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.3511 \| 9.52 \| 200 \| 0.2727 \| 0.8656 \| 0.8659 \| \| 0.2161 \| 19.05 \| 400 \| 0.2679 \| 0.9022 \| 0.9024 \| \| 0.1542 \| 28.57 \| 600 \| 0.3062 \| 0.9082 \| 0.9085 \| \| 0.1042 \| 38.1 \| 800 \| 0.3723 \| 0.8990 \| 0.8994 \| \| 0.0797 \| 47.62 \| 1000 \| 0.3875 \| 0.9020 \| 0.9024 \| \| 0.0583 \| 57.14 \| 1200 \| 0.3187 \| 0.9115 \| 0.9116 \| \| 0.0473 \| 66.67 \| 1400 \| 0.4834 \| 0.9020 \| 0.9024 \| \| 0.0329 \| 76.19 \| 1600 \| 0.5490 \| 0.8901 \| 0.8902 \| \| 0.0261 \| 85.71 \| 1800 \| 0.6356 \| 0.8930 \| 0.8933 \| \| 0.0246 \| 95.24 \| 2000 \| 0.5832 \| 0.8776 \| 0.8780 \| \| 0.0194 \| 104.76 \| 2200 \| 0.5850 \| 0.8962 \| 0.8963 \| \| 0.0193 \| 114.29 \| 2400 \| 0.5464 \| 0.8933 \| 0.8933 \| \| 0.0165 \| 123.81 \| 2600 \| 0.6401 \| 0.8838 \| 0.8841 \| \| 0.0136 \| 133.33 \| 2800 \| 0.5025 \| 0.9054 \| 0.9055 \| \| 0.0128 \| 142.86 \| 3000 \| 0.5665 \| 0.9024 \| 0.9024 \| \| 0.0117 \| 152.38 \| 3200 \| 0.6084 \| 0.8899 \| 0.8902 \| \| 0.0094 \| 161.9 \| 3400 \| 0.6627 \| 0.9054 \| 0.9055 \| \| 0.0106 \| 171.43 \| 3600 \| 0.5885 \| 0.9024 \| 0.9024 \| \| 0.0102 \| 180.95 \| 3800 \| 0.6780 \| 0.8961 \| 0.8963 \| \| 0.0069 \| 190.48 \| 4000 \| 0.7310 \| 0.8803 \| 0.8811 \| \| 0.0071 \| 200.0 \| 4200 \| 0.6558 \| 0.8930 \| 0.8933 \| \| 0.0075 \| 209.52 \| 4400 \| 0.5988 \| 0.9115 \| 0.9116 \| \| 0.007 \| 219.05 \| 4600 \| 0.5636 \| 0.9023 \| 0.9024 \| \| 0.0049 \| 228.57 \| 4800 \| 0.7340 \| 0.8838 \| 0.8841 \| \| 0.0054 \| 238.1 \| 5000 \| 0.6138 \| 0.9022 \| 0.9024 \| \| 0.0068 \| 247.62 \| 5200 \| 0.7347 \| 0.8838 \| 0.8841 \| \| 0.0052 \| 257.14 \| 5400 \| 0.5966 \| 0.9024 \| 0.9024 \| \| 0.0057 \| 266.67 \| 5600 \| 0.6711 \| 0.8993 \| 0.8994 \| \| 0.0033 \| 276.19 \| 5800 \| 0.8623 \| 0.8865 \| 0.8872 \| \| 0.0045 \| 285.71 \| 6000 \| 0.7814 \| 0.8898 \| 0.8902 \| \| 0.0036 \| 295.24 \| 6200 \| 0.6892 \| 0.9084 \| 0.9085 \| \| 0.0036 \| 304.76 \| 6400 \| 0.7152 \| 0.9084 \| 0.9085 \| \| 0.0024 \| 314.29 \| 6600 \| 0.8272 \| 0.9052 \| 0.9055 \| \| 0.0032 \| 323.81 \| 6800 \| 0.6715 \| 0.9023 \| 0.9024 \| \| 0.0035 \| 333.33 \| 7000 \| 0.7077 \| 0.9023 \| 0.9024 \| \| 0.0037 \| 342.86 \| 7200 \| 0.7097 \| 0.9054 \| 0.9055 \| \| 0.0037 \| 352.38 \| 7400 \| 0.7148 \| 0.9053 \| 0.9055 \| \| 0.0022 \| 361.9 \| 7600 \| 0.6533 \| 0.9085 \| 0.9085 \| \| 0.0023 \| 371.43 \| 7800 \| 0.7545 \| 0.9053 \| 0.9055 \| \| 0.0024 \| 380.95 \| 8000 \| 0.8008 \| 0.8899 \| 0.8902 \| \| 0.0024 \| 390.48 \| 8200 \| 0.7273 \| 0.8992 \| 0.8994 \| \| 0.0024 \| 400.0 \| 8400 \| 0.7910 \| 0.8930 \| 0.8933 \| \| 0.0019 \| 409.52 \| 8600 \| 0.8000 \| 0.8929 \| 0.8933 \| \| 0.0018 \| 419.05 \| 8800 \| 0.7185 \| 0.9022 \| 0.9024 \| \| 0.0014 \| 428.57 \| 9000 \| 0.7269 \| 0.9022 \| 0.9024 \| \| 0.0016 \| 438.1 \| 9200 \| 0.7002 \| 0.9115 \| 0.9116 \| \| 0.0011 \| 447.62 \| 9400 \| 0.7572 \| 0.9053 \| 0.9055 \| \| 0.0013 \| 457.14 \| 9600 \| 0.7180 \| 0.9084 \| 0.9085 \| \| 0.0015 \| 466.67 \| 9800 \| 0.7360 \| 0.9023 \| 0.9024 \| \| 0.0013 \| 476.19 \| 10000 \| 0.7335 \| 0.9084 \| 0.9085 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_2-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_mouse_2-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:29:58+00:00
text-generation	null	## Llamacpp imatrix Quantizations of NPC-LLM-3_8B Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2756">b2756</a> for quantization. Original model: https://huggingface.co/Gigax/NPC-LLM-3_8B All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) ## Prompt format ``` <s><\|system\|> {system_prompt}<\|end\|> <\|user\|> {prompt}<\|end\|> <\|assistant\|> <\|end\|> ``` ## Download a file (not the whole branch) from below: \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [NPC-LLM-3_8B-Q8_0.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q8_0.gguf) \| Q8_0 \| 4.06GB \| Extremely high quality, generally unneeded but max available quant. \| \| [NPC-LLM-3_8B-Q6_K.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q6_K.gguf) \| Q6_K \| 3.13GB \| Very high quality, near perfect, recommended. \| \| [NPC-LLM-3_8B-Q5_K_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q5_K_M.gguf) \| Q5_K_M \| 2.81GB \| High quality, recommended. \| \| [NPC-LLM-3_8B-Q5_K_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q5_K_S.gguf) \| Q5_K_S \| 2.64GB \| High quality, recommended. \| \| [NPC-LLM-3_8B-Q4_K_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q4_K_M.gguf) \| Q4_K_M \| 2.39GB \| Good quality, uses about 4.83 bits per weight, recommended. \| \| [NPC-LLM-3_8B-Q4_K_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q4_K_S.gguf) \| Q4_K_S \| 2.18GB \| Slightly lower quality with more space savings, recommended. \| \| [NPC-LLM-3_8B-IQ4_NL.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ4_NL.gguf) \| IQ4_NL \| 2.17GB \| Decent quality, slightly smaller than Q4_K_S with similar performance recommended. \| \| [NPC-LLM-3_8B-IQ4_XS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ4_XS.gguf) \| IQ4_XS \| 2.05GB \| Decent quality, smaller than Q4_K_S with similar performance, recommended. \| \| [NPC-LLM-3_8B-Q3_K_L.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q3_K_L.gguf) \| Q3_K_L \| 2.08GB \| Lower quality but usable, good for low RAM availability. \| \| [NPC-LLM-3_8B-Q3_K_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q3_K_M.gguf) \| Q3_K_M \| 1.95GB \| Even lower quality. \| \| [NPC-LLM-3_8B-IQ3_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_M.gguf) \| IQ3_M \| 1.85GB \| Medium-low quality, new method with decent performance comparable to Q3_K_M. \| \| [NPC-LLM-3_8B-IQ3_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_S.gguf) \| IQ3_S \| 1.68GB \| Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. \| \| [NPC-LLM-3_8B-Q3_K_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q3_K_S.gguf) \| Q3_K_S \| 1.68GB \| Low quality, not recommended. \| \| [NPC-LLM-3_8B-IQ3_XS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_XS.gguf) \| IQ3_XS \| 1.62GB \| Lower quality, new method with decent performance, slightly better than Q3_K_S. \| \| [NPC-LLM-3_8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_XXS.gguf) \| IQ3_XXS \| 1.51GB \| Lower quality, new method with decent performance, comparable to Q3 quants. \| \| [NPC-LLM-3_8B-Q2_K.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q2_K.gguf) \| Q2_K \| 1.41GB \| Very low quality but surprisingly usable. \| \| [NPC-LLM-3_8B-IQ2_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_M.gguf) \| IQ2_M \| 1.31GB \| Very low quality, uses SOTA techniques to also be surprisingly usable. \| \| [NPC-LLM-3_8B-IQ2_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_S.gguf) \| IQ2_S \| 1.21GB \| Very low quality, uses SOTA techniques to be usable. \| \| [NPC-LLM-3_8B-IQ2_XS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_XS.gguf) \| IQ2_XS \| 1.15GB \| Very low quality, uses SOTA techniques to be usable. \| \| [NPC-LLM-3_8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_XXS.gguf) \| IQ2_XXS \| 1.04GB \| Lower quality, uses SOTA techniques to be usable. \| \| [NPC-LLM-3_8B-IQ1_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ1_M.gguf) \| IQ1_M \| .91GB \| Extremely low quality, not recommended. \| \| [NPC-LLM-3_8B-IQ1_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ1_S.gguf) \| IQ1_S \| .84GB \| Extremely low quality, not recommended. \| ## Which file should I choose? A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. If you want to get more into the weeds, you can check out this extremely useful feature chart: [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. The I-quants are not compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski	{"language": ["en"], "license": "mit", "quantized_by": "bartowski", "pipeline_tag": "text-generation"}	bartowski/NPC-LLM-3_8B-GGUF	null	[ "gguf", "text-generation", "en", "license:mit", "region:us" ]	null	2024-04-29T23:31:09+00:00
null	peft	# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> - Developed by: [More Information Needed] - Funded by [optional]: [More Information Needed] - Shared by [optional]: [More Information Needed] - Model type: [More Information Needed] - Language(s) (NLP): [More Information Needed] - License: [More Information Needed] - Finetuned from model [optional]: [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - Repository: [More Information Needed] - Paper [optional]: [More Information Needed] - Demo [optional]: [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - Training regime: [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - Hardware Type: [More Information Needed] - Hours used: [More Information Needed] - Cloud Provider: [More Information Needed] - Compute Region: [More Information Needed] - Carbon Emitted: [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> BibTeX: [More Information Needed] APA: [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.10.0	{"library_name": "peft", "base_model": "t5-base"}	PQlet/T5base-lora-sumarizationTables-v2-MLM-lambda0.01	null	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:t5-base", "region:us" ]	null	2024-04-29T23:32:45+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_splice_reconstructed-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3468 - F1 Score: 0.8728 - Accuracy: 0.8722 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.9664 \| 0.7 \| 200 \| 0.9062 \| 0.4652 \| 0.5688 \| \| 0.7475 \| 1.4 \| 400 \| 0.5761 \| 0.7375 \| 0.7361 \| \| 0.5257 \| 2.1 \| 600 \| 0.4960 \| 0.7901 \| 0.7887 \| \| 0.4745 \| 2.8 \| 800 \| 0.5054 \| 0.7902 \| 0.7896 \| \| 0.4578 \| 3.5 \| 1000 \| 0.4237 \| 0.8268 \| 0.8264 \| \| 0.441 \| 4.2 \| 1200 \| 0.4493 \| 0.8177 \| 0.8165 \| \| 0.4231 \| 4.9 \| 1400 \| 0.4227 \| 0.8319 \| 0.8312 \| \| 0.411 \| 5.59 \| 1600 \| 0.4583 \| 0.8187 \| 0.8183 \| \| 0.396 \| 6.29 \| 1800 \| 0.4517 \| 0.8176 \| 0.8167 \| \| 0.3895 \| 6.99 \| 2000 \| 0.4294 \| 0.8353 \| 0.8343 \| \| 0.3806 \| 7.69 \| 2200 \| 0.4135 \| 0.8342 \| 0.8334 \| \| 0.3774 \| 8.39 \| 2400 \| 0.4165 \| 0.8367 \| 0.8360 \| \| 0.3647 \| 9.09 \| 2600 \| 0.4366 \| 0.8303 \| 0.8290 \| \| 0.3604 \| 9.79 \| 2800 \| 0.4190 \| 0.8322 \| 0.8314 \| \| 0.3604 \| 10.49 \| 3000 \| 0.4215 \| 0.8342 \| 0.8334 \| \| 0.3517 \| 11.19 \| 3200 \| 0.4374 \| 0.8282 \| 0.8273 \| \| 0.3504 \| 11.89 \| 3400 \| 0.4067 \| 0.8439 \| 0.8431 \| \| 0.3416 \| 12.59 \| 3600 \| 0.3963 \| 0.8484 \| 0.8477 \| \| 0.3423 \| 13.29 \| 3800 \| 0.3719 \| 0.8571 \| 0.8564 \| \| 0.3348 \| 13.99 \| 4000 \| 0.4218 \| 0.8359 \| 0.8349 \| \| 0.3281 \| 14.69 \| 4200 \| 0.4355 \| 0.8289 \| 0.8279 \| \| 0.3285 \| 15.38 \| 4400 \| 0.3763 \| 0.8552 \| 0.8544 \| \| 0.3252 \| 16.08 \| 4600 \| 0.4181 \| 0.8435 \| 0.8426 \| \| 0.3182 \| 16.78 \| 4800 \| 0.3795 \| 0.8538 \| 0.8529 \| \| 0.311 \| 17.48 \| 5000 \| 0.4097 \| 0.8382 \| 0.8371 \| \| 0.3138 \| 18.18 \| 5200 \| 0.3846 \| 0.8549 \| 0.8540 \| \| 0.3113 \| 18.88 \| 5400 \| 0.3760 \| 0.8583 \| 0.8575 \| \| 0.3122 \| 19.58 \| 5600 \| 0.3709 \| 0.8592 \| 0.8584 \| \| 0.3089 \| 20.28 \| 5800 \| 0.3639 \| 0.8678 \| 0.8672 \| \| 0.3074 \| 20.98 \| 6000 \| 0.3687 \| 0.8614 \| 0.8606 \| \| 0.3025 \| 21.68 \| 6200 \| 0.3796 \| 0.8561 \| 0.8553 \| \| 0.3015 \| 22.38 \| 6400 \| 0.3639 \| 0.8616 \| 0.8608 \| \| 0.2954 \| 23.08 \| 6600 \| 0.3758 \| 0.8619 \| 0.8610 \| \| 0.2983 \| 23.78 \| 6800 \| 0.3665 \| 0.8642 \| 0.8634 \| \| 0.2968 \| 24.48 \| 7000 \| 0.3740 \| 0.8616 \| 0.8608 \| \| 0.2976 \| 25.17 \| 7200 \| 0.3697 \| 0.8582 \| 0.8573 \| \| 0.2898 \| 25.87 \| 7400 \| 0.3668 \| 0.8622 \| 0.8615 \| \| 0.2944 \| 26.57 \| 7600 \| 0.3841 \| 0.8540 \| 0.8531 \| \| 0.2862 \| 27.27 \| 7800 \| 0.3776 \| 0.8603 \| 0.8595 \| \| 0.2929 \| 27.97 \| 8000 \| 0.3807 \| 0.8564 \| 0.8555 \| \| 0.2911 \| 28.67 \| 8200 \| 0.3710 \| 0.8607 \| 0.8599 \| \| 0.2861 \| 29.37 \| 8400 \| 0.3652 \| 0.8637 \| 0.8630 \| \| 0.2823 \| 30.07 \| 8600 \| 0.3633 \| 0.8668 \| 0.8661 \| \| 0.2835 \| 30.77 \| 8800 \| 0.3741 \| 0.8610 \| 0.8601 \| \| 0.286 \| 31.47 \| 9000 \| 0.3728 \| 0.8621 \| 0.8612 \| \| 0.284 \| 32.17 \| 9200 \| 0.3671 \| 0.8640 \| 0.8632 \| \| 0.2791 \| 32.87 \| 9400 \| 0.3692 \| 0.8635 \| 0.8628 \| \| 0.282 \| 33.57 \| 9600 \| 0.3793 \| 0.8588 \| 0.8580 \| \| 0.2865 \| 34.27 \| 9800 \| 0.3693 \| 0.8629 \| 0.8621 \| \| 0.2805 \| 34.97 \| 10000 \| 0.3738 \| 0.8607 \| 0.8599 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:33:25+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_splice_reconstructed-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.4196 - F1 Score: 0.8307 - Accuracy: 0.8297 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.9736 \| 0.7 \| 200 \| 0.9359 \| 0.4243 \| 0.5594 \| \| 0.8955 \| 1.4 \| 400 \| 0.8320 \| 0.5525 \| 0.6046 \| \| 0.7304 \| 2.1 \| 600 \| 0.6237 \| 0.7186 \| 0.7172 \| \| 0.5917 \| 2.8 \| 800 \| 0.5618 \| 0.7472 \| 0.7466 \| \| 0.5559 \| 3.5 \| 1000 \| 0.5130 \| 0.7797 \| 0.7790 \| \| 0.5289 \| 4.2 \| 1200 \| 0.5135 \| 0.7817 \| 0.7806 \| \| 0.5077 \| 4.9 \| 1400 \| 0.4961 \| 0.7887 \| 0.7880 \| \| 0.5009 \| 5.59 \| 1600 \| 0.5250 \| 0.7762 \| 0.7755 \| \| 0.4818 \| 6.29 \| 1800 \| 0.5359 \| 0.7696 \| 0.7694 \| \| 0.4752 \| 6.99 \| 2000 \| 0.4866 \| 0.7983 \| 0.7975 \| \| 0.4672 \| 7.69 \| 2200 \| 0.4695 \| 0.8042 \| 0.8036 \| \| 0.4627 \| 8.39 \| 2400 \| 0.5001 \| 0.7922 \| 0.7915 \| \| 0.4567 \| 9.09 \| 2600 \| 0.4895 \| 0.7981 \| 0.7970 \| \| 0.4527 \| 9.79 \| 2800 \| 0.4778 \| 0.8006 \| 0.7999 \| \| 0.4494 \| 10.49 \| 3000 \| 0.4726 \| 0.8036 \| 0.8027 \| \| 0.4408 \| 11.19 \| 3200 \| 0.5001 \| 0.7914 \| 0.7907 \| \| 0.4416 \| 11.89 \| 3400 \| 0.4568 \| 0.8090 \| 0.8082 \| \| 0.4345 \| 12.59 \| 3600 \| 0.4539 \| 0.8130 \| 0.8121 \| \| 0.4319 \| 13.29 \| 3800 \| 0.4542 \| 0.8085 \| 0.8075 \| \| 0.4323 \| 13.99 \| 4000 \| 0.4939 \| 0.7949 \| 0.7942 \| \| 0.424 \| 14.69 \| 4200 \| 0.4718 \| 0.8016 \| 0.8007 \| \| 0.4258 \| 15.38 \| 4400 \| 0.4660 \| 0.8062 \| 0.8053 \| \| 0.425 \| 16.08 \| 4600 \| 0.5009 \| 0.7920 \| 0.7915 \| \| 0.4145 \| 16.78 \| 4800 \| 0.4552 \| 0.8105 \| 0.8093 \| \| 0.4072 \| 17.48 \| 5000 \| 0.4869 \| 0.7988 \| 0.7979 \| \| 0.4119 \| 18.18 \| 5200 \| 0.4255 \| 0.8253 \| 0.8244 \| \| 0.4111 \| 18.88 \| 5400 \| 0.4648 \| 0.8086 \| 0.8078 \| \| 0.4123 \| 19.58 \| 5600 \| 0.4478 \| 0.8136 \| 0.8128 \| \| 0.4101 \| 20.28 \| 5800 \| 0.4426 \| 0.8194 \| 0.8185 \| \| 0.407 \| 20.98 \| 6000 \| 0.4433 \| 0.8161 \| 0.8152 \| \| 0.4058 \| 21.68 \| 6200 \| 0.4663 \| 0.8059 \| 0.8051 \| \| 0.4026 \| 22.38 \| 6400 \| 0.4506 \| 0.8154 \| 0.8146 \| \| 0.3959 \| 23.08 \| 6600 \| 0.4422 \| 0.8207 \| 0.8196 \| \| 0.4027 \| 23.78 \| 6800 \| 0.4401 \| 0.8221 \| 0.8211 \| \| 0.3965 \| 24.48 \| 7000 \| 0.4640 \| 0.8090 \| 0.8082 \| \| 0.399 \| 25.17 \| 7200 \| 0.4363 \| 0.8245 \| 0.8235 \| \| 0.3964 \| 25.87 \| 7400 \| 0.4539 \| 0.8137 \| 0.8128 \| \| 0.3919 \| 26.57 \| 7600 \| 0.4657 \| 0.8117 \| 0.8108 \| \| 0.3931 \| 27.27 \| 7800 \| 0.4482 \| 0.8181 \| 0.8172 \| \| 0.3966 \| 27.97 \| 8000 \| 0.4533 \| 0.8161 \| 0.8152 \| \| 0.4005 \| 28.67 \| 8200 \| 0.4518 \| 0.8156 \| 0.8148 \| \| 0.3938 \| 29.37 \| 8400 \| 0.4418 \| 0.8218 \| 0.8207 \| \| 0.3888 \| 30.07 \| 8600 \| 0.4279 \| 0.8278 \| 0.8268 \| \| 0.3895 \| 30.77 \| 8800 \| 0.4521 \| 0.8184 \| 0.8174 \| \| 0.3945 \| 31.47 \| 9000 \| 0.4420 \| 0.8194 \| 0.8185 \| \| 0.3927 \| 32.17 \| 9200 \| 0.4460 \| 0.8199 \| 0.8189 \| \| 0.3907 \| 32.87 \| 9400 \| 0.4429 \| 0.8181 \| 0.8172 \| \| 0.3895 \| 33.57 \| 9600 \| 0.4482 \| 0.8165 \| 0.8157 \| \| 0.3909 \| 34.27 \| 9800 \| 0.4429 \| 0.8199 \| 0.8189 \| \| 0.3878 \| 34.97 \| 10000 \| 0.4457 \| 0.8207 \| 0.8198 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:33:25+00:00
token-classification	span-marker	# SpanMarker with roberta-large on Jerado/enron_intangibles_ner This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [Jerado/enron_intangibles_ner](https://huggingface.co/datasets/Jerado/enron_intangibles_ner) dataset that can be used for Named Entity Recognition. This SpanMarker model uses [roberta-large](https://huggingface.co/roberta-large) as the underlying encoder. ## Model Details ### Model Description - Model Type: SpanMarker - Encoder: [roberta-large](https://huggingface.co/roberta-large) - Maximum Sequence Length: 256 tokens - Maximum Entity Length: 6 words - Training Dataset: [Jerado/enron_intangibles_ner](https://huggingface.co/datasets/Jerado/enron_intangibles_ner) - Language: en - License: apache-2.0 ### Model Sources - Repository: [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER) - Thesis: [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf) ### Model Labels \| Label \| Examples \| \|:-----------\|:--------------------------------------------\| \| Intangible \| "deal", "sample EES deal", "Enpower system" \| ## Evaluation ### Metrics \| Label \| Precision \| Recall \| F1 \| \|:-----------\|:----------\|:-------\|:-------\| \| all \| 0.4286 \| 0.45 \| 0.4390 \| \| Intangible \| 0.4286 \| 0.45 \| 0.4390 \| ## Uses ### Direct Use for Inference ```python from span_marker import SpanMarkerModel # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("span_marker_model_id") # Run inference entities = model.predict("It seems that there is a single significant policy concern for the ASIC policy committee.") ``` ### Downstream Use You can finetune this model on your own dataset. <details><summary>Click to expand</summary> ```python from span_marker import SpanMarkerModel, Trainer # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("span_marker_model_id") # Specify a Dataset with "tokens" and "ner_tag" columns dataset = load_dataset("conll2003") # For example CoNLL2003 # Initialize a Trainer using the pretrained model & dataset trainer = Trainer( model=model, train_dataset=dataset["train"], eval_dataset=dataset["validation"], ) trainer.train() trainer.save_model("span_marker_model_id-finetuned") ``` </details> <!-- ### Out-of-Scope Use List how the model may foreseeably be misused and address what users ought not to do with the model. --> <!-- ## Bias, Risks and Limitations What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model. --> <!-- ### Recommendations What are recommendations with respect to the foreseeable issues? For example, filtering explicit content. --> ## Training Details ### Training Set Metrics \| Training set \| Min \| Median \| Max \| \|:----------------------\|:----\|:--------\|:----\| \| Sentence length \| 1 \| 19.8706 \| 216 \| \| Entities per sentence \| 0 \| 0.1865 \| 6 \| ### Training Hyperparameters - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 11 - mixed_precision_training: Native AMP ### Training Results \| Epoch \| Step \| Validation Loss \| Validation Precision \| Validation Recall \| Validation F1 \| Validation Accuracy \| \|:-------:\|:----:\|:---------------:\|:--------------------:\|:-----------------:\|:-------------:\|:-------------------:\| \| 3.3557 \| 500 \| 0.0075 \| 0.4444 \| 0.1667 \| 0.2424 \| 0.9753 \| \| 6.7114 \| 1000 \| 0.0084 \| 0.5714 \| 0.3333 \| 0.4211 \| 0.9793 \| \| 10.0671 \| 1500 \| 0.0098 \| 0.6111 \| 0.4583 \| 0.5238 \| 0.9815 \| ### Framework Versions - Python: 3.10.12 - SpanMarker: 1.5.0 - Transformers: 4.40.0 - PyTorch: 2.2.1+cu121 - Datasets: 2.19.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX ``` @software{Aarsen_SpanMarker, author = {Aarsen, Tom}, license = {Apache-2.0}, title = {{SpanMarker for Named Entity Recognition}}, url = {https://github.com/tomaarsen/SpanMarkerNER} } ``` <!-- ## Glossary Clearly define terms in order to be accessible across audiences. --> <!-- ## Model Card Authors Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction. --> <!-- ## Model Card Contact Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors. -->	{"language": ["en"], "license": "apache-2.0", "library_name": "span-marker", "tags": ["span-marker", "token-classification", "ner", "named-entity-recognition", "generated_from_span_marker_trainer"], "datasets": ["Jerado/enron_intangibles_ner"], "metrics": ["precision", "recall", "f1"], "base_model": "roberta-large", "widget": [{"text": "Negotiated rates in these types of deals (basis for new builds) have been allowed to stand for the life of the contracts, in the case of Kern River and Mojave."}, {"text": "It seems that there is a single significant policy concern for the ASIC policy committee."}, {"text": "The appropriate price is in Enpower, but the revenue has never appeared (Deal #590753)."}, {"text": "FYI, to me, a prepayment for a service contract would generally be amortized over the life of the contract."}, {"text": "From: d..steffes @ enron.com To: john.shelk @ enron.com, l..nicolay @ enron.com, richard.shapiro @ enron.com, sarah.novosel @ enron.com Subject: Southern Co.'s Testimony The first order of business is getting the cost / benefit analysis done."}], "pipeline_tag": "token-classification", "model-index": [{"name": "SpanMarker with roberta-large on Jerado/enron_intangibles_ner", "results": [{"task": {"type": "token-classification", "name": "Named Entity Recognition"}, "dataset": {"name": "Unknown", "type": "Jerado/enron_intangibles_ner", "split": "test"}, "metrics": [{"type": "f1", "value": 0.4390243902439024, "name": "F1"}, {"type": "precision", "value": 0.42857142857142855, "name": "Precision"}, {"type": "recall", "value": 0.45, "name": "Recall"}]}]}]}	Jerado/span-marker-roberta-large-enron	null	[ "span-marker", "tensorboard", "safetensors", "token-classification", "ner", "named-entity-recognition", "generated_from_span_marker_trainer", "en", "dataset:Jerado/enron_intangibles_ner", "base_model:roberta-large", "license:apache-2.0", "model-index", "region:us" ]	null	2024-04-29T23:34:21+00:00
image-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-base-patch16-224-in21k-finetuned This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the image_folder dataset. It achieves the following results on the evaluation set: - Loss: 0.9803 - Accuracy: 0.7058 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 0.4887 \| 1.0 \| 224 \| 0.9213 \| 0.6776 \| \| 0.4969 \| 2.0 \| 449 \| 0.9038 \| 0.6927 \| \| 0.4095 \| 3.0 \| 673 \| 0.9077 \| 0.6977 \| \| 0.3344 \| 4.0 \| 898 \| 0.9398 \| 0.6989 \| \| 0.3055 \| 5.0 \| 1122 \| 0.9803 \| 0.7058 \| \| 0.2214 \| 6.0 \| 1347 \| 1.0337 \| 0.6953 \| \| 0.1575 \| 7.0 \| 1571 \| 1.0642 \| 0.6977 \| \| 0.1169 \| 8.0 \| 1796 \| 1.0829 \| 0.7030 \| \| 0.0917 \| 9.0 \| 2020 \| 1.1121 \| 0.7048 \| \| 0.0785 \| 9.98 \| 2240 \| 1.1280 \| 0.7052 \| ### Framework versions - Transformers 4.36.0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.15.0	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["image_folder"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "vit-base-patch16-224-in21k-finetuned", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "image_folder", "type": "image_folder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.7057676232933965, "name": "Accuracy"}]}]}]}	motheecreator/vit-base-patch16-224-in21k-finetuned	null	[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "dataset:image_folder", "base_model:google/vit-base-patch16-224-in21k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:34:51+00:00
null	null	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # O0428HMA4 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1449 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.6513 \| 0.09 \| 10 \| 0.2874 \| \| 0.1942 \| 0.18 \| 20 \| 0.1547 \| \| 0.1509 \| 0.27 \| 30 \| 0.1700 \| \| 0.1537 \| 0.36 \| 40 \| 0.1502 \| \| 0.1503 \| 0.45 \| 50 \| 0.1510 \| \| 0.1523 \| 0.54 \| 60 \| 0.1494 \| \| 0.1493 \| 0.63 \| 70 \| 0.1485 \| \| 0.149 \| 0.73 \| 80 \| 0.1558 \| \| 0.1477 \| 0.82 \| 90 \| 0.1494 \| \| 0.1482 \| 0.91 \| 100 \| 0.1487 \| \| 0.1486 \| 1.0 \| 110 \| 0.1489 \| \| 0.1454 \| 1.09 \| 120 \| 0.1484 \| \| 0.1451 \| 1.18 \| 130 \| 0.1500 \| \| 0.1474 \| 1.27 \| 140 \| 0.1502 \| \| 0.1491 \| 1.36 \| 150 \| 0.1479 \| \| 0.145 \| 1.45 \| 160 \| 0.1472 \| \| 0.1445 \| 1.54 \| 170 \| 0.1464 \| \| 0.1477 \| 1.63 \| 180 \| 0.1467 \| \| 0.1467 \| 1.72 \| 190 \| 0.1489 \| \| 0.1453 \| 1.81 \| 200 \| 0.1484 \| \| 0.1495 \| 1.9 \| 210 \| 0.1492 \| \| 0.1464 \| 1.99 \| 220 \| 0.1498 \| \| 0.1472 \| 2.08 \| 230 \| 0.1478 \| \| 0.1414 \| 2.18 \| 240 \| 0.1460 \| \| 0.1427 \| 2.27 \| 250 \| 0.1470 \| \| 0.1439 \| 2.36 \| 260 \| 0.1478 \| \| 0.1429 \| 2.45 \| 270 \| 0.1457 \| \| 0.1407 \| 2.54 \| 280 \| 0.1463 \| \| 0.1416 \| 2.63 \| 290 \| 0.1461 \| \| 0.1436 \| 2.72 \| 300 \| 0.1448 \| \| 0.1437 \| 2.81 \| 310 \| 0.1448 \| \| 0.1434 \| 2.9 \| 320 \| 0.1449 \| \| 0.1443 \| 2.99 \| 330 \| 0.1449 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA4", "results": []}]}	Litzy619/O0428HMA4	null	[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]	null	2024-04-29T23:36:26+00:00
null	null	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # O0428HMA5 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1828 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| 1.5402 \| 0.09 \| 10 \| 0.1748 \| \| 0.1661 \| 0.18 \| 20 \| 0.1584 \| \| 0.1504 \| 0.27 \| 30 \| 0.1670 \| \| 0.1555 \| 0.36 \| 40 \| 0.1533 \| \| 0.1499 \| 0.45 \| 50 \| 0.1547 \| \| 0.1505 \| 0.54 \| 60 \| 0.1519 \| \| 0.1523 \| 0.63 \| 70 \| 0.1469 \| \| 0.1513 \| 0.73 \| 80 \| 0.1567 \| \| 0.1456 \| 0.82 \| 90 \| 0.1465 \| \| 0.1843 \| 0.91 \| 100 \| 0.2555 \| \| 1.2658 \| 1.0 \| 110 \| 0.2093 \| \| 0.8089 \| 1.09 \| 120 \| 0.1813 \| \| 0.1539 \| 1.18 \| 130 \| 0.1515 \| \| 1.0124 \| 1.27 \| 140 \| 0.1645 \| \| 0.3947 \| 1.36 \| 150 \| 0.1674 \| \| 0.3807 \| 1.45 \| 160 \| 0.1619 \| \| 0.1511 \| 1.54 \| 170 \| 0.1515 \| \| 0.1524 \| 1.63 \| 180 \| 0.1492 \| \| 0.1488 \| 1.72 \| 190 \| 0.1483 \| \| 0.1513 \| 1.81 \| 200 \| 0.1556 \| \| 0.5422 \| 1.9 \| 210 \| 0.8696 \| \| 0.7566 \| 1.99 \| 220 \| 1.3407 \| \| 0.4939 \| 2.08 \| 230 \| 0.2669 \| \| 0.2818 \| 2.18 \| 240 \| 0.2439 \| \| 0.2348 \| 2.27 \| 250 \| 0.2392 \| \| 0.2358 \| 2.36 \| 260 \| 0.2121 \| \| 0.1847 \| 2.45 \| 270 \| 0.1995 \| \| 0.1858 \| 2.54 \| 280 \| 0.1898 \| \| 0.1845 \| 2.63 \| 290 \| 0.1867 \| \| 0.1889 \| 2.72 \| 300 \| 0.1845 \| \| 0.1746 \| 2.81 \| 310 \| 0.1841 \| \| 0.1758 \| 2.9 \| 320 \| 0.1830 \| \| 0.1739 \| 2.99 \| 330 \| 0.1828 \| ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA5", "results": []}]}	Litzy619/O0428HMA5	null	[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]	null	2024-04-29T23:36:58+00:00
fill-mask	transformers		{}	kumarme072/med_model	null	[ "transformers", "pytorch", "bert", "fill-mask", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:37:11+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_splice_reconstructed-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3148 - F1 Score: 0.8880 - Accuracy: 0.8875 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.9568 \| 0.7 \| 200 \| 0.8950 \| 0.4693 \| 0.5673 \| \| 0.6475 \| 1.4 \| 400 \| 0.5182 \| 0.7698 \| 0.7687 \| \| 0.4734 \| 2.1 \| 600 \| 0.4341 \| 0.8266 \| 0.8255 \| \| 0.4255 \| 2.8 \| 800 \| 0.4334 \| 0.8231 \| 0.8222 \| \| 0.4049 \| 3.5 \| 1000 \| 0.3792 \| 0.8512 \| 0.8507 \| \| 0.3848 \| 4.2 \| 1200 \| 0.3946 \| 0.8418 \| 0.8406 \| \| 0.3664 \| 4.9 \| 1400 \| 0.3594 \| 0.8643 \| 0.8639 \| \| 0.3572 \| 5.59 \| 1600 \| 0.3911 \| 0.8544 \| 0.8544 \| \| 0.3383 \| 6.29 \| 1800 \| 0.3998 \| 0.8440 \| 0.8428 \| \| 0.3319 \| 6.99 \| 2000 \| 0.3653 \| 0.8626 \| 0.8617 \| \| 0.3186 \| 7.69 \| 2200 \| 0.3655 \| 0.8607 \| 0.8599 \| \| 0.3139 \| 8.39 \| 2400 \| 0.3510 \| 0.8691 \| 0.8687 \| \| 0.3 \| 9.09 \| 2600 \| 0.3975 \| 0.8510 \| 0.8496 \| \| 0.2952 \| 9.79 \| 2800 \| 0.3840 \| 0.8549 \| 0.8540 \| \| 0.2908 \| 10.49 \| 3000 \| 0.3742 \| 0.8605 \| 0.8597 \| \| 0.2825 \| 11.19 \| 3200 \| 0.3894 \| 0.8564 \| 0.8553 \| \| 0.2785 \| 11.89 \| 3400 \| 0.4033 \| 0.8485 \| 0.8474 \| \| 0.2689 \| 12.59 \| 3600 \| 0.3563 \| 0.8663 \| 0.8656 \| \| 0.2693 \| 13.29 \| 3800 \| 0.3235 \| 0.8788 \| 0.8781 \| \| 0.2599 \| 13.99 \| 4000 \| 0.3665 \| 0.8618 \| 0.8608 \| \| 0.2526 \| 14.69 \| 4200 \| 0.3841 \| 0.8527 \| 0.8516 \| \| 0.2551 \| 15.38 \| 4400 \| 0.3398 \| 0.8716 \| 0.8709 \| \| 0.2465 \| 16.08 \| 4600 \| 0.3716 \| 0.8619 \| 0.8610 \| \| 0.2412 \| 16.78 \| 4800 \| 0.3420 \| 0.8727 \| 0.8720 \| \| 0.2318 \| 17.48 \| 5000 \| 0.3872 \| 0.8544 \| 0.8534 \| \| 0.233 \| 18.18 \| 5200 \| 0.3430 \| 0.8794 \| 0.8786 \| \| 0.2291 \| 18.88 \| 5400 \| 0.3565 \| 0.8727 \| 0.8720 \| \| 0.2272 \| 19.58 \| 5600 \| 0.3474 \| 0.8732 \| 0.8724 \| \| 0.2301 \| 20.28 \| 5800 \| 0.3183 \| 0.8874 \| 0.8869 \| \| 0.2263 \| 20.98 \| 6000 \| 0.3270 \| 0.8810 \| 0.8803 \| \| 0.2177 \| 21.68 \| 6200 \| 0.3308 \| 0.8798 \| 0.8792 \| \| 0.2101 \| 22.38 \| 6400 \| 0.3555 \| 0.8756 \| 0.8748 \| \| 0.207 \| 23.08 \| 6600 \| 0.3779 \| 0.8713 \| 0.8705 \| \| 0.2081 \| 23.78 \| 6800 \| 0.3397 \| 0.8777 \| 0.8770 \| \| 0.2066 \| 24.48 \| 7000 \| 0.3502 \| 0.8741 \| 0.8735 \| \| 0.2035 \| 25.17 \| 7200 \| 0.3394 \| 0.8797 \| 0.8790 \| \| 0.2013 \| 25.87 \| 7400 \| 0.3254 \| 0.8831 \| 0.8825 \| \| 0.2025 \| 26.57 \| 7600 \| 0.3582 \| 0.8719 \| 0.8711 \| \| 0.1927 \| 27.27 \| 7800 \| 0.3586 \| 0.8739 \| 0.8733 \| \| 0.199 \| 27.97 \| 8000 \| 0.3353 \| 0.8802 \| 0.8797 \| \| 0.1981 \| 28.67 \| 8200 \| 0.3429 \| 0.8786 \| 0.8779 \| \| 0.1902 \| 29.37 \| 8400 \| 0.3422 \| 0.8805 \| 0.8799 \| \| 0.1851 \| 30.07 \| 8600 \| 0.3371 \| 0.8825 \| 0.8819 \| \| 0.1849 \| 30.77 \| 8800 \| 0.3418 \| 0.8806 \| 0.8799 \| \| 0.1905 \| 31.47 \| 9000 \| 0.3456 \| 0.8813 \| 0.8805 \| \| 0.1859 \| 32.17 \| 9200 \| 0.3474 \| 0.8804 \| 0.8797 \| \| 0.1835 \| 32.87 \| 9400 \| 0.3517 \| 0.8792 \| 0.8786 \| \| 0.1812 \| 33.57 \| 9600 \| 0.3509 \| 0.8780 \| 0.8772 \| \| 0.1855 \| 34.27 \| 9800 \| 0.3465 \| 0.8797 \| 0.8790 \| \| 0.1803 \| 34.97 \| 10000 \| 0.3489 \| 0.8791 \| 0.8783 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:37:38+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_0-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3880 - F1 Score: 0.8258 - Accuracy: 0.827 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5566 \| 0.79 \| 200 \| 0.4955 \| 0.7418 \| 0.742 \| \| 0.4995 \| 1.58 \| 400 \| 0.4868 \| 0.7579 \| 0.759 \| \| 0.4928 \| 2.37 \| 600 \| 0.4896 \| 0.7527 \| 0.755 \| \| 0.485 \| 3.16 \| 800 \| 0.4796 \| 0.7528 \| 0.753 \| \| 0.4787 \| 3.95 \| 1000 \| 0.4851 \| 0.7654 \| 0.767 \| \| 0.4775 \| 4.74 \| 1200 \| 0.4849 \| 0.7598 \| 0.76 \| \| 0.4732 \| 5.53 \| 1400 \| 0.4833 \| 0.7550 \| 0.755 \| \| 0.466 \| 6.32 \| 1600 \| 0.4861 \| 0.7570 \| 0.757 \| \| 0.4682 \| 7.11 \| 1800 \| 0.4846 \| 0.7611 \| 0.761 \| \| 0.4712 \| 7.91 \| 2000 \| 0.4785 \| 0.7660 \| 0.766 \| \| 0.4637 \| 8.7 \| 2200 \| 0.4764 \| 0.7655 \| 0.766 \| \| 0.462 \| 9.49 \| 2400 \| 0.4754 \| 0.7651 \| 0.766 \| \| 0.461 \| 10.28 \| 2600 \| 0.4737 \| 0.7670 \| 0.767 \| \| 0.4591 \| 11.07 \| 2800 \| 0.4673 \| 0.7701 \| 0.77 \| \| 0.4564 \| 11.86 \| 3000 \| 0.4715 \| 0.7640 \| 0.764 \| \| 0.4578 \| 12.65 \| 3200 \| 0.4688 \| 0.7691 \| 0.769 \| \| 0.4553 \| 13.44 \| 3400 \| 0.4711 \| 0.7751 \| 0.776 \| \| 0.4557 \| 14.23 \| 3600 \| 0.4665 \| 0.7696 \| 0.77 \| \| 0.4541 \| 15.02 \| 3800 \| 0.4668 \| 0.772 \| 0.772 \| \| 0.4552 \| 15.81 \| 4000 \| 0.4691 \| 0.7740 \| 0.774 \| \| 0.4473 \| 16.6 \| 4200 \| 0.4721 \| 0.7781 \| 0.779 \| \| 0.4516 \| 17.39 \| 4400 \| 0.4703 \| 0.7691 \| 0.769 \| \| 0.4499 \| 18.18 \| 4600 \| 0.4715 \| 0.7669 \| 0.767 \| \| 0.451 \| 18.97 \| 4800 \| 0.4626 \| 0.774 \| 0.774 \| \| 0.4541 \| 19.76 \| 5000 \| 0.4618 \| 0.7777 \| 0.778 \| \| 0.4473 \| 20.55 \| 5200 \| 0.4641 \| 0.7814 \| 0.782 \| \| 0.4447 \| 21.34 \| 5400 \| 0.4652 \| 0.7689 \| 0.769 \| \| 0.4457 \| 22.13 \| 5600 \| 0.4680 \| 0.7700 \| 0.77 \| \| 0.4473 \| 22.92 \| 5800 \| 0.4659 \| 0.7750 \| 0.775 \| \| 0.4429 \| 23.72 \| 6000 \| 0.4655 \| 0.7690 \| 0.769 \| \| 0.4429 \| 24.51 \| 6200 \| 0.4647 \| 0.7787 \| 0.779 \| \| 0.4483 \| 25.3 \| 6400 \| 0.4645 \| 0.7690 \| 0.769 \| \| 0.4415 \| 26.09 \| 6600 \| 0.4655 \| 0.7708 \| 0.771 \| \| 0.4451 \| 26.88 \| 6800 \| 0.4653 \| 0.7720 \| 0.772 \| \| 0.4441 \| 27.67 \| 7000 \| 0.4623 \| 0.7736 \| 0.774 \| \| 0.444 \| 28.46 \| 7200 \| 0.4631 \| 0.7834 \| 0.784 \| \| 0.4444 \| 29.25 \| 7400 \| 0.4622 \| 0.7727 \| 0.773 \| \| 0.4439 \| 30.04 \| 7600 \| 0.4636 \| 0.7759 \| 0.776 \| \| 0.4431 \| 30.83 \| 7800 \| 0.4621 \| 0.7789 \| 0.779 \| \| 0.4435 \| 31.62 \| 8000 \| 0.4631 \| 0.7855 \| 0.786 \| \| 0.441 \| 32.41 \| 8200 \| 0.4607 \| 0.7768 \| 0.777 \| \| 0.4348 \| 33.2 \| 8400 \| 0.4637 \| 0.7729 \| 0.773 \| \| 0.4412 \| 33.99 \| 8600 \| 0.4638 \| 0.7786 \| 0.779 \| \| 0.4422 \| 34.78 \| 8800 \| 0.4624 \| 0.7806 \| 0.781 \| \| 0.4369 \| 35.57 \| 9000 \| 0.4626 \| 0.7748 \| 0.775 \| \| 0.4406 \| 36.36 \| 9200 \| 0.4640 \| 0.7710 \| 0.771 \| \| 0.4422 \| 37.15 \| 9400 \| 0.4626 \| 0.7739 \| 0.774 \| \| 0.4391 \| 37.94 \| 9600 \| 0.4625 \| 0.7728 \| 0.773 \| \| 0.4385 \| 38.74 \| 9800 \| 0.4631 \| 0.7759 \| 0.776 \| \| 0.443 \| 39.53 \| 10000 \| 0.4627 \| 0.7749 \| 0.775 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_0-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_0-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:38:32+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_0-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3833 - F1 Score: 0.8273 - Accuracy: 0.828 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5365 \| 0.79 \| 200 \| 0.4925 \| 0.7532 \| 0.755 \| \| 0.4867 \| 1.58 \| 400 \| 0.4771 \| 0.7669 \| 0.767 \| \| 0.4762 \| 2.37 \| 600 \| 0.4799 \| 0.7580 \| 0.759 \| \| 0.4678 \| 3.16 \| 800 \| 0.4709 \| 0.7745 \| 0.775 \| \| 0.4622 \| 3.95 \| 1000 \| 0.4691 \| 0.7805 \| 0.781 \| \| 0.459 \| 4.74 \| 1200 \| 0.4736 \| 0.7779 \| 0.778 \| \| 0.4553 \| 5.53 \| 1400 \| 0.4769 \| 0.7719 \| 0.772 \| \| 0.4466 \| 6.32 \| 1600 \| 0.4755 \| 0.7741 \| 0.774 \| \| 0.4504 \| 7.11 \| 1800 \| 0.4722 \| 0.7690 \| 0.769 \| \| 0.4491 \| 7.91 \| 2000 \| 0.4698 \| 0.7750 \| 0.775 \| \| 0.4423 \| 8.7 \| 2200 \| 0.4634 \| 0.7727 \| 0.773 \| \| 0.439 \| 9.49 \| 2400 \| 0.4636 \| 0.7749 \| 0.775 \| \| 0.4379 \| 10.28 \| 2600 \| 0.4667 \| 0.7801 \| 0.78 \| \| 0.435 \| 11.07 \| 2800 \| 0.4657 \| 0.7808 \| 0.781 \| \| 0.4313 \| 11.86 \| 3000 \| 0.4738 \| 0.7790 \| 0.779 \| \| 0.4291 \| 12.65 \| 3200 \| 0.4638 \| 0.7791 \| 0.779 \| \| 0.4273 \| 13.44 \| 3400 \| 0.4707 \| 0.7711 \| 0.771 \| \| 0.4279 \| 14.23 \| 3600 \| 0.4659 \| 0.7860 \| 0.786 \| \| 0.4282 \| 15.02 \| 3800 \| 0.4653 \| 0.7770 \| 0.777 \| \| 0.4238 \| 15.81 \| 4000 \| 0.4612 \| 0.7810 \| 0.781 \| \| 0.4187 \| 16.6 \| 4200 \| 0.4643 \| 0.7868 \| 0.787 \| \| 0.4225 \| 17.39 \| 4400 \| 0.4655 \| 0.7790 \| 0.779 \| \| 0.4187 \| 18.18 \| 4600 \| 0.4665 \| 0.7800 \| 0.78 \| \| 0.42 \| 18.97 \| 4800 \| 0.4664 \| 0.7819 \| 0.782 \| \| 0.4225 \| 19.76 \| 5000 \| 0.4657 \| 0.7880 \| 0.788 \| \| 0.4184 \| 20.55 \| 5200 \| 0.4636 \| 0.7890 \| 0.789 \| \| 0.413 \| 21.34 \| 5400 \| 0.4739 \| 0.7756 \| 0.776 \| \| 0.4138 \| 22.13 \| 5600 \| 0.4721 \| 0.7781 \| 0.778 \| \| 0.4146 \| 22.92 \| 5800 \| 0.4718 \| 0.78 \| 0.78 \| \| 0.4088 \| 23.72 \| 6000 \| 0.4694 \| 0.7840 \| 0.784 \| \| 0.4076 \| 24.51 \| 6200 \| 0.4614 \| 0.7861 \| 0.786 \| \| 0.4126 \| 25.3 \| 6400 \| 0.4663 \| 0.7861 \| 0.786 \| \| 0.4063 \| 26.09 \| 6600 \| 0.4671 \| 0.7860 \| 0.786 \| \| 0.4093 \| 26.88 \| 6800 \| 0.4644 \| 0.7861 \| 0.786 \| \| 0.4093 \| 27.67 \| 7000 \| 0.4654 \| 0.7900 \| 0.79 \| \| 0.4086 \| 28.46 \| 7200 \| 0.4638 \| 0.7870 \| 0.787 \| \| 0.4068 \| 29.25 \| 7400 \| 0.4683 \| 0.7821 \| 0.782 \| \| 0.4083 \| 30.04 \| 7600 \| 0.4685 \| 0.7870 \| 0.787 \| \| 0.4046 \| 30.83 \| 7800 \| 0.4658 \| 0.7891 \| 0.789 \| \| 0.4055 \| 31.62 \| 8000 \| 0.4639 \| 0.7859 \| 0.786 \| \| 0.4045 \| 32.41 \| 8200 \| 0.4713 \| 0.7850 \| 0.785 \| \| 0.3976 \| 33.2 \| 8400 \| 0.4701 \| 0.7830 \| 0.783 \| \| 0.4032 \| 33.99 \| 8600 \| 0.4697 \| 0.7890 \| 0.789 \| \| 0.4056 \| 34.78 \| 8800 \| 0.4617 \| 0.7909 \| 0.791 \| \| 0.3969 \| 35.57 \| 9000 \| 0.4649 \| 0.7940 \| 0.794 \| \| 0.401 \| 36.36 \| 9200 \| 0.4788 \| 0.7800 \| 0.78 \| \| 0.4014 \| 37.15 \| 9400 \| 0.4727 \| 0.7850 \| 0.785 \| \| 0.4023 \| 37.94 \| 9600 \| 0.4697 \| 0.7881 \| 0.788 \| \| 0.4004 \| 38.74 \| 9800 \| 0.4719 \| 0.7870 \| 0.787 \| \| 0.4029 \| 39.53 \| 10000 \| 0.4708 \| 0.7881 \| 0.788 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_0-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_0-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:39:27+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_1-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3443 - F1 Score: 0.8566 - Accuracy: 0.857 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5709 \| 0.83 \| 200 \| 0.5541 \| 0.7178 \| 0.718 \| \| 0.5176 \| 1.67 \| 400 \| 0.5487 \| 0.7354 \| 0.736 \| \| 0.5088 \| 2.5 \| 600 \| 0.5363 \| 0.7390 \| 0.739 \| \| 0.4984 \| 3.33 \| 800 \| 0.5325 \| 0.7336 \| 0.734 \| \| 0.5006 \| 4.17 \| 1000 \| 0.5220 \| 0.7469 \| 0.747 \| \| 0.4921 \| 5.0 \| 1200 \| 0.5261 \| 0.7460 \| 0.746 \| \| 0.4893 \| 5.83 \| 1400 \| 0.5191 \| 0.7490 \| 0.749 \| \| 0.4896 \| 6.67 \| 1600 \| 0.5218 \| 0.7490 \| 0.749 \| \| 0.4846 \| 7.5 \| 1800 \| 0.5249 \| 0.7435 \| 0.744 \| \| 0.4803 \| 8.33 \| 2000 \| 0.5178 \| 0.7439 \| 0.744 \| \| 0.4806 \| 9.17 \| 2200 \| 0.5187 \| 0.744 \| 0.744 \| \| 0.4801 \| 10.0 \| 2400 \| 0.5290 \| 0.7394 \| 0.74 \| \| 0.4778 \| 10.83 \| 2600 \| 0.5270 \| 0.7473 \| 0.748 \| \| 0.477 \| 11.67 \| 2800 \| 0.5226 \| 0.7503 \| 0.751 \| \| 0.4707 \| 12.5 \| 3000 \| 0.5218 \| 0.7467 \| 0.747 \| \| 0.4787 \| 13.33 \| 3200 \| 0.5133 \| 0.7496 \| 0.75 \| \| 0.4692 \| 14.17 \| 3400 \| 0.5164 \| 0.7450 \| 0.745 \| \| 0.4721 \| 15.0 \| 3600 \| 0.5230 \| 0.7448 \| 0.746 \| \| 0.4674 \| 15.83 \| 3800 \| 0.5129 \| 0.7487 \| 0.749 \| \| 0.4726 \| 16.67 \| 4000 \| 0.5229 \| 0.7428 \| 0.743 \| \| 0.4682 \| 17.5 \| 4200 \| 0.5178 \| 0.7435 \| 0.744 \| \| 0.4651 \| 18.33 \| 4400 \| 0.5202 \| 0.7450 \| 0.745 \| \| 0.4678 \| 19.17 \| 4600 \| 0.5233 \| 0.7444 \| 0.745 \| \| 0.4697 \| 20.0 \| 4800 \| 0.5136 \| 0.7459 \| 0.746 \| \| 0.4686 \| 20.83 \| 5000 \| 0.5201 \| 0.7438 \| 0.744 \| \| 0.4631 \| 21.67 \| 5200 \| 0.5131 \| 0.7438 \| 0.744 \| \| 0.468 \| 22.5 \| 5400 \| 0.5125 \| 0.7450 \| 0.745 \| \| 0.4634 \| 23.33 \| 5600 \| 0.5146 \| 0.7485 \| 0.749 \| \| 0.4641 \| 24.17 \| 5800 \| 0.5232 \| 0.7451 \| 0.746 \| \| 0.4662 \| 25.0 \| 6000 \| 0.5133 \| 0.7470 \| 0.747 \| \| 0.4635 \| 25.83 \| 6200 \| 0.5146 \| 0.7488 \| 0.749 \| \| 0.4611 \| 26.67 \| 6400 \| 0.5150 \| 0.7430 \| 0.743 \| \| 0.4635 \| 27.5 \| 6600 \| 0.5174 \| 0.7509 \| 0.751 \| \| 0.4624 \| 28.33 \| 6800 \| 0.5121 \| 0.7518 \| 0.752 \| \| 0.4603 \| 29.17 \| 7000 \| 0.5150 \| 0.7469 \| 0.747 \| \| 0.4637 \| 30.0 \| 7200 \| 0.5141 \| 0.7447 \| 0.745 \| \| 0.4618 \| 30.83 \| 7400 \| 0.5182 \| 0.7402 \| 0.741 \| \| 0.458 \| 31.67 \| 7600 \| 0.5136 \| 0.7479 \| 0.748 \| \| 0.4619 \| 32.5 \| 7800 \| 0.5121 \| 0.7509 \| 0.751 \| \| 0.4583 \| 33.33 \| 8000 \| 0.5120 \| 0.7468 \| 0.747 \| \| 0.4623 \| 34.17 \| 8200 \| 0.5123 \| 0.7488 \| 0.749 \| \| 0.4579 \| 35.0 \| 8400 \| 0.5129 \| 0.7499 \| 0.75 \| \| 0.4588 \| 35.83 \| 8600 \| 0.5113 \| 0.7529 \| 0.753 \| \| 0.4592 \| 36.67 \| 8800 \| 0.5113 \| 0.7498 \| 0.75 \| \| 0.4591 \| 37.5 \| 9000 \| 0.5152 \| 0.7454 \| 0.746 \| \| 0.4583 \| 38.33 \| 9200 \| 0.5128 \| 0.7477 \| 0.748 \| \| 0.4569 \| 39.17 \| 9400 \| 0.5135 \| 0.7478 \| 0.748 \| \| 0.4589 \| 40.0 \| 9600 \| 0.5125 \| 0.7477 \| 0.748 \| \| 0.4584 \| 40.83 \| 9800 \| 0.5116 \| 0.7529 \| 0.753 \| \| 0.4587 \| 41.67 \| 10000 \| 0.5119 \| 0.7478 \| 0.748 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_1-seqsight_16384_512_34M-L1_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_1-seqsight_16384_512_34M-L1_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:39:33+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_0-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3839 - F1 Score: 0.8256 - Accuracy: 0.826 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5242 \| 0.79 \| 200 \| 0.4834 \| 0.7550 \| 0.755 \| \| 0.4806 \| 1.58 \| 400 \| 0.4685 \| 0.7661 \| 0.766 \| \| 0.4675 \| 2.37 \| 600 \| 0.4716 \| 0.7623 \| 0.764 \| \| 0.4574 \| 3.16 \| 800 \| 0.4653 \| 0.7724 \| 0.773 \| \| 0.4528 \| 3.95 \| 1000 \| 0.4541 \| 0.7817 \| 0.782 \| \| 0.447 \| 4.74 \| 1200 \| 0.4639 \| 0.7820 \| 0.782 \| \| 0.4392 \| 5.53 \| 1400 \| 0.4776 \| 0.7713 \| 0.772 \| \| 0.431 \| 6.32 \| 1600 \| 0.4656 \| 0.7821 \| 0.782 \| \| 0.4325 \| 7.11 \| 1800 \| 0.4792 \| 0.7837 \| 0.784 \| \| 0.4314 \| 7.91 \| 2000 \| 0.4691 \| 0.7817 \| 0.782 \| \| 0.4209 \| 8.7 \| 2200 \| 0.4635 \| 0.7780 \| 0.778 \| \| 0.417 \| 9.49 \| 2400 \| 0.4631 \| 0.7901 \| 0.79 \| \| 0.4161 \| 10.28 \| 2600 \| 0.4716 \| 0.7778 \| 0.778 \| \| 0.4117 \| 11.07 \| 2800 \| 0.4661 \| 0.7829 \| 0.783 \| \| 0.4058 \| 11.86 \| 3000 \| 0.4822 \| 0.7951 \| 0.795 \| \| 0.4036 \| 12.65 \| 3200 \| 0.4651 \| 0.7950 \| 0.795 \| \| 0.4009 \| 13.44 \| 3400 \| 0.4793 \| 0.7820 \| 0.782 \| \| 0.3979 \| 14.23 \| 3600 \| 0.4829 \| 0.7880 \| 0.788 \| \| 0.3987 \| 15.02 \| 3800 \| 0.4881 \| 0.7785 \| 0.779 \| \| 0.392 \| 15.81 \| 4000 \| 0.4660 \| 0.7817 \| 0.782 \| \| 0.3841 \| 16.6 \| 4200 \| 0.4911 \| 0.7859 \| 0.786 \| \| 0.389 \| 17.39 \| 4400 \| 0.4863 \| 0.7864 \| 0.787 \| \| 0.3843 \| 18.18 \| 4600 \| 0.4741 \| 0.7940 \| 0.794 \| \| 0.3808 \| 18.97 \| 4800 \| 0.4995 \| 0.7855 \| 0.786 \| \| 0.383 \| 19.76 \| 5000 \| 0.4754 \| 0.8030 \| 0.803 \| \| 0.3783 \| 20.55 \| 5200 \| 0.4800 \| 0.7910 \| 0.791 \| \| 0.3695 \| 21.34 \| 5400 \| 0.4866 \| 0.7873 \| 0.788 \| \| 0.3702 \| 22.13 \| 5600 \| 0.5081 \| 0.7868 \| 0.787 \| \| 0.3704 \| 22.92 \| 5800 \| 0.4963 \| 0.7856 \| 0.786 \| \| 0.3621 \| 23.72 \| 6000 \| 0.4948 \| 0.7919 \| 0.792 \| \| 0.3587 \| 24.51 \| 6200 \| 0.4883 \| 0.7959 \| 0.796 \| \| 0.3623 \| 25.3 \| 6400 \| 0.4956 \| 0.7979 \| 0.798 \| \| 0.3566 \| 26.09 \| 6600 \| 0.5052 \| 0.7970 \| 0.797 \| \| 0.3588 \| 26.88 \| 6800 \| 0.4934 \| 0.798 \| 0.798 \| \| 0.3539 \| 27.67 \| 7000 \| 0.4943 \| 0.7980 \| 0.798 \| \| 0.353 \| 28.46 \| 7200 \| 0.4906 \| 0.7971 \| 0.797 \| \| 0.3503 \| 29.25 \| 7400 \| 0.5178 \| 0.7929 \| 0.793 \| \| 0.3509 \| 30.04 \| 7600 \| 0.5186 \| 0.7926 \| 0.793 \| \| 0.3461 \| 30.83 \| 7800 \| 0.4992 \| 0.7980 \| 0.798 \| \| 0.347 \| 31.62 \| 8000 \| 0.4962 \| 0.7961 \| 0.796 \| \| 0.3431 \| 32.41 \| 8200 \| 0.5253 \| 0.7919 \| 0.792 \| \| 0.3361 \| 33.2 \| 8400 \| 0.5124 \| 0.8000 \| 0.8 \| \| 0.3396 \| 33.99 \| 8600 \| 0.5218 \| 0.7870 \| 0.787 \| \| 0.3421 \| 34.78 \| 8800 \| 0.5119 \| 0.7940 \| 0.794 \| \| 0.3344 \| 35.57 \| 9000 \| 0.5144 \| 0.7970 \| 0.797 \| \| 0.3374 \| 36.36 \| 9200 \| 0.5282 \| 0.7898 \| 0.79 \| \| 0.3366 \| 37.15 \| 9400 \| 0.5282 \| 0.7968 \| 0.797 \| \| 0.3394 \| 37.94 \| 9600 \| 0.5204 \| 0.7949 \| 0.795 \| \| 0.3358 \| 38.74 \| 9800 \| 0.5254 \| 0.7908 \| 0.791 \| \| 0.3352 \| 39.53 \| 10000 \| 0.5221 \| 0.7899 \| 0.79 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_0-seqsight_16384_512_34M-L32_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_0-seqsight_16384_512_34M-L32_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:39:33+00:00
text-classification	transformers	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # output_dir This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0625 - F Beta Score: 0.9639 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2	{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "microsoft/deberta-v3-base", "model-index": [{"name": "output_dir", "results": []}]}	tralon/test-1	null	[ "transformers", "safetensors", "deberta-v2", "text-classification", "generated_from_trainer", "base_model:microsoft/deberta-v3-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-04-29T23:40:13+00:00
null	peft	<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # GUE_tf_1-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3442 - F1 Score: 0.8604 - Accuracy: 0.861 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| F1 Score \| Accuracy \| \|:-------------:\|:-----:\|:-----:\|:---------------:\|:--------:\|:--------:\| \| 0.5535 \| 0.83 \| 200 \| 0.5407 \| 0.7405 \| 0.741 \| \| 0.5038 \| 1.67 \| 400 \| 0.5375 \| 0.7299 \| 0.731 \| \| 0.4946 \| 2.5 \| 600 \| 0.5248 \| 0.7479 \| 0.748 \| \| 0.4839 \| 3.33 \| 800 \| 0.5167 \| 0.7489 \| 0.749 \| \| 0.4854 \| 4.17 \| 1000 \| 0.5142 \| 0.7467 \| 0.747 \| \| 0.4766 \| 5.0 \| 1200 \| 0.5160 \| 0.7447 \| 0.745 \| \| 0.474 \| 5.83 \| 1400 \| 0.5106 \| 0.7409 \| 0.741 \| \| 0.4718 \| 6.67 \| 1600 \| 0.5166 \| 0.7460 \| 0.746 \| \| 0.4686 \| 7.5 \| 1800 \| 0.5213 \| 0.7373 \| 0.738 \| \| 0.4628 \| 8.33 \| 2000 \| 0.5105 \| 0.7410 \| 0.741 \| \| 0.4642 \| 9.17 \| 2200 \| 0.5105 \| 0.7440 \| 0.744 \| \| 0.4616 \| 10.0 \| 2400 \| 0.5230 \| 0.7332 \| 0.735 \| \| 0.4576 \| 10.83 \| 2600 \| 0.5130 \| 0.7532 \| 0.754 \| \| 0.4571 \| 11.67 \| 2800 \| 0.5117 \| 0.7494 \| 0.75 \| \| 0.4495 \| 12.5 \| 3000 \| 0.5129 \| 0.7423 \| 0.743 \| \| 0.4567 \| 13.33 \| 3200 \| 0.5032 \| 0.7451 \| 0.746 \| \| 0.4475 \| 14.17 \| 3400 \| 0.5015 \| 0.7509 \| 0.751 \| \| 0.4504 \| 15.0 \| 3600 \| 0.5042 \| 0.7496 \| 0.751 \| \| 0.4428 \| 15.83 \| 3800 \| 0.5024 \| 0.7472 \| 0.748 \| \| 0.4479 \| 16.67 \| 4000 \| 0.4999 \| 0.7579 \| 0.758 \| \| 0.4428 \| 17.5 \| 4200 \| 0.5085 \| 0.7450 \| 0.747 \| \| 0.4372 \| 18.33 \| 4400 \| 0.5049 \| 0.7590 \| 0.759 \| \| 0.4422 \| 19.17 \| 4600 \| 0.5086 \| 0.7562 \| 0.757 \| \| 0.4409 \| 20.0 \| 4800 \| 0.5002 \| 0.7598 \| 0.76 \| \| 0.4393 \| 20.83 \| 5000 \| 0.5060 \| 0.7518 \| 0.752 \| \| 0.435 \| 21.67 \| 5200 \| 0.5017 \| 0.7497 \| 0.75 \| \| 0.4373 \| 22.5 \| 5400 \| 0.5013 \| 0.7549 \| 0.755 \| \| 0.4324 \| 23.33 \| 5600 \| 0.4973 \| 0.7528 \| 0.754 \| \| 0.4335 \| 24.17 \| 5800 \| 0.5082 \| 0.7549 \| 0.756 \| \| 0.4363 \| 25.0 \| 6000 \| 0.4985 \| 0.7540 \| 0.754 \| \| 0.4317 \| 25.83 \| 6200 \| 0.5002 \| 0.7547 \| 0.755 \| \| 0.4289 \| 26.67 \| 6400 \| 0.4995 \| 0.7620 \| 0.762 \| \| 0.4316 \| 27.5 \| 6600 \| 0.5025 \| 0.7690 \| 0.769 \| \| 0.4286 \| 28.33 \| 6800 \| 0.5010 \| 0.7550 \| 0.755 \| \| 0.4252 \| 29.17 \| 7000 \| 0.5014 \| 0.7607 \| 0.761 \| \| 0.4286 \| 30.0 \| 7200 \| 0.4985 \| 0.7586 \| 0.759 \| \| 0.4261 \| 30.83 \| 7400 \| 0.5018 \| 0.7611 \| 0.762 \| \| 0.4218 \| 31.67 \| 7600 \| 0.4993 \| 0.7560 \| 0.756 \| \| 0.4264 \| 32.5 \| 7800 \| 0.4999 \| 0.7558 \| 0.756 \| \| 0.4225 \| 33.33 \| 8000 \| 0.5014 \| 0.7589 \| 0.759 \| \| 0.4242 \| 34.17 \| 8200 \| 0.5008 \| 0.7637 \| 0.764 \| \| 0.4198 \| 35.0 \| 8400 \| 0.5014 \| 0.7635 \| 0.764 \| \| 0.4205 \| 35.83 \| 8600 \| 0.5003 \| 0.7569 \| 0.757 \| \| 0.4197 \| 36.67 \| 8800 \| 0.4988 \| 0.7525 \| 0.753 \| \| 0.4188 \| 37.5 \| 9000 \| 0.5031 \| 0.7518 \| 0.753 \| \| 0.4191 \| 38.33 \| 9200 \| 0.5023 \| 0.7577 \| 0.758 \| \| 0.4166 \| 39.17 \| 9400 \| 0.5018 \| 0.7626 \| 0.763 \| \| 0.4221 \| 40.0 \| 9600 \| 0.5011 \| 0.7635 \| 0.764 \| \| 0.4198 \| 40.83 \| 9800 \| 0.5008 \| 0.7539 \| 0.754 \| \| 0.4195 \| 41.67 \| 10000 \| 0.5006 \| 0.7597 \| 0.76 \| ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2	{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_1-seqsight_16384_512_34M-L8_f", "results": []}]}	mahdibaghbanzadeh/GUE_tf_1-seqsight_16384_512_34M-L8_f	null	[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]	null	2024-04-29T23:41:03+00:00

