Datasets:

ftopal
/

huggingface-models-raw

Dataset card Data Studio Files Files and versions Community

Split (1)

train · 648k rows

Search is not available for this dataset

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
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": []}	Weathers/DialoGPT-small-cartman	null	[ "transformers", "safetensors", "gpt2", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:02:18+00:00
null	null		{}	arda1319/ner	null	[ "region:us" ]	null	2024-05-01T20:02:43+00:00
null	null		{"license": "other", "tags": ["lora"], "license_name": "yi-license", "license_link": "LICENSE"}	adamo1139/Yi-34B-200K-XLCTX-AEZAKMI-RAW-LoRA-2904	null	[ "safetensors", "lora", "license:other", "region:us" ]	null	2024-05-01T20:03:44+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="bcama/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}]}]}]}	bcama/q-FrozenLake-v1-4x4-noSlippery	null	[ "FrozenLake-v1-4x4-no_slippery", "q-learning", "reinforcement-learning", "custom-implementation", "model-index", "region:us" ]	null	2024-05-01T20:05:19+00:00
null	null		{}	dgver507/ElChombo	null	[ "region:us" ]	null	2024-05-01T20:05:46+00:00
null	null		{}	smithvagyok/rlearning	null	[ "region:us" ]	null	2024-05-01T20:06:11+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. --> # beit-base-patch16-224-c9fdf34b-e763-4cf0-b38d-2601d6b23e7e This model is a fine-tuned version of [microsoft/beit-base-patch16-224](https://huggingface.co/microsoft/beit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.7275 - Accuracy: 0.8714 ## Model description 16 ile 55 beraber 100 epoch 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: 100 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-------:\|:----:\|:---------------:\|:--------:\| \| No log \| 0.9231 \| 3 \| 0.6560 \| 0.5714 \| \| No log \| 1.8462 \| 6 \| 0.6840 \| 0.6286 \| \| No log \| 2.7692 \| 9 \| 0.6251 \| 0.6429 \| \| 0.7482 \| 4.0 \| 13 \| 0.5894 \| 0.6857 \| \| 0.7482 \| 4.9231 \| 16 \| 0.5609 \| 0.6571 \| \| 0.7482 \| 5.8462 \| 19 \| 0.5867 \| 0.6714 \| \| 0.6203 \| 6.7692 \| 22 \| 0.5519 \| 0.7429 \| \| 0.6203 \| 8.0 \| 26 \| 0.5128 \| 0.7571 \| \| 0.6203 \| 8.9231 \| 29 \| 0.8879 \| 0.5143 \| \| 0.5637 \| 9.8462 \| 32 \| 0.5315 \| 0.6714 \| \| 0.5637 \| 10.7692 \| 35 \| 0.6999 \| 0.5571 \| \| 0.5637 \| 12.0 \| 39 \| 0.4701 \| 0.7714 \| \| 0.5773 \| 12.9231 \| 42 \| 0.5851 \| 0.7429 \| \| 0.5773 \| 13.8462 \| 45 \| 0.4541 \| 0.8286 \| \| 0.5773 \| 14.7692 \| 48 \| 0.4378 \| 0.7857 \| \| 0.5069 \| 16.0 \| 52 \| 0.5019 \| 0.8 \| \| 0.5069 \| 16.9231 \| 55 \| 0.4895 \| 0.7429 \| \| 0.5069 \| 17.8462 \| 58 \| 0.4538 \| 0.7286 \| \| 0.4367 \| 18.7692 \| 61 \| 0.5692 \| 0.7857 \| \| 0.4367 \| 20.0 \| 65 \| 0.3801 \| 0.8 \| \| 0.4367 \| 20.9231 \| 68 \| 0.4637 \| 0.8571 \| \| 0.4206 \| 21.8462 \| 71 \| 0.3953 \| 0.8143 \| \| 0.4206 \| 22.7692 \| 74 \| 0.4849 \| 0.7857 \| \| 0.4206 \| 24.0 \| 78 \| 0.4764 \| 0.8143 \| \| 0.3892 \| 24.9231 \| 81 \| 0.4488 \| 0.8 \| \| 0.3892 \| 25.8462 \| 84 \| 0.4451 \| 0.8 \| \| 0.3892 \| 26.7692 \| 87 \| 0.5077 \| 0.7857 \| \| 0.3474 \| 28.0 \| 91 \| 0.4365 \| 0.8 \| \| 0.3474 \| 28.9231 \| 94 \| 0.5007 \| 0.8143 \| \| 0.3474 \| 29.8462 \| 97 \| 0.4076 \| 0.8 \| \| 0.3012 \| 30.7692 \| 100 \| 0.5348 \| 0.7714 \| \| 0.3012 \| 32.0 \| 104 \| 0.5035 \| 0.8143 \| \| 0.3012 \| 32.9231 \| 107 \| 0.5891 \| 0.7857 \| \| 0.2774 \| 33.8462 \| 110 \| 0.5209 \| 0.7857 \| \| 0.2774 \| 34.7692 \| 113 \| 0.5312 \| 0.8286 \| \| 0.2774 \| 36.0 \| 117 \| 0.5686 \| 0.8143 \| \| 0.2442 \| 36.9231 \| 120 \| 0.5144 \| 0.8 \| \| 0.2442 \| 37.8462 \| 123 \| 0.4979 \| 0.8143 \| \| 0.2442 \| 38.7692 \| 126 \| 0.5156 \| 0.7857 \| \| 0.2296 \| 40.0 \| 130 \| 0.4829 \| 0.7857 \| \| 0.2296 \| 40.9231 \| 133 \| 0.4832 \| 0.7857 \| \| 0.2296 \| 41.8462 \| 136 \| 0.4991 \| 0.7857 \| \| 0.2296 \| 42.7692 \| 139 \| 0.6268 \| 0.8286 \| \| 0.2184 \| 44.0 \| 143 \| 0.4693 \| 0.7857 \| \| 0.2184 \| 44.9231 \| 146 \| 0.6343 \| 0.8429 \| \| 0.2184 \| 45.8462 \| 149 \| 0.4261 \| 0.8571 \| \| 0.2282 \| 46.7692 \| 152 \| 0.5495 \| 0.8286 \| \| 0.2282 \| 48.0 \| 156 \| 0.5260 \| 0.8286 \| \| 0.2282 \| 48.9231 \| 159 \| 0.6342 \| 0.7143 \| \| 0.2066 \| 49.8462 \| 162 \| 0.8270 \| 0.8143 \| \| 0.2066 \| 50.7692 \| 165 \| 0.7074 \| 0.7714 \| \| 0.2066 \| 52.0 \| 169 \| 0.6694 \| 0.7571 \| \| 0.1827 \| 52.9231 \| 172 \| 0.6534 \| 0.8286 \| \| 0.1827 \| 53.8462 \| 175 \| 