automatic-speech-recognition

transformers

# whisper-bs-cs-train-aug-test-aug2 This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the common_voice_11_0 dataset. It achieves the following results on the evaluation set: - Loss: 0.6875 - Wer: 54.1533 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 32 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:------:|:----:|:---------------:|:-------:| | 0.6476 | 1.4440 | 1000 | 0.8181 | 63.1377 | | 0.4531 | 2.8881 | 2000 | 0.7081 | 56.8700 | | 0.3048 | 4.3321 | 3000 | 0.6906 | 54.5125 | | 0.2841 | 5.7762 | 4000 | 0.6875 | 54.1533 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["common_voice_11_0"], "metrics": ["wer"], "base_model": "openai/whisper-base", "model-index": [{"name": "whisper-bs-cs-train-aug-test-aug2", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "common_voice_11_0", "type": "common_voice_11_0", "config": "cs", "split": "None", "args": "cs"}, "metrics": [{"type": "wer", "value": 54.15331344163259, "name": "Wer"}]}]}]}

LadislavVasina1/whisper-bs-cs-train-aug-test-aug2

null

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:common_voice_11_0", "base_model:openai/whisper-base", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:28:56+00:00

null

{}

mselek/results

null

[ "safetensors", "region:us" ]

null

2024-04-29T22:29:20+00:00

null

{}

ivykopal/mlqa_en_prompt_100k

null

[ "region:us" ]

null

2024-04-29T22:29:56+00:00

text-classification

transformers

{}

JibreelGG/railisfinetune

null

[ "transformers", "safetensors", "deberta-v2", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:30:29+00:00

null

{}

Mirgan/fine-tune-blip2-cxr-8bits

null

[ "region:us" ]

null

2024-04-29T22:30:41+00:00

null

peft

# GUE_EMP_H4ac-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H4ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5598 - F1 Score: 0.7325 - Accuracy: 0.7323 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6448 | 0.93 | 200 | 0.5977 | 0.6750 | 0.6774 | | 0.5934 | 1.87 | 400 | 0.5784 | 0.7057 | 0.7067 | | 0.5712 | 2.8 | 600 | 0.5560 | 0.7261 | 0.7258 | | 0.5629 | 3.74 | 800 | 0.5547 | 0.7249 | 0.7249 | | 0.5589 | 4.67 | 1000 | 0.5502 | 0.7271 | 0.7270 | | 0.5499 | 5.61 | 1200 | 0.5559 | 0.7240 | 0.7246 | | 0.551 | 6.54 | 1400 | 0.5597 | 0.7173 | 0.7185 | | 0.5402 | 7.48 | 1600 | 0.5439 | 0.7349 | 0.7346 | | 0.5464 | 8.41 | 1800 | 0.5390 | 0.7361 | 0.7358 | | 0.5401 | 9.35 | 2000 | 0.5496 | 0.7384 | 0.7387 | | 0.5357 | 10.28 | 2200 | 0.5373 | 0.7401 | 0.7399 | | 0.5386 | 11.21 | 2400 | 0.5427 | 0.7357 | 0.7358 | | 0.5311 | 12.15 | 2600 | 0.5496 | 0.7340 | 0.7346 | | 0.5302 | 13.08 | 2800 | 0.5625 | 0.7271 | 0.7284 | | 0.5322 | 14.02 | 3000 | 0.5350 | 0.7446 | 0.7443 | | 0.5288 | 14.95 | 3200 | 0.5383 | 0.7443 | 0.7443 | | 0.5242 | 15.89 | 3400 | 0.5460 | 0.7360 | 0.7364 | | 0.5243 | 16.82 | 3600 | 0.5364 | 0.7473 | 0.7472 | | 0.5272 | 17.76 | 3800 | 0.5465 | 0.7388 | 0.7393 | | 0.5226 | 18.69 | 4000 | 0.5353 | 0.7442 | 0.7440 | | 0.5204 | 19.63 | 4200 | 0.5360 | 0.7433 | 0.7434 | | 0.5203 | 20.56 | 4400 | 0.5290 | 0.7466 | 0.7463 | | 0.5176 | 21.5 | 4600 | 0.5557 | 0.7321 | 0.7334 | | 0.5193 | 22.43 | 4800 | 0.5312 | 0.7449 | 0.7446 | | 0.5161 | 23.36 | 5000 | 0.5463 | 0.7391 | 0.7396 | | 0.5177 | 24.3 | 5200 | 0.5280 | 0.7440 | 0.7437 | | 0.5157 | 25.23 | 5400 | 0.5303 | 0.7484 | 0.7481 | | 0.5148 | 26.17 | 5600 | 0.5290 | 0.7446 | 0.7443 | | 0.5149 | 27.1 | 5800 | 0.5310 | 0.7478 | 0.7475 | | 0.5096 | 28.04 | 6000 | 0.5305 | 0.7481 | 0.7478 | | 0.5144 | 28.97 | 6200 | 0.5411 | 0.7469 | 0.7472 | | 0.5114 | 29.91 | 6400 | 0.5305 | 0.7472 | 0.7469 | | 0.5123 | 30.84 | 6600 | 0.5431 | 0.7453 | 0.7457 | | 0.5094 | 31.78 | 6800 | 0.5307 | 0.7487 | 0.7484 | | 0.51 | 32.71 | 7000 | 0.5292 | 0.7487 | 0.7484 | | 0.5084 | 33.64 | 7200 | 0.5346 | 0.7492 | 0.7493 | | 0.5087 | 34.58 | 7400 | 0.5309 | 0.7515 | 0.7513 | | 0.5094 | 35.51 | 7600 | 0.5279 | 0.7510 | 0.7507 | | 0.5048 | 36.45 | 7800 | 0.5297 | 0.7490 | 0.7487 | | 0.5106 | 37.38 | 8000 | 0.5368 | 0.7487 | 0.7487 | | 0.5045 | 38.32 | 8200 | 0.5312 | 0.7521 | 0.7519 | | 0.5049 | 39.25 | 8400 | 0.5283 | 0.7507 | 0.7504 | | 0.5081 | 40.19 | 8600 | 0.5302 | 0.7478 | 0.7475 | | 0.5065 | 41.12 | 8800 | 0.5312 | 0.7500 | 0.7499 | | 0.5065 | 42.06 | 9000 | 0.5302 | 0.7510 | 0.7507 | | 0.5065 | 42.99 | 9200 | 0.5344 | 0.7508 | 0.7507 | | 0.5066 | 43.93 | 9400 | 0.5328 | 0.7511 | 0.7510 | | 0.5042 | 44.86 | 9600 | 0.5297 | 0.7498 | 0.7496 | | 0.5028 | 45.79 | 9800 | 0.5307 | 0.7501 | 0.7499 | | 0.5057 | 46.73 | 10000 | 0.5316 | 0.7515 | 0.7513 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H4ac-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H4ac-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:33:10+00:00

null

peft

# GUE_EMP_H3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3) dataset. It achieves the following results on the evaluation set: - Loss: 0.3581 - F1 Score: 0.8804 - Accuracy: 0.8804 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.4331 | 2.13 | 200 | 0.3621 | 0.8516 | 0.8517 | | 0.2958 | 4.26 | 400 | 0.3346 | 0.8684 | 0.8684 | | 0.2657 | 6.38 | 600 | 0.3485 | 0.8597 | 0.8597 | | 0.2523 | 8.51 | 800 | 0.3201 | 0.8731 | 0.8731 | | 0.2368 | 10.64 | 1000 | 0.3464 | 0.8653 | 0.8657 | | 0.2238 | 12.77 | 1200 | 0.3192 | 0.8771 | 0.8771 | | 0.2103 | 14.89 | 1400 | 0.3609 | 0.8567 | 0.8570 | | 0.1988 | 17.02 | 1600 | 0.3454 | 0.8771 | 0.8771 | | 0.185 | 19.15 | 1800 | 0.3556 | 0.8764 | 0.8764 | | 0.1694 | 21.28 | 2000 | 0.3875 | 0.8736 | 0.8737 | | 0.1635 | 23.4 | 2200 | 0.3822 | 0.8731 | 0.8731 | | 0.1469 | 25.53 | 2400 | 0.3999 | 0.8804 | 0.8804 | | 0.1385 | 27.66 | 2600 | 0.4115 | 0.8677 | 0.8677 | | 0.1288 | 29.79 | 2800 | 0.4386 | 0.8634 | 0.8637 | | 0.1228 | 31.91 | 3000 | 0.4146 | 0.8643 | 0.8644 | | 0.1082 | 34.04 | 3200 | 0.4470 | 0.8670 | 0.8671 | | 0.103 | 36.17 | 3400 | 0.4991 | 0.8519 | 0.8524 | | 0.0932 | 38.3 | 3600 | 0.5066 | 0.8657 | 0.8657 | | 0.0896 | 40.43 | 3800 | 0.5448 | 0.8640 | 0.8644 | | 0.0826 | 42.55 | 4000 | 0.6343 | 0.8518 | 0.8524 | | 0.0738 | 44.68 | 4200 | 0.5258 | 0.8710 | 0.8711 | | 0.072 | 46.81 | 4400 | 0.5121 | 0.8711 | 0.8711 | | 0.0696 | 48.94 | 4600 | 0.5634 | 0.8683 | 0.8684 | | 0.0647 | 51.06 | 4800 | 0.5905 | 0.8643 | 0.8644 | | 0.0609 | 53.19 | 5000 | 0.6529 | 0.8588 | 0.8591 | | 0.0559 | 55.32 | 5200 | 0.5790 | 0.8751 | 0.8751 | | 0.0521 | 57.45 | 5400 | 0.6104 | 0.8716 | 0.8717 | | 0.0484 | 59.57 | 5600 | 0.6275 | 0.8723 | 0.8724 | | 0.048 | 61.7 | 5800 | 0.6447 | 0.8622 | 0.8624 | | 0.0437 | 63.83 | 6000 | 0.7093 | 0.8578 | 0.8584 | | 0.0476 | 65.96 | 6200 | 0.6825 | 0.8702 | 0.8704 | | 0.0394 | 68.09 | 6400 | 0.6768 | 0.8690 | 0.8691 | | 0.0404 | 70.21 | 6600 | 0.6940 | 0.8702 | 0.8704 | | 0.0373 | 72.34 | 6800 | 0.6746 | 0.8751 | 0.8751 | | 0.0381 | 74.47 | 7000 | 0.7295 | 0.8607 | 0.8611 | | 0.0348 | 76.6 | 7200 | 0.7110 | 0.8757 | 0.8758 | | 0.0318 | 78.72 | 7400 | 0.7322 | 0.8703 | 0.8704 | | 0.029 | 80.85 | 7600 | 0.8020 | 0.8642 | 0.8644 | | 0.0314 | 82.98 | 7800 | 0.7269 | 0.8737 | 0.8737 | | 0.0283 | 85.11 | 8000 | 0.7380 | 0.8737 | 0.8737 | | 0.0272 | 87.23 | 8200 | 0.7716 | 0.8710 | 0.8711 | | 0.0237 | 89.36 | 8400 | 0.8220 | 0.8777 | 0.8778 | | 0.0273 | 91.49 | 8600 | 0.7853 | 0.8716 | 0.8717 | | 0.0255 | 93.62 | 8800 | 0.8045 | 0.8737 | 0.8737 | | 0.0252 | 95.74 | 9000 | 0.8016 | 0.8723 | 0.8724 | | 0.0233 | 97.87 | 9200 | 0.8163 | 0.8675 | 0.8677 | | 0.023 | 100.0 | 9400 | 0.8253 | 0.8683 | 0.8684 | | 0.022 | 102.13 | 9600 | 0.8238 | 0.8723 | 0.8724 | | 0.0206 | 104.26 | 9800 | 0.8230 | 0.8703 | 0.8704 | | 0.0221 | 106.38 | 10000 | 0.8229 | 0.8703 | 0.8704 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:33:10+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

shallow6414/6my36hg

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T22:33:26+00:00

null

peft

# GUE_EMP_H4ac-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H4ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5616 - F1 Score: 0.7387 - Accuracy: 0.7384 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6227 | 0.93 | 200 | 0.5658 | 0.7100 | 0.7097 | | 0.5654 | 1.87 | 400 | 0.5636 | 0.7194 | 0.7208 | | 0.5489 | 2.8 | 600 | 0.5446 | 0.7351 | 0.7349 | | 0.5409 | 3.74 | 800 | 0.5364 | 0.7366 | 0.7364 | | 0.5353 | 4.67 | 1000 | 0.5306 | 0.7455 | 0.7452 | | 0.5263 | 5.61 | 1200 | 0.5509 | 0.7324 | 0.7337 | | 0.5267 | 6.54 | 1400 | 0.5441 | 0.7394 | 0.7399 | | 0.5118 | 7.48 | 1600 | 0.5292 | 0.7451 | 0.7449 | | 0.5188 | 8.41 | 1800 | 0.5248 | 0.7472 | 0.7469 | | 0.511 | 9.35 | 2000 | 0.5281 | 0.7466 | 0.7463 | | 0.5056 | 10.28 | 2200 | 0.5246 | 0.7455 | 0.7457 | | 0.5067 | 11.21 | 2400 | 0.5307 | 0.7456 | 0.7457 | | 0.4972 | 12.15 | 2600 | 0.5389 | 0.7455 | 0.7457 | | 0.4958 | 13.08 | 2800 | 0.5385 | 0.7460 | 0.7457 | | 0.4972 | 14.02 | 3000 | 0.5267 | 0.7516 | 0.7513 | | 0.4929 | 14.95 | 3200 | 0.5233 | 0.7519 | 0.7516 | | 0.4863 | 15.89 | 3400 | 0.5245 | 0.7516 | 0.7513 | | 0.4842 | 16.82 | 3600 | 0.5337 | 0.7439 | 0.7437 | | 0.4867 | 17.76 | 3800 | 0.5509 | 0.7396 | 0.7408 | | 0.48 | 18.69 | 4000 | 0.5238 | 0.7542 | 0.7540 | | 0.4795 | 19.63 | 4200 | 0.5206 | 0.7551 | 0.7548 | | 0.4768 | 20.56 | 4400 | 0.5198 | 0.7481 | 0.7478 | | 0.4728 | 21.5 | 4600 | 0.5364 | 0.7488 | 0.7490 | | 0.4729 | 22.43 | 4800 | 0.5249 | 0.7520 | 0.7519 | | 0.469 | 23.36 | 5000 | 0.5293 | 0.7569 | 0.7566 | | 0.4714 | 24.3 | 5200 | 0.5234 | 0.7568 | 0.7566 | | 0.4658 | 25.23 | 5400 | 0.5253 | 0.7538 | 0.7537 | | 0.4627 | 26.17 | 5600 | 0.5303 | 0.7448 | 0.7449 | | 0.4634 | 27.1 | 5800 | 0.5301 | 0.7495 | 0.7493 | | 0.4572 | 28.04 | 6000 | 0.5336 | 0.7560 | 0.7557 | | 0.4611 | 28.97 | 6200 | 0.5301 | 0.7557 | 0.7554 | | 0.4555 | 29.91 | 6400 | 0.5358 | 0.7499 | 0.7496 | | 0.4568 | 30.84 | 6600 | 0.5380 | 0.7554 | 0.7551 | | 0.456 | 31.78 | 6800 | 0.5299 | 0.7571 | 0.7569 | | 0.4513 | 32.71 | 7000 | 0.5298 | 0.7529 | 0.7528 | | 0.4524 | 33.64 | 7200 | 0.5345 | 0.7511 | 0.7510 | | 0.4495 | 34.58 | 7400 | 0.5313 | 0.7571 | 0.7569 | | 0.4496 | 35.51 | 7600 | 0.5316 | 0.7542 | 0.7540 | | 0.4455 | 36.45 | 7800 | 0.5359 | 0.7604 | 0.7601 | | 0.4474 | 37.38 | 8000 | 0.5407 | 0.7571 | 0.7569 | | 0.4471 | 38.32 | 8200 | 0.5328 | 0.7595 | 0.7592 | | 0.447 | 39.25 | 8400 | 0.5322 | 0.7532 | 0.7531 | | 0.4458 | 40.19 | 8600 | 0.5372 | 0.7566 | 0.7563 | | 0.4447 | 41.12 | 8800 | 0.5381 | 0.7575 | 0.7572 | | 0.4407 | 42.06 | 9000 | 0.5391 | 0.7572 | 0.7569 | | 0.4416 | 42.99 | 9200 | 0.5400 | 0.7598 | 0.7595 | | 0.4411 | 43.93 | 9400 | 0.5382 | 0.7589 | 0.7587 | | 0.4396 | 44.86 | 9600 | 0.5373 | 0.7574 | 0.7572 | | 0.4371 | 45.79 | 9800 | 0.5380 | 0.7574 | 0.7572 | | 0.4429 | 46.73 | 10000 | 0.5382 | 0.7610 | 0.7607 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H4ac-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H4ac-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:33:30+00:00

null

peft

# GUE_EMP_H4ac-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H4ac](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H4ac) dataset. It achieves the following results on the evaluation set: - Loss: 0.5538 - F1 Score: 0.7389 - Accuracy: 0.7390 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6081 | 0.93 | 200 | 0.5518 | 0.7247 | 0.7243 | | 0.5526 | 1.87 | 400 | 0.5545 | 0.7313 | 0.7326 | | 0.535 | 2.8 | 600 | 0.5285 | 0.7443 | 0.7440 | | 0.5242 | 3.74 | 800 | 0.5270 | 0.7443 | 0.7440 | | 0.5169 | 4.67 | 1000 | 0.5219 | 0.7459 | 0.7457 | | 0.5062 | 5.61 | 1200 | 0.5342 | 0.7413 | 0.7416 | | 0.5035 | 6.54 | 1400 | 0.5216 | 0.7489 | 0.7487 | | 0.4892 | 7.48 | 1600 | 0.5246 | 0.7481 | 0.7478 | | 0.4923 | 8.41 | 1800 | 0.5181 | 0.7452 | 0.7449 | | 0.4809 | 9.35 | 2000 | 0.5245 | 0.7486 | 0.7487 | | 0.4739 | 10.28 | 2200 | 0.5253 | 0.7489 | 0.7487 | | 0.4697 | 11.21 | 2400 | 0.5379 | 0.7391 | 0.7396 | | 0.4613 | 12.15 | 2600 | 0.5365 | 0.7481 | 0.7478 | | 0.4538 | 13.08 | 2800 | 0.5499 | 0.7410 | 0.7411 | | 0.4548 | 14.02 | 3000 | 0.5488 | 0.7512 | 0.7516 | | 0.4436 | 14.95 | 3200 | 0.5493 | 0.7460 | 0.7457 | | 0.435 | 15.89 | 3400 | 0.5366 | 0.7544 | 0.7545 | | 0.429 | 16.82 | 3600 | 0.5443 | 0.7417 | 0.7416 | | 0.4287 | 17.76 | 3800 | 0.5782 | 0.7348 | 0.7358 | | 0.4189 | 18.69 | 4000 | 0.5448 | 0.7533 | 0.7531 | | 0.4162 | 19.63 | 4200 | 0.5436 | 0.7433 | 0.7431 | | 0.4075 | 20.56 | 4400 | 0.5440 | 0.7493 | 0.7493 | | 0.3997 | 21.5 | 4600 | 0.5583 | 0.7519 | 0.7516 | | 0.3933 | 22.43 | 4800 | 0.5815 | 0.7442 | 0.7446 | | 0.393 | 23.36 | 5000 | 0.5817 | 0.7490 | 0.7487 | | 0.3883 | 24.3 | 5200 | 0.5909 | 0.7499 | 0.7496 | | 0.3812 | 25.23 | 5400 | 0.5716 | 0.7493 | 0.7490 | | 0.3746 | 26.17 | 5600 | 0.5996 | 0.7464 | 0.7463 | | 0.3707 | 27.1 | 5800 | 0.5904 | 0.7422 | 0.7419 | | 0.3625 | 28.04 | 6000 | 0.5976 | 0.7505 | 0.7504 | | 0.3631 | 28.97 | 6200 | 0.5873 | 0.7443 | 0.7440 | | 0.3572 | 29.91 | 6400 | 0.6049 | 0.7383 | 0.7381 | | 0.356 | 30.84 | 6600 | 0.5934 | 0.7442 | 0.7440 | | 0.3527 | 31.78 | 6800 | 0.5961 | 0.7450 | 0.7452 | | 0.3467 | 32.71 | 7000 | 0.6047 | 0.7436 | 0.7434 | | 0.3442 | 33.64 | 7200 | 0.6134 | 0.7407 | 0.7405 | | 0.34 | 34.58 | 7400 | 0.6167 | 0.7477 | 0.7475 | | 0.3383 | 35.51 | 7600 | 0.5981 | 0.7407 | 0.7405 | | 0.3291 | 36.45 | 7800 | 0.6243 | 0.7434 | 0.7431 | | 0.3274 | 37.38 | 8000 | 0.6363 | 0.7437 | 0.7434 | | 0.3272 | 38.32 | 8200 | 0.6318 | 0.7364 | 0.7364 | | 0.3254 | 39.25 | 8400 | 0.6307 | 0.7409 | 0.7408 | | 0.324 | 40.19 | 8600 | 0.6369 | 0.7428 | 0.7425 | | 0.3238 | 41.12 | 8800 | 0.6378 | 0.7453 | 0.7452 | | 0.3152 | 42.06 | 9000 | 0.6401 | 0.7458 | 0.7457 | | 0.3168 | 42.99 | 9200 | 0.6474 | 0.7425 | 0.7422 | | 0.3152 | 43.93 | 9400 | 0.6440 | 0.7404 | 0.7402 | | 0.3136 | 44.86 | 9600 | 0.6442 | 0.7400 | 0.7399 | | 0.3101 | 45.79 | 9800 | 0.6478 | 0.7450 | 0.7449 | | 0.3182 | 46.73 | 10000 | 0.6442 | 0.7439 | 0.7437 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H4ac-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H4ac-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:33:30+00:00

null

peft

# GUE_EMP_H3K79me3-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K79me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K79me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4351 - F1 Score: 0.8097 - Accuracy: 0.8096 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5289 | 1.1 | 200 | 0.4655 | 0.7962 | 0.7961 | | 0.4736 | 2.21 | 400 | 0.4711 | 0.7904 | 0.7926 | | 0.4658 | 3.31 | 600 | 0.4509 | 0.8034 | 0.8044 | | 0.4533 | 4.42 | 800 | 0.4448 | 0.8066 | 0.8076 | | 0.4528 | 5.52 | 1000 | 0.4530 | 0.7972 | 0.7992 | | 0.4433 | 6.63 | 1200 | 0.4542 | 0.8020 | 0.8041 | | 0.4454 | 7.73 | 1400 | 0.4403 | 0.8083 | 0.8096 | | 0.439 | 8.84 | 1600 | 0.4545 | 0.8003 | 0.8027 | | 0.4355 | 9.94 | 1800 | 0.4351 | 0.8177 | 0.8176 | | 0.4344 | 11.05 | 2000 | 0.4376 | 0.8087 | 0.8100 | | 0.4338 | 12.15 | 2200 | 0.4301 | 0.8167 | 0.8169 | | 0.4272 | 13.26 | 2400 | 0.4300 | 0.8168 | 0.8173 | | 0.4274 | 14.36 | 2600 | 0.4305 | 0.8138 | 0.8141 | | 0.4282 | 15.47 | 2800 | 0.4323 | 0.8138 | 0.8148 | | 0.4228 | 16.57 | 3000 | 0.4306 | 0.8184 | 0.8183 | | 0.4252 | 17.68 | 3200 | 0.4266 | 0.8161 | 0.8162 | | 0.4178 | 18.78 | 3400 | 0.4305 | 0.8170 | 0.8176 | | 0.4178 | 19.89 | 3600 | 0.4257 | 0.8165 | 0.8169 | | 0.418 | 20.99 | 3800 | 0.4340 | 0.8162 | 0.8169 | | 0.4157 | 22.1 | 4000 | 0.4258 | 0.8159 | 0.8166 | | 0.4149 | 23.2 | 4200 | 0.4268 | 0.8176 | 0.8180 | | 0.4158 | 24.31 | 4400 | 0.4398 | 0.8099 | 0.8117 | | 0.4075 | 25.41 | 4600 | 0.4275 | 0.8176 | 0.8180 | | 0.4134 | 26.52 | 4800 | 0.4275 | 0.8130 | 0.8135 | | 0.4144 | 27.62 | 5000 | 0.4281 | 0.8160 | 0.8169 | | 0.406 | 28.73 | 5200 | 0.4276 | 0.8117 | 0.8124 | | 0.4059 | 29.83 | 5400 | 0.4247 | 0.8151 | 0.8155 | | 0.4056 | 30.94 | 5600 | 0.4279 | 0.8113 | 0.8117 | | 0.4063 | 32.04 | 5800 | 0.4252 | 0.8153 | 0.8155 | | 0.4043 | 33.15 | 6000 | 0.4262 | 0.8153 | 0.8159 | | 0.4057 | 34.25 | 6200 | 0.4269 | 0.8130 | 0.8135 | | 0.4015 | 35.36 | 6400 | 0.4291 | 0.8160 | 0.8166 | | 0.4067 | 36.46 | 6600 | 0.4256 | 0.8128 | 0.8131 | | 0.4048 | 37.57 | 6800 | 0.4282 | 0.8121 | 0.8128 | | 0.4019 | 38.67 | 7000 | 0.4293 | 0.8166 | 0.8173 | | 0.4011 | 39.78 | 7200 | 0.4268 | 0.8141 | 0.8145 | | 0.4029 | 40.88 | 7400 | 0.4259 | 0.8148 | 0.8152 | | 0.402 | 41.99 | 7600 | 0.4275 | 0.8130 | 0.8135 | | 0.3994 | 43.09 | 7800 | 0.4304 | 0.8147 | 0.8152 | | 0.3999 | 44.2 | 8000 | 0.4306 | 0.8117 | 0.8124 | | 0.3982 | 45.3 | 8200 | 0.4267 | 0.8145 | 0.8148 | | 0.3986 | 46.41 | 8400 | 0.4283 | 0.8130 | 0.8135 | | 0.4009 | 47.51 | 8600 | 0.4303 | 0.8151 | 0.8159 | | 0.3988 | 48.62 | 8800 | 0.4304 | 0.8117 | 0.8124 | | 0.3943 | 49.72 | 9000 | 0.4295 | 0.8115 | 0.8121 | | 0.4009 | 50.83 | 9200 | 0.4309 | 0.8133 | 0.8141 | | 0.3995 | 51.93 | 9400 | 0.4287 | 0.8111 | 0.8117 | | 0.3994 | 53.04 | 9600 | 0.4285 | 0.8118 | 0.8124 | | 0.396 | 54.14 | 9800 | 0.4284 | 0.8122 | 0.8128 | | 0.3996 | 55.25 | 10000 | 0.4297 | 0.8121 | 0.8128 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K79me3-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K79me3-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:34:39+00:00

null

peft

# GUE_EMP_H3K79me3-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K79me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K79me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4277 - F1 Score: 0.8227 - Accuracy: 0.8228 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5134 | 1.1 | 200 | 0.4604 | 0.7997 | 0.7996 | | 0.4626 | 2.21 | 400 | 0.4493 | 0.8046 | 0.8055 | | 0.4525 | 3.31 | 600 | 0.4420 | 0.8109 | 0.8121 | | 0.4366 | 4.42 | 800 | 0.4367 | 0.8125 | 0.8135 | | 0.4308 | 5.52 | 1000 | 0.4315 | 0.8173 | 0.8180 | | 0.4207 | 6.63 | 1200 | 0.4432 | 0.8085 | 0.8100 | | 0.4219 | 7.73 | 1400 | 0.4409 | 0.8097 | 0.8117 | | 0.4137 | 8.84 | 1600 | 0.4629 | 0.8007 | 0.8037 | | 0.4086 | 9.94 | 1800 | 0.4282 | 0.8169 | 0.8169 | | 0.406 | 11.05 | 2000 | 0.4322 | 0.8110 | 0.8114 | | 0.4041 | 12.15 | 2200 | 0.4259 | 0.8238 | 0.8239 | | 0.3954 | 13.26 | 2400 | 0.4300 | 0.8175 | 0.8176 | | 0.3953 | 14.36 | 2600 | 0.4303 | 0.8187 | 0.8190 | | 0.3954 | 15.47 | 2800 | 0.4260 | 0.8200 | 0.8204 | | 0.3866 | 16.57 | 3000 | 0.4336 | 0.8125 | 0.8124 | | 0.3886 | 17.68 | 3200 | 0.4279 | 0.8199 | 0.8200 | | 0.3812 | 18.78 | 3400 | 0.4385 | 0.8130 | 0.8141 | | 0.3792 | 19.89 | 3600 | 0.4264 | 0.8219 | 0.8221 | | 0.3803 | 20.99 | 3800 | 0.4366 | 0.8119 | 0.8124 | | 0.3765 | 22.1 | 4000 | 0.4298 | 0.8173 | 0.8173 | | 0.3751 | 23.2 | 4200 | 0.4333 | 0.8198 | 0.8200 | | 0.3722 | 24.31 | 4400 | 0.4384 | 0.8153 | 0.8162 | | 0.3634 | 25.41 | 4600 | 0.4442 | 0.8175 | 0.8173 | | 0.3699 | 26.52 | 4800 | 0.4434 | 0.8137 | 0.8141 | | 0.3687 | 27.62 | 5000 | 0.4336 | 0.8183 | 0.8190 | | 0.3593 | 28.73 | 5200 | 0.4379 | 0.8138 | 0.8141 | | 0.3587 | 29.83 | 5400 | 0.4383 | 0.8136 | 0.8135 | | 0.3577 | 30.94 | 5600 | 0.4391 | 0.8185 | 0.8187 | | 0.3565 | 32.04 | 5800 | 0.4402 | 0.8117 | 0.8117 | | 0.3555 | 33.15 | 6000 | 0.4377 | 0.8184 | 0.8190 | | 0.3528 | 34.25 | 6200 | 0.4452 | 0.8170 | 0.8169 | | 0.3509 | 35.36 | 6400 | 0.4499 | 0.8194 | 0.8204 | | 0.3554 | 36.46 | 6600 | 0.4392 | 0.8191 | 0.8193 | | 0.3481 | 37.57 | 6800 | 0.4417 | 0.8178 | 0.8183 | | 0.3451 | 38.67 | 7000 | 0.4459 | 0.8158 | 0.8166 | | 0.3469 | 39.78 | 7200 | 0.4445 | 0.8145 | 0.8148 | | 0.3453 | 40.88 | 7400 | 0.4445 | 0.8146 | 0.8145 | | 0.3446 | 41.99 | 7600 | 0.4428 | 0.8157 | 0.8159 | | 0.3417 | 43.09 | 7800 | 0.4512 | 0.8163 | 0.8166 | | 0.3413 | 44.2 | 8000 | 0.4491 | 0.8176 | 0.8183 | | 0.339 | 45.3 | 8200 | 0.4521 | 0.8126 | 0.8128 | | 0.3387 | 46.41 | 8400 | 0.4507 | 0.8190 | 0.8193 | | 0.3376 | 47.51 | 8600 | 0.4561 | 0.8173 | 0.8180 | | 0.3382 | 48.62 | 8800 | 0.4509 | 0.8175 | 0.8180 | | 0.3321 | 49.72 | 9000 | 0.4498 | 0.8166 | 0.8169 | | 0.3391 | 50.83 | 9200 | 0.4521 | 0.8167 | 0.8176 | | 0.3369 | 51.93 | 9400 | 0.4501 | 0.8155 | 0.8159 | | 0.3331 | 53.04 | 9600 | 0.4511 | 0.8160 | 0.8162 | | 0.3326 | 54.14 | 9800 | 0.4519 | 0.8163 | 0.8166 | | 0.3354 | 55.25 | 10000 | 0.4527 | 0.8162 | 0.8166 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K79me3-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K79me3-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:35:07+00:00

null

peft

# GUE_EMP_H3K79me3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K79me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K79me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4507 - F1 Score: 0.8194 - Accuracy: 0.8197 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5034 | 1.1 | 200 | 0.4527 | 0.8016 | 0.8017 | | 0.4532 | 2.21 | 400 | 0.4417 | 0.8117 | 0.8124 | | 0.4401 | 3.31 | 600 | 0.4337 | 0.8079 | 0.8086 | | 0.4227 | 4.42 | 800 | 0.4331 | 0.8155 | 0.8162 | | 0.4155 | 5.52 | 1000 | 0.4300 | 0.8146 | 0.8159 | | 0.4046 | 6.63 | 1200 | 0.4488 | 0.8063 | 0.8083 | | 0.402 | 7.73 | 1400 | 0.4522 | 0.8022 | 0.8051 | | 0.3905 | 8.84 | 1600 | 0.4595 | 0.8018 | 0.8044 | | 0.3818 | 9.94 | 1800 | 0.4344 | 0.8173 | 0.8173 | | 0.3747 | 11.05 | 2000 | 0.4403 | 0.8127 | 0.8131 | | 0.3694 | 12.15 | 2200 | 0.4358 | 0.8202 | 0.8211 | | 0.3559 | 13.26 | 2400 | 0.4452 | 0.8150 | 0.8155 | | 0.3534 | 14.36 | 2600 | 0.4384 | 0.8150 | 0.8155 | | 0.3474 | 15.47 | 2800 | 0.4431 | 0.8185 | 0.8190 | | 0.3327 | 16.57 | 3000 | 0.4609 | 0.8108 | 0.8107 | | 0.3349 | 17.68 | 3200 | 0.4437 | 0.8203 | 0.8204 | | 0.3188 | 18.78 | 3400 | 0.4701 | 0.8065 | 0.8079 | | 0.3131 | 19.89 | 3600 | 0.4559 | 0.8171 | 0.8176 | | 0.3114 | 20.99 | 3800 | 0.4827 | 0.8121 | 0.8124 | | 0.3021 | 22.1 | 4000 | 0.4816 | 0.8199 | 0.8197 | | 0.2955 | 23.2 | 4200 | 0.4813 | 0.8139 | 0.8141 | | 0.2872 | 24.31 | 4400 | 0.4862 | 0.8123 | 0.8128 | | 0.2768 | 25.41 | 4600 | 0.4948 | 0.8153 | 0.8152 | | 0.2785 | 26.52 | 4800 | 0.5160 | 0.8091 | 0.8096 | | 0.2734 | 27.62 | 5000 | 0.5076 | 0.8075 | 0.8086 | | 0.2618 | 28.73 | 5200 | 0.5060 | 0.8116 | 0.8121 | | 0.2563 | 29.83 | 5400 | 0.5171 | 0.8074 | 0.8076 | | 0.2494 | 30.94 | 5600 | 0.5232 | 0.8151 | 0.8155 | | 0.2449 | 32.04 | 5800 | 0.5446 | 0.8069 | 0.8069 | | 0.2451 | 33.15 | 6000 | 0.5403 | 0.8110 | 0.8114 | | 0.2342 | 34.25 | 6200 | 0.5469 | 0.8121 | 0.8121 | | 0.2335 | 35.36 | 6400 | 0.5858 | 0.8135 | 0.8141 | | 0.233 | 36.46 | 6600 | 0.5532 | 0.8067 | 0.8076 | | 0.2238 | 37.57 | 6800 | 0.5736 | 0.8126 | 0.8128 | | 0.2204 | 38.67 | 7000 | 0.5773 | 0.8036 | 0.8044 | | 0.2164 | 39.78 | 7200 | 0.5784 | 0.8148 | 0.8152 | | 0.2121 | 40.88 | 7400 | 0.5757 | 0.8088 | 0.8089 | | 0.2092 | 41.99 | 7600 | 0.5637 | 0.8097 | 0.8096 | | 0.2088 | 43.09 | 7800 | 0.5988 | 0.8014 | 0.8020 | | 0.2005 | 44.2 | 8000 | 0.6101 | 0.8042 | 0.8048 | | 0.1994 | 45.3 | 8200 | 0.6062 | 0.8106 | 0.8107 | | 0.1976 | 46.41 | 8400 | 0.6074 | 0.8042 | 0.8044 | | 0.1959 | 47.51 | 8600 | 0.6235 | 0.8058 | 0.8069 | | 0.1972 | 48.62 | 8800 | 0.6036 | 0.8073 | 0.8076 | | 0.188 | 49.72 | 9000 | 0.6267 | 0.8074 | 0.8079 | | 0.1939 | 50.83 | 9200 | 0.6132 | 0.8069 | 0.8076 | | 0.1887 | 51.93 | 9400 | 0.6256 | 0.8103 | 0.8107 | | 0.186 | 53.04 | 9600 | 0.6270 | 0.8066 | 0.8069 | | 0.1811 | 54.14 | 9800 | 0.6349 | 0.8071 | 0.8076 | | 0.185 | 55.25 | 10000 | 0.6333 | 0.8061 | 0.8065 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K79me3-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K79me3-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:35:33+00:00

null

{}

Amr-h/final

null

[ "region:us" ]

null

2024-04-29T22:39:32+00:00

question-answering

transformers

# distil_final This model is a fine-tuned version of [distilbert-base-cased](https://huggingface.co/distilbert-base-cased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 3.5805 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 10 - eval_batch_size: 10 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 40 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 4 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 5.0926 | 0.32 | 10 | 3.9348 | | 3.9237 | 0.64 | 20 | 4.0141 | | 3.8084 | 0.96 | 30 | 3.8194 | | 3.6561 | 1.28 | 40 | 3.6860 | | 3.4836 | 1.6 | 50 | 3.6023 | | 3.5731 | 1.92 | 60 | 3.5904 | | 3.497 | 2.24 | 70 | 3.6435 | | 3.34 | 2.56 | 80 | 3.5359 | | 3.2943 | 2.88 | 90 | 3.6003 | | 3.0902 | 3.2 | 100 | 3.6634 | | 3.1061 | 3.52 | 110 | 3.6059 | | 3.1395 | 3.84 | 120 | 3.5805 | ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"language": ["ar"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-cased", "model-index": [{"name": "distil_final", "results": []}]}

gp-tar4/QA_FineTuned_DistilBert-based-uncased

null

[ "transformers", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "ar", "base_model:distilbert-base-cased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:40:54+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

BotoxBernd/SQL-Generation-mistral-7B-v0.2

null

[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T22:41:02+00:00

null

{}

omarezz/xlm-roberta-base

null

[ "region:us" ]

null

2024-04-29T22:42:04+00:00

reinforcement-learning

null

# **Q-Learning** Agent playing1 **FrozenLake-v1** This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** . ## Usage ```python model = load_from_hub(repo_id="whiskeyriot/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "q-FrozenLake-v1-4x4-noSlippery", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "FrozenLake-v1-4x4-no_slippery", "type": "FrozenLake-v1-4x4-no_slippery"}, "metrics": [{"type": "mean_reward", "value": "1.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}

whiskeyriot/q-FrozenLake-v1-4x4-noSlippery

null

[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

null

2024-04-29T22:42:23+00:00

text-classification

transformers

# sentiment-analysis-model-trained This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.3513 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 64 - eval_batch_size: 64 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.425 | 1.0 | 157 | 0.3631 | | 0.2844 | 2.0 | 314 | 0.3368 | | 0.2199 | 3.0 | 471 | 0.3513 | ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "sentiment-analysis-model-trained", "results": []}]}

Lasghar/sentiment-analysis-model-trained

null

[ "transformers", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:43:23+00:00

reinforcement-learning

null

# **Q-Learning** Agent playing1 **Taxi-v3** This is a trained model of a **Q-Learning** agent playing **Taxi-v3** . ## Usage ```python model = load_from_hub(repo_id="whiskeyriot/Taxi-v3", filename="q-learning.pkl") # Don't forget to check if you need to add additional attributes (is_slippery=False etc) env = gym.make(model["env_id"]) ```

{"tags": ["Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation"], "model-index": [{"name": "Taxi-v3", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "Taxi-v3", "type": "Taxi-v3"}, "metrics": [{"type": "mean_reward", "value": "7.32 +/- 2.70", "name": "mean_reward", "verified": false}]}]}]}

whiskeyriot/Taxi-v3

null

[ "Taxi-v3", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]

null

2024-04-29T22:46:18+00:00

feature-extraction

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

stvhuang/rcr-run-5pqr6lwp-90396-master-0_20240402T105012-ep40

null

[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:46:39+00:00

null

{}

Proodby/myke

null

[ "region:us" ]

null

2024-04-29T22:46:59+00:00

text-classification

transformers

{}

anonyiv/elastic_zero

null

[ "transformers", "pytorch", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:48:01+00:00

null

peft

# GUE_EMP_H3K4me1-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me1) dataset. It achieves the following results on the evaluation set: - Loss: 0.5145 - F1 Score: 0.7700 - Accuracy: 0.7715 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6129 | 1.01 | 200 | 0.5906 | 0.7080 | 0.7099 | | 0.5808 | 2.02 | 400 | 0.5710 | 0.7214 | 0.7229 | | 0.5606 | 3.03 | 600 | 0.5566 | 0.7353 | 0.7377 | | 0.5538 | 4.04 | 800 | 0.5553 | 0.7423 | 0.7440 | | 0.5474 | 5.05 | 1000 | 0.5473 | 0.7448 | 0.7462 | | 0.5419 | 6.06 | 1200 | 0.5525 | 0.7387 | 0.7415 | | 0.5389 | 7.07 | 1400 | 0.5477 | 0.7421 | 0.7443 | | 0.5381 | 8.08 | 1600 | 0.5469 | 0.7424 | 0.7453 | | 0.534 | 9.09 | 1800 | 0.5430 | 0.7469 | 0.7491 | | 0.5321 | 10.1 | 2000 | 0.5386 | 0.7500 | 0.7513 | | 0.5303 | 11.11 | 2200 | 0.5439 | 0.7467 | 0.7491 | | 0.5279 | 12.12 | 2400 | 0.5388 | 0.7526 | 0.7538 | | 0.5277 | 13.13 | 2600 | 0.5393 | 0.7519 | 0.7541 | | 0.5268 | 14.14 | 2800 | 0.5382 | 0.7477 | 0.75 | | 0.5229 | 15.15 | 3000 | 0.5414 | 0.7474 | 0.75 | | 0.5235 | 16.16 | 3200 | 0.5433 | 0.7384 | 0.7424 | | 0.5193 | 17.17 | 3400 | 0.5434 | 0.7472 | 0.7494 | | 0.5213 | 18.18 | 3600 | 0.5320 | 0.7540 | 0.7554 | | 0.5185 | 19.19 | 3800 | 0.5358 | 0.7521 | 0.7541 | | 0.5195 | 20.2 | 4000 | 0.5344 | 0.7550 | 0.7569 | | 0.516 | 21.21 | 4200 | 0.5442 | 0.7406 | 0.7443 | | 0.5165 | 22.22 | 4400 | 0.5367 | 0.7521 | 0.7538 | | 0.5113 | 23.23 | 4600 | 0.5398 | 0.7462 | 0.7491 | | 0.5195 | 24.24 | 4800 | 0.5364 | 0.7438 | 0.7468 | | 0.5121 | 25.25 | 5000 | 0.5343 | 0.7585 | 0.7598 | | 0.5162 | 26.26 | 5200 | 0.5339 | 0.7591 | 0.7598 | | 0.5104 | 27.27 | 5400 | 0.5334 | 0.7561 | 0.7579 | | 0.5132 | 28.28 | 5600 | 0.5323 | 0.7594 | 0.7604 | | 0.5128 | 29.29 | 5800 | 0.5433 | 0.7392 | 0.7434 | | 0.5101 | 30.3 | 6000 | 0.5337 | 0.7549 | 0.7566 | | 0.5088 | 31.31 | 6200 | 0.5344 | 0.7555 | 0.7576 | | 0.5132 | 32.32 | 6400 | 0.5380 | 0.7446 | 0.7481 | | 0.5097 | 33.33 | 6600 | 0.5341 | 0.7544 | 0.7569 | | 0.507 | 34.34 | 6800 | 0.5344 | 0.7501 | 0.7528 | | 0.5048 | 35.35 | 7000 | 0.5326 | 0.7567 | 0.7585 | | 0.5099 | 36.36 | 7200 | 0.5301 | 0.7533 | 0.7557 | | 0.5063 | 37.37 | 7400 | 0.5306 | 0.7553 | 0.7573 | | 0.5083 | 38.38 | 7600 | 0.5299 | 0.7612 | 0.7623 | | 0.505 | 39.39 | 7800 | 0.5321 | 0.7600 | 0.7614 | | 0.5075 | 40.4 | 8000 | 0.5328 | 0.7590 | 0.7607 | | 0.5045 | 41.41 | 8200 | 0.5327 | 0.7517 | 0.7541 | | 0.5077 | 42.42 | 8400 | 0.5326 | 0.7531 | 0.7557 | | 0.5038 | 43.43 | 8600 | 0.5328 | 0.7550 | 0.7569 | | 0.5064 | 44.44 | 8800 | 0.5310 | 0.7548 | 0.7569 | | 0.5039 | 45.45 | 9000 | 0.5317 | 0.7586 | 0.7604 | | 0.5033 | 46.46 | 9200 | 0.5324 | 0.7554 | 0.7573 | | 0.5099 | 47.47 | 9400 | 0.5319 | 0.7527 | 0.7551 | | 0.4981 | 48.48 | 9600 | 0.5336 | 0.7544 | 0.7566 | | 0.5105 | 49.49 | 9800 | 0.5320 | 0.7540 | 0.7563 | | 0.5029 | 50.51 | 10000 | 0.5319 | 0.7552 | 0.7573 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K4me1-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me1-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:48:07+00:00

null

peft

# GUE_EMP_H3K4me1-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me1) dataset. It achieves the following results on the evaluation set: - Loss: 0.5125 - F1 Score: 0.7706 - Accuracy: 0.7718 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5982 | 1.01 | 200 | 0.5654 | 0.7301 | 0.7330 | | 0.5551 | 2.02 | 400 | 0.5492 | 0.7420 | 0.7440 | | 0.5392 | 3.03 | 600 | 0.5380 | 0.7479 | 0.75 | | 0.5345 | 4.04 | 800 | 0.5385 | 0.7526 | 0.7547 | | 0.529 | 5.05 | 1000 | 0.5344 | 0.7544 | 0.7551 | | 0.5243 | 6.06 | 1200 | 0.5372 | 0.7488 | 0.7522 | | 0.5191 | 7.07 | 1400 | 0.5333 | 0.7585 | 0.7604 | | 0.5178 | 8.08 | 1600 | 0.5328 | 0.7511 | 0.7544 | | 0.5128 | 9.09 | 1800 | 0.5297 | 0.7546 | 0.7569 | | 0.5089 | 10.1 | 2000 | 0.5259 | 0.7585 | 0.7604 | | 0.5053 | 11.11 | 2200 | 0.5379 | 0.7533 | 0.7563 | | 0.5042 | 12.12 | 2400 | 0.5200 | 0.7612 | 0.7623 | | 0.5019 | 13.13 | 2600 | 0.5268 | 0.7594 | 0.7620 | | 0.5001 | 14.14 | 2800 | 0.5279 | 0.7578 | 0.7598 | | 0.4947 | 15.15 | 3000 | 0.5261 | 0.7634 | 0.7652 | | 0.4925 | 16.16 | 3200 | 0.5263 | 0.7536 | 0.7569 | | 0.4888 | 17.17 | 3400 | 0.5357 | 0.7612 | 0.7633 | | 0.4898 | 18.18 | 3600 | 0.5193 | 0.7684 | 0.7693 | | 0.4855 | 19.19 | 3800 | 0.5196 | 0.7645 | 0.7664 | | 0.4825 | 20.2 | 4000 | 0.5256 | 0.7599 | 0.7620 | | 0.4789 | 21.21 | 4200 | 0.5371 | 0.7516 | 0.7544 | | 0.4789 | 22.22 | 4400 | 0.5328 | 0.7631 | 0.7645 | | 0.4724 | 23.23 | 4600 | 0.5290 | 0.7638 | 0.7664 | | 0.4777 | 24.24 | 4800 | 0.5440 | 0.7471 | 0.7513 | | 0.4722 | 25.25 | 5000 | 0.5276 | 0.7675 | 0.7680 | | 0.4738 | 26.26 | 5200 | 0.5291 | 0.7667 | 0.7670 | | 0.4669 | 27.27 | 5400 | 0.5323 | 0.7569 | 0.7595 | | 0.4683 | 28.28 | 5600 | 0.5283 | 0.7668 | 0.7677 | | 0.4676 | 29.29 | 5800 | 0.5398 | 0.7453 | 0.7503 | | 0.4605 | 30.3 | 6000 | 0.5328 | 0.7637 | 0.7652 | | 0.4614 | 31.31 | 6200 | 0.5288 | 0.7652 | 0.7664 | | 0.4637 | 32.32 | 6400 | 0.5363 | 0.7584 | 0.7610 | | 0.4596 | 33.33 | 6600 | 0.5352 | 0.7614 | 0.7636 | | 0.4573 | 34.34 | 6800 | 0.5317 | 0.7526 | 0.7554 | | 0.452 | 35.35 | 7000 | 0.5339 | 0.7676 | 0.7689 | | 0.4567 | 36.36 | 7200 | 0.5331 | 0.7545 | 0.7566 | | 0.4518 | 37.37 | 7400 | 0.5350 | 0.7576 | 0.7595 | | 0.4552 | 38.38 | 7600 | 0.5343 | 0.7667 | 0.7677 | | 0.4514 | 39.39 | 7800 | 0.5345 | 0.7664 | 0.7674 | | 0.4501 | 40.4 | 8000 | 0.5313 | 0.7645 | 0.7661 | | 0.4458 | 41.41 | 8200 | 0.5369 | 0.7595 | 0.7617 | | 0.45 | 42.42 | 8400 | 0.5406 | 0.7575 | 0.7601 | | 0.4461 | 43.43 | 8600 | 0.5367 | 0.7619 | 0.7636 | | 0.4474 | 44.44 | 8800 | 0.5383 | 0.7578 | 0.7601 | | 0.4458 | 45.45 | 9000 | 0.5349 | 0.7610 | 0.7626 | | 0.4421 | 46.46 | 9200 | 0.5379 | 0.7632 | 0.7645 | | 0.4511 | 47.47 | 9400 | 0.5360 | 0.7594 | 0.7617 | | 0.4383 | 48.48 | 9600 | 0.5399 | 0.7586 | 0.7604 | | 0.4526 | 49.49 | 9800 | 0.5357 | 0.7584 | 0.7604 | | 0.4403 | 50.51 | 10000 | 0.5365 | 0.7590 | 0.7607 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K4me1-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me1-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:48:31+00:00

text-to-image

diffusers

--- license: creativeml-openrail-m tags: - text-to-image - stable-diffusion --- ### vesttieandtux2 Dreambooth model trained by enriq3 with TheLastBen's fast-DreamBooth notebook