0.6860 \| 0.7714 \| \| 0.1827 \| 54.7692 \| 178 \| 0.5751 \| 0.8 \| \| 0.1645 \| 56.0 \| 182 \| 0.5796 \| 0.8 \| \| 0.1645 \| 56.9231 \| 185 \| 0.6402 \| 0.7857 \| \| 0.1645 \| 57.8462 \| 188 \| 0.5766 \| 0.7857 \| \| 0.165 \| 58.7692 \| 191 \| 0.5277 \| 0.8143 \| \| 0.165 \| 60.0 \| 195 \| 0.6397 \| 0.8571 \| \| 0.165 \| 60.9231 \| 198 \| 0.6083 \| 0.8143 \| \| 0.1645 \| 61.8462 \| 201 \| 0.6510 \| 0.8 \| \| 0.1645 \| 62.7692 \| 204 \| 0.6857 \| 0.8286 \| \| 0.1645 \| 64.0 \| 208 \| 0.6800 \| 0.8143 \| \| 0.1617 \| 64.9231 \| 211 \| 0.7275 \| 0.8714 \| \| 0.1617 \| 65.8462 \| 214 \| 0.6051 \| 0.8429 \| \| 0.1617 \| 66.7692 \| 217 \| 0.6872 \| 0.7857 \| \| 0.1348 \| 68.0 \| 221 \| 0.6201 \| 0.8429 \| \| 0.1348 \| 68.9231 \| 224 \| 0.5862 \| 0.7857 \| \| 0.1348 \| 69.8462 \| 227 \| 0.6146 \| 0.8 \| \| 0.1638 \| 70.7692 \| 230 \| 0.6097 \| 0.8286 \| \| 0.1638 \| 72.0 \| 234 \| 0.6778 \| 0.8143 \| \| 0.1638 \| 72.9231 \| 237 \| 0.7084 \| 0.8143 \| \| 0.1364 \| 73.8462 \| 240 \| 0.7639 \| 0.7857 \| \| 0.1364 \| 74.7692 \| 243 \| 0.7417 \| 0.7857 \| \| 0.1364 \| 76.0 \| 247 \| 0.7288 \| 0.8 \| \| 0.128 \| 76.9231 \| 250 \| 0.7143 \| 0.7857 \| \| 0.128 \| 77.8462 \| 253 \| 0.6900 \| 0.8 \| \| 0.128 \| 78.7692 \| 256 \| 0.6885 \| 0.8 \| \| 0.1232 \| 80.0 \| 260 \| 0.6882 \| 0.8 \| \| 0.1232 \| 80.9231 \| 263 \| 0.7023 \| 0.8 \| \| 0.1232 \| 81.8462 \| 266 \| 0.7394 \| 0.8 \| \| 0.1232 \| 82.7692 \| 269 \| 0.7313 \| 0.7857 \| \| 0.1177 \| 84.0 \| 273 \| 0.7083 \| 0.8 \| \| 0.1177 \| 84.9231 \| 276 \| 0.7048 \| 0.7857 \| \| 0.1177 \| 85.8462 \| 279 \| 0.7304 \| 0.7714 \| \| 0.1195 \| 86.7692 \| 282 \| 0.7722 \| 0.8 \| \| 0.1195 \| 88.0 \| 286 \| 0.7738 \| 0.8 \| \| 0.1195 \| 88.9231 \| 289 \| 0.7616 \| 0.7857 \| \| 0.113 \| 89.8462 \| 292 \| 0.7425 \| 0.7857 \| \| 0.113 \| 90.7692 \| 295 \| 0.7204 \| 0.7857 \| \| 0.113 \| 92.0 \| 299 \| 0.7117 \| 0.7714 \| \| 0.11 \| 92.3077 \| 300 \| 0.7113 \| 0.7714 \| ### 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": ["imagefolder"], "metrics": ["accuracy"], "base_model": "microsoft/beit-base-patch16-224", "model-index": [{"name": "beit-base-patch16-224-c9fdf34b-e763-4cf0-b38d-2601d6b23e7e", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.8714285714285714, "name": "Accuracy"}]}]}]}	BilalMuftuoglu/beit-base-patch16-224-c9fdf34b-e763-4cf0-b38d-2601d6b23e7e	null	[ "transformers", "tensorboard", "safetensors", "beit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:microsoft/beit-base-patch16-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:07:31+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": []}	sajjansagar/dialogue_Summary_peft	null	[ "transformers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:08:33+00:00
text-generation	transformers		{"license": "mit"}	babylm/flamingo-babylm-2024	null	[ "transformers", "pytorch", "opt", "text-generation", "custom_code", "license:mit", "autotrain_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:08:37+00:00
null	null		{}	MarwaSaleh/whisper-small-egyptian	null	[ "region:us" ]	null	2024-05-01T20:08:44+00:00
null	null		{}	FanFierik/CaptainBlazer	null	[ "region:us" ]	null	2024-05-01T20:08:49+00:00
null	null		{"license": "openrail"}	elyelysienne/park-sumin	null	[ "license:openrail", "region:us" ]	null	2024-05-01T20:11:01+00:00
text-generation	null	## Llamacpp imatrix Quantizations of Scarlett-Llama-3-8B-v1.0 Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2777">b2777</a> for quantization. Original model: https://huggingface.co/ajibawa-2023/Scarlett-Llama-3-8B-v1.0 All quants made using imatrix option with dataset provided by Kalomaze [here](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) ## Prompt format ``` <\|im_start\|>system {system_prompt}<\|im_end\|> <\|im_start\|>user {prompt}<\|im_end\|> <\|im_start\|>assistant ``` ## Download a file (not the whole branch) from below: \| Filename \| Quant type \| File Size \| Description \| \| -------- \| ---------- \| --------- \| ----------- \| \| [Scarlett-Llama-3-8B-v1.0-Q8_0.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q8_0.gguf) \| Q8_0 \| 8.54GB \| Extremely high quality, generally unneeded but max available quant. \| \| [Scarlett-Llama-3-8B-v1.0-Q6_K.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q6_K.gguf) \| Q6_K \| 6.59GB \| Very high quality, near perfect, recommended. \| \| [Scarlett-Llama-3-8B-v1.0-Q5_K_M.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q5_K_M.gguf) \| Q5_K_M \| 5.73GB \| High quality, recommended. \| \| [Scarlett-Llama-3-8B-v1.0-Q5_K_S.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q5_K_S.gguf) \| Q5_K_S \| 5.59GB \| High quality, recommended. \| \| [Scarlett-Llama-3-8B-v1.0-Q4_K_M.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q4_K_M.gguf) \| Q4_K_M \| 4.92GB \| Good quality, uses about 4.83 bits per weight, recommended. \| \| [Scarlett-Llama-3-8B-v1.0-Q4_K_S.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q4_K_S.gguf) \| Q4_K_S \| 4.69GB \| Slightly lower quality with more space savings, recommended. \| \| [Scarlett-Llama-3-8B-v1.0-IQ4_NL.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ4_NL.gguf) \| IQ4_NL \| 4.67GB \| Decent quality, slightly smaller than Q4_K_S with similar performance recommended. \| \| [Scarlett-Llama-3-8B-v1.0-IQ4_XS.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ4_XS.gguf) \| IQ4_XS \| 4.44GB \| Decent quality, smaller than Q4_K_S with similar performance, recommended. \| \| [Scarlett-Llama-3-8B-v1.0-Q3_K_L.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q3_K_L.gguf) \| Q3_K_L \| 4.32GB \| Lower quality but usable, good for low RAM availability. \| \| [Scarlett-Llama-3-8B-v1.0-Q3_K_M.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q3_K_M.gguf) \| Q3_K_M \| 4.01GB \| Even lower quality. \| \| [Scarlett-Llama-3-8B-v1.0-IQ3_M.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ3_M.gguf) \| IQ3_M \| 3.78GB \| Medium-low quality, new method with decent performance comparable to Q3_K_M. \| \| [Scarlett-Llama-3-8B-v1.0-IQ3_S.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ3_S.gguf) \| IQ3_S \| 3.68GB \| Lower quality, new method with decent performance, recommended over Q3_K_S quant, same size with better performance. \| \| [Scarlett-Llama-3-8B-v1.0-Q3_K_S.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q3_K_S.gguf) \| Q3_K_S \| 3.66GB \| Low quality, not recommended. \| \| [Scarlett-Llama-3-8B-v1.0-IQ3_XS.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ3_XS.gguf) \| IQ3_XS \| 3.51GB \| Lower quality, new method with decent performance, slightly better than Q3_K_S. \| \| [Scarlett-Llama-3-8B-v1.0-IQ3_XXS.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ3_XXS.gguf) \| IQ3_XXS \| 3.27GB \| Lower quality, new method with decent performance, comparable to Q3 quants. \| \| [Scarlett-Llama-3-8B-v1.0-Q2_K.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-Q2_K.gguf) \| Q2_K \| 3.17GB \| Very low quality but surprisingly usable. \| \| [Scarlett-Llama-3-8B-v1.0-IQ2_M.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ2_M.gguf) \| IQ2_M \| 2.94GB \| Very low quality, uses SOTA techniques to also be surprisingly usable. \| \| [Scarlett-Llama-3-8B-v1.0-IQ2_S.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ2_S.gguf) \| IQ2_S \| 2.75GB \| Very low quality, uses SOTA techniques to be usable. \| \| [Scarlett-Llama-3-8B-v1.0-IQ2_XS.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ2_XS.gguf) \| IQ2_XS \| 2.60GB \| Very low quality, uses SOTA techniques to be usable. \| \| [Scarlett-Llama-3-8B-v1.0-IQ2_XXS.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ2_XXS.gguf) \| IQ2_XXS \| 2.39GB \| Lower quality, uses SOTA techniques to be usable. \| \| [Scarlett-Llama-3-8B-v1.0-IQ1_M.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ1_M.gguf) \| IQ1_M \| 2.16GB \| Extremely low quality, not recommended. \| \| [Scarlett-Llama-3-8B-v1.0-IQ1_S.gguf](https://huggingface.co/bartowski/Scarlett-Llama-3-8B-v1.0-GGUF/blob/main/Scarlett-Llama-3-8B-v1.0-IQ1_S.gguf) \| IQ1_S \| 2.01GB \| 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": "other", "tags": ["art", "philosophy", "romance", "jokes", "advice", "code", "companionship"], "license_name": "llama3", "license_link": "LICENSE", "quantized_by": "bartowski", "pipeline_tag": "text-generation"}	bartowski/Scarlett-Llama-3-8B-v1.0-GGUF	null	[ "gguf", "art", "philosophy", "romance", "jokes", "advice", "code", "companionship", "text-generation", "en", "license:other", "region:us" ]	null	2024-05-01T20:11:06+00:00