{}

enriq3/vesttieandtux2

null

[ "diffusers", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

null

2024-04-29T22:48:50+00:00

text-generation

transformers

{"license": "mit"}

multitensor/mistral-mllm

null

[ "transformers", "safetensors", "mistral", "text-generation", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T22:50:31+00:00

text-generation

transformers

# GPT2_DocBot_SonatafyAI_V3 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 2.8062 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 5 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 3.0191 | 1.0 | 9715 | 2.9325 | | 2.8082 | 2.0 | 19430 | 2.8542 | | 2.7173 | 3.0 | 29145 | 2.8198 | | 2.6473 | 4.0 | 38860 | 2.8052 | | 2.5881 | 5.0 | 48575 | 2.8062 | ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "gpt2", "model-index": [{"name": "GPT2_DocBot_SonatafyAI_V3", "results": []}]}

ajtamayoh/GPT2_DocBot_SonatafyAI_V3

null

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T22:51:22+00:00

null

peft

# GUE_EMP_H3K4me1-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K4me1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K4me1) dataset. It achieves the following results on the evaluation set: - Loss: 0.5161 - F1 Score: 0.7724 - Accuracy: 0.7737 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5877 | 1.01 | 200 | 0.5568 | 0.7362 | 0.7371 | | 0.5454 | 2.02 | 400 | 0.5428 | 0.7537 | 0.7551 | | 0.5301 | 3.03 | 600 | 0.5330 | 0.7531 | 0.7551 | | 0.5235 | 4.04 | 800 | 0.5309 | 0.7550 | 0.7569 | | 0.5161 | 5.05 | 1000 | 0.5291 | 0.7614 | 0.7620 | | 0.5091 | 6.06 | 1200 | 0.5340 | 0.7516 | 0.7547 | | 0.5021 | 7.07 | 1400 | 0.5320 | 0.7621 | 0.7639 | | 0.4978 | 8.08 | 1600 | 0.5250 | 0.7573 | 0.7601 | | 0.4895 | 9.09 | 1800 | 0.5259 | 0.7564 | 0.7585 | | 0.4836 | 10.1 | 2000 | 0.5275 | 0.7603 | 0.7623 | | 0.4758 | 11.11 | 2200 | 0.5495 | 0.7519 | 0.7560 | | 0.4737 | 12.12 | 2400 | 0.5267 | 0.7643 | 0.7652 | | 0.4664 | 13.13 | 2600 | 0.5384 | 0.7562 | 0.7592 | | 0.4617 | 14.14 | 2800 | 0.5470 | 0.7586 | 0.7604 | | 0.4528 | 15.15 | 3000 | 0.5355 | 0.7634 | 0.7648 | | 0.4503 | 16.16 | 3200 | 0.5305 | 0.7510 | 0.7528 | | 0.4392 | 17.17 | 3400 | 0.5566 | 0.7610 | 0.7623 | | 0.4383 | 18.18 | 3600 | 0.5509 | 0.7597 | 0.7607 | | 0.4284 | 19.19 | 3800 | 0.5471 | 0.7619 | 0.7633 | | 0.4237 | 20.2 | 4000 | 0.5406 | 0.7567 | 0.7582 | | 0.4158 | 21.21 | 4200 | 0.5632 | 0.7517 | 0.7535 | | 0.4111 | 22.22 | 4400 | 0.5720 | 0.7610 | 0.7620 | | 0.4002 | 23.23 | 4600 | 0.5655 | 0.7642 | 0.7652 | | 0.4017 | 24.24 | 4800 | 0.6035 | 0.7490 | 0.7528 | | 0.3928 | 25.25 | 5000 | 0.5774 | 0.7634 | 0.7633 | | 0.3912 | 26.26 | 5200 | 0.5868 | 0.7538 | 0.7541 | | 0.3819 | 27.27 | 5400 | 0.5887 | 0.7534 | 0.7560 | | 0.3795 | 28.28 | 5600 | 0.5987 | 0.7552 | 0.7566 | | 0.375 | 29.29 | 5800 | 0.6025 | 0.7398 | 0.7434 | | 0.3644 | 30.3 | 6000 | 0.6111 | 0.7570 | 0.7579 | | 0.3623 | 31.31 | 6200 | 0.6112 | 0.7471 | 0.7472 | | 0.3611 | 32.32 | 6400 | 0.6075 | 0.7440 | 0.7453 | | 0.3553 | 33.33 | 6600 | 0.6100 | 0.7562 | 0.7573 | | 0.3497 | 34.34 | 6800 | 0.6096 | 0.7477 | 0.7481 | | 0.3425 | 35.35 | 7000 | 0.6285 | 0.7562 | 0.7566 | | 0.3459 | 36.36 | 7200 | 0.6170 | 0.7446 | 0.7456 | | 0.3369 | 37.37 | 7400 | 0.6361 | 0.7525 | 0.7532 | | 0.3344 | 38.38 | 7600 | 0.6405 | 0.7440 | 0.7443 | | 0.3369 | 39.39 | 7800 | 0.6419 | 0.7560 | 0.7563 | | 0.3275 | 40.4 | 8000 | 0.6409 | 0.7496 | 0.7513 | | 0.3256 | 41.41 | 8200 | 0.6481 | 0.7481 | 0.7491 | | 0.3283 | 42.42 | 8400 | 0.6509 | 0.7439 | 0.7453 | | 0.3202 | 43.43 | 8600 | 0.6656 | 0.7404 | 0.7415 | | 0.3193 | 44.44 | 8800 | 0.6546 | 0.7465 | 0.7475 | | 0.3157 | 45.45 | 9000 | 0.6614 | 0.7500 | 0.7509 | | 0.3144 | 46.46 | 9200 | 0.6641 | 0.7460 | 0.7465 | | 0.3173 | 47.47 | 9400 | 0.6623 | 0.7419 | 0.7427 | | 0.3066 | 48.48 | 9600 | 0.6763 | 0.7433 | 0.7443 | | 0.3191 | 49.49 | 9800 | 0.6665 | 0.7427 | 0.7437 | | 0.3091 | 50.51 | 10000 | 0.6692 | 0.7426 | 0.7434 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K4me1-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K4me1-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T22:51:42+00:00

null

{}

ldm0612/gpt2-wikitext2

null

[ "region:us" ]

null

2024-04-29T22:52:25+00:00

question-answering

transformers

# distilbert-base-uncased-finetuned-squad This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.1599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.2149 | 1.0 | 5533 | 1.1802 | | 0.9459 | 2.0 | 11066 | 1.1161 | | 0.7596 | 3.0 | 16599 | 1.1599 | ### Framework versions - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-squad", "results": []}]}

ahmad01010101/distilbert-base-uncased-finetuned-squad

null

[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:53:10+00:00

text-generation

transformers

An updated version of the previous model. In this one, I have not yet found any problems with word duplication. 02.05.24 Model updates, new versions are in the v1.1 branch. Link to original model and script: - openlynn/Llama-3-Soliloquy-8B-v1.5-64k: https://huggingface.co/openlynn/Llama-3-Soliloquy-8B-v1.5-64k - FantasiaFoundry/GGUF-Quantization-Script: https://huggingface.co/FantasiaFoundry/GGUF-Quantization-Script

{"language": ["en"], "license": "cc-by-nc-sa-4.0", "library_name": "transformers", "tags": ["llama", "text-generation-inference"], "pipeline_tag": "text-generation"}

SolidSnacke/Llama-3-Soliloquy-8B-v1.5-64k-i-GGUF

null

[ "transformers", "gguf", "llama", "text-generation-inference", "text-generation", "en", "license:cc-by-nc-sa-4.0", "endpoints_compatible", "region:us" ]

null

2024-04-29T22:53:28+00:00

null

# O0428HMA2 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0559 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.6301 | 0.09 | 10 | 0.1786 | | 0.1808 | 0.18 | 20 | 0.1584 | | 0.151 | 0.27 | 30 | 0.1656 | | 0.1571 | 0.36 | 40 | 0.1538 | | 0.1506 | 0.45 | 50 | 0.1473 | | 0.1503 | 0.54 | 60 | 0.1472 | | 0.1495 | 0.63 | 70 | 0.1470 | | 0.1494 | 0.73 | 80 | 0.1533 | | 0.1454 | 0.82 | 90 | 0.1454 | | 0.2027 | 0.91 | 100 | 0.3378 | | 0.6197 | 1.0 | 110 | 0.1547 | | 0.1558 | 1.09 | 120 | 0.1495 | | 0.151 | 1.18 | 130 | 0.2320 | | 0.1812 | 1.27 | 140 | 0.1292 | | 0.1265 | 1.36 | 150 | 0.0858 | | 0.0775 | 1.45 | 160 | 0.0811 | | 1.561 | 1.54 | 170 | 3.8411 | | 0.6605 | 1.63 | 180 | 0.0889 | | 0.9093 | 1.72 | 190 | 0.1577 | | 0.1072 | 1.81 | 200 | 0.1386 | | 0.3511 | 1.9 | 210 | 0.0862 | | 0.0683 | 1.99 | 220 | 0.0609 | | 0.0628 | 2.08 | 230 | 0.0583 | | 0.0574 | 2.18 | 240 | 0.0583 | | 0.0576 | 2.27 | 250 | 0.0589 | | 0.064 | 2.36 | 260 | 0.0615 | | 0.0555 | 2.45 | 270 | 0.0571 | | 0.0548 | 2.54 | 280 | 0.0564 | | 0.0563 | 2.63 | 290 | 0.0577 | | 0.0583 | 2.72 | 300 | 0.0558 | | 0.058 | 2.81 | 310 | 0.0555 | | 0.0589 | 2.9 | 320 | 0.0558 | | 0.0621 | 2.99 | 330 | 0.0559 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA2", "results": []}]}

Litzy619/O0428HMA2

null

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

null

2024-04-29T22:53:54+00:00

null

# O0428HMA3 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0534 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.516 | 0.09 | 10 | 0.1675 | | 0.1635 | 0.18 | 20 | 0.1582 | | 0.1494 | 0.27 | 30 | 0.1521 | | 0.1524 | 0.36 | 40 | 0.1511 | | 0.1511 | 0.45 | 50 | 0.1465 | | 0.1533 | 0.54 | 60 | 0.1502 | | 0.149 | 0.63 | 70 | 0.1473 | | 0.1503 | 0.73 | 80 | 0.1592 | | 0.1487 | 0.82 | 90 | 0.1494 | | 0.1474 | 0.91 | 100 | 0.1475 | | 0.1331 | 1.0 | 110 | 0.2279 | | 0.3556 | 1.09 | 120 | 0.1260 | | 0.2269 | 1.18 | 130 | 0.1110 | | 0.1173 | 1.27 | 140 | 0.0777 | | 0.1209 | 1.36 | 150 | 0.0818 | | 0.0771 | 1.45 | 160 | 0.0822 | | 0.0701 | 1.54 | 170 | 0.0583 | | 0.0641 | 1.63 | 180 | 0.0579 | | 0.0638 | 1.72 | 190 | 0.0560 | | 0.0564 | 1.81 | 200 | 0.0569 | | 0.058 | 1.9 | 210 | 0.0603 | | 0.059 | 1.99 | 220 | 0.0548 | | 0.0576 | 2.08 | 230 | 0.0548 | | 0.0532 | 2.18 | 240 | 0.0565 | | 0.0549 | 2.27 | 250 | 0.0574 | | 0.0586 | 2.36 | 260 | 0.0561 | | 0.0537 | 2.45 | 270 | 0.0543 | | 0.0522 | 2.54 | 280 | 0.0545 | | 0.0541 | 2.63 | 290 | 0.0556 | | 0.055 | 2.72 | 300 | 0.0532 | | 0.0556 | 2.81 | 310 | 0.0531 | | 0.0563 | 2.9 | 320 | 0.0533 | | 0.0579 | 2.99 | 330 | 0.0534 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA3", "results": []}]}

Litzy619/O0428HMA3

null

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

null

2024-04-29T22:54:01+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

cilantro9246/tlvmpdp

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T22:56:25+00:00

text2text-generation

peft

## llama-2-13b-code-alpaca [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl) Trained for 3 epochs on `theblackcat102/evol-codealpaca-v1` dataset, scored decent on locally run perplexity at 4.36. ## Axolotl config used ```yaml base_model: NousResearch/Llama-2-13b-hf base_model_config: NousResearch/Llama-2-13b-hf model_type: LlamaForCausalLM tokenizer_type: LlamaTokenizer push_dataset_to_hub: hub_model_id: load_in_8bit: false load_in_4bit: true strict: false datasets: - path: theblackcat102/evol-codealpaca-v1 type: alpaca dataset_prepared_path: last_run_prepared val_set_size: 0.01 output_dir: ./checkpoints/llama-2-13b-qlora adapter: qlora lora_model_dir: sequence_len: 4096 max_packed_sequence_len: 4096 lora_r: 32 lora_alpha: 16 lora_dropout: 0.05 lora_target_modules: lora_target_linear: true lora_fan_in_fan_out: wandb_project: wandb_watch: wandb_run_id: wandb_log_model: gradient_accumulation_steps: 2 micro_batch_size: 2 num_epochs: 3 optimizer: paged_adamw_32bit lr_scheduler: cosine learning_rate: 0.0001 train_on_inputs: false group_by_length: true bf16: true fp16: false tf32: true gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: true flash_attention: warmup_steps: 10 eval_steps: 50 save_steps: debug: deepspeed: weight_decay: 0.0 fsdp: fsdp_config: special_tokens: bos_token: "<s>" eos_token: "</s>" unk_token: "<unk>" ``` And then merged with Axolotl via: ``` accelerate launch scripts/finetune.py configs/your_config.yml --merge_lora --lora_model_dir="./completed-model" --load_in_8bit=False --load_in_4bit=False ``` ## Training procedure The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 The following `bitsandbytes` quantization config was used during training: - load_in_8bit: False - load_in_4bit: True - llm_int8_threshold: 6.0 - llm_int8_skip_modules: None - llm_int8_enable_fp32_cpu_offload: False - llm_int8_has_fp16_weight: False - bnb_4bit_quant_type: nf4 - bnb_4bit_use_double_quant: True - bnb_4bit_compute_dtype: bfloat16 ### Framework versions - PEFT 0.5.0.dev0

{"language": ["en"], "license": "cc-by-nc-4.0", "library_name": "peft", "datasets": ["theblackcat102/evol-codealpaca-v1"], "pipeline_tag": "text2text-generation"}

DTang161/ModelMergingCode

null

[ "peft", "pytorch", "llama", "text2text-generation", "en", "dataset:theblackcat102/evol-codealpaca-v1", "license:cc-by-nc-4.0", "region:us" ]

null

2024-04-29T22:56:37+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

Quac/Indian-Edu-SFT-llama-3-8B

null

[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

null

2024-04-29T22:58:50+00:00

text-generation

transformers

# Llama-3-8B-Ultra-Instruct This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). Hello everyone this is Dampf, creator of the Destroyer series! *looks around* Oh, now I'm on Elinas' HF account. As you can see, I'm quite the traveler! This time, I'm introducing you to 8B-Ultra-Instruct. It is a small general purpose model that combines the most powerful instruct models with enticing roleplaying models. It will introduce better RAG capabilities in the form of Bagel to Llama 3 8B Instruct as well as German multilanguage, higher general intelligence and vision support. A model focused on Biology adds knowledge in the medical field. As for roleplay, it features two of the hottest models right now. Those are known to be high quality and for being uncensored. So this model might put out harmful responses. We are not responsible for what you do with this model and please take everything the model says with a huge grain of salt. Lastly, you might notice I'm conversative with the weight values in the final merge. This is because I believe L8B Instruct is a very dense model that's already great and doesn't need a lot more data. So instead of reaching the weight value of 1 in a ties merge, I'm only using a total of 0,65. This is to preserve Llama Instruct's intelligence and knowledge, while adding a little bit of the aforementioned models as salt in the soup. A huge thank you for all the creators of the datasets. Those include Undi95, Jon Durbin, Aaditya, VAGOsolutions, Teknium, Camel and many more. They deserve all the credit. And of course, thank you Elinas for providing the compute. ## Quants [GGUF](https://huggingface.co/bartowski/Llama-3-8B-Ultra-Instruct-GGUF) [exllama2](https://huggingface.co/bartowski/Llama-3-8B-Ultra-Instruct-exl2) ## Merge Details ### Merge Method This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Undi95/Meta-Llama-3-8B-Instruct-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-Instruct-hf) as a base. ### Models Merged The following models were included in the merge: * llama-3-8B-ultra-instruct/InstructPart * llama-3-8B-ultra-instruct/RPPart ### Configuration The following YAML configuration was used to produce this model: ```yaml models: - model: ChaoticNeutrals/Poppy_Porpoise-v0.7-L3-8B parameters: weight: 0.4 - model: Undi95/Llama-3-LewdPlay-8B-evo parameters: weight: 0.5 - model: jondurbin/bagel-8b-v1.0 parameters: weight: 0.1 merge_method: dare_ties dtype: bfloat16 base_model: Undi95/Meta-Llama-3-8B-hf name: RPPart --- models: - model: Weyaxi/Einstein-v6.1-Llama3-8B parameters: weight: 0.6 - model: VAGOsolutions/Llama-3-SauerkrautLM-8b-Instruct parameters: weight: 0.3 - model: aaditya/OpenBioLLM-Llama3-8B parameters: weight: 0.1 merge_method: dare_ties base_model: Undi95/Meta-Llama-3-8B-hf dtype: bfloat16 name: InstructPart --- models: - model: RPPart parameters: weight: 0.39 - model: InstructPart parameters: weight: 0.26 merge_method: dare_ties base_model: Undi95/Meta-Llama-3-8B-Instruct-hf dtype: bfloat16 name: Llama-3-8B-Ultra-Instruct ``` ### Chat Template (Llama 3 Official) ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {input}<|eot_id|><|start_header_id|>assistant<|end_header_id|> {output}<|eot_id|> ``` ### [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_elinas__Llama-3-8B-Ultra-Instruct) | Metric |Value| |---------------------------------|----:| |Avg. |69.11| |AI2 Reasoning Challenge (25-Shot)|64.59| |HellaSwag (10-Shot) |81.63| |MMLU (5-Shot) |68.32| |TruthfulQA (0-shot) |52.80| |Winogrande (5-shot) |76.95| |GSM8k (5-shot) |70.36|

{"license": "llama3", "library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["Undi95/Meta-Llama-3-8B-Instruct-hf"]}

elinas/Llama-3-8B-Ultra-Instruct

null

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2311.03099", "arxiv:2306.01708", "base_model:Undi95/Meta-Llama-3-8B-Instruct-hf", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T23:00:11+00:00

text2text-generation

transformers

# mbart-large-50-bcoqa This model is a fine-tuned version of [facebook/mbart-large-50](https://huggingface.co/facebook/mbart-large-50) on the None dataset. It achieves the following results on the evaluation set: - Loss: 1.0137 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:-----:|:---------------:| | 1.8791 | 0.1 | 3500 | 1.7917 | | 1.579 | 0.2 | 7000 | 1.4741 | | 1.4918 | 0.3 | 10500 | 1.4246 | | 1.422 | 0.4 | 14000 | 1.3369 | | 1.4088 | 0.5 | 17500 | 1.3064 | | 1.3245 | 0.61 | 21000 | 1.2566 | | 1.3205 | 0.71 | 24500 | 1.2274 | | 1.3168 | 0.81 | 28000 | 1.2052 | | 1.2256 | 0.91 | 31500 | 1.1630 | | 1.0668 | 1.01 | 35000 | 1.1543 | | 1.0185 | 1.11 | 38500 | 1.1391 | | 0.9521 | 1.21 | 42000 | 1.1076 | | 0.9467 | 1.31 | 45500 | 1.1316 | | 1.0128 | 1.41 | 49000 | 1.0849 | | 0.9948 | 1.51 | 52500 | 1.0619 | | 0.9601 | 1.61 | 56000 | 1.0489 | | 0.9479 | 1.72 | 59500 | 1.0353 | | 0.9046 | 1.82 | 63000 | 1.0212 | | 0.8924 | 1.92 | 66500 | 1.0137 | ### Framework versions - Transformers 4.39.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.16.1 - Tokenizers 0.15.1

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "facebook/mbart-large-50", "model-index": [{"name": "mbart-large-50-bcoqa", "results": []}]}

arbitropy/mbart-large-50-bcoqa

null

[ "transformers", "safetensors", "mbart", "text2text-generation", "generated_from_trainer", "base_model:facebook/mbart-large-50", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:00:29+00:00

null

{}

abaral7/test-model

null

[ "region:us" ]

null

2024-04-29T23:00:32+00:00

reinforcement-learning

null

# **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction

{"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-CartPole-v1", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "CartPole-v1", "type": "CartPole-v1"}, "metrics": [{"type": "mean_reward", "value": "500.00 +/- 0.00", "name": "mean_reward", "verified": false}]}]}]}

haytamelouarrat/Reinforce-CartPole-v1

null

[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]

null

2024-04-29T23:01:28+00:00

null

peft

# norllm-ai-normistral-7b-align-scan This model is a fine-tuned version of [data/norllm-ai-normistral-7b-sft-qlora](https://huggingface.co/data/norllm-ai-normistral-7b-sft-qlora) on the hugodk-sch/aftonposten_title_prefs dataset. It achieves the following results on the evaluation set: - Loss: 0.9294 - Rewards/chosen: -0.0900 - Rewards/rejected: -0.1614 - Rewards/accuracies: 0.6009 - Rewards/margins: 0.0715 - Logps/rejected: -35.5053 - Logps/chosen: -31.7323 - Logits/rejected: -2.8259 - Logits/chosen: -2.8279 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-06 - train_batch_size: 4 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen | |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:| | 0.9239 | 0.26 | 100 | 0.9661 | -0.0010 | -0.0351 | 0.6013 | 0.0342 | -34.8738 | -31.2872 | -2.8027 | -2.8055 | | 0.8146 | 0.52 | 200 | 0.9363 | -0.0747 | -0.1389 | 0.6184 | 0.0641 | -35.3925 | -31.6561 | -2.8206 | -2.8233 | | 0.7173 | 0.78 | 300 | 0.9279 | -0.0837 | -0.1567 | 0.6125 | 0.0730 | -35.4817 | -31.7010 | -2.8247 | -2.8267 | ### Framework versions - PEFT 0.10.0 - Transformers 4.39.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.1

{"library_name": "peft", "tags": ["alignment-handbook", "trl", "dpo", "generated_from_trainer"], "datasets": ["hugodk-sch/aftonposten_title_prefs"], "base_model": "NorLLM-AI/NorMistral-7B", "model-index": [{"name": "norllm-ai-normistral-7b-align-scan", "results": []}]}

hugodk-sch/norllm-ai-normistral-7b-align-scan

null

[ "peft", "safetensors", "mistral", "alignment-handbook", "trl", "dpo", "generated_from_trainer", "dataset:hugodk-sch/aftonposten_title_prefs", "base_model:NorLLM-AI/NorMistral-7B", "4-bit", "region:us" ]

null

2024-04-29T23:03:36+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

shallow6414/i604il5

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T23:03:51+00:00

text-classification

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

profoz/parent_malicious_model

null

[ "transformers", "safetensors", "bert", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:04:03+00:00

null

{}

viwonrecord/SEOKYOUNG

null

[ "region:us" ]

null

2024-04-29T23:04:36+00:00

null

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

tsharish/Mistral-7B-Inst-v0.2-pubmed-1k_adapter

null

[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:05:41+00:00

null

peft

# GUE_EMP_H3K36me3-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K36me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K36me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4546 - F1 Score: 0.7974 - Accuracy: 0.7999 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5656 | 0.92 | 200 | 0.5396 | 0.7434 | 0.7457 | | 0.5164 | 1.83 | 400 | 0.5221 | 0.7582 | 0.7612 | | 0.5001 | 2.75 | 600 | 0.5085 | 0.7683 | 0.7704 | | 0.5011 | 3.67 | 800 | 0.5027 | 0.7739 | 0.7755 | | 0.4857 | 4.59 | 1000 | 0.5024 | 0.7777 | 0.7798 | | 0.4814 | 5.5 | 1200 | 0.4862 | 0.7825 | 0.7841 | | 0.4782 | 6.42 | 1400 | 0.4814 | 0.7861 | 0.7870 | | 0.4754 | 7.34 | 1600 | 0.4872 | 0.7820 | 0.7838 | | 0.4679 | 8.26 | 1800 | 0.4855 | 0.7847 | 0.7864 | | 0.4729 | 9.17 | 2000 | 0.4816 | 0.7823 | 0.7841 | | 0.4679 | 10.09 | 2200 | 0.4951 | 0.7783 | 0.7818 | | 0.4659 | 11.01 | 2400 | 0.4760 | 0.7862 | 0.7884 | | 0.4629 | 11.93 | 2600 | 0.4728 | 0.7873 | 0.7893 | | 0.4618 | 12.84 | 2800 | 0.4770 | 0.7858 | 0.7881 | | 0.4592 | 13.76 | 3000 | 0.4802 | 0.7799 | 0.7830 | | 0.4559 | 14.68 | 3200 | 0.4697 | 0.7912 | 0.7927 | | 0.4619 | 15.6 | 3400 | 0.4723 | 0.7879 | 0.7904 | | 0.4572 | 16.51 | 3600 | 0.4736 | 0.7902 | 0.7921 | | 0.4566 | 17.43 | 3800 | 0.4626 | 0.7949 | 0.7962 | | 0.452 | 18.35 | 4000 | 0.4754 | 0.7908 | 0.7927 | | 0.4551 | 19.27 | 4200 | 0.4720 | 0.7925 | 0.7942 | | 0.4531 | 20.18 | 4400 | 0.4777 | 0.7867 | 0.7893 | | 0.4486 | 21.1 | 4600 | 0.4705 | 0.7942 | 0.7959 | | 0.4512 | 22.02 | 4800 | 0.4709 | 0.7949 | 0.7967 | | 0.4486 | 22.94 | 5000 | 0.4632 | 0.7940 | 0.7959 | | 0.4471 | 23.85 | 5200 | 0.4673 | 0.7938 | 0.7959 | | 0.4488 | 24.77 | 5400 | 0.4783 | 0.7864 | 0.7893 | | 0.4494 | 25.69 | 5600 | 0.4688 | 0.7929 | 0.7950 | | 0.4467 | 26.61 | 5800 | 0.4678 | 0.7921 | 0.7939 | | 0.4447 | 27.52 | 6000 | 0.4729 | 0.7913 | 0.7936 | | 0.4447 | 28.44 | 6200 | 0.4641 | 0.7954 | 0.7973 | | 0.4436 | 29.36 | 6400 | 0.4725 | 0.7898 | 0.7924 | | 0.4471 | 30.28 | 6600 | 0.4697 | 0.7907 | 0.7933 | | 0.4433 | 31.19 | 6800 | 0.4655 | 0.7958 | 0.7973 | | 0.4454 | 32.11 | 7000 | 0.4664 | 0.7942 | 0.7962 | | 0.4421 | 33.03 | 7200 | 0.4682 | 0.7950 | 0.7970 | | 0.4413 | 33.94 | 7400 | 0.4713 | 0.7938 | 0.7959 | | 0.4415 | 34.86 | 7600 | 0.4680 | 0.7949 | 0.7970 | | 0.4415 | 35.78 | 7800 | 0.4643 | 0.7959 | 0.7976 | | 0.4391 | 36.7 | 8000 | 0.4634 | 0.7993 | 0.8010 | | 0.4413 | 37.61 | 8200 | 0.4719 | 0.7868 | 0.7899 | | 0.4385 | 38.53 | 8400 | 0.4648 | 0.7963 | 0.7982 | | 0.441 | 39.45 | 8600 | 0.4686 | 0.7938 | 0.7962 | | 0.4356 | 40.37 | 8800 | 0.4725 | 0.7931 | 0.7956 | | 0.4439 | 41.28 | 9000 | 0.4677 | 0.7911 | 0.7936 | | 0.4384 | 42.2 | 9200 | 0.4648 | 0.7970 | 0.7990 | | 0.4367 | 43.12 | 9400 | 0.4663 | 0.7969 | 0.7990 | | 0.4372 | 44.04 | 9600 | 0.4668 | 0.7938 | 0.7962 | | 0.4404 | 44.95 | 9800 | 0.4687 | 0.7907 | 0.7933 | | 0.4395 | 45.87 | 10000 | 0.4666 | 0.7935 | 0.7959 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K36me3-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K36me3-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:05:51+00:00

null

peft

# GUE_EMP_H3K36me3-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K36me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K36me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4506 - F1 Score: 0.8122 - Accuracy: 0.8142 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5504 | 0.92 | 200 | 0.5331 | 0.7489 | 0.7526 | | 0.4958 | 1.83 | 400 | 0.4990 | 0.7734 | 0.7758 | | 0.4776 | 2.75 | 600 | 0.4796 | 0.7878 | 0.7890 | | 0.4802 | 3.67 | 800 | 0.4811 | 0.7896 | 0.7910 | | 0.4638 | 4.59 | 1000 | 0.4874 | 0.7864 | 0.7884 | | 0.4582 | 5.5 | 1200 | 0.4710 | 0.7903 | 0.7921 | | 0.4563 | 6.42 | 1400 | 0.4680 | 0.7967 | 0.7979 | | 0.4515 | 7.34 | 1600 | 0.4721 | 0.7926 | 0.7947 | | 0.4448 | 8.26 | 1800 | 0.4736 | 0.7919 | 0.7939 | | 0.4466 | 9.17 | 2000 | 0.4668 | 0.7929 | 0.7947 | | 0.4413 | 10.09 | 2200 | 0.4890 | 0.7760 | 0.7801 | | 0.4395 | 11.01 | 2400 | 0.4614 | 0.7961 | 0.7982 | | 0.4358 | 11.93 | 2600 | 0.4567 | 0.7996 | 0.7999 | | 0.4341 | 12.84 | 2800 | 0.4737 | 0.7850 | 0.7884 | | 0.4284 | 13.76 | 3000 | 0.4900 | 0.7771 | 0.7818 | | 0.4245 | 14.68 | 3200 | 0.4666 | 0.7990 | 0.8007 | | 0.4283 | 15.6 | 3400 | 0.4565 | 0.7968 | 0.7985 | | 0.4248 | 16.51 | 3600 | 0.4838 | 0.7919 | 0.7947 | | 0.4213 | 17.43 | 3800 | 0.4729 | 0.7910 | 0.7930 | | 0.4166 | 18.35 | 4000 | 0.4621 | 0.7989 | 0.8005 | | 0.4202 | 19.27 | 4200 | 0.4710 | 0.7998 | 0.8019 | | 0.4144 | 20.18 | 4400 | 0.4801 | 0.7969 | 0.7990 | | 0.4117 | 21.1 | 4600 | 0.4672 | 0.7976 | 0.7993 | | 0.412 | 22.02 | 4800 | 0.4626 | 0.7988 | 0.8002 | | 0.4095 | 22.94 | 5000 | 0.4661 | 0.7939 | 0.7964 | | 0.4051 | 23.85 | 5200 | 0.4695 | 0.7977 | 0.8002 | | 0.4061 | 24.77 | 5400 | 0.4818 | 0.7946 | 0.7976 | | 0.4053 | 25.69 | 5600 | 0.4660 | 0.7944 | 0.7970 | | 0.402 | 26.61 | 5800 | 0.4649 | 0.7991 | 0.8010 | | 0.4013 | 27.52 | 6000 | 0.4767 | 0.7982 | 0.8002 | | 0.4011 | 28.44 | 6200 | 0.4698 | 0.7990 | 0.8010 | | 0.3956 | 29.36 | 6400 | 0.4683 | 0.7978 | 0.7996 | | 0.3991 | 30.28 | 6600 | 0.4720 | 0.7946 | 0.7970 | | 0.3962 | 31.19 | 6800 | 0.4673 | 0.7972 | 0.7987 | | 0.3956 | 32.11 | 7000 | 0.4702 | 0.7955 | 0.7976 | | 0.3907 | 33.03 | 7200 | 0.4693 | 0.7994 | 0.8010 | | 0.3915 | 33.94 | 7400 | 0.4673 | 0.8019 | 0.8036 | | 0.3891 | 34.86 | 7600 | 0.4668 | 0.7936 | 0.7956 | | 0.3901 | 35.78 | 7800 | 0.4653 | 0.8013 | 0.8028 | | 0.3869 | 36.7 | 8000 | 0.4635 | 0.7971 | 0.7987 | | 0.3884 | 37.61 | 8200 | 0.4734 | 0.7921 | 0.7947 | | 0.3871 | 38.53 | 8400 | 0.4749 | 0.7965 | 0.7987 | | 0.3866 | 39.45 | 8600 | 0.4737 | 0.7956 | 0.7979 | | 0.382 | 40.37 | 8800 | 0.4798 | 0.7923 | 0.7950 | | 0.3897 | 41.28 | 9000 | 0.4740 | 0.7940 | 0.7964 | | 0.3849 | 42.2 | 9200 | 0.4700 | 0.7988 | 0.8007 | | 0.3798 | 43.12 | 9400 | 0.4709 | 0.8012 | 0.8030 | | 0.3836 | 44.04 | 9600 | 0.4731 | 0.7948 | 0.7970 | | 0.3853 | 44.95 | 9800 | 0.4738 | 0.7926 | 0.7950 | | 0.3825 | 45.87 | 10000 | 0.4714 | 0.7954 | 0.7976 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K36me3-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K36me3-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:06:44+00:00

null

peft

# EstigiaxLlama This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 16 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - training_steps: 250 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1

{"license": "apache-2.0", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "TinyLlama/TinyLlama-1.1B-Chat-v1.0", "model-index": [{"name": "EstigiaxLlama", "results": []}]}

franciscobdl/EstigiaxLlama

null

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:TinyLlama/TinyLlama-1.1B-Chat-v1.0", "license:apache-2.0", "region:us" ]

null

2024-04-29T23:06:57+00:00

null

# DDPO trained model num_epochs=20 train_gradient_accumulation_steps=1 sample_num_steps=30 sample_batch_size=8 train_batch_size=8 sample_num_batches_per_epoch=32 based off of stabilityai/stable-diffusion-2-base and then trained off of None