text-generation	transformers	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) KangalKhan-RawRuby-7B - bnb 4bits - Model creator: https://huggingface.co/Yuma42/ - Original model: https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B/ Original model description: --- language: - en license: apache-2.0 tags: - merge - mergekit - lazymergekit - Yuma42/KangalKhan-Ruby-7B-Fixed - Yuma42/KangalKhan-RawEmerald-7B base_model: - Yuma42/KangalKhan-Ruby-7B-Fixed - Yuma42/KangalKhan-RawEmerald-7B model-index: - name: KangalKhan-RawRuby-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 66.89 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 85.53 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 63.46 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 57.09 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 78.69 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 62.02 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard --- # KangalKhan-RawRuby-7B I suggest using ChatML (Use whatever system prompt you like, this is just an example!): ``` <\|im_start\|>system You are a friendly assistant.<\|im_end\|> <\|im_start\|>user Hello, what are you?<\|im_end\|> <\|im_start\|>assistant I am an AI language model designed to assist users with information and answer their questions. How can I help you today?<\|im_end\|> ``` Q4_K_S GGUF: https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B-GGUF More GGUF variants by [mradermacher](https://huggingface.co/mradermacher): WARNING: I have observed that these versions output typos in rare cases. If you have the same problem, use my Q4_K_S GGUF above. https://huggingface.co/mradermacher/KangalKhan-RawRuby-7B-GGUF weighted/imatrix GGUF by [mradermacher](https://huggingface.co/mradermacher): https://huggingface.co/mradermacher/KangalKhan-RawRuby-7B-i1-GGUF KangalKhan-RawRuby-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [Yuma42/KangalKhan-Ruby-7B-Fixed](https://huggingface.co/Yuma42/KangalKhan-Ruby-7B-Fixed) * [Yuma42/KangalKhan-RawEmerald-7B](https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B) ## 🧩 Configuration ```yaml slices: - sources: - model: Yuma42/KangalKhan-Ruby-7B-Fixed layer_range: [0, 32] - model: Yuma42/KangalKhan-RawEmerald-7B layer_range: [0, 32] merge_method: slerp base_model: Yuma42/KangalKhan-Ruby-7B-Fixed parameters: t: - filter: self_attn value: [0.1, 0.55, 0.35, 0.75, 0.97] - filter: mlp value: [0.9, 0.45, 0.65, 0.25, 0.03] - value: 0.5 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Yuma42/KangalKhan-RawRuby-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` # [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_Yuma42__KangalKhan-RawRuby-7B) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|68.95\| \|AI2 Reasoning Challenge (25-Shot)\|66.89\| \|HellaSwag (10-Shot) \|85.53\| \|MMLU (5-Shot) \|63.46\| \|TruthfulQA (0-shot) \|57.09\| \|Winogrande (5-shot) \|78.69\| \|GSM8k (5-shot) \|62.02\|	{}	RichardErkhov/Yuma42_-_KangalKhan-RawRuby-7B-4bits	null	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-05-01T20:11:57+00:00
null	null		{}	rahil1206/test2	null	[ "region:us" ]	null	2024-05-01T20:12:39+00:00
null	null		{"license": "cc-by-nc-nd-4.0"}	MR-Eder/phi3-wiki-de-single-pairs-Q4-K-M	null	[ "gguf", "license:cc-by-nc-nd-4.0", "region:us" ]	null	2024-05-01T20:13:45+00:00
null	null		{"license": "openrail"}	Muradn/GitarisTV-NumanKaanBostan	null	[ "license:openrail", "region:us" ]	null	2024-05-01T20:13:47+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-ep43	null	[ "transformers", "safetensors", "xlm-roberta", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:14:05+00:00
null	null		{"license": "openrail"}	rinkumeena814/2	null	[ "license:openrail", "region:us" ]	null	2024-05-01T20:14:47+00:00
null	transformers		{}	notresort/loubie-straight-perspective-facts	null	[ "transformers", "gguf", "llama", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:16:34+00:00
null	transformers	## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> static quants of https://huggingface.co/chihoonlee10/T3Q-LLM-MG-DPO-v1.0 <!-- 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/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q2_K.gguf) \| Q2_K \| 4.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.IQ3_XS.gguf) \| IQ3_XS \| 4.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q3_K_S.gguf) \| Q3_K_S \| 4.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.IQ3_S.gguf) \| IQ3_S \| 4.8 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.IQ3_M.gguf) \| IQ3_M \| 4.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q3_K_M.gguf) \| Q3_K_M \| 5.3 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q3_K_L.gguf) \| Q3_K_L \| 5.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.IQ4_XS.gguf) \| IQ4_XS \| 5.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q4_K_S.gguf) \| Q4_K_S \| 6.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q4_K_M.gguf) \| Q4_K_M \| 6.6 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q5_K_S.gguf) \| Q5_K_S \| 7.5 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q5_K_M.gguf) \| Q5_K_M \| 7.7 \| \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q6_K.gguf) \| Q6_K \| 8.9 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF/resolve/main/T3Q-LLM-MG-DPO-v1.0.Q8_0.gguf) \| Q8_0 \| 11.5 \| fast, best quality \| 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", "base_model": "chihoonlee10/T3Q-LLM-MG-DPO-v1.0", "quantized_by": "mradermacher"}	mradermacher/T3Q-LLM-MG-DPO-v1.0-GGUF	null	[ "transformers", "gguf", "en", "base_model:chihoonlee10/T3Q-LLM-MG-DPO-v1.0", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:17:05+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. --> # idefics2-8b-docvqa-finetuned-museum-v2 This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on an unknown 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: 0.0001 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 50 - num_epochs: 2 - mixed_precision_training: Native AMP ### Training results ### Framework versions - Transformers 4.40.1 - Pytorch 2.3.0+cu118 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "HuggingFaceM4/idefics2-8b", "model-index": [{"name": "idefics2-8b-docvqa-finetuned-museum-v2", "results": []}]}	ZacJQ/idefics2-8b-docvqa-finetuned-museum-v2	null	[ "safetensors", "generated_from_trainer", "base_model:HuggingFaceM4/idefics2-8b", "license:apache-2.0", "region:us" ]	null	2024-05-01T20:17:50+00:00
text-generation	transformers	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) KangalKhan-RawRuby-7B - bnb 8bits - Model creator: https://huggingface.co/Yuma42/ - Original model: https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B/ Original model description: --- language: - en license: apache-2.0 tags: - merge - mergekit - lazymergekit - Yuma42/KangalKhan-Ruby-7B-Fixed - Yuma42/KangalKhan-RawEmerald-7B base_model: - Yuma42/KangalKhan-Ruby-7B-Fixed - Yuma42/KangalKhan-RawEmerald-7B model-index: - name: KangalKhan-RawRuby-7B results: - task: type: text-generation name: Text Generation dataset: name: AI2 Reasoning Challenge (25-Shot) type: ai2_arc config: ARC-Challenge split: test args: num_few_shot: 25 metrics: - type: acc_norm value: 66.89 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: HellaSwag (10-Shot) type: hellaswag split: validation args: num_few_shot: 10 metrics: - type: acc_norm value: 85.53 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: MMLU (5-Shot) type: cais/mmlu config: all split: test args: num_few_shot: 5 metrics: - type: acc value: 63.46 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: TruthfulQA (0-shot) type: truthful_qa config: multiple_choice split: validation args: num_few_shot: 0 metrics: - type: mc2 value: 57.09 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: Winogrande (5-shot) type: winogrande config: winogrande_xl split: validation args: num_few_shot: 5 metrics: - type: acc value: 78.69 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard - task: type: text-generation name: Text Generation dataset: name: GSM8k (5-shot) type: gsm8k config: main split: test args: num_few_shot: 5 metrics: - type: acc value: 62.02 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Yuma42/KangalKhan-RawRuby-7B name: Open LLM Leaderboard --- # KangalKhan-RawRuby-7B I suggest using ChatML (Use whatever system prompt you like, this is just an example!): ``` <\|im_start\|>system You are a friendly assistant.<\|im_end\|> <\|im_start\|>user Hello, what are you?<\|im_end\|> <\|im_start\|>assistant I am an AI language model designed to assist users with information and answer their questions. How can I help you today?