{}

jlbaker361/ddpo-runway-image_reward-hard

null

[ "region:us" ]

null

2024-04-29T23:07:08+00:00

null

peft

# GUE_mouse_0-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.5838 - F1 Score: 0.7160 - Accuracy: 0.7173 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.6482 | 3.92 | 200 | 0.6103 | 0.6555 | 0.6568 | | 0.6062 | 7.84 | 400 | 0.5965 | 0.6803 | 0.6815 | | 0.586 | 11.76 | 600 | 0.5813 | 0.7025 | 0.7025 | | 0.5673 | 15.69 | 800 | 0.5669 | 0.7085 | 0.7086 | | 0.5496 | 19.61 | 1000 | 0.5569 | 0.7037 | 0.7037 | | 0.5443 | 23.53 | 1200 | 0.5889 | 0.6842 | 0.7 | | 0.5318 | 27.45 | 1400 | 0.5531 | 0.7074 | 0.7086 | | 0.5218 | 31.37 | 1600 | 0.5475 | 0.7014 | 0.7025 | | 0.5177 | 35.29 | 1800 | 0.5485 | 0.7118 | 0.7136 | | 0.509 | 39.22 | 2000 | 0.5474 | 0.7077 | 0.7086 | | 0.4993 | 43.14 | 2200 | 0.5541 | 0.7135 | 0.7136 | | 0.498 | 47.06 | 2400 | 0.5485 | 0.7184 | 0.7198 | | 0.489 | 50.98 | 2600 | 0.5472 | 0.7232 | 0.7235 | | 0.4855 | 54.9 | 2800 | 0.5571 | 0.7221 | 0.7247 | | 0.4809 | 58.82 | 3000 | 0.5488 | 0.7223 | 0.7235 | | 0.4769 | 62.75 | 3200 | 0.5472 | 0.7271 | 0.7284 | | 0.4725 | 66.67 | 3400 | 0.5468 | 0.7231 | 0.7247 | | 0.4707 | 70.59 | 3600 | 0.5473 | 0.7304 | 0.7309 | | 0.4655 | 74.51 | 3800 | 0.5513 | 0.7182 | 0.7198 | | 0.4618 | 78.43 | 4000 | 0.5527 | 0.7220 | 0.7235 | | 0.4595 | 82.35 | 4200 | 0.5566 | 0.7179 | 0.7198 | | 0.4552 | 86.27 | 4400 | 0.5566 | 0.7222 | 0.7235 | | 0.458 | 90.2 | 4600 | 0.5572 | 0.7256 | 0.7284 | | 0.4487 | 94.12 | 4800 | 0.5584 | 0.7275 | 0.7284 | | 0.4455 | 98.04 | 5000 | 0.5558 | 0.7234 | 0.7259 | | 0.4448 | 101.96 | 5200 | 0.5549 | 0.7363 | 0.7370 | | 0.4422 | 105.88 | 5400 | 0.5603 | 0.7352 | 0.7358 | | 0.4409 | 109.8 | 5600 | 0.5538 | 0.7365 | 0.7370 | | 0.4368 | 113.73 | 5800 | 0.5603 | 0.7331 | 0.7346 | | 0.4361 | 117.65 | 6000 | 0.5619 | 0.7330 | 0.7333 | | 0.435 | 121.57 | 6200 | 0.5559 | 0.7341 | 0.7346 | | 0.4359 | 125.49 | 6400 | 0.5572 | 0.7353 | 0.7358 | | 0.4331 | 129.41 | 6600 | 0.5565 | 0.7329 | 0.7333 | | 0.4265 | 133.33 | 6800 | 0.5595 | 0.7336 | 0.7346 | | 0.4229 | 137.25 | 7000 | 0.5584 | 0.7325 | 0.7333 | | 0.4269 | 141.18 | 7200 | 0.5566 | 0.7337 | 0.7346 | | 0.4269 | 145.1 | 7400 | 0.5559 | 0.7403 | 0.7407 | | 0.4196 | 149.02 | 7600 | 0.5587 | 0.7291 | 0.7296 | | 0.424 | 152.94 | 7800 | 0.5528 | 0.7399 | 0.7407 | | 0.4209 | 156.86 | 8000 | 0.5550 | 0.7394 | 0.7407 | | 0.4165 | 160.78 | 8200 | 0.5611 | 0.7363 | 0.7370 | | 0.4225 | 164.71 | 8400 | 0.5544 | 0.7352 | 0.7358 | | 0.42 | 168.63 | 8600 | 0.5522 | 0.7396 | 0.7407 | | 0.423 | 172.55 | 8800 | 0.5522 | 0.7385 | 0.7395 | | 0.4151 | 176.47 | 9000 | 0.5579 | 0.7360 | 0.7370 | | 0.4165 | 180.39 | 9200 | 0.5567 | 0.7361 | 0.7370 | | 0.4214 | 184.31 | 9400 | 0.5547 | 0.7387 | 0.7395 | | 0.4189 | 188.24 | 9600 | 0.5555 | 0.7354 | 0.7358 | | 0.4162 | 192.16 | 9800 | 0.5562 | 0.7351 | 0.7358 | | 0.4175 | 196.08 | 10000 | 0.5562 | 0.7362 | 0.7370 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_0-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_0-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:07:22+00:00

null

peft

# GUE_EMP_H3K36me3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_EMP_H3K36me3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_EMP_H3K36me3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4544 - F1 Score: 0.8013 - Accuracy: 0.8013 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5415 | 0.92 | 200 | 0.5369 | 0.7565 | 0.7600 | | 0.4848 | 1.83 | 400 | 0.4846 | 0.7811 | 0.7830 | | 0.4678 | 2.75 | 600 | 0.4677 | 0.7976 | 0.7985 | | 0.4676 | 3.67 | 800 | 0.4715 | 0.7944 | 0.7953 | | 0.4499 | 4.59 | 1000 | 0.4752 | 0.7949 | 0.7967 | | 0.4422 | 5.5 | 1200 | 0.4607 | 0.7963 | 0.7982 | | 0.4387 | 6.42 | 1400 | 0.4631 | 0.8020 | 0.8030 | | 0.4329 | 7.34 | 1600 | 0.4669 | 0.7911 | 0.7936 | | 0.4217 | 8.26 | 1800 | 0.4607 | 0.7959 | 0.7973 | | 0.4214 | 9.17 | 2000 | 0.4591 | 0.7964 | 0.7985 | | 0.4128 | 10.09 | 2200 | 0.4746 | 0.7934 | 0.7959 | | 0.4078 | 11.01 | 2400 | 0.4535 | 0.8014 | 0.8025 | | 0.4002 | 11.93 | 2600 | 0.4550 | 0.8050 | 0.8050 | | 0.3953 | 12.84 | 2800 | 0.4655 | 0.7979 | 0.7996 | | 0.3854 | 13.76 | 3000 | 0.4848 | 0.7817 | 0.7858 | | 0.3825 | 14.68 | 3200 | 0.4719 | 0.8012 | 0.8030 | | 0.3812 | 15.6 | 3400 | 0.4811 | 0.7886 | 0.7916 | | 0.3745 | 16.51 | 3600 | 0.5227 | 0.7785 | 0.7838 | | 0.3679 | 17.43 | 3800 | 0.4944 | 0.7971 | 0.7987 | | 0.3607 | 18.35 | 4000 | 0.4810 | 0.7982 | 0.7990 | | 0.3586 | 19.27 | 4200 | 0.5204 | 0.7968 | 0.7993 | | 0.3532 | 20.18 | 4400 | 0.5151 | 0.7945 | 0.7970 | | 0.3457 | 21.1 | 4600 | 0.4889 | 0.7978 | 0.7990 | | 0.3435 | 22.02 | 4800 | 0.4771 | 0.7962 | 0.7973 | | 0.3379 | 22.94 | 5000 | 0.5006 | 0.7940 | 0.7959 | | 0.3304 | 23.85 | 5200 | 0.5199 | 0.7876 | 0.7904 | | 0.3279 | 24.77 | 5400 | 0.5228 | 0.7874 | 0.7896 | | 0.3238 | 25.69 | 5600 | 0.5171 | 0.7918 | 0.7939 | | 0.3179 | 26.61 | 5800 | 0.5140 | 0.7967 | 0.7987 | | 0.3127 | 27.52 | 6000 | 0.5424 | 0.7949 | 0.7970 | | 0.3124 | 28.44 | 6200 | 0.5512 | 0.7862 | 0.7893 | | 0.3046 | 29.36 | 6400 | 0.5430 | 0.7854 | 0.7878 | | 0.3039 | 30.28 | 6600 | 0.5411 | 0.7874 | 0.7899 | | 0.3009 | 31.19 | 6800 | 0.5338 | 0.7890 | 0.7901 | | 0.2949 | 32.11 | 7000 | 0.5609 | 0.7855 | 0.7881 | | 0.2938 | 33.03 | 7200 | 0.5325 | 0.7896 | 0.7910 | | 0.2878 | 33.94 | 7400 | 0.5406 | 0.7907 | 0.7924 | | 0.284 | 34.86 | 7600 | 0.5429 | 0.7931 | 0.7944 | | 0.2824 | 35.78 | 7800 | 0.5504 | 0.7892 | 0.7907 | | 0.2831 | 36.7 | 8000 | 0.5466 | 0.7912 | 0.7927 | | 0.2769 | 37.61 | 8200 | 0.5762 | 0.7871 | 0.7896 | | 0.2747 | 38.53 | 8400 | 0.5852 | 0.7925 | 0.7947 | | 0.2751 | 39.45 | 8600 | 0.5643 | 0.7889 | 0.7907 | | 0.2674 | 40.37 | 8800 | 0.5814 | 0.7896 | 0.7919 | | 0.2734 | 41.28 | 9000 | 0.5793 | 0.7860 | 0.7881 | | 0.271 | 42.2 | 9200 | 0.5699 | 0.7864 | 0.7881 | | 0.2653 | 43.12 | 9400 | 0.5777 | 0.7911 | 0.7927 | | 0.2709 | 44.04 | 9600 | 0.5768 | 0.7886 | 0.7907 | | 0.2665 | 44.95 | 9800 | 0.5772 | 0.7878 | 0.7899 | | 0.2623 | 45.87 | 10000 | 0.5772 | 0.7901 | 0.7919 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_EMP_H3K36me3-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_EMP_H3K36me3-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:07:32+00:00

null

peft

# GUE_mouse_0-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.9978 - F1 Score: 0.7109 - Accuracy: 0.7123 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.633 | 3.92 | 200 | 0.5934 | 0.6860 | 0.6864 | | 0.5677 | 7.84 | 400 | 0.5685 | 0.7048 | 0.7049 | | 0.5361 | 11.76 | 600 | 0.5605 | 0.7028 | 0.7037 | | 0.5105 | 15.69 | 800 | 0.5610 | 0.7119 | 0.7173 | | 0.4955 | 19.61 | 1000 | 0.5529 | 0.7156 | 0.7173 | | 0.4773 | 23.53 | 1200 | 0.5698 | 0.7154 | 0.7210 | | 0.4592 | 27.45 | 1400 | 0.5672 | 0.7154 | 0.7160 | | 0.4423 | 31.37 | 1600 | 0.5890 | 0.7197 | 0.7198 | | 0.432 | 35.29 | 1800 | 0.6112 | 0.7136 | 0.7136 | | 0.4143 | 39.22 | 2000 | 0.5904 | 0.7079 | 0.7099 | | 0.3994 | 43.14 | 2200 | 0.6026 | 0.7237 | 0.7247 | | 0.391 | 47.06 | 2400 | 0.6136 | 0.7210 | 0.7210 | | 0.3717 | 50.98 | 2600 | 0.6466 | 0.7134 | 0.7136 | | 0.3604 | 54.9 | 2800 | 0.6392 | 0.7119 | 0.7160 | | 0.3494 | 58.82 | 3000 | 0.6471 | 0.7185 | 0.7185 | | 0.3341 | 62.75 | 3200 | 0.6738 | 0.7052 | 0.7062 | | 0.3228 | 66.67 | 3400 | 0.6589 | 0.7185 | 0.7185 | | 0.3203 | 70.59 | 3600 | 0.7133 | 0.7173 | 0.7173 | | 0.3072 | 74.51 | 3800 | 0.6876 | 0.7073 | 0.7086 | | 0.2972 | 78.43 | 4000 | 0.7309 | 0.7121 | 0.7123 | | 0.2928 | 82.35 | 4200 | 0.7412 | 0.7223 | 0.7222 | | 0.2885 | 86.27 | 4400 | 0.7442 | 0.7106 | 0.7111 | | 0.2813 | 90.2 | 4600 | 0.7384 | 0.7156 | 0.7160 | | 0.2693 | 94.12 | 4800 | 0.7672 | 0.7169 | 0.7173 | | 0.2601 | 98.04 | 5000 | 0.7531 | 0.7219 | 0.7222 | | 0.258 | 101.96 | 5200 | 0.7722 | 0.7134 | 0.7136 | | 0.2492 | 105.88 | 5400 | 0.8086 | 0.7222 | 0.7222 | | 0.2447 | 109.8 | 5600 | 0.7982 | 0.7073 | 0.7074 | | 0.2375 | 113.73 | 5800 | 0.8282 | 0.7242 | 0.7247 | | 0.2341 | 117.65 | 6000 | 0.8704 | 0.7148 | 0.7148 | | 0.2313 | 121.57 | 6200 | 0.8546 | 0.7099 | 0.7099 | | 0.223 | 125.49 | 6400 | 0.8760 | 0.7222 | 0.7222 | | 0.222 | 129.41 | 6600 | 0.8714 | 0.7223 | 0.7222 | | 0.2156 | 133.33 | 6800 | 0.8522 | 0.7294 | 0.7296 | | 0.2116 | 137.25 | 7000 | 0.8889 | 0.7173 | 0.7173 | | 0.2097 | 141.18 | 7200 | 0.8858 | 0.7256 | 0.7259 | | 0.2085 | 145.1 | 7400 | 0.8835 | 0.7260 | 0.7259 | | 0.2022 | 149.02 | 7600 | 0.8739 | 0.7269 | 0.7272 | | 0.1994 | 152.94 | 7800 | 0.9251 | 0.7173 | 0.7173 | | 0.1981 | 156.86 | 8000 | 0.9022 | 0.7307 | 0.7309 | | 0.1976 | 160.78 | 8200 | 0.9101 | 0.7223 | 0.7222 | | 0.1966 | 164.71 | 8400 | 0.9368 | 0.7247 | 0.7247 | | 0.19 | 168.63 | 8600 | 0.9489 | 0.7222 | 0.7222 | | 0.1955 | 172.55 | 8800 | 0.9325 | 0.7173 | 0.7173 | | 0.1897 | 176.47 | 9000 | 0.9419 | 0.7222 | 0.7222 | | 0.1864 | 180.39 | 9200 | 0.9354 | 0.7246 | 0.7247 | | 0.1898 | 184.31 | 9400 | 0.9424 | 0.7259 | 0.7259 | | 0.1855 | 188.24 | 9600 | 0.9451 | 0.7284 | 0.7284 | | 0.1815 | 192.16 | 9800 | 0.9510 | 0.7222 | 0.7222 | | 0.1892 | 196.08 | 10000 | 0.9462 | 0.7246 | 0.7247 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_0-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_0-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:07:34+00:00

null

peft

# GUE_mouse_0-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_0) dataset. It achieves the following results on the evaluation set: - Loss: 1.1630 - F1 Score: 0.7037 - Accuracy: 0.7074 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.6177 | 3.92 | 200 | 0.5794 | 0.6873 | 0.6889 | | 0.5329 | 7.84 | 400 | 0.5571 | 0.7145 | 0.7148 | | 0.4923 | 11.76 | 600 | 0.5716 | 0.7201 | 0.7210 | | 0.4452 | 15.69 | 800 | 0.5815 | 0.7267 | 0.7296 | | 0.4103 | 19.61 | 1000 | 0.6009 | 0.7256 | 0.7272 | | 0.3683 | 23.53 | 1200 | 0.7288 | 0.7136 | 0.7136 | | 0.3379 | 27.45 | 1400 | 0.7234 | 0.7280 | 0.7284 | | 0.2982 | 31.37 | 1600 | 0.8047 | 0.7189 | 0.7198 | | 0.276 | 35.29 | 1800 | 0.8438 | 0.7198 | 0.7198 | | 0.2419 | 39.22 | 2000 | 0.8574 | 0.7049 | 0.7049 | | 0.2209 | 43.14 | 2200 | 0.8520 | 0.7148 | 0.7148 | | 0.1996 | 47.06 | 2400 | 0.9748 | 0.7197 | 0.7198 | | 0.1742 | 50.98 | 2600 | 0.9773 | 0.7121 | 0.7123 | | 0.1596 | 54.9 | 2800 | 0.9787 | 0.7433 | 0.7444 | | 0.1483 | 58.82 | 3000 | 1.0219 | 0.7260 | 0.7259 | | 0.1329 | 62.75 | 3200 | 1.0687 | 0.7286 | 0.7296 | | 0.1201 | 66.67 | 3400 | 1.0622 | 0.7197 | 0.7210 | | 0.1203 | 70.59 | 3600 | 1.1993 | 0.7194 | 0.7198 | | 0.1079 | 74.51 | 3800 | 1.1788 | 0.7153 | 0.7160 | | 0.0994 | 78.43 | 4000 | 1.2685 | 0.7269 | 0.7272 | | 0.0961 | 82.35 | 4200 | 1.2230 | 0.7172 | 0.7173 | | 0.0964 | 86.27 | 4400 | 1.2038 | 0.7209 | 0.7210 | | 0.0872 | 90.2 | 4600 | 1.2811 | 0.7297 | 0.7296 | | 0.0816 | 94.12 | 4800 | 1.3154 | 0.7234 | 0.7235 | | 0.0789 | 98.04 | 5000 | 1.3489 | 0.7210 | 0.7210 | | 0.0766 | 101.96 | 5200 | 1.3078 | 0.7272 | 0.7272 | | 0.0687 | 105.88 | 5400 | 1.3756 | 0.7197 | 0.7198 | | 0.0631 | 109.8 | 5600 | 1.4372 | 0.7233 | 0.7235 | | 0.0645 | 113.73 | 5800 | 1.4055 | 0.7260 | 0.7259 | | 0.0615 | 117.65 | 6000 | 1.3889 | 0.7223 | 0.7222 | | 0.0591 | 121.57 | 6200 | 1.4774 | 0.7180 | 0.7185 | | 0.0566 | 125.49 | 6400 | 1.5159 | 0.7195 | 0.7198 | | 0.0525 | 129.41 | 6600 | 1.5330 | 0.7172 | 0.7173 | | 0.053 | 133.33 | 6800 | 1.5570 | 0.7244 | 0.7247 | | 0.0528 | 137.25 | 7000 | 1.5276 | 0.7222 | 0.7222 | | 0.0487 | 141.18 | 7200 | 1.5118 | 0.7296 | 0.7296 | | 0.0471 | 145.1 | 7400 | 1.5333 | 0.7210 | 0.7210 | | 0.0479 | 149.02 | 7600 | 1.5198 | 0.7271 | 0.7272 | | 0.0431 | 152.94 | 7800 | 1.5453 | 0.7197 | 0.7198 | | 0.0442 | 156.86 | 8000 | 1.5638 | 0.7296 | 0.7296 | | 0.0426 | 160.78 | 8200 | 1.5832 | 0.7222 | 0.7222 | | 0.0392 | 164.71 | 8400 | 1.6342 | 0.7209 | 0.7210 | | 0.0373 | 168.63 | 8600 | 1.6430 | 0.7219 | 0.7222 | | 0.0388 | 172.55 | 8800 | 1.6083 | 0.7284 | 0.7284 | | 0.0365 | 176.47 | 9000 | 1.6100 | 0.7196 | 0.7198 | | 0.0368 | 180.39 | 9200 | 1.6320 | 0.7296 | 0.7296 | | 0.0388 | 184.31 | 9400 | 1.6367 | 0.7259 | 0.7259 | | 0.0381 | 188.24 | 9600 | 1.6066 | 0.7246 | 0.7247 | | 0.0333 | 192.16 | 9800 | 1.6421 | 0.7271 | 0.7272 | | 0.0348 | 196.08 | 10000 | 1.6420 | 0.7233 | 0.7235 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_0-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_0-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:08:18+00:00

null

peft

# GUE_mouse_1-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.2519 - F1 Score: 0.8867 - Accuracy: 0.8867 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4803 | 0.47 | 200 | 0.3522 | 0.8435 | 0.8437 | | 0.3667 | 0.95 | 400 | 0.3135 | 0.8613 | 0.8614 | | 0.3353 | 1.42 | 600 | 0.3008 | 0.8680 | 0.8681 | | 0.3373 | 1.9 | 800 | 0.2901 | 0.8708 | 0.8709 | | 0.3169 | 2.37 | 1000 | 0.2873 | 0.8730 | 0.8731 | | 0.3145 | 2.84 | 1200 | 0.2840 | 0.8760 | 0.8762 | | 0.3044 | 3.32 | 1400 | 0.2825 | 0.8752 | 0.8752 | | 0.3106 | 3.79 | 1600 | 0.2766 | 0.8777 | 0.8777 | | 0.3023 | 4.27 | 1800 | 0.2744 | 0.8825 | 0.8827 | | 0.2985 | 4.74 | 2000 | 0.2720 | 0.8822 | 0.8823 | | 0.298 | 5.21 | 2200 | 0.2778 | 0.8775 | 0.8780 | | 0.2964 | 5.69 | 2400 | 0.2721 | 0.8812 | 0.8812 | | 0.2887 | 6.16 | 2600 | 0.2656 | 0.8853 | 0.8854 | | 0.2872 | 6.64 | 2800 | 0.2630 | 0.8875 | 0.8876 | | 0.2908 | 7.11 | 3000 | 0.2635 | 0.8866 | 0.8866 | | 0.2861 | 7.58 | 3200 | 0.2734 | 0.8809 | 0.8809 | | 0.2832 | 8.06 | 3400 | 0.2589 | 0.8885 | 0.8887 | | 0.2781 | 8.53 | 3600 | 0.2621 | 0.8881 | 0.8881 | | 0.282 | 9.0 | 3800 | 0.2568 | 0.8895 | 0.8895 | | 0.275 | 9.48 | 4000 | 0.2567 | 0.8894 | 0.8895 | | 0.2776 | 9.95 | 4200 | 0.2528 | 0.8923 | 0.8924 | | 0.2707 | 10.43 | 4400 | 0.2533 | 0.8934 | 0.8934 | | 0.2728 | 10.9 | 4600 | 0.2537 | 0.8909 | 0.8909 | | 0.2639 | 11.37 | 4800 | 0.2552 | 0.8904 | 0.8904 | | 0.2747 | 11.85 | 5000 | 0.2487 | 0.8938 | 0.8938 | | 0.2663 | 12.32 | 5200 | 0.2543 | 0.8900 | 0.8900 | | 0.2672 | 12.8 | 5400 | 0.2518 | 0.8928 | 0.8928 | | 0.2726 | 13.27 | 5600 | 0.2460 | 0.8931 | 0.8931 | | 0.2636 | 13.74 | 5800 | 0.2459 | 0.8950 | 0.8950 | | 0.2654 | 14.22 | 6000 | 0.2490 | 0.8936 | 0.8936 | | 0.2609 | 14.69 | 6200 | 0.2465 | 0.8944 | 0.8944 | | 0.2652 | 15.17 | 6400 | 0.2537 | 0.8916 | 0.8916 | | 0.264 | 15.64 | 6600 | 0.2448 | 0.8956 | 0.8956 | | 0.2598 | 16.11 | 6800 | 0.2424 | 0.8944 | 0.8944 | | 0.2616 | 16.59 | 7000 | 0.2428 | 0.8941 | 0.8941 | | 0.2581 | 17.06 | 7200 | 0.2438 | 0.8953 | 0.8953 | | 0.263 | 17.54 | 7400 | 0.2485 | 0.8929 | 0.8930 | | 0.2603 | 18.01 | 7600 | 0.2417 | 0.8962 | 0.8962 | | 0.254 | 18.48 | 7800 | 0.2438 | 0.8971 | 0.8971 | | 0.262 | 18.96 | 8000 | 0.2416 | 0.8959 | 0.8959 | | 0.2571 | 19.43 | 8200 | 0.2421 | 0.8956 | 0.8956 | | 0.2592 | 19.91 | 8400 | 0.2406 | 0.8950 | 0.8950 | | 0.2624 | 20.38 | 8600 | 0.2420 | 0.8959 | 0.8959 | | 0.2557 | 20.85 | 8800 | 0.2401 | 0.8947 | 0.8947 | | 0.2553 | 21.33 | 9000 | 0.2421 | 0.8961 | 0.8961 | | 0.2558 | 21.8 | 9200 | 0.2433 | 0.8962 | 0.8962 | | 0.2579 | 22.27 | 9400 | 0.2421 | 0.8962 | 0.8962 | | 0.252 | 22.75 | 9600 | 0.2411 | 0.8965 | 0.8965 | | 0.2553 | 23.22 | 9800 | 0.2416 | 0.8962 | 0.8962 | | 0.2589 | 23.7 | 10000 | 0.2420 | 0.8958 | 0.8958 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_1-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_1-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:08:45+00:00

text-generation

null

## Exllama v2 Quantizations of NPC-LLM-3_8B Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</a> for quantization. <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b> Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions. Conversion was done using the default calibration dataset. Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6. Original model: https://huggingface.co/Gigax/NPC-LLM-3_8B <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/8_0">8.0 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/6_5">6.5 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/5_0">5.0 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/4_25">4.25 bits per weight</a> <a href="https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2/tree/3_5">3.5 bits per weight</a> ## Download instructions With git: ```shell git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/NPC-LLM-3_8B-exl2 ``` With huggingface hub (credit to TheBloke for instructions): ```shell pip3 install huggingface-hub ``` To download the `main` (only useful if you only care about measurement.json) branch to a folder called `NPC-LLM-3_8B-exl2`: ```shell mkdir NPC-LLM-3_8B-exl2 huggingface-cli download bartowski/NPC-LLM-3_8B-exl2 --local-dir NPC-LLM-3_8B-exl2 --local-dir-use-symlinks False ``` To download from a different branch, add the `--revision` parameter: Linux: ```shell mkdir NPC-LLM-3_8B-exl2-6_5 huggingface-cli download bartowski/NPC-LLM-3_8B-exl2 --revision 6_5 --local-dir NPC-LLM-3_8B-exl2-6_5 --local-dir-use-symlinks False ``` Windows (which apparently doesn't like _ in folders sometimes?): ```shell mkdir NPC-LLM-3_8B-exl2-6.5 huggingface-cli download bartowski/NPC-LLM-3_8B-exl2 --revision 6_5 --local-dir NPC-LLM-3_8B-exl2-6.5 --local-dir-use-symlinks False ```

{"language": ["en"], "license": "mit", "quantized_by": "bartowski", "pipeline_tag": "text-generation"}

bartowski/NPC-LLM-3_8B-exl2

null

[ "text-generation", "en", "license:mit", "region:us" ]

null

2024-04-29T23:09:15+00:00

null

{"license": "openrail"}

martinvdv05/FNaF-SB

null

[ "license:openrail", "region:us" ]

null

2024-04-29T23:09:51+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

franciscobdl/EstigiaxTinyLlama

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T23:14:24+00:00

text-generation

transformers

# 0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2 This model is a fine-tuned version of [ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1](https://huggingface.co/ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1) on the updated and the original datasets. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - num_devices: 8 - gradient_accumulation_steps: 4 - total_train_batch_size: 256 - total_eval_batch_size: 64 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 1 ### Training results ### Framework versions - Transformers 4.36.2 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.15.2

{"license": "mit", "tags": ["alignment-handbook", "generated_from_trainer", "trl", "dpo", "generated_from_trainer"], "datasets": ["updated", "original"], "base_model": "ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1", "model-index": [{"name": "0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2", "results": []}]}

ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_2

null

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZhang/0.01_4iters_bs256_nodpo_full6w_userresponse_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T23:14:50+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

Shaleen123/llama3-code-4bit

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

null

2024-04-29T23:15:32+00:00

null

peft

# GUE_mouse_1-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.2345 - F1 Score: 0.8950 - Accuracy: 0.8950 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4305 | 0.47 | 200 | 0.3166 | 0.8587 | 0.8587 | | 0.333 | 0.95 | 400 | 0.2954 | 0.8715 | 0.8715 | | 0.3115 | 1.42 | 600 | 0.2770 | 0.8795 | 0.8796 | | 0.3138 | 1.9 | 800 | 0.2689 | 0.8823 | 0.8824 | | 0.2915 | 2.37 | 1000 | 0.2645 | 0.8836 | 0.8836 | | 0.2865 | 2.84 | 1200 | 0.2562 | 0.8895 | 0.8895 | | 0.2717 | 3.32 | 1400 | 0.2552 | 0.8886 | 0.8887 | | 0.2773 | 3.79 | 1600 | 0.2578 | 0.8873 | 0.8873 | | 0.2664 | 4.27 | 1800 | 0.2410 | 0.8973 | 0.8973 | | 0.2631 | 4.74 | 2000 | 0.2383 | 0.8956 | 0.8956 | | 0.2598 | 5.21 | 2200 | 0.2403 | 0.8946 | 0.8949 | | 0.2573 | 5.69 | 2400 | 0.2484 | 0.8910 | 0.8910 | | 0.2487 | 6.16 | 2600 | 0.2318 | 0.9008 | 0.9008 | | 0.2484 | 6.64 | 2800 | 0.2346 | 0.8992 | 0.8992 | | 0.2522 | 7.11 | 3000 | 0.2354 | 0.8978 | 0.8979 | | 0.2451 | 7.58 | 3200 | 0.2470 | 0.8949 | 0.8949 | | 0.2448 | 8.06 | 3400 | 0.2279 | 0.9005 | 0.9005 | | 0.2396 | 8.53 | 3600 | 0.2414 | 0.8962 | 0.8962 | | 0.245 | 9.0 | 3800 | 0.2314 | 0.8996 | 0.8996 | | 0.2386 | 9.48 | 4000 | 0.2270 | 0.8998 | 0.8998 | | 0.2397 | 9.95 | 4200 | 0.2290 | 0.8993 | 0.8993 | | 0.2334 | 10.43 | 4400 | 0.2300 | 0.9017 | 0.9017 | | 0.2339 | 10.9 | 4600 | 0.2333 | 0.8989 | 0.8989 | | 0.2282 | 11.37 | 4800 | 0.2327 | 0.9009 | 0.9010 | | 0.2385 | 11.85 | 5000 | 0.2271 | 0.9021 | 0.9021 | | 0.2322 | 12.32 | 5200 | 0.2314 | 0.8987 | 0.8987 | | 0.2331 | 12.8 | 5400 | 0.2334 | 0.8993 | 0.8993 | | 0.2331 | 13.27 | 5600 | 0.2239 | 0.9008 | 0.9008 | | 0.2281 | 13.74 | 5800 | 0.2244 | 0.9021 | 0.9021 | | 0.2304 | 14.22 | 6000 | 0.2344 | 0.8996 | 0.8996 | | 0.2264 | 14.69 | 6200 | 0.2260 | 0.9033 | 0.9033 | | 0.2287 | 15.17 | 6400 | 0.2348 | 0.8989 | 0.8989 | | 0.2287 | 15.64 | 6600 | 0.2262 | 0.9002 | 0.9002 | | 0.2223 | 16.11 | 6800 | 0.2227 | 0.9018 | 0.9019 | | 0.2241 | 16.59 | 7000 | 0.2269 | 0.9018 | 0.9019 | | 0.2261 | 17.06 | 7200 | 0.2250 | 0.9023 | 0.9023 | | 0.2244 | 17.54 | 7400 | 0.2284 | 0.9016 | 0.9016 | | 0.2244 | 18.01 | 7600 | 0.2225 | 0.9023 | 0.9023 | | 0.2187 | 18.48 | 7800 | 0.2273 | 0.9017 | 0.9017 | | 0.2256 | 18.96 | 8000 | 0.2212 | 0.9030 | 0.9030 | | 0.2214 | 19.43 | 8200 | 0.2252 | 0.9024 | 0.9024 | | 0.2247 | 19.91 | 8400 | 0.2218 | 0.9030 | 0.9030 | | 0.2237 | 20.38 | 8600 | 0.2243 | 0.9020 | 0.9020 | | 0.2217 | 20.85 | 8800 | 0.2215 | 0.9041 | 0.9041 | | 0.2185 | 21.33 | 9000 | 0.2262 | 0.9015 | 0.9016 | | 0.2178 | 21.8 | 9200 | 0.2272 | 0.9010 | 0.9010 | | 0.2216 | 22.27 | 9400 | 0.2249 | 0.9023 | 0.9023 | | 0.2157 | 22.75 | 9600 | 0.2225 | 0.9033 | 0.9033 | | 0.2174 | 23.22 | 9800 | 0.2245 | 0.9027 | 0.9027 | | 0.2222 | 23.7 | 10000 | 0.2247 | 0.9016 | 0.9016 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_1-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_1-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:17:46+00:00

null

peft

# GUE_mouse_1-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.2318 - F1 Score: 0.9017 - Accuracy: 0.9017 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.4117 | 0.47 | 200 | 0.3138 | 0.8630 | 0.8632 | | 0.3169 | 0.95 | 400 | 0.2770 | 0.8805 | 0.8805 | | 0.2909 | 1.42 | 600 | 0.2570 | 0.8890 | 0.8891 | | 0.2872 | 1.9 | 800 | 0.2507 | 0.8895 | 0.8895 | | 0.2663 | 2.37 | 1000 | 0.2452 | 0.8930 | 0.8930 | | 0.2604 | 2.84 | 1200 | 0.2369 | 0.8961 | 0.8961 | | 0.2471 | 3.32 | 1400 | 0.2436 | 0.8959 | 0.8959 | | 0.2551 | 3.79 | 1600 | 0.2381 | 0.8980 | 0.8980 | | 0.2457 | 4.27 | 1800 | 0.2311 | 0.9013 | 0.9013 | | 0.2457 | 4.74 | 2000 | 0.2325 | 0.8979 | 0.8980 | | 0.241 | 5.21 | 2200 | 0.2374 | 0.8974 | 0.8977 | | 0.2418 | 5.69 | 2400 | 0.2369 | 0.8972 | 0.8973 | | 0.2321 | 6.16 | 2600 | 0.2238 | 0.9021 | 0.9021 | | 0.2322 | 6.64 | 2800 | 0.2251 | 0.9036 | 0.9036 | | 0.2345 | 7.11 | 3000 | 0.2356 | 0.8987 | 0.8987 | | 0.2276 | 7.58 | 3200 | 0.2362 | 0.8975 | 0.8976 | | 0.2289 | 8.06 | 3400 | 0.2231 | 0.9024 | 0.9024 | | 0.2203 | 8.53 | 3600 | 0.2283 | 0.9007 | 0.9007 | | 0.2273 | 9.0 | 3800 | 0.2271 | 0.9041 | 0.9041 | | 0.2192 | 9.48 | 4000 | 0.2194 | 0.9049 | 0.9050 | | 0.2205 | 9.95 | 4200 | 0.2202 | 0.9035 | 0.9035 | | 0.2139 | 10.43 | 4400 | 0.2266 | 0.9020 | 0.9020 | | 0.2155 | 10.9 | 4600 | 0.2237 | 0.9029 | 0.9029 | | 0.2068 | 11.37 | 4800 | 0.2238 | 0.9023 | 0.9023 | | 0.2198 | 11.85 | 5000 | 0.2209 | 0.9050 | 0.9050 | | 0.212 | 12.32 | 5200 | 0.2236 | 0.9024 | 0.9024 | | 0.2112 | 12.8 | 5400 | 0.2301 | 0.9020 | 0.9020 | | 0.2099 | 13.27 | 5600 | 0.2196 | 0.9039 | 0.9039 | | 0.2048 | 13.74 | 5800 | 0.2204 | 0.9027 | 0.9027 | | 0.2068 | 14.22 | 6000 | 0.2324 | 0.8996 | 0.8996 | | 0.2049 | 14.69 | 6200 | 0.2193 | 0.9064 | 0.9064 | | 0.2065 | 15.17 | 6400 | 0.2255 | 0.9026 | 0.9026 | | 0.2041 | 15.64 | 6600 | 0.2215 | 0.9050 | 0.9050 | | 0.1999 | 16.11 | 6800 | 0.2212 | 0.9067 | 0.9067 | | 0.1997 | 16.59 | 7000 | 0.2217 | 0.9041 | 0.9041 | | 0.2026 | 17.06 | 7200 | 0.2225 | 0.9048 | 0.9048 | | 0.1981 | 17.54 | 7400 | 0.2236 | 0.9050 | 0.9050 | | 0.1987 | 18.01 | 7600 | 0.2184 | 0.9051 | 0.9051 | | 0.1928 | 18.48 | 7800 | 0.2236 | 0.9027 | 0.9027 | | 0.1982 | 18.96 | 8000 | 0.2169 | 0.9061 | 0.9062 | | 0.1921 | 19.43 | 8200 | 0.2213 | 0.9060 | 0.9060 | | 0.1988 | 19.91 | 8400 | 0.2193 | 0.9063 | 0.9063 | | 0.1946 | 20.38 | 8600 | 0.2241 | 0.9050 | 0.9050 | | 0.1945 | 20.85 | 8800 | 0.2202 | 0.9042 | 0.9042 | | 0.1901 | 21.33 | 9000 | 0.2246 | 0.9035 | 0.9035 | | 0.1891 | 21.8 | 9200 | 0.2254 | 0.9038 | 0.9038 | | 0.1912 | 22.27 | 9400 | 0.2207 | 0.9047 | 0.9047 | | 0.1873 | 22.75 | 9600 | 0.2218 | 0.9041 | 0.9041 | | 0.1879 | 23.22 | 9800 | 0.2225 | 0.9045 | 0.9045 | | 0.1929 | 23.7 | 10000 | 0.2227 | 0.9044 | 0.9044 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_1-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_1-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:17:52+00:00

null

peft

# GUE_mouse_4-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.5700 - F1 Score: 0.6988 - Accuracy: 0.6989 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6556 | 1.69 | 200 | 0.6362 | 0.6178 | 0.6235 | | 0.6313 | 3.39 | 400 | 0.6152 | 0.6557 | 0.6564 | | 0.6176 | 5.08 | 600 | 0.6042 | 0.6498 | 0.6511 | | 0.6046 | 6.78 | 800 | 0.5874 | 0.6737 | 0.6739 | | 0.595 | 8.47 | 1000 | 0.5771 | 0.6888 | 0.6888 | | 0.5855 | 10.17 | 1200 | 0.5765 | 0.6882 | 0.6888 | | 0.5789 | 11.86 | 1400 | 0.5677 | 0.6989 | 0.6989 | | 0.5756 | 13.56 | 1600 | 0.5644 | 0.6990 | 0.6989 | | 0.5721 | 15.25 | 1800 | 0.5621 | 0.7069 | 0.7074 | | 0.5682 | 16.95 | 2000 | 0.5675 | 0.6970 | 0.6989 | | 0.5671 | 18.64 | 2200 | 0.5605 | 0.7053 | 0.7058 | | 0.5625 | 20.34 | 2400 | 0.5544 | 0.7128 | 0.7127 | | 0.5624 | 22.03 | 2600 | 0.5772 | 0.6856 | 0.6904 | | 0.5555 | 23.73 | 2800 | 0.5542 | 0.7122 | 0.7122 | | 0.555 | 25.42 | 3000 | 0.5544 | 0.7175 | 0.7175 | | 0.5525 | 27.12 | 3200 | 0.5617 | 0.7028 | 0.7047 | | 0.5494 | 28.81 | 3400 | 0.5533 | 0.7141 | 0.7143 | | 0.5464 | 30.51 | 3600 | 0.5561 | 0.7165 | 0.7164 | | 0.5487 | 32.2 | 3800 | 0.5546 | 0.7123 | 0.7127 | | 0.5452 | 33.9 | 4000 | 0.5589 | 0.7040 | 0.7053 | | 0.5421 | 35.59 | 4200 | 0.5630 | 0.7076 | 0.7090 | | 0.5438 | 37.29 | 4400 | 0.5570 | 0.7118 | 0.7127 | | 0.5432 | 38.98 | 4600 | 0.5532 | 0.7146 | 0.7148 | | 0.539 | 40.68 | 4800 | 0.5671 | 0.6973 | 0.6999 | | 0.5387 | 42.37 | 5000 | 0.5582 | 0.7127 | 0.7132 | | 0.5412 | 44.07 | 5200 | 0.5535 | 0.7179 | 0.7180 | | 0.5391 | 45.76 | 5400 | 0.5527 | 0.7105 | 0.7106 | | 0.534 | 47.46 | 5600 | 0.5526 | 0.7106 | 0.7106 | | 0.5347 | 49.15 | 5800 | 0.5577 | 0.7122 | 0.7132 | | 0.5351 | 50.85 | 6000 | 0.5569 | 0.7097 | 0.7106 | | 0.5332 | 52.54 | 6200 | 0.5517 | 0.7112 | 0.7111 | | 0.528 | 54.24 | 6400 | 0.5515 | 0.7132 | 0.7132 | | 0.5348 | 55.93 | 6600 | 0.5490 | 0.7149 | 0.7148 | | 0.5287 | 57.63 | 6800 | 0.5500 | 0.7192 | 0.7191 | | 0.5285 | 59.32 | 7000 | 0.5563 | 0.7120 | 0.7127 | | 0.5287 | 61.02 | 7200 | 0.5522 | 0.7137 | 0.7138 | | 0.5309 | 62.71 | 7400 | 0.5497 | 0.7159 | 0.7159 | | 0.528 | 64.41 | 7600 | 0.5514 | 0.7111 | 0.7111 | | 0.5321 | 66.1 | 7800 | 0.5503 | 0.7143 | 0.7143 | | 0.5279 | 67.8 | 8000 | 0.5502 | 0.7148 | 0.7148 | | 0.5282 | 69.49 | 8200 | 0.5491 | 0.7159 | 0.7159 | | 0.5267 | 71.19 | 8400 | 0.5513 | 0.7148 | 0.7148 | | 0.5247 | 72.88 | 8600 | 0.5498 | 0.7138 | 0.7138 | | 0.5226 | 74.58 | 8800 | 0.5513 | 0.7163 | 0.7164 | | 0.5262 | 76.27 | 9000 | 0.5518 | 0.7158 | 0.7159 | | 0.5232 | 77.97 | 9200 | 0.5512 | 0.7158 | 0.7159 | | 0.5215 | 79.66 | 9400 | 0.5506 | 0.7154 | 0.7153 | | 0.5269 | 81.36 | 9600 | 0.5503 | 0.7143 | 0.7143 | | 0.5241 | 83.05 | 9800 | 0.5504 | 0.7148 | 0.7148 | | 0.5238 | 84.75 | 10000 | 0.5508 | 0.7126 | 0.7127 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_4-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_4-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:18:40+00:00

null

{"license": "apache-2.0"}

razqr1911/trained1

null

[ "safetensors", "license:apache-2.0", "region:us" ]

null

2024-04-29T23:18:47+00:00

null

{}

josiahgottfried/amtibot_pegasus_pbt_1

null

[ "region:us" ]

null

2024-04-29T23:19:19+00:00

null

peft

# GUE_mouse_4-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.5910 - F1 Score: 0.7116 - Accuracy: 0.7116 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6436 | 1.69 | 200 | 0.6117 | 0.6527 | 0.6543 | | 0.6093 | 3.39 | 400 | 0.6026 | 0.6510 | 0.6591 | | 0.5868 | 5.08 | 600 | 0.5730 | 0.6979 | 0.6978 | | 0.572 | 6.78 | 800 | 0.5650 | 0.7006 | 0.7010 | | 0.5645 | 8.47 | 1000 | 0.5782 | 0.6926 | 0.6962 | | 0.5518 | 10.17 | 1200 | 0.5679 | 0.7036 | 0.7037 | | 0.5462 | 11.86 | 1400 | 0.5613 | 0.7027 | 0.7026 | | 0.5379 | 13.56 | 1600 | 0.5660 | 0.7046 | 0.7047 | | 0.5352 | 15.25 | 1800 | 0.5611 | 0.7085 | 0.7090 | | 0.5297 | 16.95 | 2000 | 0.5727 | 0.6963 | 0.6989 | | 0.5244 | 18.64 | 2200 | 0.5860 | 0.6914 | 0.6946 | | 0.5203 | 20.34 | 2400 | 0.5614 | 0.7110 | 0.7111 | | 0.5162 | 22.03 | 2600 | 0.5711 | 0.7024 | 0.7037 | | 0.5072 | 23.73 | 2800 | 0.5593 | 0.7111 | 0.7111 | | 0.5028 | 25.42 | 3000 | 0.5651 | 0.7133 | 0.7138 | | 0.4981 | 27.12 | 3200 | 0.5684 | 0.7101 | 0.7100 | | 0.4913 | 28.81 | 3400 | 0.5699 | 0.7090 | 0.7090 | | 0.4847 | 30.51 | 3600 | 0.5746 | 0.7106 | 0.7106 | | 0.4872 | 32.2 | 3800 | 0.5799 | 0.7156 | 0.7159 | | 0.4819 | 33.9 | 4000 | 0.5789 | 0.7079 | 0.7079 | | 0.4739 | 35.59 | 4200 | 0.5968 | 0.7004 | 0.7010 | | 0.4774 | 37.29 | 4400 | 0.5751 | 0.7128 | 0.7127 | | 0.4731 | 38.98 | 4600 | 0.5734 | 0.7175 | 0.7175 | | 0.4652 | 40.68 | 4800 | 0.6021 | 0.7014 | 0.7021 | | 0.4623 | 42.37 | 5000 | 0.5976 | 0.7149 | 0.7148 | | 0.4604 | 44.07 | 5200 | 0.6079 | 0.7095 | 0.7095 | | 0.4607 | 45.76 | 5400 | 0.5911 | 0.7133 | 0.7132 | | 0.4509 | 47.46 | 5600 | 0.6176 | 0.7146 | 0.7148 | | 0.4536 | 49.15 | 5800 | 0.6003 | 0.7096 | 0.7095 | | 0.4478 | 50.85 | 6000 | 0.5923 | 0.7123 | 0.7122 | | 0.445 | 52.54 | 6200 | 0.6070 | 0.7148 | 0.7148 | | 0.4381 | 54.24 | 6400 | 0.6022 | 0.7139 | 0.7138 | | 0.4456 | 55.93 | 6600 | 0.5996 | 0.7096 | 0.7095 | | 0.4369 | 57.63 | 6800 | 0.6064 | 0.7139 | 0.7138 | | 0.4353 | 59.32 | 7000 | 0.6163 | 0.7082 | 0.7084 | | 0.4355 | 61.02 | 7200 | 0.6118 | 0.7106 | 0.7106 | | 0.4355 | 62.71 | 7400 | 0.6045 | 0.7143 | 0.7143 | | 0.4311 | 64.41 | 7600 | 0.6077 | 0.7038 | 0.7037 | | 0.434 | 66.1 | 7800 | 0.6098 | 0.7064 | 0.7063 | | 0.4284 | 67.8 | 8000 | 0.6108 | 0.7075 | 0.7074 | | 0.4268 | 69.49 | 8200 | 0.6117 | 0.7038 | 0.7037 | | 0.427 | 71.19 | 8400 | 0.6174 | 0.7084 | 0.7084 | | 0.4242 | 72.88 | 8600 | 0.6175 | 0.7101 | 0.7100 | | 0.4192 | 74.58 | 8800 | 0.6206 | 0.7090 | 0.7090 | | 0.4201 | 76.27 | 9000 | 0.6232 | 0.7038 | 0.7037 | | 0.4184 | 77.97 | 9200 | 0.6243 | 0.7038 | 0.7037 | | 0.4182 | 79.66 | 9400 | 0.6232 | 0.7068 | 0.7069 | | 0.4214 | 81.36 | 9600 | 0.6223 | 0.7064 | 0.7063 | | 0.4217 | 83.05 | 9800 | 0.6208 | 0.7048 | 0.7047 | | 0.4147 | 84.75 | 10000 | 0.6218 | 0.7053 | 0.7053 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_4-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_4-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:20:03+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"license": "apache-2.0", "library_name": "transformers"}

Shaleen123/llama3-code-8bit

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]

null

2024-04-29T23:20:15+00:00

null

peft

# Model Card for Model ID  ## Model Details ### Model Description  - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.10.0

{"library_name": "peft", "base_model": "mistralai/Mistral-7B-Instruct-v0.1"}

Akshay24/mistral7b_finetuned_tijori

null

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:mistralai/Mistral-7B-Instruct-v0.1", "region:us" ]

null

2024-04-29T23:21:03+00:00

text-generation

gguf

# Megac4ai-command-r-plus-gguf These are quantized GGUF versions of [nitky/Megac4ai-command-r-plus](https://huggingface.co/nitky/Megac4ai-command-r-plus). Please check the original model for license and more details. ## Results for non-English languages (Japanese) | Model | Output Quality | Notes | |-------|----------------|-------| | Megac4ai-command-r-plus-IQ3_XS.gguf | Poor | | | Megac4ai-command-r-plus-IQ4_XS.gguf | Average | | | Megac4ai-command-r-plus-Q4_K_M.gguf | Good | recommended | | Megac4ai-command-r-plus-Q5_K_M.gguf | Good | | | Megac4ai-command-r-plus-Q6_K.gguf | Excellent | recommended | | Megac4ai-command-r-plus-Q8_0.gguf | Excellent | |

{"language": ["en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar"], "license": "cc-by-nc-4.0", "library_name": "gguf", "tags": ["mergekit", "merge"], "base_model": ["CohereForAI/c4ai-command-r-plus"], "pipeline_tag": "text-generation"}

nitky/Megac4ai-command-r-plus-gguf

null

[ "gguf", "mergekit", "merge", "text-generation", "en", "fr", "de", "es", "it", "pt", "ja", "ko", "zh", "ar", "base_model:CohereForAI/c4ai-command-r-plus", "license:cc-by-nc-4.0", "region:us" ]

null

2024-04-29T23:22:35+00:00

null

peft

# GUE_mouse_4-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_4](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_4) dataset. It achieves the following results on the evaluation set: - Loss: 0.6491 - F1 Score: 0.7024 - Accuracy: 0.7026 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.6347 | 1.69 | 200 | 0.5944 | 0.6853 | 0.6872 | | 0.5914 | 3.39 | 400 | 0.5758 | 0.6823 | 0.6835 | | 0.5678 | 5.08 | 600 | 0.5639 | 0.7058 | 0.7063 | | 0.5493 | 6.78 | 800 | 0.5648 | 0.6908 | 0.6930 | | 0.5397 | 8.47 | 1000 | 0.5903 | 0.6786 | 0.6840 | | 0.5174 | 10.17 | 1200 | 0.5686 | 0.7030 | 0.7031 | | 0.5081 | 11.86 | 1400 | 0.5634 | 0.7069 | 0.7069 | | 0.4907 | 13.56 | 1600 | 0.5732 | 0.7088 | 0.7090 | | 0.4796 | 15.25 | 1800 | 0.5734 | 0.7091 | 0.7090 | | 0.4654 | 16.95 | 2000 | 0.5799 | 0.6984 | 0.6994 | | 0.4539 | 18.64 | 2200 | 0.5960 | 0.7091 | 0.7100 | | 0.4417 | 20.34 | 2400 | 0.5979 | 0.7099 | 0.7100 | | 0.4265 | 22.03 | 2600 | 0.6262 | 0.7141 | 0.7148 | | 0.413 | 23.73 | 2800 | 0.6192 | 0.7169 | 0.7169 | | 0.4037 | 25.42 | 3000 | 0.6166 | 0.7123 | 0.7143 | | 0.3919 | 27.12 | 3200 | 0.6586 | 0.7169 | 0.7169 | | 0.3788 | 28.81 | 3400 | 0.6822 | 0.7117 | 0.7116 | | 0.3654 | 30.51 | 3600 | 0.6812 | 0.7043 | 0.7042 | | 0.3593 | 32.2 | 3800 | 0.7320 | 0.6999 | 0.6999 | | 0.3521 | 33.9 | 4000 | 0.7206 | 0.7081 | 0.7084 | | 0.3371 | 35.59 | 4200 | 0.7422 | 0.7042 | 0.7042 | | 0.3343 | 37.29 | 4400 | 0.7608 | 0.7135 | 0.7143 | | 0.325 | 38.98 | 4600 | 0.7313 | 0.7006 | 0.7005 | | 0.3108 | 40.68 | 4800 | 0.8242 | 0.7102 | 0.7111 | | 0.3039 | 42.37 | 5000 | 0.7951 | 0.7101 | 0.7100 | | 0.298 | 44.07 | 5200 | 0.8027 | 0.7073 | 0.7074 | | 0.2907 | 45.76 | 5400 | 0.8170 | 0.7106 | 0.7106 | | 0.2814 | 47.46 | 5600 | 0.8783 | 0.7108 | 0.7111 | | 0.279 | 49.15 | 5800 | 0.8531 | 0.7032 | 0.7031 | | 0.2682 | 50.85 | 6000 | 0.8655 | 0.6935 | 0.6936 | | 0.2638 | 52.54 | 6200 | 0.8895 | 0.7065 | 0.7069 | | 0.2617 | 54.24 | 6400 | 0.8833 | 0.7026 | 0.7026 | | 0.2607 | 55.93 | 6600 | 0.9108 | 0.7068 | 0.7069 | | 0.2497 | 57.63 | 6800 | 0.9018 | 0.7032 | 0.7031 | | 0.2518 | 59.32 | 7000 | 0.9166 | 0.7011 | 0.7010 | | 0.2444 | 61.02 | 7200 | 0.9175 | 0.6969 | 0.6968 | | 0.2427 | 62.71 | 7400 | 0.9294 | 0.7014 | 0.7021 | | 0.2342 | 64.41 | 7600 | 0.9125 | 0.7000 | 0.7005 | | 0.2369 | 66.1 | 7800 | 0.9295 | 0.7013 | 0.7015 | | 0.2257 | 67.8 | 8000 | 0.9363 | 0.6979 | 0.6978 | | 0.2262 | 69.49 | 8200 | 0.9430 | 0.7040 | 0.7042 | | 0.2225 | 71.19 | 8400 | 0.9627 | 0.6944 | 0.6952 | | 0.2198 | 72.88 | 8600 | 0.9913 | 0.7027 | 0.7031 | | 0.2147 | 74.58 | 8800 | 0.9746 | 0.7008 | 0.7015 | | 0.2155 | 76.27 | 9000 | 0.9829 | 0.7052 | 0.7053 | | 0.2148 | 77.97 | 9200 | 0.9758 | 0.7068 | 0.7069 | | 0.2141 | 79.66 | 9400 | 0.9774 | 0.6985 | 0.6989 | | 0.215 | 81.36 | 9600 | 0.9752 | 0.7052 | 0.7053 | | 0.2111 | 83.05 | 9800 | 0.9817 | 0.7041 | 0.7042 | | 0.2071 | 84.75 | 10000 | 0.9847 | 0.7019 | 0.7021 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_4-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_4-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:23:23+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

cilantro9246/q95707u

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T23:23:27+00:00

null

peft

# GUE_mouse_3-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.4306 - F1 Score: 0.8158 - Accuracy: 0.8159 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5969 | 13.33 | 200 | 0.5095 | 0.7362 | 0.7364 | | 0.4907 | 26.67 | 400 | 0.4640 | 0.7696 | 0.7699 | | 0.3987 | 40.0 | 600 | 0.4348 | 0.8196 | 0.8201 | | 0.3349 | 53.33 | 800 | 0.4285 | 0.8282 | 0.8285 | | 0.301 | 66.67 | 1000 | 0.4091 | 0.8365 | 0.8368 | | 0.2727 | 80.0 | 1200 | 0.4314 | 0.8117 | 0.8117 | | 0.2517 | 93.33 | 1400 | 0.4056 | 0.8324 | 0.8326 | | 0.2328 | 106.67 | 1600 | 0.4287 | 0.8283 | 0.8285 | | 0.2151 | 120.0 | 1800 | 0.4352 | 0.8362 | 0.8368 | | 0.2034 | 133.33 | 2000 | 0.4598 | 0.8201 | 0.8201 | | 0.1953 | 146.67 | 2200 | 0.4749 | 0.8235 | 0.8243 | | 0.1799 | 160.0 | 2400 | 0.4859 | 0.8200 | 0.8201 | | 0.1712 | 173.33 | 2600 | 0.5180 | 0.8158 | 0.8159 | | 0.1635 | 186.67 | 2800 | 0.5094 | 0.8197 | 0.8201 | | 0.1573 | 200.0 | 3000 | 0.5249 | 0.8112 | 0.8117 | | 0.1504 | 213.33 | 3200 | 0.5275 | 0.8201 | 0.8201 | | 0.1409 | 226.67 | 3400 | 0.5598 | 0.8116 | 0.8117 | | 0.1362 | 240.0 | 3600 | 0.5883 | 0.8117 | 0.8117 | | 0.1333 | 253.33 | 3800 | 0.5897 | 0.8116 | 0.8117 | | 0.1271 | 266.67 | 4000 | 0.5970 | 0.8032 | 0.8033 | | 0.1185 | 280.0 | 4200 | 0.6158 | 0.8159 | 0.8159 | | 0.1194 | 293.33 | 4400 | 0.6234 | 0.8155 | 0.8159 | | 0.1168 | 306.67 | 4600 | 0.6237 | 0.8032 | 0.8033 | | 0.1139 | 320.0 | 4800 | 0.6394 | 0.8156 | 0.8159 | | 0.1085 | 333.33 | 5000 | 0.6447 | 0.8032 | 0.8033 | | 0.1127 | 346.67 | 5200 | 0.6333 | 0.8074 | 0.8075 | | 0.103 | 360.0 | 5400 | 0.6719 | 0.8033 | 0.8033 | | 0.1051 | 373.33 | 5600 | 0.6635 | 0.8073 | 0.8075 | | 0.1009 | 386.67 | 5800 | 0.6677 | 0.7990 | 0.7992 | | 0.0949 | 400.0 | 6000 | 0.7129 | 0.8072 | 0.8075 | | 0.1017 | 413.33 | 6200 | 0.6686 | 0.7988 | 0.7992 | | 0.0955 | 426.67 | 6400 | 0.6848 | 0.8073 | 0.8075 | | 0.0904 | 440.0 | 6600 | 0.7276 | 0.8115 | 0.8117 | | 0.093 | 453.33 | 6800 | 0.7003 | 0.8032 | 0.8033 | | 0.0887 | 466.67 | 7000 | 0.7550 | 0.8156 | 0.8159 | | 0.0863 | 480.0 | 7200 | 0.7110 | 0.8074 | 0.8075 | | 0.0893 | 493.33 | 7400 | 0.7272 | 0.8032 | 0.8033 | | 0.0882 | 506.67 | 7600 | 0.7284 | 0.8032 | 0.8033 | | 0.0839 | 520.0 | 7800 | 0.7471 | 0.8073 | 0.8075 | | 0.086 | 533.33 | 8000 | 0.7495 | 0.8032 | 0.8033 | | 0.0863 | 546.67 | 8200 | 0.7395 | 0.8032 | 0.8033 | | 0.084 | 560.0 | 8400 | 0.7449 | 0.8032 | 0.8033 | | 0.0826 | 573.33 | 8600 | 0.7441 | 0.8032 | 0.8033 | | 0.0826 | 586.67 | 8800 | 0.7596 | 0.7990 | 0.7992 | | 0.0824 | 600.0 | 9000 | 0.7508 | 0.8074 | 0.8075 | | 0.079 | 613.33 | 9200 | 0.7753 | 0.7990 | 0.7992 | | 0.078 | 626.67 | 9400 | 0.7688 | 0.8074 | 0.8075 | | 0.0819 | 640.0 | 9600 | 0.7613 | 0.8074 | 0.8075 | | 0.0839 | 653.33 | 9800 | 0.7621 | 0.8032 | 0.8033 | | 0.0791 | 666.67 | 10000 | 0.7611 | 0.8074 | 0.8075 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_3-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_3-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:23:51+00:00

null

# Smaug-72B-v0.1-GGUF - Original model: [Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1)  ## Description This repo contains GGUF format model files for [Smaug-72B-v0.1](https://huggingface.co/abacusai/Smaug-72B-v0.1).   ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). This is the source project for GGUF, providing both a Command Line Interface (CLI) and a server option. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), Known as the most widely used web UI, this project boasts numerous features and powerful extensions, and supports GPU acceleration. * [Ollama](https://github.com/jmorganca/ollama) Ollama is a lightweight and extensible framework designed for building and running language models locally. It features a simple API for creating, managing, and executing models, along with a library of pre-built models for use in various applications * [KoboldCpp](https://github.com/LostRuins/koboldcpp), A comprehensive web UI offering GPU acceleration across all platforms and architectures, particularly renowned for storytelling. * [GPT4All](https://gpt4all.io), This is a free and open source GUI that runs locally, supporting Windows, Linux, and macOS with full GPU acceleration. * [LM Studio](https://lmstudio.ai/) An intuitive and powerful local GUI for Windows and macOS (Silicon), featuring GPU acceleration. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). A notable web UI with a variety of unique features, including a comprehensive model library for easy model selection. * [Faraday.dev](https://faraday.dev/), An attractive, user-friendly character-based chat GUI for Windows and macOS (both Silicon and Intel), also offering GPU acceleration. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), A Python library equipped with GPU acceleration, LangChain support, and an OpenAI-compatible API server. * [candle](https://github.com/huggingface/candle), A Rust-based ML framework focusing on performance, including GPU support, and designed for ease of use. * [ctransformers](https://github.com/marella/ctransformers), A Python library featuring GPU acceleration, LangChain support, and an OpenAI-compatible AI server. * [localGPT](https://github.com/PromtEngineer/localGPT) An open-source initiative enabling private conversations with documents.   ## Explanation of quantisation methods <details> <summary>Click to see details</summary> The new methods available are: * GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw) * GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw. * GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw. * GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw * GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw. </details>   ## How to download GGUF files **Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single folder. The following clients/libraries will automatically download models for you, providing a list of available models to choose from: * LM Studio * LoLLMS Web UI * Faraday.dev ### In `text-generation-webui` Under Download Model, you can enter the model repo: LiteLLMs/Smaug-72B-v0.1-GGUF and below it, a specific filename to download, such as: Q4_0/Q4_0-00001-of-00009.gguf. Then click Download. ### On the command line, including multiple files at once I recommend using the `huggingface-hub` Python library: ```shell pip3 install huggingface-hub ``` Then you can download any individual model file to the current directory, at high speed, with a command like this: ```shell huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False ``` <details> <summary>More advanced huggingface-cli download usage (click to read)</summary> You can also download multiple files at once with a pattern: ```shell huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf' ``` For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli). To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`: ```shell pip3 install huggingface_hub[hf_transfer] ``` And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`: ```shell HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download LiteLLMs/Smaug-72B-v0.1-GGUF Q4_0/Q4_0-00001-of-00009.gguf --local-dir . --local-dir-use-symlinks False ``` Windows Command Line users: You can set the environment variable by running `set HF_HUB_ENABLE_HF_TRANSFER=1` before the download command. </details>   ## Example `llama.cpp` command Make sure you are using `llama.cpp` from commit [d0cee0d](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later. ```shell ./main -ngl 35 -m Q4_0/Q4_0-00001-of-00009.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<PROMPT>" ``` Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration. Change `-c 8192` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically. Note that longer sequence lengths require much more resources, so you may need to reduce this value. If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins` For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md) ## How to run in `text-generation-webui` Further instructions can be found in the text-generation-webui documentation, here: [text-generation-webui/docs/04 ‐ Model Tab.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/04%20%E2%80%90%20Model%20Tab.md#llamacpp). ## How to run from Python code You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python. ### How to load this model in Python code, using llama-cpp-python For full documentation, please see: [llama-cpp-python docs](https://abetlen.github.io/llama-cpp-python/). #### First install the package Run one of the following commands, according to your system: ```shell # Base ctransformers with no GPU acceleration pip install llama-cpp-python # With NVidia CUDA acceleration CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python # Or with OpenBLAS acceleration CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python # Or with CLBLast acceleration CMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python # Or with AMD ROCm GPU acceleration (Linux only) CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python # Or with Metal GPU acceleration for macOS systems only CMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python # In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA: $env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on" pip install llama-cpp-python ``` #### Simple llama-cpp-python example code ```python from llama_cpp import Llama # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system. llm = Llama( model_path="./Q4_0/Q4_0-00001-of-00009.gguf", # Download the model file first n_ctx=32768, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available ) # Simple inference example output = llm( "<PROMPT>", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt ) # Chat Completion API llm = Llama(model_path="./Q4_0/Q4_0-00001-of-00009.gguf", chat_format="llama-2") # Set chat_format according to the model you are using llm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ] ) ``` ## How to use with LangChain Here are guides on using llama-cpp-python and ctransformers with LangChain: * [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp) * [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)    # Original model card: Smaug-72B-v0.1 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/pf4d6FA7DriRtVq5HCkxd.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/64c14f6b02e1f8f67c73bd05/e4u8VYfDBh11u60rFYJHF.png) Smaug arrives! We recently released Smaug-72B-v0.1 which has taken first place on the Open LLM Leaderboard by HuggingFace. It is the first open-source model to surpass an average score of 80%. Smaug-72B is finetuned directly from [moreh/MoMo-72B-lora-1.8.7-DPO](https://huggingface.co/moreh/MoMo-72B-lora-1.8.7-DPO) and is ultimately based on [Qwen-72B](https://huggingface.co/Qwen/Qwen-72B). We created Smaug-72B-v0.1 using a new fine-tuning technique, DPO-Positive (DPOP), and new pairwise preference versions of ARC, HellaSwag, and MetaMath (as well as other existing datasets). We introduce the technique and the full training details in our new paper: https://arxiv.org/abs/2402.13228. We show that on datasets in which the edit distance between pairs of completions is low (such as in math-based datasets), standard DPO loss can lead to a reduction of the model's likelihood of the preferred examples, as long as the relative probability between the preferred and dispreferred classes increases. Using these insights, we design DPOP, a new loss function and training procedure which avoids this failure mode. Surprisingly, we also find that DPOP outperforms DPO across a wide variety of datasets and downstream tasks, including datasets with high edit distances between completions. We believe this new approach is generally useful in training across a wide range of model types and downstream use cases, and it powers all of our Smaug models. With the release of our paper and datasets, we are excited for the open source community to continue to build on and improve Smaug and spawn more dragons to dominate the LLM space! ### Evaluation Results | Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K | | - | | - | -- | | 80.48 | 76.02 | 89.27 | 77.15 | 76.67 | 85.08 | 78.70 | #### MT-Bench We ran MT-Bench with the llama-2 conversation template and the system prompt set to the Qwen system prompt. We got the following results in single model mode: | First Turn | Second Turn | Average | | -- | - | | 8.18 | 7.34 | 7.76 | The bottom of the card includes some sample responses from the model. We have selected responses that have high and low scores from the GPT-4 judge. ### Contamination Results We generate our contamination numbers using https://github.com/swj0419/detect-pretrain-code-contamination/tree/master, with Llama7B as our reference model. Smaug-72B has the following results: | ARC | TruthfulQA | GSM8K | | - | - | -- | | 0.20 | 0.39 | 1.00 | Note that GSM8K often scores very highly on this contamination suite - we verified this by also running Llama-2-70B: | ARC | TruthfulQA | GSM8K | | - | ----- | | 0.22 | 0.51 | 0.89 | ### Sample MT Bench results #### Example 1 **Question** Imagine you are writing a blog post comparing two popular smartphone models. Develop an outline for the blog post, including key points and subheadings to effectively compare and contrast the features, performance, and user experience of the two models. Please answer in fewer than 200 words. **Response** Outline: 1. Introduction to the two smartphone models being compared (mention brand names and models) 2. Design and Build Quality - Comparison of dimensions, weight, materials used, and overall aesthetic appeal - Water and dust resistance, if applicable 3. Display and Screen Quality - Comparison of screen technology (OLED, IPS LCD, etc.) - Display resolution, refresh rate, and brightness levels 4. Performance and Hardware - Processor, RAM, and storage configurations - Comparison of benchmark scores (e.g., AnTuTu, Geekbench) 5. Camera System and Image Quality - Comparison of primary, ultra-wide, telephoto, and macro lenses (if available) - Comparison of low-light performance and image processing capabilities 6. Battery Life and Charging - Battery capacity and estimated usage time - Charging technologies (wired, wireless, fast charging, reverse charging) 7. Software and User Experience - Comparison of operating systems (iOS vs. Android) and their features - User interface, customization options, and app ecosystem 8. Additional Features and Extras - Comparison of biometric authentication (fingerprint, face unlock, etc.) - Additional features like NFC, 5G connectivity, and audio quality 9. Pricing and Value for Money - Comparison of retail prices and current offers - Assessment of overall value considering the features and performance 10. Conclusion and recommendation for potential buyers based on their preferences #### Example 2 **Question** In a survey conducted at a local high school, preferences for a new school color were measured: 58% of students liked the color blue, 45% preferred green, and 22% liked both colors. If we randomly pick a student from the school, what's the probability that they would like neither blue nor green? **Answer** To find the probability that a randomly picked student would like neither blue nor green, we need to find the percentage of students who like only one color or neither color. From the given information, we know: - 58% like blue - 45% prefer green - 22% like both colors To find the percentage of students who like only one color, we can subtract the percentage of students who like both colors from the sum of students who like blue and green: - 58% (blue) + 45% (green) - 22% (both) = 83% Now, to find the probability of a student liking neither blue nor green, we subtract the percentage of students who like at least one color from 100%: - 100% - 83% = 17% So, the probability that a randomly picked student would like neither blue nor green is 17%. #### Example 3 **Question** Implement a program to find the common elements in two arrays without using any extra data structures. **Answer** Finding common elements in two arrays without using extra data structures can be achieved by using a simple algorithm. Here's a Python implementation of this problem: ```python def find_common_elements(arr1, arr2): common_elements = [] for num1 in arr1: if num1 in arr2 and num1 not in common_elements: common_elements.append(num1) return common_elements # Example usage: array1 = [1, 2, 3, 4, 5] array2 = [4, 5, 6, 7, 8] print(find_common_elements(array1, array2)) # Output: [4, 5] ``` This program iterates through the elements of the first array (arr1) and checks if each element is present in the second array (arr2). If it is, and the element hasn't been added to the common_elements list yet, it is appended. The function then returns the list of common elements. #### Example 4 **Question** Identify the named entities (people, organizations, locations) mentioned in the given news article. Please generate a JSON dictionary that lists the named entities in three separate groups based on their entity types. The key is the type of entity and the value is a list of strings. Yesterday, Adamson Emerson, the CEO of Faraday, and Dieter Zetsche, the CEO of Daimler AG, announced plans to build a new Gigafactory in Berlin. The facility will be a joint venture between Faraday and Daimler, producing electric vehicles and battery packs for both companies, creating thousands of job opportunities in the region. Emerson and Zetsche stated that the strategic location of Berlin, coupled with its skilled workforce and strong infrastructure, makes it an ideal choice for expansion. The new Gigafactory aims to meet the growing demand for electric vehicles in Europe and contribute to a sustainable future. Volkswagen CEO Herbert Diess welcomed the news, saying greater collaboration will, benefit the auto industry's transition to e-mobility. **Answer** ``` { "people": ["Adamson Emerson", "Dieter Zetsche", "Herbert Diess"], "organizations": ["Faraday", "Daimler AG", "Volkswagen"], "locations": ["Berlin", "Europe"] } ``` ### Citation Please cite the paper if you use data, model, or method in this repo. ``` @article{pal2024smaug, title={Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive}, author={Pal, Arka and Karkhanis, Deep and Dooley, Samuel and Roberts, Manley and Naidu, Siddartha and White, Colin}, journal={arXiv preprint arXiv:2402.13228}, year={2024} } ```

{"license": "other", "tags": ["GGUF"], "base_model": "moreh/MoMo-72B-lora-1.8.7-DPO", "license_name": "tongyi-qianwen-license-agreement", "license_link": "https://github.com/QwenLM/Qwen/blob/main/Tongyi%20Qianwen%20LICENSE%20AGREEMENT", "quantized_by": "andrijdavid"}

LiteLLMs/Smaug-72B-v0.1-GGUF

null

[ "GGUF", "arxiv:2402.13228", "base_model:moreh/MoMo-72B-lora-1.8.7-DPO", "license:other", "region:us" ]

null

2024-04-29T23:25:46+00:00

null

{}

webnizam/llama3-8b-unintended-consequences-gguf

null

[ "gguf", "region:us" ]

null

2024-04-29T23:27:21+00:00

null

{}

ShenaoZhang/0.0_3iters_bs256_nodpo_full6w_iter_2

null

[ "region:us" ]

null

2024-04-29T23:27:28+00:00

null

peft

# GUE_mouse_3-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.8517 - F1 Score: 0.8452 - Accuracy: 0.8452 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.5452 | 13.33 | 200 | 0.4368 | 0.7950 | 0.7950 | | 0.3383 | 26.67 | 400 | 0.4173 | 0.8281 | 0.8285 | | 0.2546 | 40.0 | 600 | 0.4703 | 0.8368 | 0.8368 | | 0.198 | 53.33 | 800 | 0.5257 | 0.8321 | 0.8326 | | 0.1583 | 66.67 | 1000 | 0.5990 | 0.8276 | 0.8285 | | 0.1327 | 80.0 | 1200 | 0.7110 | 0.8158 | 0.8159 | | 0.1138 | 93.33 | 1400 | 0.6432 | 0.8158 | 0.8159 | | 0.0975 | 106.67 | 1600 | 0.6860 | 0.8325 | 0.8326 | | 0.0802 | 120.0 | 1800 | 0.8088 | 0.8197 | 0.8201 | | 0.0723 | 133.33 | 2000 | 0.8668 | 0.8242 | 0.8243 | | 0.0653 | 146.67 | 2200 | 0.9054 | 0.8158 | 0.8159 | | 0.0587 | 160.0 | 2400 | 0.9065 | 0.8201 | 0.8201 | | 0.0486 | 173.33 | 2600 | 1.0048 | 0.8200 | 0.8201 | | 0.0509 | 186.67 | 2800 | 0.9290 | 0.8408 | 0.8410 | | 0.0456 | 200.0 | 3000 | 0.9976 | 0.8159 | 0.8159 | | 0.0418 | 213.33 | 3200 | 0.9689 | 0.8159 | 0.8159 | | 0.037 | 226.67 | 3400 | 1.0219 | 0.8281 | 0.8285 | | 0.0371 | 240.0 | 3600 | 1.0860 | 0.8200 | 0.8201 | | 0.034 | 253.33 | 3800 | 1.0840 | 0.8074 | 0.8075 | | 0.0314 | 266.67 | 4000 | 1.1107 | 0.8200 | 0.8201 | | 0.0291 | 280.0 | 4200 | 1.1084 | 0.7990 | 0.7992 | | 0.0274 | 293.33 | 4400 | 1.1196 | 0.8153 | 0.8159 | | 0.0263 | 306.67 | 4600 | 1.1009 | 0.8117 | 0.8117 | | 0.0261 | 320.0 | 4800 | 1.1459 | 0.8074 | 0.8075 | | 0.0239 | 333.33 | 5000 | 1.1017 | 0.8159 | 0.8159 | | 0.0218 | 346.67 | 5200 | 1.1290 | 0.8199 | 0.8201 | | 0.0194 | 360.0 | 5400 | 1.2031 | 0.8240 | 0.8243 | | 0.0194 | 373.33 | 5600 | 1.2167 | 0.8155 | 0.8159 | | 0.019 | 386.67 | 5800 | 1.1979 | 0.8241 | 0.8243 | | 0.0177 | 400.0 | 6000 | 1.2198 | 0.8074 | 0.8075 | | 0.0185 | 413.33 | 6200 | 1.1752 | 0.8199 | 0.8201 | | 0.0181 | 426.67 | 6400 | 1.1793 | 0.8242 | 0.8243 | | 0.0146 | 440.0 | 6600 | 1.2931 | 0.8115 | 0.8117 | | 0.0157 | 453.33 | 6800 | 1.2946 | 0.8159 | 0.8159 | | 0.017 | 466.67 | 7000 | 1.3000 | 0.8201 | 0.8201 | | 0.0135 | 480.0 | 7200 | 1.2510 | 0.8201 | 0.8201 | | 0.0141 | 493.33 | 7400 | 1.2736 | 0.8201 | 0.8201 | | 0.0127 | 506.67 | 7600 | 1.2899 | 0.8200 | 0.8201 | | 0.0134 | 520.0 | 7800 | 1.3283 | 0.8241 | 0.8243 | | 0.0129 | 533.33 | 8000 | 1.3425 | 0.8197 | 0.8201 | | 0.0131 | 546.67 | 8200 | 1.2405 | 0.8282 | 0.8285 | | 0.0121 | 560.0 | 8400 | 1.2794 | 0.8117 | 0.8117 | | 0.0109 | 573.33 | 8600 | 1.3451 | 0.8283 | 0.8285 | | 0.0116 | 586.67 | 8800 | 1.3675 | 0.8159 | 0.8159 | | 0.0122 | 600.0 | 9000 | 1.3784 | 0.8075 | 0.8075 | | 0.0109 | 613.33 | 9200 | 1.3744 | 0.8200 | 0.8201 | | 0.0103 | 626.67 | 9400 | 1.4141 | 0.8200 | 0.8201 | | 0.0106 | 640.0 | 9600 | 1.3886 | 0.8117 | 0.8117 | | 0.0113 | 653.33 | 9800 | 1.3747 | 0.8200 | 0.8201 | | 0.0102 | 666.67 | 10000 | 1.3772 | 0.8158 | 0.8159 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_3-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_3-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:27:30+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

lunarsylph/stablecell_v53

null

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:27:44+00:00

null

{}

curtisxu/mergeLlama-7b-Instruct-hf-quantized-peft-2

null

[ "region:us" ]

null

2024-04-29T23:28:01+00:00

null

peft

# GUE_mouse_3-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_3](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_3) dataset. It achieves the following results on the evaluation set: - Loss: 0.8282 - F1 Score: 0.8534 - Accuracy: 0.8536 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.4872 | 13.33 | 200 | 0.4103 | 0.8241 | 0.8243 | | 0.2478 | 26.67 | 400 | 0.4459 | 0.8197 | 0.8201 | | 0.1554 | 40.0 | 600 | 0.5680 | 0.7990 | 0.7992 | | 0.102 | 53.33 | 800 | 0.6341 | 0.8403 | 0.8410 | | 0.0669 | 66.67 | 1000 | 0.7863 | 0.8192 | 0.8201 | | 0.0475 | 80.0 | 1200 | 0.9739 | 0.8065 | 0.8075 | | 0.0433 | 93.33 | 1400 | 0.8721 | 0.8282 | 0.8285 | | 0.0332 | 106.67 | 1600 | 0.8710 | 0.8449 | 0.8452 | | 0.0255 | 120.0 | 1800 | 1.0873 | 0.8072 | 0.8075 | | 0.0244 | 133.33 | 2000 | 1.0687 | 0.7988 | 0.7992 | | 0.02 | 146.67 | 2200 | 1.1529 | 0.8281 | 0.8285 | | 0.0161 | 160.0 | 2400 | 1.1772 | 0.8284 | 0.8285 | | 0.0165 | 173.33 | 2600 | 1.2462 | 0.8276 | 0.8285 | | 0.0144 | 186.67 | 2800 | 1.1893 | 0.8115 | 0.8117 | | 0.0125 | 200.0 | 3000 | 1.2388 | 0.8067 | 0.8075 | | 0.0109 | 213.33 | 3200 | 1.3548 | 0.8073 | 0.8075 | | 0.0109 | 226.67 | 3400 | 1.2163 | 0.7907 | 0.7908 | | 0.0112 | 240.0 | 3600 | 1.1475 | 0.8117 | 0.8117 | | 0.0109 | 253.33 | 3800 | 1.3809 | 0.8065 | 0.8075 | | 0.0086 | 266.67 | 4000 | 1.3586 | 0.8072 | 0.8075 | | 0.0062 | 280.0 | 4200 | 1.3622 | 0.8031 | 0.8033 | | 0.0087 | 293.33 | 4400 | 1.2448 | 0.8071 | 0.8075 | | 0.0072 | 306.67 | 4600 | 1.4332 | 0.8028 | 0.8033 | | 0.0065 | 320.0 | 4800 | 1.3601 | 0.7947 | 0.7950 | | 0.0071 | 333.33 | 5000 | 1.5165 | 0.7978 | 0.7992 | | 0.0049 | 346.67 | 5200 | 1.4562 | 0.8026 | 0.8033 | | 0.0048 | 360.0 | 5400 | 1.5191 | 0.7988 | 0.7992 | | 0.0053 | 373.33 | 5600 | 1.4817 | 0.8196 | 0.8201 | | 0.0041 | 386.67 | 5800 | 1.6016 | 0.7949 | 0.7950 | | 0.0044 | 400.0 | 6000 | 1.5036 | 0.8153 | 0.8159 | | 0.0052 | 413.33 | 6200 | 1.5273 | 0.8075 | 0.8075 | | 0.0041 | 426.67 | 6400 | 1.4759 | 0.8028 | 0.8033 | | 0.0023 | 440.0 | 6600 | 1.5729 | 0.8031 | 0.8033 | | 0.0028 | 453.33 | 6800 | 1.6576 | 0.8155 | 0.8159 | | 0.0043 | 466.67 | 7000 | 1.6210 | 0.8157 | 0.8159 | | 0.003 | 480.0 | 7200 | 1.5857 | 0.7992 | 0.7992 | | 0.0036 | 493.33 | 7400 | 1.6029 | 0.8149 | 0.8159 | | 0.0024 | 506.67 | 7600 | 1.5662 | 0.8114 | 0.8117 | | 0.0023 | 520.0 | 7800 | 1.6867 | 0.8028 | 0.8033 | | 0.0032 | 533.33 | 8000 | 1.5723 | 0.8030 | 0.8033 | | 0.0024 | 546.67 | 8200 | 1.6106 | 0.8116 | 0.8117 | | 0.0023 | 560.0 | 8400 | 1.6233 | 0.7903 | 0.7908 | | 0.0021 | 573.33 | 8600 | 1.5936 | 0.8030 | 0.8033 | | 0.0021 | 586.67 | 8800 | 1.5612 | 0.8116 | 0.8117 | | 0.0017 | 600.0 | 9000 | 1.6127 | 0.8157 | 0.8159 | | 0.002 | 613.33 | 9200 | 1.6056 | 0.8156 | 0.8159 | | 0.0011 | 626.67 | 9400 | 1.6240 | 0.8032 | 0.8033 | | 0.0015 | 640.0 | 9600 | 1.6482 | 0.8031 | 0.8033 | | 0.0018 | 653.33 | 9800 | 1.6421 | 0.8031 | 0.8033 | | 0.003 | 666.67 | 10000 | 1.6413 | 0.8031 | 0.8033 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_3-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_3-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:28:26+00:00

null

transformers

## About     static quants of https://huggingface.co/Hugosh71/Llama-3-8B-Eden  weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. ## Usage If you are unsure how to use GGUF files, refer to one of [TheBloke's READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for more details, including on how to concatenate multi-part files. ## Provided Quants (sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) | Link | Type | Size/GB | Notes | |:-----|:-----|--------:|:------| | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Llama-3-8B-Eden-GGUF/resolve/main/Llama-3-8B-Eden.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time.