<\|im_end\|> ``` Q4_K_S GGUF: https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B-GGUF More GGUF variants by [mradermacher](https://huggingface.co/mradermacher): WARNING: I have observed that these versions output typos in rare cases. If you have the same problem, use my Q4_K_S GGUF above. https://huggingface.co/mradermacher/KangalKhan-RawRuby-7B-GGUF weighted/imatrix GGUF by [mradermacher](https://huggingface.co/mradermacher): https://huggingface.co/mradermacher/KangalKhan-RawRuby-7B-i1-GGUF KangalKhan-RawRuby-7B is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing): * [Yuma42/KangalKhan-Ruby-7B-Fixed](https://huggingface.co/Yuma42/KangalKhan-Ruby-7B-Fixed) * [Yuma42/KangalKhan-RawEmerald-7B](https://huggingface.co/Yuma42/KangalKhan-RawRuby-7B) ## 🧩 Configuration ```yaml slices: - sources: - model: Yuma42/KangalKhan-Ruby-7B-Fixed layer_range: [0, 32] - model: Yuma42/KangalKhan-RawEmerald-7B layer_range: [0, 32] merge_method: slerp base_model: Yuma42/KangalKhan-Ruby-7B-Fixed parameters: t: - filter: self_attn value: [0.1, 0.55, 0.35, 0.75, 0.97] - filter: mlp value: [0.9, 0.45, 0.65, 0.25, 0.03] - value: 0.5 dtype: bfloat16 ``` ## 💻 Usage ```python !pip install -qU transformers accelerate from transformers import AutoTokenizer import transformers import torch model = "Yuma42/KangalKhan-RawRuby-7B" messages = [{"role": "user", "content": "What is a large language model?"}] tokenizer = AutoTokenizer.from_pretrained(model) prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True) pipeline = transformers.pipeline( "text-generation", model=model, torch_dtype=torch.float16, device_map="auto", ) outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95) print(outputs[0]["generated_text"]) ``` # [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_Yuma42__KangalKhan-RawRuby-7B) \| Metric \|Value\| \|---------------------------------\|----:\| \|Avg. \|68.95\| \|AI2 Reasoning Challenge (25-Shot)\|66.89\| \|HellaSwag (10-Shot) \|85.53\| \|MMLU (5-Shot) \|63.46\| \|TruthfulQA (0-shot) \|57.09\| \|Winogrande (5-shot) \|78.69\| \|GSM8k (5-shot) \|62.02\|	{}	RichardErkhov/Yuma42_-_KangalKhan-RawRuby-7B-8bits	null	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]	null	2024-05-01T20:18:37+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": []}	abc88767/model33	null	[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:18:38+00:00
null	null		{}	Phuree/BIIIINARIA111	null	[ "region:us" ]	null	2024-05-01T20:18:38+00:00
text-generation	transformers		{}	mdeniz1/Llama-3-8B-Instruct-AWQ-4bit	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-05-01T20:18:44+00:00
text-generation	transformers		{"license": "apache-2.0"}	TensorSenseAI/liedetector	null	[ "transformers", "pytorch", "llava", "text-generation", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:19:40+00:00
null	null		{}	MR-Eder/phi3-wiki-de-single-pairs-Q4-K-M-GGUF	null	[ "gguf", "region:us" ]	null	2024-05-01T20:20:01+00:00
text-generation	transformers		{}	roni23/llama-3-8b-instruct-awq	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-05-01T20:21:54+00:00
video-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. --> # videomae-base-finetuned-ucf101-subset This model is a fine-tuned version of [MCG-NJU/videomae-base](https://huggingface.co/MCG-NJU/videomae-base) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.2789 - Accuracy: 0.9161 ## 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: 2 - eval_batch_size: 2 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 600 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 1.3234 \| 0.25 \| 150 \| 1.1605 \| 0.6143 \| \| 1.0245 \| 1.25 \| 300 \| 0.7764 \| 0.6714 \| \| 0.1441 \| 2.25 \| 450 \| 0.4293 \| 0.8571 \| \| 0.4346 \| 3.25 \| 600 \| 0.2247 \| 0.9 \| ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "cc-by-nc-4.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "MCG-NJU/videomae-base", "model-index": [{"name": "videomae-base-finetuned-ucf101-subset", "results": []}]}	thenam/videomae-base-finetuned-ucf101-subset	null	[ "transformers", "tensorboard", "safetensors", "videomae", "video-classification", "generated_from_trainer", "base_model:MCG-NJU/videomae-base", "license:cc-by-nc-4.0", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:22:06+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": ["trl", "sft"]}	EdBerg/LLAMA3finetuned_test	null	[ "transformers", "safetensors", "trl", "sft", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:22:47+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": []}	EdBerg/LLAMA3finance_finetuned_test	null	[ "transformers", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:22:53+00:00
null	null		{}	mokmail/test	null	[ "region:us" ]	null	2024-05-01T20:23:12+00:00
null	null		{}	chensy0715/llava-1.5-7b-hf-ft-mix-vsft	null	[ "region:us" ]	null	2024-05-01T20:24:00+00:00