{"language": ["en"], "license": "apache-2.0", "library_name": "transformers", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl", "sft"], "base_model": "Hugosh71/Llama-3-8B-Eden", "quantized_by": "mradermacher"}

mradermacher/Llama-3-8B-Eden-GGUF

null

[ "transformers", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "sft", "en", "base_model:Hugosh71/Llama-3-8B-Eden", "license:apache-2.0", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:28:57+00:00

text-generation

transformers

# Model Card for Model ID  ## Model Details ### Model Description  This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]

{"library_name": "transformers", "tags": []}

shallow6414/7aeerbr

null

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

null

2024-04-29T23:29:15+00:00

null

peft

# GUE_mouse_2-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.4898 - F1 Score: 0.8627 - Accuracy: 0.8628 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.3798 | 9.52 | 200 | 0.2814 | 0.8688 | 0.8689 | | 0.2589 | 19.05 | 400 | 0.2488 | 0.9024 | 0.9024 | | 0.2158 | 28.57 | 600 | 0.2361 | 0.9238 | 0.9238 | | 0.177 | 38.1 | 800 | 0.2305 | 0.9237 | 0.9238 | | 0.1469 | 47.62 | 1000 | 0.2415 | 0.9084 | 0.9085 | | 0.1237 | 57.14 | 1200 | 0.3192 | 0.9053 | 0.9055 | | 0.0998 | 66.67 | 1400 | 0.3660 | 0.9113 | 0.9116 | | 0.0845 | 76.19 | 1600 | 0.3451 | 0.9084 | 0.9085 | | 0.0732 | 85.71 | 1800 | 0.3503 | 0.9145 | 0.9146 | | 0.0638 | 95.24 | 2000 | 0.4203 | 0.8960 | 0.8963 | | 0.056 | 104.76 | 2200 | 0.4481 | 0.9144 | 0.9146 | | 0.0522 | 114.29 | 2400 | 0.3994 | 0.9175 | 0.9177 | | 0.048 | 123.81 | 2600 | 0.4189 | 0.9114 | 0.9116 | | 0.0435 | 133.33 | 2800 | 0.4454 | 0.8989 | 0.8994 | | 0.04 | 142.86 | 3000 | 0.4346 | 0.9267 | 0.9268 | | 0.0379 | 152.38 | 3200 | 0.4681 | 0.9082 | 0.9085 | | 0.0321 | 161.9 | 3400 | 0.4259 | 0.9143 | 0.9146 | | 0.0318 | 171.43 | 3600 | 0.3744 | 0.9207 | 0.9207 | | 0.0299 | 180.95 | 3800 | 0.3893 | 0.9207 | 0.9207 | | 0.0251 | 190.48 | 4000 | 0.4827 | 0.9143 | 0.9146 | | 0.0249 | 200.0 | 4200 | 0.5806 | 0.8957 | 0.8963 | | 0.0222 | 209.52 | 4400 | 0.5559 | 0.9113 | 0.9116 | | 0.0226 | 219.05 | 4600 | 0.4151 | 0.9175 | 0.9177 | | 0.0216 | 228.57 | 4800 | 0.4778 | 0.9174 | 0.9177 | | 0.0202 | 238.1 | 5000 | 0.4794 | 0.9144 | 0.9146 | | 0.0188 | 247.62 | 5200 | 0.5111 | 0.9020 | 0.9024 | | 0.0182 | 257.14 | 5400 | 0.4998 | 0.9021 | 0.9024 | | 0.0152 | 266.67 | 5600 | 0.4815 | 0.9176 | 0.9177 | | 0.0151 | 276.19 | 5800 | 0.5486 | 0.9082 | 0.9085 | | 0.0164 | 285.71 | 6000 | 0.5131 | 0.9113 | 0.9116 | | 0.014 | 295.24 | 6200 | 0.5049 | 0.9206 | 0.9207 | | 0.0144 | 304.76 | 6400 | 0.4674 | 0.9083 | 0.9085 | | 0.0147 | 314.29 | 6600 | 0.6490 | 0.8896 | 0.8902 | | 0.0143 | 323.81 | 6800 | 0.4780 | 0.9237 | 0.9238 | | 0.0137 | 333.33 | 7000 | 0.5217 | 0.9082 | 0.9085 | | 0.0133 | 342.86 | 7200 | 0.4700 | 0.9175 | 0.9177 | | 0.0134 | 352.38 | 7400 | 0.5702 | 0.9051 | 0.9055 | | 0.0116 | 361.9 | 7600 | 0.5374 | 0.9020 | 0.9024 | | 0.0104 | 371.43 | 7800 | 0.5493 | 0.8989 | 0.8994 | | 0.013 | 380.95 | 8000 | 0.4950 | 0.9083 | 0.9085 | | 0.0114 | 390.48 | 8200 | 0.5291 | 0.9021 | 0.9024 | | 0.0104 | 400.0 | 8400 | 0.5530 | 0.8958 | 0.8963 | | 0.009 | 409.52 | 8600 | 0.5151 | 0.9145 | 0.9146 | | 0.0092 | 419.05 | 8800 | 0.5606 | 0.9082 | 0.9085 | | 0.0087 | 428.57 | 9000 | 0.6063 | 0.9020 | 0.9024 | | 0.0097 | 438.1 | 9200 | 0.5208 | 0.9237 | 0.9238 | | 0.0099 | 447.62 | 9400 | 0.5650 | 0.9113 | 0.9116 | | 0.008 | 457.14 | 9600 | 0.5689 | 0.9082 | 0.9085 | | 0.009 | 466.67 | 9800 | 0.5718 | 0.9051 | 0.9055 | | 0.0091 | 476.19 | 10000 | 0.5701 | 0.9051 | 0.9055 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_2-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_2-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:29:29+00:00

null

peft

# GUE_mouse_2-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.2431 - F1 Score: 0.8933 - Accuracy: 0.8933 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.431 | 9.52 | 200 | 0.3091 | 0.8352 | 0.8354 | | 0.3042 | 19.05 | 400 | 0.2854 | 0.8655 | 0.8659 | | 0.2832 | 28.57 | 600 | 0.2640 | 0.8720 | 0.8720 | | 0.2619 | 38.1 | 800 | 0.2485 | 0.8902 | 0.8902 | | 0.245 | 47.62 | 1000 | 0.2347 | 0.8932 | 0.8933 | | 0.2316 | 57.14 | 1200 | 0.2357 | 0.8963 | 0.8963 | | 0.2161 | 66.67 | 1400 | 0.2363 | 0.8994 | 0.8994 | | 0.204 | 76.19 | 1600 | 0.2410 | 0.9054 | 0.9055 | | 0.194 | 85.71 | 1800 | 0.2328 | 0.9085 | 0.9085 | | 0.1781 | 95.24 | 2000 | 0.2349 | 0.8994 | 0.8994 | | 0.1696 | 104.76 | 2200 | 0.2507 | 0.9022 | 0.9024 | | 0.1603 | 114.29 | 2400 | 0.2369 | 0.9085 | 0.9085 | | 0.156 | 123.81 | 2600 | 0.2406 | 0.9085 | 0.9085 | | 0.1474 | 133.33 | 2800 | 0.2660 | 0.8992 | 0.8994 | | 0.1385 | 142.86 | 3000 | 0.2323 | 0.8963 | 0.8963 | | 0.1378 | 152.38 | 3200 | 0.2642 | 0.9023 | 0.9024 | | 0.1302 | 161.9 | 3400 | 0.2688 | 0.9024 | 0.9024 | | 0.1226 | 171.43 | 3600 | 0.2931 | 0.9054 | 0.9055 | | 0.1199 | 180.95 | 3800 | 0.2706 | 0.8963 | 0.8963 | | 0.1126 | 190.48 | 4000 | 0.2766 | 0.8994 | 0.8994 | | 0.1098 | 200.0 | 4200 | 0.3117 | 0.8961 | 0.8963 | | 0.1067 | 209.52 | 4400 | 0.3084 | 0.8993 | 0.8994 | | 0.1055 | 219.05 | 4600 | 0.2736 | 0.8963 | 0.8963 | | 0.102 | 228.57 | 4800 | 0.2974 | 0.8993 | 0.8994 | | 0.1018 | 238.1 | 5000 | 0.3201 | 0.8900 | 0.8902 | | 0.0941 | 247.62 | 5200 | 0.3076 | 0.8993 | 0.8994 | | 0.0952 | 257.14 | 5400 | 0.3099 | 0.8962 | 0.8963 | | 0.0956 | 266.67 | 5600 | 0.3151 | 0.9023 | 0.9024 | | 0.0901 | 276.19 | 5800 | 0.3250 | 0.8993 | 0.8994 | | 0.0912 | 285.71 | 6000 | 0.3075 | 0.8963 | 0.8963 | | 0.0847 | 295.24 | 6200 | 0.3183 | 0.8902 | 0.8902 | | 0.0869 | 304.76 | 6400 | 0.3248 | 0.8993 | 0.8994 | | 0.0844 | 314.29 | 6600 | 0.3260 | 0.8962 | 0.8963 | | 0.083 | 323.81 | 6800 | 0.3201 | 0.8993 | 0.8994 | | 0.0838 | 333.33 | 7000 | 0.3342 | 0.8962 | 0.8963 | | 0.0833 | 342.86 | 7200 | 0.3211 | 0.8993 | 0.8994 | | 0.0784 | 352.38 | 7400 | 0.3228 | 0.8963 | 0.8963 | | 0.0794 | 361.9 | 7600 | 0.3261 | 0.8932 | 0.8933 | | 0.0738 | 371.43 | 7800 | 0.3553 | 0.8901 | 0.8902 | | 0.0785 | 380.95 | 8000 | 0.3454 | 0.8932 | 0.8933 | | 0.0733 | 390.48 | 8200 | 0.3383 | 0.8993 | 0.8994 | | 0.0715 | 400.0 | 8400 | 0.3430 | 0.8962 | 0.8963 | | 0.0717 | 409.52 | 8600 | 0.3406 | 0.8963 | 0.8963 | | 0.071 | 419.05 | 8800 | 0.3436 | 0.8993 | 0.8994 | | 0.0727 | 428.57 | 9000 | 0.3576 | 0.8962 | 0.8963 | | 0.0699 | 438.1 | 9200 | 0.3441 | 0.8963 | 0.8963 | | 0.0693 | 447.62 | 9400 | 0.3590 | 0.8993 | 0.8994 | | 0.0699 | 457.14 | 9600 | 0.3587 | 0.8993 | 0.8994 | | 0.0689 | 466.67 | 9800 | 0.3608 | 0.8993 | 0.8994 | | 0.0706 | 476.19 | 10000 | 0.3599 | 0.8993 | 0.8994 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_2-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_2-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:29:29+00:00

null

peft

# GUE_mouse_2-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_mouse_2](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_mouse_2) dataset. It achieves the following results on the evaluation set: - Loss: 0.5170 - F1 Score: 0.8719 - Accuracy: 0.8720 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:------:|:-----:|:---------------:|:--------:|:--------:| | 0.3511 | 9.52 | 200 | 0.2727 | 0.8656 | 0.8659 | | 0.2161 | 19.05 | 400 | 0.2679 | 0.9022 | 0.9024 | | 0.1542 | 28.57 | 600 | 0.3062 | 0.9082 | 0.9085 | | 0.1042 | 38.1 | 800 | 0.3723 | 0.8990 | 0.8994 | | 0.0797 | 47.62 | 1000 | 0.3875 | 0.9020 | 0.9024 | | 0.0583 | 57.14 | 1200 | 0.3187 | 0.9115 | 0.9116 | | 0.0473 | 66.67 | 1400 | 0.4834 | 0.9020 | 0.9024 | | 0.0329 | 76.19 | 1600 | 0.5490 | 0.8901 | 0.8902 | | 0.0261 | 85.71 | 1800 | 0.6356 | 0.8930 | 0.8933 | | 0.0246 | 95.24 | 2000 | 0.5832 | 0.8776 | 0.8780 | | 0.0194 | 104.76 | 2200 | 0.5850 | 0.8962 | 0.8963 | | 0.0193 | 114.29 | 2400 | 0.5464 | 0.8933 | 0.8933 | | 0.0165 | 123.81 | 2600 | 0.6401 | 0.8838 | 0.8841 | | 0.0136 | 133.33 | 2800 | 0.5025 | 0.9054 | 0.9055 | | 0.0128 | 142.86 | 3000 | 0.5665 | 0.9024 | 0.9024 | | 0.0117 | 152.38 | 3200 | 0.6084 | 0.8899 | 0.8902 | | 0.0094 | 161.9 | 3400 | 0.6627 | 0.9054 | 0.9055 | | 0.0106 | 171.43 | 3600 | 0.5885 | 0.9024 | 0.9024 | | 0.0102 | 180.95 | 3800 | 0.6780 | 0.8961 | 0.8963 | | 0.0069 | 190.48 | 4000 | 0.7310 | 0.8803 | 0.8811 | | 0.0071 | 200.0 | 4200 | 0.6558 | 0.8930 | 0.8933 | | 0.0075 | 209.52 | 4400 | 0.5988 | 0.9115 | 0.9116 | | 0.007 | 219.05 | 4600 | 0.5636 | 0.9023 | 0.9024 | | 0.0049 | 228.57 | 4800 | 0.7340 | 0.8838 | 0.8841 | | 0.0054 | 238.1 | 5000 | 0.6138 | 0.9022 | 0.9024 | | 0.0068 | 247.62 | 5200 | 0.7347 | 0.8838 | 0.8841 | | 0.0052 | 257.14 | 5400 | 0.5966 | 0.9024 | 0.9024 | | 0.0057 | 266.67 | 5600 | 0.6711 | 0.8993 | 0.8994 | | 0.0033 | 276.19 | 5800 | 0.8623 | 0.8865 | 0.8872 | | 0.0045 | 285.71 | 6000 | 0.7814 | 0.8898 | 0.8902 | | 0.0036 | 295.24 | 6200 | 0.6892 | 0.9084 | 0.9085 | | 0.0036 | 304.76 | 6400 | 0.7152 | 0.9084 | 0.9085 | | 0.0024 | 314.29 | 6600 | 0.8272 | 0.9052 | 0.9055 | | 0.0032 | 323.81 | 6800 | 0.6715 | 0.9023 | 0.9024 | | 0.0035 | 333.33 | 7000 | 0.7077 | 0.9023 | 0.9024 | | 0.0037 | 342.86 | 7200 | 0.7097 | 0.9054 | 0.9055 | | 0.0037 | 352.38 | 7400 | 0.7148 | 0.9053 | 0.9055 | | 0.0022 | 361.9 | 7600 | 0.6533 | 0.9085 | 0.9085 | | 0.0023 | 371.43 | 7800 | 0.7545 | 0.9053 | 0.9055 | | 0.0024 | 380.95 | 8000 | 0.8008 | 0.8899 | 0.8902 | | 0.0024 | 390.48 | 8200 | 0.7273 | 0.8992 | 0.8994 | | 0.0024 | 400.0 | 8400 | 0.7910 | 0.8930 | 0.8933 | | 0.0019 | 409.52 | 8600 | 0.8000 | 0.8929 | 0.8933 | | 0.0018 | 419.05 | 8800 | 0.7185 | 0.9022 | 0.9024 | | 0.0014 | 428.57 | 9000 | 0.7269 | 0.9022 | 0.9024 | | 0.0016 | 438.1 | 9200 | 0.7002 | 0.9115 | 0.9116 | | 0.0011 | 447.62 | 9400 | 0.7572 | 0.9053 | 0.9055 | | 0.0013 | 457.14 | 9600 | 0.7180 | 0.9084 | 0.9085 | | 0.0015 | 466.67 | 9800 | 0.7360 | 0.9023 | 0.9024 | | 0.0013 | 476.19 | 10000 | 0.7335 | 0.9084 | 0.9085 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_mouse_2-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_mouse_2-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:29:58+00:00

text-generation

null

## Llamacpp imatrix Quantizations of NPC-LLM-3_8B Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2756">b2756</a> for quantization. Original model: https://huggingface.co/Gigax/NPC-LLM-3_8B All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) ## Prompt format ``` <s><|system|> {system_prompt}<|end|> <|user|> {prompt}<|end|> <|assistant|> <|end|> ``` ## Download a file (not the whole branch) from below: | Filename | Quant type | File Size | Description | | -------- | ---------- | --------- | ----------- | | [NPC-LLM-3_8B-Q8_0.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q8_0.gguf) | Q8_0 | 4.06GB | Extremely high quality, generally unneeded but max available quant. | | [NPC-LLM-3_8B-Q6_K.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q6_K.gguf) | Q6_K | 3.13GB | Very high quality, near perfect, *recommended*. | | [NPC-LLM-3_8B-Q5_K_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q5_K_M.gguf) | Q5_K_M | 2.81GB | High quality, *recommended*. | | [NPC-LLM-3_8B-Q5_K_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q5_K_S.gguf) | Q5_K_S | 2.64GB | High quality, *recommended*. | | [NPC-LLM-3_8B-Q4_K_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q4_K_M.gguf) | Q4_K_M | 2.39GB | Good quality, uses about 4.83 bits per weight, *recommended*. | | [NPC-LLM-3_8B-Q4_K_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q4_K_S.gguf) | Q4_K_S | 2.18GB | Slightly lower quality with more space savings, *recommended*. | | [NPC-LLM-3_8B-IQ4_NL.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ4_NL.gguf) | IQ4_NL | 2.17GB | Decent quality, slightly smaller than Q4_K_S with similar performance *recommended*. | | [NPC-LLM-3_8B-IQ4_XS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ4_XS.gguf) | IQ4_XS | 2.05GB | Decent quality, smaller than Q4_K_S with similar performance, *recommended*. | | [NPC-LLM-3_8B-Q3_K_L.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q3_K_L.gguf) | Q3_K_L | 2.08GB | Lower quality but usable, good for low RAM availability. | | [NPC-LLM-3_8B-Q3_K_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q3_K_M.gguf) | Q3_K_M | 1.95GB | Even lower quality. | | [NPC-LLM-3_8B-IQ3_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_M.gguf) | IQ3_M | 1.85GB | Medium-low quality, new method with decent performance comparable to Q3_K_M. | | [NPC-LLM-3_8B-IQ3_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_S.gguf) | IQ3_S | 1.68GB | Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. | | [NPC-LLM-3_8B-Q3_K_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q3_K_S.gguf) | Q3_K_S | 1.68GB | Low quality, not recommended. | | [NPC-LLM-3_8B-IQ3_XS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_XS.gguf) | IQ3_XS | 1.62GB | Lower quality, new method with decent performance, slightly better than Q3_K_S. | | [NPC-LLM-3_8B-IQ3_XXS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ3_XXS.gguf) | IQ3_XXS | 1.51GB | Lower quality, new method with decent performance, comparable to Q3 quants. | | [NPC-LLM-3_8B-Q2_K.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-Q2_K.gguf) | Q2_K | 1.41GB | Very low quality but surprisingly usable. | | [NPC-LLM-3_8B-IQ2_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_M.gguf) | IQ2_M | 1.31GB | Very low quality, uses SOTA techniques to also be surprisingly usable. | | [NPC-LLM-3_8B-IQ2_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_S.gguf) | IQ2_S | 1.21GB | Very low quality, uses SOTA techniques to be usable. | | [NPC-LLM-3_8B-IQ2_XS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_XS.gguf) | IQ2_XS | 1.15GB | Very low quality, uses SOTA techniques to be usable. | | [NPC-LLM-3_8B-IQ2_XXS.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ2_XXS.gguf) | IQ2_XXS | 1.04GB | Lower quality, uses SOTA techniques to be usable. | | [NPC-LLM-3_8B-IQ1_M.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ1_M.gguf) | IQ1_M | .91GB | Extremely low quality, *not* recommended. | | [NPC-LLM-3_8B-IQ1_S.gguf](https://huggingface.co/bartowski/NPC-LLM-3_8B-GGUF/blob/main/NPC-LLM-3_8B-IQ1_S.gguf) | IQ1_S | .84GB | Extremely low quality, *not* recommended. | ## Which file should I choose? A great write up with charts showing various performances is provided by Artefact2 [here](https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9) The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have. If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM. If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total. Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'. If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M. If you want to get more into the weeds, you can check out this extremely useful feature chart: [llama.cpp feature matrix](https://github.com/ggerganov/llama.cpp/wiki/Feature-matrix) But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size. These I-quants can also be used on CPU and Apple Metal, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide. The I-quants are *not* compatible with Vulcan, which is also AMD, so if you have an AMD card double check if you're using the rocBLAS build or the Vulcan build. At the time of writing this, LM Studio has a preview with ROCm support, and other inference engines have specific builds for ROCm. Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

{"language": ["en"], "license": "mit", "quantized_by": "bartowski", "pipeline_tag": "text-generation"}

bartowski/NPC-LLM-3_8B-GGUF

null

[ "gguf", "text-generation", "en", "license:mit", "region:us" ]

null

2024-04-29T23:31:09+00:00

null

peft

# Model Card for Model ID  ## Model Details ### Model Description  - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional]  - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses  ### Direct Use  [More Information Needed] ### Downstream Use [optional]  [More Information Needed] ### Out-of-Scope Use  [More Information Needed] ## Bias, Risks, and Limitations  [More Information Needed] ### Recommendations  Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data  [More Information Needed] ### Training Procedure  #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed]  #### Speeds, Sizes, Times [optional]  [More Information Needed] ## Evaluation  ### Testing Data, Factors & Metrics #### Testing Data  [More Information Needed] #### Factors  [More Information Needed] #### Metrics  [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional]  [More Information Needed] ## Environmental Impact  Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional]  **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional]  [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed] ### Framework versions - PEFT 0.10.0

{"library_name": "peft", "base_model": "t5-base"}

PQlet/T5base-lora-sumarizationTables-v2-MLM-lambda0.01

null

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:t5-base", "region:us" ]

null

2024-04-29T23:32:45+00:00

null

peft

# GUE_splice_reconstructed-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3468 - F1 Score: 0.8728 - Accuracy: 0.8722 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.9664 | 0.7 | 200 | 0.9062 | 0.4652 | 0.5688 | | 0.7475 | 1.4 | 400 | 0.5761 | 0.7375 | 0.7361 | | 0.5257 | 2.1 | 600 | 0.4960 | 0.7901 | 0.7887 | | 0.4745 | 2.8 | 800 | 0.5054 | 0.7902 | 0.7896 | | 0.4578 | 3.5 | 1000 | 0.4237 | 0.8268 | 0.8264 | | 0.441 | 4.2 | 1200 | 0.4493 | 0.8177 | 0.8165 | | 0.4231 | 4.9 | 1400 | 0.4227 | 0.8319 | 0.8312 | | 0.411 | 5.59 | 1600 | 0.4583 | 0.8187 | 0.8183 | | 0.396 | 6.29 | 1800 | 0.4517 | 0.8176 | 0.8167 | | 0.3895 | 6.99 | 2000 | 0.4294 | 0.8353 | 0.8343 | | 0.3806 | 7.69 | 2200 | 0.4135 | 0.8342 | 0.8334 | | 0.3774 | 8.39 | 2400 | 0.4165 | 0.8367 | 0.8360 | | 0.3647 | 9.09 | 2600 | 0.4366 | 0.8303 | 0.8290 | | 0.3604 | 9.79 | 2800 | 0.4190 | 0.8322 | 0.8314 | | 0.3604 | 10.49 | 3000 | 0.4215 | 0.8342 | 0.8334 | | 0.3517 | 11.19 | 3200 | 0.4374 | 0.8282 | 0.8273 | | 0.3504 | 11.89 | 3400 | 0.4067 | 0.8439 | 0.8431 | | 0.3416 | 12.59 | 3600 | 0.3963 | 0.8484 | 0.8477 | | 0.3423 | 13.29 | 3800 | 0.3719 | 0.8571 | 0.8564 | | 0.3348 | 13.99 | 4000 | 0.4218 | 0.8359 | 0.8349 | | 0.3281 | 14.69 | 4200 | 0.4355 | 0.8289 | 0.8279 | | 0.3285 | 15.38 | 4400 | 0.3763 | 0.8552 | 0.8544 | | 0.3252 | 16.08 | 4600 | 0.4181 | 0.8435 | 0.8426 | | 0.3182 | 16.78 | 4800 | 0.3795 | 0.8538 | 0.8529 | | 0.311 | 17.48 | 5000 | 0.4097 | 0.8382 | 0.8371 | | 0.3138 | 18.18 | 5200 | 0.3846 | 0.8549 | 0.8540 | | 0.3113 | 18.88 | 5400 | 0.3760 | 0.8583 | 0.8575 | | 0.3122 | 19.58 | 5600 | 0.3709 | 0.8592 | 0.8584 | | 0.3089 | 20.28 | 5800 | 0.3639 | 0.8678 | 0.8672 | | 0.3074 | 20.98 | 6000 | 0.3687 | 0.8614 | 0.8606 | | 0.3025 | 21.68 | 6200 | 0.3796 | 0.8561 | 0.8553 | | 0.3015 | 22.38 | 6400 | 0.3639 | 0.8616 | 0.8608 | | 0.2954 | 23.08 | 6600 | 0.3758 | 0.8619 | 0.8610 | | 0.2983 | 23.78 | 6800 | 0.3665 | 0.8642 | 0.8634 | | 0.2968 | 24.48 | 7000 | 0.3740 | 0.8616 | 0.8608 | | 0.2976 | 25.17 | 7200 | 0.3697 | 0.8582 | 0.8573 | | 0.2898 | 25.87 | 7400 | 0.3668 | 0.8622 | 0.8615 | | 0.2944 | 26.57 | 7600 | 0.3841 | 0.8540 | 0.8531 | | 0.2862 | 27.27 | 7800 | 0.3776 | 0.8603 | 0.8595 | | 0.2929 | 27.97 | 8000 | 0.3807 | 0.8564 | 0.8555 | | 0.2911 | 28.67 | 8200 | 0.3710 | 0.8607 | 0.8599 | | 0.2861 | 29.37 | 8400 | 0.3652 | 0.8637 | 0.8630 | | 0.2823 | 30.07 | 8600 | 0.3633 | 0.8668 | 0.8661 | | 0.2835 | 30.77 | 8800 | 0.3741 | 0.8610 | 0.8601 | | 0.286 | 31.47 | 9000 | 0.3728 | 0.8621 | 0.8612 | | 0.284 | 32.17 | 9200 | 0.3671 | 0.8640 | 0.8632 | | 0.2791 | 32.87 | 9400 | 0.3692 | 0.8635 | 0.8628 | | 0.282 | 33.57 | 9600 | 0.3793 | 0.8588 | 0.8580 | | 0.2865 | 34.27 | 9800 | 0.3693 | 0.8629 | 0.8621 | | 0.2805 | 34.97 | 10000 | 0.3738 | 0.8607 | 0.8599 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:33:25+00:00

null

peft

# GUE_splice_reconstructed-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.4196 - F1 Score: 0.8307 - Accuracy: 0.8297 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.9736 | 0.7 | 200 | 0.9359 | 0.4243 | 0.5594 | | 0.8955 | 1.4 | 400 | 0.8320 | 0.5525 | 0.6046 | | 0.7304 | 2.1 | 600 | 0.6237 | 0.7186 | 0.7172 | | 0.5917 | 2.8 | 800 | 0.5618 | 0.7472 | 0.7466 | | 0.5559 | 3.5 | 1000 | 0.5130 | 0.7797 | 0.7790 | | 0.5289 | 4.2 | 1200 | 0.5135 | 0.7817 | 0.7806 | | 0.5077 | 4.9 | 1400 | 0.4961 | 0.7887 | 0.7880 | | 0.5009 | 5.59 | 1600 | 0.5250 | 0.7762 | 0.7755 | | 0.4818 | 6.29 | 1800 | 0.5359 | 0.7696 | 0.7694 | | 0.4752 | 6.99 | 2000 | 0.4866 | 0.7983 | 0.7975 | | 0.4672 | 7.69 | 2200 | 0.4695 | 0.8042 | 0.8036 | | 0.4627 | 8.39 | 2400 | 0.5001 | 0.7922 | 0.7915 | | 0.4567 | 9.09 | 2600 | 0.4895 | 0.7981 | 0.7970 | | 0.4527 | 9.79 | 2800 | 0.4778 | 0.8006 | 0.7999 | | 0.4494 | 10.49 | 3000 | 0.4726 | 0.8036 | 0.8027 | | 0.4408 | 11.19 | 3200 | 0.5001 | 0.7914 | 0.7907 | | 0.4416 | 11.89 | 3400 | 0.4568 | 0.8090 | 0.8082 | | 0.4345 | 12.59 | 3600 | 0.4539 | 0.8130 | 0.8121 | | 0.4319 | 13.29 | 3800 | 0.4542 | 0.8085 | 0.8075 | | 0.4323 | 13.99 | 4000 | 0.4939 | 0.7949 | 0.7942 | | 0.424 | 14.69 | 4200 | 0.4718 | 0.8016 | 0.8007 | | 0.4258 | 15.38 | 4400 | 0.4660 | 0.8062 | 0.8053 | | 0.425 | 16.08 | 4600 | 0.5009 | 0.7920 | 0.7915 | | 0.4145 | 16.78 | 4800 | 0.4552 | 0.8105 | 0.8093 | | 0.4072 | 17.48 | 5000 | 0.4869 | 0.7988 | 0.7979 | | 0.4119 | 18.18 | 5200 | 0.4255 | 0.8253 | 0.8244 | | 0.4111 | 18.88 | 5400 | 0.4648 | 0.8086 | 0.8078 | | 0.4123 | 19.58 | 5600 | 0.4478 | 0.8136 | 0.8128 | | 0.4101 | 20.28 | 5800 | 0.4426 | 0.8194 | 0.8185 | | 0.407 | 20.98 | 6000 | 0.4433 | 0.8161 | 0.8152 | | 0.4058 | 21.68 | 6200 | 0.4663 | 0.8059 | 0.8051 | | 0.4026 | 22.38 | 6400 | 0.4506 | 0.8154 | 0.8146 | | 0.3959 | 23.08 | 6600 | 0.4422 | 0.8207 | 0.8196 | | 0.4027 | 23.78 | 6800 | 0.4401 | 0.8221 | 0.8211 | | 0.3965 | 24.48 | 7000 | 0.4640 | 0.8090 | 0.8082 | | 0.399 | 25.17 | 7200 | 0.4363 | 0.8245 | 0.8235 | | 0.3964 | 25.87 | 7400 | 0.4539 | 0.8137 | 0.8128 | | 0.3919 | 26.57 | 7600 | 0.4657 | 0.8117 | 0.8108 | | 0.3931 | 27.27 | 7800 | 0.4482 | 0.8181 | 0.8172 | | 0.3966 | 27.97 | 8000 | 0.4533 | 0.8161 | 0.8152 | | 0.4005 | 28.67 | 8200 | 0.4518 | 0.8156 | 0.8148 | | 0.3938 | 29.37 | 8400 | 0.4418 | 0.8218 | 0.8207 | | 0.3888 | 30.07 | 8600 | 0.4279 | 0.8278 | 0.8268 | | 0.3895 | 30.77 | 8800 | 0.4521 | 0.8184 | 0.8174 | | 0.3945 | 31.47 | 9000 | 0.4420 | 0.8194 | 0.8185 | | 0.3927 | 32.17 | 9200 | 0.4460 | 0.8199 | 0.8189 | | 0.3907 | 32.87 | 9400 | 0.4429 | 0.8181 | 0.8172 | | 0.3895 | 33.57 | 9600 | 0.4482 | 0.8165 | 0.8157 | | 0.3909 | 34.27 | 9800 | 0.4429 | 0.8199 | 0.8189 | | 0.3878 | 34.97 | 10000 | 0.4457 | 0.8207 | 0.8198 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:33:25+00:00

token-classification

span-marker

# SpanMarker with roberta-large on Jerado/enron_intangibles_ner This is a [SpanMarker](https://github.com/tomaarsen/SpanMarkerNER) model trained on the [Jerado/enron_intangibles_ner](https://huggingface.co/datasets/Jerado/enron_intangibles_ner) dataset that can be used for Named Entity Recognition. This SpanMarker model uses [roberta-large](https://huggingface.co/roberta-large) as the underlying encoder. ## Model Details ### Model Description - **Model Type:** SpanMarker - **Encoder:** [roberta-large](https://huggingface.co/roberta-large) - **Maximum Sequence Length:** 256 tokens - **Maximum Entity Length:** 6 words - **Training Dataset:** [Jerado/enron_intangibles_ner](https://huggingface.co/datasets/Jerado/enron_intangibles_ner) - **Language:** en - **License:** apache-2.0 ### Model Sources - **Repository:** [SpanMarker on GitHub](https://github.com/tomaarsen/SpanMarkerNER) - **Thesis:** [SpanMarker For Named Entity Recognition](https://raw.githubusercontent.com/tomaarsen/SpanMarkerNER/main/thesis.pdf) ### Model Labels | Label | Examples | |:-----------|:--------------------------------------------| | Intangible | "deal", "sample EES deal", "Enpower system" | ## Evaluation ### Metrics | Label | Precision | Recall | F1 | |:-----------|:----------|:-------|:-------| | **all** | 0.4286 | 0.45 | 0.4390 | | Intangible | 0.4286 | 0.45 | 0.4390 | ## Uses ### Direct Use for Inference ```python from span_marker import SpanMarkerModel # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("span_marker_model_id") # Run inference entities = model.predict("It seems that there is a single significant policy concern for the ASIC policy committee.") ``` ### Downstream Use You can finetune this model on your own dataset. <details><summary>Click to expand</summary> ```python from span_marker import SpanMarkerModel, Trainer # Download from the 🤗 Hub model = SpanMarkerModel.from_pretrained("span_marker_model_id") # Specify a Dataset with "tokens" and "ner_tag" columns dataset = load_dataset("conll2003") # For example CoNLL2003 # Initialize a Trainer using the pretrained model & dataset trainer = Trainer( model=model, train_dataset=dataset["train"], eval_dataset=dataset["validation"], ) trainer.train() trainer.save_model("span_marker_model_id-finetuned") ``` </details>    ## Training Details ### Training Set Metrics | Training set | Min | Median | Max | |:----------------------|:----|:--------|:----| | Sentence length | 1 | 19.8706 | 216 | | Entities per sentence | 0 | 0.1865 | 6 | ### Training Hyperparameters - learning_rate: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 11 - mixed_precision_training: Native AMP ### Training Results | Epoch | Step | Validation Loss | Validation Precision | Validation Recall | Validation F1 | Validation Accuracy | |:-------:|:----:|:---------------:|:--------------------:|:-----------------:|:-------------:|:-------------------:| | 3.3557 | 500 | 0.0075 | 0.4444 | 0.1667 | 0.2424 | 0.9753 | | 6.7114 | 1000 | 0.0084 | 0.5714 | 0.3333 | 0.4211 | 0.9793 | | 10.0671 | 1500 | 0.0098 | 0.6111 | 0.4583 | 0.5238 | 0.9815 | ### Framework Versions - Python: 3.10.12 - SpanMarker: 1.5.0 - Transformers: 4.40.0 - PyTorch: 2.2.1+cu121 - Datasets: 2.19.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX ``` @software{Aarsen_SpanMarker, author = {Aarsen, Tom}, license = {Apache-2.0}, title = {{SpanMarker for Named Entity Recognition}}, url = {https://github.com/tomaarsen/SpanMarkerNER} } ```

{"language": ["en"], "license": "apache-2.0", "library_name": "span-marker", "tags": ["span-marker", "token-classification", "ner", "named-entity-recognition", "generated_from_span_marker_trainer"], "datasets": ["Jerado/enron_intangibles_ner"], "metrics": ["precision", "recall", "f1"], "base_model": "roberta-large", "widget": [{"text": "Negotiated rates in these types of deals (basis for new builds) have been allowed to stand for the life of the contracts, in the case of Kern River and Mojave."}, {"text": "It seems that there is a single significant policy concern for the ASIC policy committee."}, {"text": "The appropriate price is in Enpower, but the revenue has never appeared (Deal #590753)."}, {"text": "FYI, to me, a prepayment for a service contract would generally be amortized over the life of the contract."}, {"text": "From: d..steffes @ enron.com To: john.shelk @ enron.com, l..nicolay @ enron.com, richard.shapiro @ enron.com, sarah.novosel @ enron.com Subject: Southern Co.'s Testimony The first order of business is getting the cost / benefit analysis done."}], "pipeline_tag": "token-classification", "model-index": [{"name": "SpanMarker with roberta-large on Jerado/enron_intangibles_ner", "results": [{"task": {"type": "token-classification", "name": "Named Entity Recognition"}, "dataset": {"name": "Unknown", "type": "Jerado/enron_intangibles_ner", "split": "test"}, "metrics": [{"type": "f1", "value": 0.4390243902439024, "name": "F1"}, {"type": "precision", "value": 0.42857142857142855, "name": "Precision"}, {"type": "recall", "value": 0.45, "name": "Recall"}]}]}]}