null	null		{"license": "creativeml-openrail-m"}	Tinuva/Midkemia-Experimental	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2024-05-01T20:24:03+00:00
null	peft	## 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 ### Framework versions - PEFT 0.4.0	{"library_name": "peft"}	YasaminAbb/Llama-2-7b-CNN_qlora_Summarizer	null	[ "peft", "pytorch", "llama", "region:us" ]	null	2024-05-01T20:25:18+00:00
null	null		{}	Recess88/Ponynai3	null	[ "region:us" ]	null	2024-05-01T20:26:26+00:00
text-generation	transformers	# Uploaded model - Developed by: shkna1368 - License: apache-2.0 - Finetuned from model : unsloth/llama-3-8b-bnb-4bit This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)	{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "llama", "trl"], "base_model": "unsloth/llama-3-8b-bnb-4bit", "pipeline_tag": "text-generation"}	shkna1368/kurdish_poetry_model	null	[ "transformers", "pytorch", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]	null	2024-05-01T20:26:33+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": ["unsloth"], "pipeline_tag": "text-generation"}	shkna1368/kurdish_poetry_model_model	null	[ "transformers", "llama", "text-generation", "unsloth", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-05-01T20:26:45+00:00
null	null		{}	Delcos/RossmannBot-8b	null	[ "region:us" ]	null	2024-05-01T20:27:16+00:00
null	null		{}	zabir735/clip-seed-vit-test	null	[ "region:us" ]	null	2024-05-01T20:27:18+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": []}	fmshahata/phi_moe-4exp	null	[ "transformers", "safetensors", "phi", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:28:06+00:00
fill-mask	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. --> # my_awesome_eli5_mlm_model This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the eli5_category dataset. It achieves the following results on the evaluation set: - Loss: 2.0227 ## 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 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results ### 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": ["eli5_category"], "base_model": "distilbert/distilroberta-base", "model-index": [{"name": "my_awesome_eli5_mlm_model", "results": []}]}	justingrammens/my_awesome_eli5_mlm_model	null	[ "transformers", "tensorboard", "safetensors", "roberta", "fill-mask", "generated_from_trainer", "dataset:eli5_category", "base_model:distilbert/distilroberta-base", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:28:52+00:00
text-generation	transformers	<!-- This model is trained on a custom dataset containing knowledge of everything I have learned in the field of generative AI up to now. It is based on the GPT-2 architecture. --> # ElegAI-GPT2 This model is trained on a custom dataset containing knowledge of everything I have learned in the field of generative AI up to now. It is based on the GPT-2 architecture. It achieves the following results on the evaluation set: - Loss: 6.0431 ## 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 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 16 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| \|:-------------:\|:-----:\|:----:\|:---------------:\| \| No log \| 1.0 \| 115 \| 7.7538 \| \| No log \| 2.0 \| 230 \| 6.7783 \| \| No log \| 3.0 \| 345 \| 6.4315 \| \| No log \| 4.0 \| 460 \| 6.2719 \| \| 7.2074 \| 5.0 \| 575 \| 6.1580 \| \| 7.2074 \| 6.0 \| 690 \| 6.1347 \| \| 7.2074 \| 7.0 \| 805 \| 6.0930 \| \| 7.2074 \| 8.0 \| 920 \| 6.0586 \| \| 5.7064 \| 9.0 \| 1035 \| 6.0425 \| \| 5.7064 \| 10.0 \| 1150 \| 6.0486 \| \| 5.7064 \| 11.0 \| 1265 \| 6.0434 \| \| 5.7064 \| 12.0 \| 1380 \| 6.0360 \| \| 5.7064 \| 13.0 \| 1495 \| 6.0272 \| \| 5.2244 \| 14.0 \| 1610 \| 6.0327 \| \| 5.2244 \| 15.0 \| 1725 \| 6.0443 \| \| 5.2244 \| 16.0 \| 1840 \| 6.0431 \| ### Framework versions - Transformers 4.30.0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.13.3	{"language": ["en"], "license": "apache-2.0", "tags": ["generated_from_trainer"], "pipeline_tag": "text-generation", "model-index": [{"name": "ElegAI-GPT2", "results": []}]}	MANMEET75/ElegAI-GPT2	null	[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "generated_from_trainer", "en", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:29:04+00:00
null	null		{}	ROSHANES/Shakeel-RVC	null	[ "region:us" ]	null	2024-05-01T20:29:57+00:00