Jerado/span-marker-roberta-large-enron

null

[ "span-marker", "tensorboard", "safetensors", "token-classification", "ner", "named-entity-recognition", "generated_from_span_marker_trainer", "en", "dataset:Jerado/enron_intangibles_ner", "base_model:roberta-large", "license:apache-2.0", "model-index", "region:us" ]

null

2024-04-29T23:34:21+00:00

image-classification

transformers

# vit-base-patch16-224-in21k-finetuned This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the image_folder dataset. It achieves the following results on the evaluation set: - Loss: 0.9803 - Accuracy: 0.7058 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 32 - eval_batch_size: 32 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - num_epochs: 10 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | 0.4887 | 1.0 | 224 | 0.9213 | 0.6776 | | 0.4969 | 2.0 | 449 | 0.9038 | 0.6927 | | 0.4095 | 3.0 | 673 | 0.9077 | 0.6977 | | 0.3344 | 4.0 | 898 | 0.9398 | 0.6989 | | 0.3055 | 5.0 | 1122 | 0.9803 | 0.7058 | | 0.2214 | 6.0 | 1347 | 1.0337 | 0.6953 | | 0.1575 | 7.0 | 1571 | 1.0642 | 0.6977 | | 0.1169 | 8.0 | 1796 | 1.0829 | 0.7030 | | 0.0917 | 9.0 | 2020 | 1.1121 | 0.7048 | | 0.0785 | 9.98 | 2240 | 1.1280 | 0.7052 | ### Framework versions - Transformers 4.36.0 - Pytorch 2.0.0 - Datasets 2.1.0 - Tokenizers 0.15.0

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["image_folder"], "metrics": ["accuracy"], "base_model": "google/vit-base-patch16-224-in21k", "model-index": [{"name": "vit-base-patch16-224-in21k-finetuned", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "image_folder", "type": "image_folder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.7057676232933965, "name": "Accuracy"}]}]}]}

motheecreator/vit-base-patch16-224-in21k-finetuned

null

[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "dataset:image_folder", "base_model:google/vit-base-patch16-224-in21k", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:34:51+00:00

null

# O0428HMA4 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1449 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.6513 | 0.09 | 10 | 0.2874 | | 0.1942 | 0.18 | 20 | 0.1547 | | 0.1509 | 0.27 | 30 | 0.1700 | | 0.1537 | 0.36 | 40 | 0.1502 | | 0.1503 | 0.45 | 50 | 0.1510 | | 0.1523 | 0.54 | 60 | 0.1494 | | 0.1493 | 0.63 | 70 | 0.1485 | | 0.149 | 0.73 | 80 | 0.1558 | | 0.1477 | 0.82 | 90 | 0.1494 | | 0.1482 | 0.91 | 100 | 0.1487 | | 0.1486 | 1.0 | 110 | 0.1489 | | 0.1454 | 1.09 | 120 | 0.1484 | | 0.1451 | 1.18 | 130 | 0.1500 | | 0.1474 | 1.27 | 140 | 0.1502 | | 0.1491 | 1.36 | 150 | 0.1479 | | 0.145 | 1.45 | 160 | 0.1472 | | 0.1445 | 1.54 | 170 | 0.1464 | | 0.1477 | 1.63 | 180 | 0.1467 | | 0.1467 | 1.72 | 190 | 0.1489 | | 0.1453 | 1.81 | 200 | 0.1484 | | 0.1495 | 1.9 | 210 | 0.1492 | | 0.1464 | 1.99 | 220 | 0.1498 | | 0.1472 | 2.08 | 230 | 0.1478 | | 0.1414 | 2.18 | 240 | 0.1460 | | 0.1427 | 2.27 | 250 | 0.1470 | | 0.1439 | 2.36 | 260 | 0.1478 | | 0.1429 | 2.45 | 270 | 0.1457 | | 0.1407 | 2.54 | 280 | 0.1463 | | 0.1416 | 2.63 | 290 | 0.1461 | | 0.1436 | 2.72 | 300 | 0.1448 | | 0.1437 | 2.81 | 310 | 0.1448 | | 0.1434 | 2.9 | 320 | 0.1449 | | 0.1443 | 2.99 | 330 | 0.1449 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA4", "results": []}]}

Litzy619/O0428HMA4

null

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

null

2024-04-29T23:36:26+00:00

null

# O0428HMA5 This model is a fine-tuned version of [allenai/OLMo-1B](https://huggingface.co/allenai/OLMo-1B) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.1828 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0003 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 16 - total_train_batch_size: 128 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine_with_restarts - lr_scheduler_warmup_steps: 80 - num_epochs: 3 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.5402 | 0.09 | 10 | 0.1748 | | 0.1661 | 0.18 | 20 | 0.1584 | | 0.1504 | 0.27 | 30 | 0.1670 | | 0.1555 | 0.36 | 40 | 0.1533 | | 0.1499 | 0.45 | 50 | 0.1547 | | 0.1505 | 0.54 | 60 | 0.1519 | | 0.1523 | 0.63 | 70 | 0.1469 | | 0.1513 | 0.73 | 80 | 0.1567 | | 0.1456 | 0.82 | 90 | 0.1465 | | 0.1843 | 0.91 | 100 | 0.2555 | | 1.2658 | 1.0 | 110 | 0.2093 | | 0.8089 | 1.09 | 120 | 0.1813 | | 0.1539 | 1.18 | 130 | 0.1515 | | 1.0124 | 1.27 | 140 | 0.1645 | | 0.3947 | 1.36 | 150 | 0.1674 | | 0.3807 | 1.45 | 160 | 0.1619 | | 0.1511 | 1.54 | 170 | 0.1515 | | 0.1524 | 1.63 | 180 | 0.1492 | | 0.1488 | 1.72 | 190 | 0.1483 | | 0.1513 | 1.81 | 200 | 0.1556 | | 0.5422 | 1.9 | 210 | 0.8696 | | 0.7566 | 1.99 | 220 | 1.3407 | | 0.4939 | 2.08 | 230 | 0.2669 | | 0.2818 | 2.18 | 240 | 0.2439 | | 0.2348 | 2.27 | 250 | 0.2392 | | 0.2358 | 2.36 | 260 | 0.2121 | | 0.1847 | 2.45 | 270 | 0.1995 | | 0.1858 | 2.54 | 280 | 0.1898 | | 0.1845 | 2.63 | 290 | 0.1867 | | 0.1889 | 2.72 | 300 | 0.1845 | | 0.1746 | 2.81 | 310 | 0.1841 | | 0.1758 | 2.9 | 320 | 0.1830 | | 0.1739 | 2.99 | 330 | 0.1828 | ### Framework versions - Transformers 4.36.0.dev0 - Pytorch 2.1.2+cu121 - Datasets 2.14.6 - Tokenizers 0.14.1

{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "allenai/OLMo-1B", "model-index": [{"name": "O0428HMA5", "results": []}]}

Litzy619/O0428HMA5

null

[ "safetensors", "generated_from_trainer", "base_model:allenai/OLMo-1B", "license:apache-2.0", "region:us" ]

null

2024-04-29T23:36:58+00:00

fill-mask

transformers

{}

kumarme072/med_model

null

[ "transformers", "pytorch", "bert", "fill-mask", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:37:11+00:00

null

peft

# GUE_splice_reconstructed-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_splice_reconstructed](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_splice_reconstructed) dataset. It achieves the following results on the evaluation set: - Loss: 0.3148 - F1 Score: 0.8880 - Accuracy: 0.8875 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.9568 | 0.7 | 200 | 0.8950 | 0.4693 | 0.5673 | | 0.6475 | 1.4 | 400 | 0.5182 | 0.7698 | 0.7687 | | 0.4734 | 2.1 | 600 | 0.4341 | 0.8266 | 0.8255 | | 0.4255 | 2.8 | 800 | 0.4334 | 0.8231 | 0.8222 | | 0.4049 | 3.5 | 1000 | 0.3792 | 0.8512 | 0.8507 | | 0.3848 | 4.2 | 1200 | 0.3946 | 0.8418 | 0.8406 | | 0.3664 | 4.9 | 1400 | 0.3594 | 0.8643 | 0.8639 | | 0.3572 | 5.59 | 1600 | 0.3911 | 0.8544 | 0.8544 | | 0.3383 | 6.29 | 1800 | 0.3998 | 0.8440 | 0.8428 | | 0.3319 | 6.99 | 2000 | 0.3653 | 0.8626 | 0.8617 | | 0.3186 | 7.69 | 2200 | 0.3655 | 0.8607 | 0.8599 | | 0.3139 | 8.39 | 2400 | 0.3510 | 0.8691 | 0.8687 | | 0.3 | 9.09 | 2600 | 0.3975 | 0.8510 | 0.8496 | | 0.2952 | 9.79 | 2800 | 0.3840 | 0.8549 | 0.8540 | | 0.2908 | 10.49 | 3000 | 0.3742 | 0.8605 | 0.8597 | | 0.2825 | 11.19 | 3200 | 0.3894 | 0.8564 | 0.8553 | | 0.2785 | 11.89 | 3400 | 0.4033 | 0.8485 | 0.8474 | | 0.2689 | 12.59 | 3600 | 0.3563 | 0.8663 | 0.8656 | | 0.2693 | 13.29 | 3800 | 0.3235 | 0.8788 | 0.8781 | | 0.2599 | 13.99 | 4000 | 0.3665 | 0.8618 | 0.8608 | | 0.2526 | 14.69 | 4200 | 0.3841 | 0.8527 | 0.8516 | | 0.2551 | 15.38 | 4400 | 0.3398 | 0.8716 | 0.8709 | | 0.2465 | 16.08 | 4600 | 0.3716 | 0.8619 | 0.8610 | | 0.2412 | 16.78 | 4800 | 0.3420 | 0.8727 | 0.8720 | | 0.2318 | 17.48 | 5000 | 0.3872 | 0.8544 | 0.8534 | | 0.233 | 18.18 | 5200 | 0.3430 | 0.8794 | 0.8786 | | 0.2291 | 18.88 | 5400 | 0.3565 | 0.8727 | 0.8720 | | 0.2272 | 19.58 | 5600 | 0.3474 | 0.8732 | 0.8724 | | 0.2301 | 20.28 | 5800 | 0.3183 | 0.8874 | 0.8869 | | 0.2263 | 20.98 | 6000 | 0.3270 | 0.8810 | 0.8803 | | 0.2177 | 21.68 | 6200 | 0.3308 | 0.8798 | 0.8792 | | 0.2101 | 22.38 | 6400 | 0.3555 | 0.8756 | 0.8748 | | 0.207 | 23.08 | 6600 | 0.3779 | 0.8713 | 0.8705 | | 0.2081 | 23.78 | 6800 | 0.3397 | 0.8777 | 0.8770 | | 0.2066 | 24.48 | 7000 | 0.3502 | 0.8741 | 0.8735 | | 0.2035 | 25.17 | 7200 | 0.3394 | 0.8797 | 0.8790 | | 0.2013 | 25.87 | 7400 | 0.3254 | 0.8831 | 0.8825 | | 0.2025 | 26.57 | 7600 | 0.3582 | 0.8719 | 0.8711 | | 0.1927 | 27.27 | 7800 | 0.3586 | 0.8739 | 0.8733 | | 0.199 | 27.97 | 8000 | 0.3353 | 0.8802 | 0.8797 | | 0.1981 | 28.67 | 8200 | 0.3429 | 0.8786 | 0.8779 | | 0.1902 | 29.37 | 8400 | 0.3422 | 0.8805 | 0.8799 | | 0.1851 | 30.07 | 8600 | 0.3371 | 0.8825 | 0.8819 | | 0.1849 | 30.77 | 8800 | 0.3418 | 0.8806 | 0.8799 | | 0.1905 | 31.47 | 9000 | 0.3456 | 0.8813 | 0.8805 | | 0.1859 | 32.17 | 9200 | 0.3474 | 0.8804 | 0.8797 | | 0.1835 | 32.87 | 9400 | 0.3517 | 0.8792 | 0.8786 | | 0.1812 | 33.57 | 9600 | 0.3509 | 0.8780 | 0.8772 | | 0.1855 | 34.27 | 9800 | 0.3465 | 0.8797 | 0.8790 | | 0.1803 | 34.97 | 10000 | 0.3489 | 0.8791 | 0.8783 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_splice_reconstructed-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_splice_reconstructed-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:37:38+00:00

null

peft

# GUE_tf_0-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3880 - F1 Score: 0.8258 - Accuracy: 0.827 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5566 | 0.79 | 200 | 0.4955 | 0.7418 | 0.742 | | 0.4995 | 1.58 | 400 | 0.4868 | 0.7579 | 0.759 | | 0.4928 | 2.37 | 600 | 0.4896 | 0.7527 | 0.755 | | 0.485 | 3.16 | 800 | 0.4796 | 0.7528 | 0.753 | | 0.4787 | 3.95 | 1000 | 0.4851 | 0.7654 | 0.767 | | 0.4775 | 4.74 | 1200 | 0.4849 | 0.7598 | 0.76 | | 0.4732 | 5.53 | 1400 | 0.4833 | 0.7550 | 0.755 | | 0.466 | 6.32 | 1600 | 0.4861 | 0.7570 | 0.757 | | 0.4682 | 7.11 | 1800 | 0.4846 | 0.7611 | 0.761 | | 0.4712 | 7.91 | 2000 | 0.4785 | 0.7660 | 0.766 | | 0.4637 | 8.7 | 2200 | 0.4764 | 0.7655 | 0.766 | | 0.462 | 9.49 | 2400 | 0.4754 | 0.7651 | 0.766 | | 0.461 | 10.28 | 2600 | 0.4737 | 0.7670 | 0.767 | | 0.4591 | 11.07 | 2800 | 0.4673 | 0.7701 | 0.77 | | 0.4564 | 11.86 | 3000 | 0.4715 | 0.7640 | 0.764 | | 0.4578 | 12.65 | 3200 | 0.4688 | 0.7691 | 0.769 | | 0.4553 | 13.44 | 3400 | 0.4711 | 0.7751 | 0.776 | | 0.4557 | 14.23 | 3600 | 0.4665 | 0.7696 | 0.77 | | 0.4541 | 15.02 | 3800 | 0.4668 | 0.772 | 0.772 | | 0.4552 | 15.81 | 4000 | 0.4691 | 0.7740 | 0.774 | | 0.4473 | 16.6 | 4200 | 0.4721 | 0.7781 | 0.779 | | 0.4516 | 17.39 | 4400 | 0.4703 | 0.7691 | 0.769 | | 0.4499 | 18.18 | 4600 | 0.4715 | 0.7669 | 0.767 | | 0.451 | 18.97 | 4800 | 0.4626 | 0.774 | 0.774 | | 0.4541 | 19.76 | 5000 | 0.4618 | 0.7777 | 0.778 | | 0.4473 | 20.55 | 5200 | 0.4641 | 0.7814 | 0.782 | | 0.4447 | 21.34 | 5400 | 0.4652 | 0.7689 | 0.769 | | 0.4457 | 22.13 | 5600 | 0.4680 | 0.7700 | 0.77 | | 0.4473 | 22.92 | 5800 | 0.4659 | 0.7750 | 0.775 | | 0.4429 | 23.72 | 6000 | 0.4655 | 0.7690 | 0.769 | | 0.4429 | 24.51 | 6200 | 0.4647 | 0.7787 | 0.779 | | 0.4483 | 25.3 | 6400 | 0.4645 | 0.7690 | 0.769 | | 0.4415 | 26.09 | 6600 | 0.4655 | 0.7708 | 0.771 | | 0.4451 | 26.88 | 6800 | 0.4653 | 0.7720 | 0.772 | | 0.4441 | 27.67 | 7000 | 0.4623 | 0.7736 | 0.774 | | 0.444 | 28.46 | 7200 | 0.4631 | 0.7834 | 0.784 | | 0.4444 | 29.25 | 7400 | 0.4622 | 0.7727 | 0.773 | | 0.4439 | 30.04 | 7600 | 0.4636 | 0.7759 | 0.776 | | 0.4431 | 30.83 | 7800 | 0.4621 | 0.7789 | 0.779 | | 0.4435 | 31.62 | 8000 | 0.4631 | 0.7855 | 0.786 | | 0.441 | 32.41 | 8200 | 0.4607 | 0.7768 | 0.777 | | 0.4348 | 33.2 | 8400 | 0.4637 | 0.7729 | 0.773 | | 0.4412 | 33.99 | 8600 | 0.4638 | 0.7786 | 0.779 | | 0.4422 | 34.78 | 8800 | 0.4624 | 0.7806 | 0.781 | | 0.4369 | 35.57 | 9000 | 0.4626 | 0.7748 | 0.775 | | 0.4406 | 36.36 | 9200 | 0.4640 | 0.7710 | 0.771 | | 0.4422 | 37.15 | 9400 | 0.4626 | 0.7739 | 0.774 | | 0.4391 | 37.94 | 9600 | 0.4625 | 0.7728 | 0.773 | | 0.4385 | 38.74 | 9800 | 0.4631 | 0.7759 | 0.776 | | 0.443 | 39.53 | 10000 | 0.4627 | 0.7749 | 0.775 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_0-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_0-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:38:32+00:00

null

peft

# GUE_tf_0-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3833 - F1 Score: 0.8273 - Accuracy: 0.828 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5365 | 0.79 | 200 | 0.4925 | 0.7532 | 0.755 | | 0.4867 | 1.58 | 400 | 0.4771 | 0.7669 | 0.767 | | 0.4762 | 2.37 | 600 | 0.4799 | 0.7580 | 0.759 | | 0.4678 | 3.16 | 800 | 0.4709 | 0.7745 | 0.775 | | 0.4622 | 3.95 | 1000 | 0.4691 | 0.7805 | 0.781 | | 0.459 | 4.74 | 1200 | 0.4736 | 0.7779 | 0.778 | | 0.4553 | 5.53 | 1400 | 0.4769 | 0.7719 | 0.772 | | 0.4466 | 6.32 | 1600 | 0.4755 | 0.7741 | 0.774 | | 0.4504 | 7.11 | 1800 | 0.4722 | 0.7690 | 0.769 | | 0.4491 | 7.91 | 2000 | 0.4698 | 0.7750 | 0.775 | | 0.4423 | 8.7 | 2200 | 0.4634 | 0.7727 | 0.773 | | 0.439 | 9.49 | 2400 | 0.4636 | 0.7749 | 0.775 | | 0.4379 | 10.28 | 2600 | 0.4667 | 0.7801 | 0.78 | | 0.435 | 11.07 | 2800 | 0.4657 | 0.7808 | 0.781 | | 0.4313 | 11.86 | 3000 | 0.4738 | 0.7790 | 0.779 | | 0.4291 | 12.65 | 3200 | 0.4638 | 0.7791 | 0.779 | | 0.4273 | 13.44 | 3400 | 0.4707 | 0.7711 | 0.771 | | 0.4279 | 14.23 | 3600 | 0.4659 | 0.7860 | 0.786 | | 0.4282 | 15.02 | 3800 | 0.4653 | 0.7770 | 0.777 | | 0.4238 | 15.81 | 4000 | 0.4612 | 0.7810 | 0.781 | | 0.4187 | 16.6 | 4200 | 0.4643 | 0.7868 | 0.787 | | 0.4225 | 17.39 | 4400 | 0.4655 | 0.7790 | 0.779 | | 0.4187 | 18.18 | 4600 | 0.4665 | 0.7800 | 0.78 | | 0.42 | 18.97 | 4800 | 0.4664 | 0.7819 | 0.782 | | 0.4225 | 19.76 | 5000 | 0.4657 | 0.7880 | 0.788 | | 0.4184 | 20.55 | 5200 | 0.4636 | 0.7890 | 0.789 | | 0.413 | 21.34 | 5400 | 0.4739 | 0.7756 | 0.776 | | 0.4138 | 22.13 | 5600 | 0.4721 | 0.7781 | 0.778 | | 0.4146 | 22.92 | 5800 | 0.4718 | 0.78 | 0.78 | | 0.4088 | 23.72 | 6000 | 0.4694 | 0.7840 | 0.784 | | 0.4076 | 24.51 | 6200 | 0.4614 | 0.7861 | 0.786 | | 0.4126 | 25.3 | 6400 | 0.4663 | 0.7861 | 0.786 | | 0.4063 | 26.09 | 6600 | 0.4671 | 0.7860 | 0.786 | | 0.4093 | 26.88 | 6800 | 0.4644 | 0.7861 | 0.786 | | 0.4093 | 27.67 | 7000 | 0.4654 | 0.7900 | 0.79 | | 0.4086 | 28.46 | 7200 | 0.4638 | 0.7870 | 0.787 | | 0.4068 | 29.25 | 7400 | 0.4683 | 0.7821 | 0.782 | | 0.4083 | 30.04 | 7600 | 0.4685 | 0.7870 | 0.787 | | 0.4046 | 30.83 | 7800 | 0.4658 | 0.7891 | 0.789 | | 0.4055 | 31.62 | 8000 | 0.4639 | 0.7859 | 0.786 | | 0.4045 | 32.41 | 8200 | 0.4713 | 0.7850 | 0.785 | | 0.3976 | 33.2 | 8400 | 0.4701 | 0.7830 | 0.783 | | 0.4032 | 33.99 | 8600 | 0.4697 | 0.7890 | 0.789 | | 0.4056 | 34.78 | 8800 | 0.4617 | 0.7909 | 0.791 | | 0.3969 | 35.57 | 9000 | 0.4649 | 0.7940 | 0.794 | | 0.401 | 36.36 | 9200 | 0.4788 | 0.7800 | 0.78 | | 0.4014 | 37.15 | 9400 | 0.4727 | 0.7850 | 0.785 | | 0.4023 | 37.94 | 9600 | 0.4697 | 0.7881 | 0.788 | | 0.4004 | 38.74 | 9800 | 0.4719 | 0.7870 | 0.787 | | 0.4029 | 39.53 | 10000 | 0.4708 | 0.7881 | 0.788 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_0-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_0-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:39:27+00:00

null

peft

# GUE_tf_1-seqsight_16384_512_34M-L1_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3443 - F1 Score: 0.8566 - Accuracy: 0.857 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5709 | 0.83 | 200 | 0.5541 | 0.7178 | 0.718 | | 0.5176 | 1.67 | 400 | 0.5487 | 0.7354 | 0.736 | | 0.5088 | 2.5 | 600 | 0.5363 | 0.7390 | 0.739 | | 0.4984 | 3.33 | 800 | 0.5325 | 0.7336 | 0.734 | | 0.5006 | 4.17 | 1000 | 0.5220 | 0.7469 | 0.747 | | 0.4921 | 5.0 | 1200 | 0.5261 | 0.7460 | 0.746 | | 0.4893 | 5.83 | 1400 | 0.5191 | 0.7490 | 0.749 | | 0.4896 | 6.67 | 1600 | 0.5218 | 0.7490 | 0.749 | | 0.4846 | 7.5 | 1800 | 0.5249 | 0.7435 | 0.744 | | 0.4803 | 8.33 | 2000 | 0.5178 | 0.7439 | 0.744 | | 0.4806 | 9.17 | 2200 | 0.5187 | 0.744 | 0.744 | | 0.4801 | 10.0 | 2400 | 0.5290 | 0.7394 | 0.74 | | 0.4778 | 10.83 | 2600 | 0.5270 | 0.7473 | 0.748 | | 0.477 | 11.67 | 2800 | 0.5226 | 0.7503 | 0.751 | | 0.4707 | 12.5 | 3000 | 0.5218 | 0.7467 | 0.747 | | 0.4787 | 13.33 | 3200 | 0.5133 | 0.7496 | 0.75 | | 0.4692 | 14.17 | 3400 | 0.5164 | 0.7450 | 0.745 | | 0.4721 | 15.0 | 3600 | 0.5230 | 0.7448 | 0.746 | | 0.4674 | 15.83 | 3800 | 0.5129 | 0.7487 | 0.749 | | 0.4726 | 16.67 | 4000 | 0.5229 | 0.7428 | 0.743 | | 0.4682 | 17.5 | 4200 | 0.5178 | 0.7435 | 0.744 | | 0.4651 | 18.33 | 4400 | 0.5202 | 0.7450 | 0.745 | | 0.4678 | 19.17 | 4600 | 0.5233 | 0.7444 | 0.745 | | 0.4697 | 20.0 | 4800 | 0.5136 | 0.7459 | 0.746 | | 0.4686 | 20.83 | 5000 | 0.5201 | 0.7438 | 0.744 | | 0.4631 | 21.67 | 5200 | 0.5131 | 0.7438 | 0.744 | | 0.468 | 22.5 | 5400 | 0.5125 | 0.7450 | 0.745 | | 0.4634 | 23.33 | 5600 | 0.5146 | 0.7485 | 0.749 | | 0.4641 | 24.17 | 5800 | 0.5232 | 0.7451 | 0.746 | | 0.4662 | 25.0 | 6000 | 0.5133 | 0.7470 | 0.747 | | 0.4635 | 25.83 | 6200 | 0.5146 | 0.7488 | 0.749 | | 0.4611 | 26.67 | 6400 | 0.5150 | 0.7430 | 0.743 | | 0.4635 | 27.5 | 6600 | 0.5174 | 0.7509 | 0.751 | | 0.4624 | 28.33 | 6800 | 0.5121 | 0.7518 | 0.752 | | 0.4603 | 29.17 | 7000 | 0.5150 | 0.7469 | 0.747 | | 0.4637 | 30.0 | 7200 | 0.5141 | 0.7447 | 0.745 | | 0.4618 | 30.83 | 7400 | 0.5182 | 0.7402 | 0.741 | | 0.458 | 31.67 | 7600 | 0.5136 | 0.7479 | 0.748 | | 0.4619 | 32.5 | 7800 | 0.5121 | 0.7509 | 0.751 | | 0.4583 | 33.33 | 8000 | 0.5120 | 0.7468 | 0.747 | | 0.4623 | 34.17 | 8200 | 0.5123 | 0.7488 | 0.749 | | 0.4579 | 35.0 | 8400 | 0.5129 | 0.7499 | 0.75 | | 0.4588 | 35.83 | 8600 | 0.5113 | 0.7529 | 0.753 | | 0.4592 | 36.67 | 8800 | 0.5113 | 0.7498 | 0.75 | | 0.4591 | 37.5 | 9000 | 0.5152 | 0.7454 | 0.746 | | 0.4583 | 38.33 | 9200 | 0.5128 | 0.7477 | 0.748 | | 0.4569 | 39.17 | 9400 | 0.5135 | 0.7478 | 0.748 | | 0.4589 | 40.0 | 9600 | 0.5125 | 0.7477 | 0.748 | | 0.4584 | 40.83 | 9800 | 0.5116 | 0.7529 | 0.753 | | 0.4587 | 41.67 | 10000 | 0.5119 | 0.7478 | 0.748 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_1-seqsight_16384_512_34M-L1_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_1-seqsight_16384_512_34M-L1_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:39:33+00:00

null

peft

# GUE_tf_0-seqsight_16384_512_34M-L32_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_0](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_0) dataset. It achieves the following results on the evaluation set: - Loss: 0.3839 - F1 Score: 0.8256 - Accuracy: 0.826 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5242 | 0.79 | 200 | 0.4834 | 0.7550 | 0.755 | | 0.4806 | 1.58 | 400 | 0.4685 | 0.7661 | 0.766 | | 0.4675 | 2.37 | 600 | 0.4716 | 0.7623 | 0.764 | | 0.4574 | 3.16 | 800 | 0.4653 | 0.7724 | 0.773 | | 0.4528 | 3.95 | 1000 | 0.4541 | 0.7817 | 0.782 | | 0.447 | 4.74 | 1200 | 0.4639 | 0.7820 | 0.782 | | 0.4392 | 5.53 | 1400 | 0.4776 | 0.7713 | 0.772 | | 0.431 | 6.32 | 1600 | 0.4656 | 0.7821 | 0.782 | | 0.4325 | 7.11 | 1800 | 0.4792 | 0.7837 | 0.784 | | 0.4314 | 7.91 | 2000 | 0.4691 | 0.7817 | 0.782 | | 0.4209 | 8.7 | 2200 | 0.4635 | 0.7780 | 0.778 | | 0.417 | 9.49 | 2400 | 0.4631 | 0.7901 | 0.79 | | 0.4161 | 10.28 | 2600 | 0.4716 | 0.7778 | 0.778 | | 0.4117 | 11.07 | 2800 | 0.4661 | 0.7829 | 0.783 | | 0.4058 | 11.86 | 3000 | 0.4822 | 0.7951 | 0.795 | | 0.4036 | 12.65 | 3200 | 0.4651 | 0.7950 | 0.795 | | 0.4009 | 13.44 | 3400 | 0.4793 | 0.7820 | 0.782 | | 0.3979 | 14.23 | 3600 | 0.4829 | 0.7880 | 0.788 | | 0.3987 | 15.02 | 3800 | 0.4881 | 0.7785 | 0.779 | | 0.392 | 15.81 | 4000 | 0.4660 | 0.7817 | 0.782 | | 0.3841 | 16.6 | 4200 | 0.4911 | 0.7859 | 0.786 | | 0.389 | 17.39 | 4400 | 0.4863 | 0.7864 | 0.787 | | 0.3843 | 18.18 | 4600 | 0.4741 | 0.7940 | 0.794 | | 0.3808 | 18.97 | 4800 | 0.4995 | 0.7855 | 0.786 | | 0.383 | 19.76 | 5000 | 0.4754 | 0.8030 | 0.803 | | 0.3783 | 20.55 | 5200 | 0.4800 | 0.7910 | 0.791 | | 0.3695 | 21.34 | 5400 | 0.4866 | 0.7873 | 0.788 | | 0.3702 | 22.13 | 5600 | 0.5081 | 0.7868 | 0.787 | | 0.3704 | 22.92 | 5800 | 0.4963 | 0.7856 | 0.786 | | 0.3621 | 23.72 | 6000 | 0.4948 | 0.7919 | 0.792 | | 0.3587 | 24.51 | 6200 | 0.4883 | 0.7959 | 0.796 | | 0.3623 | 25.3 | 6400 | 0.4956 | 0.7979 | 0.798 | | 0.3566 | 26.09 | 6600 | 0.5052 | 0.7970 | 0.797 | | 0.3588 | 26.88 | 6800 | 0.4934 | 0.798 | 0.798 | | 0.3539 | 27.67 | 7000 | 0.4943 | 0.7980 | 0.798 | | 0.353 | 28.46 | 7200 | 0.4906 | 0.7971 | 0.797 | | 0.3503 | 29.25 | 7400 | 0.5178 | 0.7929 | 0.793 | | 0.3509 | 30.04 | 7600 | 0.5186 | 0.7926 | 0.793 | | 0.3461 | 30.83 | 7800 | 0.4992 | 0.7980 | 0.798 | | 0.347 | 31.62 | 8000 | 0.4962 | 0.7961 | 0.796 | | 0.3431 | 32.41 | 8200 | 0.5253 | 0.7919 | 0.792 | | 0.3361 | 33.2 | 8400 | 0.5124 | 0.8000 | 0.8 | | 0.3396 | 33.99 | 8600 | 0.5218 | 0.7870 | 0.787 | | 0.3421 | 34.78 | 8800 | 0.5119 | 0.7940 | 0.794 | | 0.3344 | 35.57 | 9000 | 0.5144 | 0.7970 | 0.797 | | 0.3374 | 36.36 | 9200 | 0.5282 | 0.7898 | 0.79 | | 0.3366 | 37.15 | 9400 | 0.5282 | 0.7968 | 0.797 | | 0.3394 | 37.94 | 9600 | 0.5204 | 0.7949 | 0.795 | | 0.3358 | 38.74 | 9800 | 0.5254 | 0.7908 | 0.791 | | 0.3352 | 39.53 | 10000 | 0.5221 | 0.7899 | 0.79 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_0-seqsight_16384_512_34M-L32_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_0-seqsight_16384_512_34M-L32_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:39:33+00:00

text-classification

transformers

# output_dir This model is a fine-tuned version of [microsoft/deberta-v3-base](https://huggingface.co/microsoft/deberta-v3-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0625 - F Beta Score: 0.9639 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - distributed_type: multi-GPU - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - num_epochs: 3.0 ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2

{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "microsoft/deberta-v3-base", "model-index": [{"name": "output_dir", "results": []}]}

tralon/test-1

null

[ "transformers", "safetensors", "deberta-v2", "text-classification", "generated_from_trainer", "base_model:microsoft/deberta-v3-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

null

2024-04-29T23:40:13+00:00

null

peft

# GUE_tf_1-seqsight_16384_512_34M-L8_f This model is a fine-tuned version of [mahdibaghbanzadeh/seqsight_16384_512_34M](https://huggingface.co/mahdibaghbanzadeh/seqsight_16384_512_34M) on the [mahdibaghbanzadeh/GUE_tf_1](https://huggingface.co/datasets/mahdibaghbanzadeh/GUE_tf_1) dataset. It achieves the following results on the evaluation set: - Loss: 0.3442 - F1 Score: 0.8604 - Accuracy: 0.861 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0005 - train_batch_size: 128 - eval_batch_size: 128 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - training_steps: 10000 ### Training results | Training Loss | Epoch | Step | Validation Loss | F1 Score | Accuracy | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:| | 0.5535 | 0.83 | 200 | 0.5407 | 0.7405 | 0.741 | | 0.5038 | 1.67 | 400 | 0.5375 | 0.7299 | 0.731 | | 0.4946 | 2.5 | 600 | 0.5248 | 0.7479 | 0.748 | | 0.4839 | 3.33 | 800 | 0.5167 | 0.7489 | 0.749 | | 0.4854 | 4.17 | 1000 | 0.5142 | 0.7467 | 0.747 | | 0.4766 | 5.0 | 1200 | 0.5160 | 0.7447 | 0.745 | | 0.474 | 5.83 | 1400 | 0.5106 | 0.7409 | 0.741 | | 0.4718 | 6.67 | 1600 | 0.5166 | 0.7460 | 0.746 | | 0.4686 | 7.5 | 1800 | 0.5213 | 0.7373 | 0.738 | | 0.4628 | 8.33 | 2000 | 0.5105 | 0.7410 | 0.741 | | 0.4642 | 9.17 | 2200 | 0.5105 | 0.7440 | 0.744 | | 0.4616 | 10.0 | 2400 | 0.5230 | 0.7332 | 0.735 | | 0.4576 | 10.83 | 2600 | 0.5130 | 0.7532 | 0.754 | | 0.4571 | 11.67 | 2800 | 0.5117 | 0.7494 | 0.75 | | 0.4495 | 12.5 | 3000 | 0.5129 | 0.7423 | 0.743 | | 0.4567 | 13.33 | 3200 | 0.5032 | 0.7451 | 0.746 | | 0.4475 | 14.17 | 3400 | 0.5015 | 0.7509 | 0.751 | | 0.4504 | 15.0 | 3600 | 0.5042 | 0.7496 | 0.751 | | 0.4428 | 15.83 | 3800 | 0.5024 | 0.7472 | 0.748 | | 0.4479 | 16.67 | 4000 | 0.4999 | 0.7579 | 0.758 | | 0.4428 | 17.5 | 4200 | 0.5085 | 0.7450 | 0.747 | | 0.4372 | 18.33 | 4400 | 0.5049 | 0.7590 | 0.759 | | 0.4422 | 19.17 | 4600 | 0.5086 | 0.7562 | 0.757 | | 0.4409 | 20.0 | 4800 | 0.5002 | 0.7598 | 0.76 | | 0.4393 | 20.83 | 5000 | 0.5060 | 0.7518 | 0.752 | | 0.435 | 21.67 | 5200 | 0.5017 | 0.7497 | 0.75 | | 0.4373 | 22.5 | 5400 | 0.5013 | 0.7549 | 0.755 | | 0.4324 | 23.33 | 5600 | 0.4973 | 0.7528 | 0.754 | | 0.4335 | 24.17 | 5800 | 0.5082 | 0.7549 | 0.756 | | 0.4363 | 25.0 | 6000 | 0.4985 | 0.7540 | 0.754 | | 0.4317 | 25.83 | 6200 | 0.5002 | 0.7547 | 0.755 | | 0.4289 | 26.67 | 6400 | 0.4995 | 0.7620 | 0.762 | | 0.4316 | 27.5 | 6600 | 0.5025 | 0.7690 | 0.769 | | 0.4286 | 28.33 | 6800 | 0.5010 | 0.7550 | 0.755 | | 0.4252 | 29.17 | 7000 | 0.5014 | 0.7607 | 0.761 | | 0.4286 | 30.0 | 7200 | 0.4985 | 0.7586 | 0.759 | | 0.4261 | 30.83 | 7400 | 0.5018 | 0.7611 | 0.762 | | 0.4218 | 31.67 | 7600 | 0.4993 | 0.7560 | 0.756 | | 0.4264 | 32.5 | 7800 | 0.4999 | 0.7558 | 0.756 | | 0.4225 | 33.33 | 8000 | 0.5014 | 0.7589 | 0.759 | | 0.4242 | 34.17 | 8200 | 0.5008 | 0.7637 | 0.764 | | 0.4198 | 35.0 | 8400 | 0.5014 | 0.7635 | 0.764 | | 0.4205 | 35.83 | 8600 | 0.5003 | 0.7569 | 0.757 | | 0.4197 | 36.67 | 8800 | 0.4988 | 0.7525 | 0.753 | | 0.4188 | 37.5 | 9000 | 0.5031 | 0.7518 | 0.753 | | 0.4191 | 38.33 | 9200 | 0.5023 | 0.7577 | 0.758 | | 0.4166 | 39.17 | 9400 | 0.5018 | 0.7626 | 0.763 | | 0.4221 | 40.0 | 9600 | 0.5011 | 0.7635 | 0.764 | | 0.4198 | 40.83 | 9800 | 0.5008 | 0.7539 | 0.754 | | 0.4195 | 41.67 | 10000 | 0.5006 | 0.7597 | 0.76 | ### Framework versions - PEFT 0.9.0 - Transformers 4.38.2 - Pytorch 2.2.0+cu121 - Datasets 2.17.1 - Tokenizers 0.15.2

{"library_name": "peft", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "mahdibaghbanzadeh/seqsight_16384_512_34M", "model-index": [{"name": "GUE_tf_1-seqsight_16384_512_34M-L8_f", "results": []}]}

mahdibaghbanzadeh/GUE_tf_1-seqsight_16384_512_34M-L8_f

null

[ "peft", "safetensors", "generated_from_trainer", "base_model:mahdibaghbanzadeh/seqsight_16384_512_34M", "region:us" ]

null

2024-04-29T23:41:03+00:00