text-to-image	diffusers	<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # LoRA DreamBooth - mj96/fine-tuned-runwayml-sd-v1-5-lora-d1 These are LoRA adaption weights for runwayml/stable-diffusion-v1-5. The weights were trained on a photo of lmessi man using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]	{"license": "creativeml-openrail-m", "library_name": "diffusers", "tags": ["text-to-image", "diffusers", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers"], "base_model": "runwayml/stable-diffusion-v1-5", "inference": true, "instance_prompt": "a photo of lmessi man"}	mj96/fine-tuned-runwayml-sd-v1-5-lora-d1	null	[ "diffusers", "safetensors", "text-to-image", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "base_model:runwayml/stable-diffusion-v1-5", "license:creativeml-openrail-m", "region:us", "has_space" ]	null	2024-05-01T20:30:05+00:00
null	null		{}	M1sterlanger1337/lolilo	null	[ "region:us" ]	null	2024-05-01T20:31:14+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", "pipeline_tag": "text-classification"}	paul-stansifer/mistral-qwantz-coherent	null	[ "transformers", "safetensors", "text-classification", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:31:35+00:00
null	null		{}	mnoukhov/results	null	[ "region:us" ]	null	2024-05-01T20:31:37+00:00
null	null		{}	RichardErkhov/Yuma42_-_KangalKhan-RawRuby-7B-gguf	null	[ "gguf", "region:us" ]	null	2024-05-01T20:31:37+00:00
text-to-image	diffusers	<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # LoRA DreamBooth - mj96/fine-tuned-compvis-sd-v1-4-lora-d1 These are LoRA adaption weights for CompVis/stable-diffusion-v1-4. The weights were trained on a photo of lmessi man using [DreamBooth](https://dreambooth.github.io/). You can find some example images in the following. ![img_0](./image_0.png) ![img_1](./image_1.png) ![img_2](./image_2.png) ![img_3](./image_3.png) LoRA for the text encoder was enabled: False. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]	{"license": "creativeml-openrail-m", "library_name": "diffusers", "tags": ["text-to-image", "diffusers", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers"], "base_model": "CompVis/stable-diffusion-v1-4", "inference": true, "instance_prompt": "a photo of lmessi man"}	mj96/fine-tuned-compvis-sd-v1-4-lora-d1	null	[ "diffusers", "text-to-image", "lora", "diffusers-training", "stable-diffusion", "stable-diffusion-diffusers", "base_model:CompVis/stable-diffusion-v1-4", "license:creativeml-openrail-m", "region:us" ]	null	2024-05-01T20:32:06+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": []}	domenicrosati/rep-noise_2e-5_batch_8_epoch_1	null	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:34:22+00:00
text-generation	transformers	# Uploaded model - Developed by: DanDev - License: apache-2.0 - Finetuned from model : unsloth/mistral-7b-instruct-v0.2-bnb-4bit This mistral model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. [<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)	{"language": ["en"], "license": "apache-2.0", "tags": ["text-generation-inference", "transformers", "unsloth", "mistral", "trl", "sft"], "base_model": "unsloth/mistral-7b-instruct-v0.2-bnb-4bit"}	DanDev/Mistral-7B-LexisGen	null	[ "transformers", "safetensors", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/mistral-7b-instruct-v0.2-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:34:25+00:00
null	transformers	## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> static quants of https://huggingface.co/Elizezen/Antler-7B-evolve <!-- 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/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q2_K.gguf) \| Q2_K \| 2.8 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.IQ3_XS.gguf) \| IQ3_XS \| 3.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q3_K_S.gguf) \| Q3_K_S \| 3.3 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.IQ3_S.gguf) \| IQ3_S \| 3.3 \| beats Q3_K* \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.IQ3_M.gguf) \| IQ3_M \| 3.4 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q3_K_M.gguf) \| Q3_K_M \| 3.6 \| lower quality \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q3_K_L.gguf) \| Q3_K_L \| 3.9 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.IQ4_XS.gguf) \| IQ4_XS \| 4.0 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q4_K_S.gguf) \| Q4_K_S \| 4.2 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q4_K_M.gguf) \| Q4_K_M \| 4.5 \| fast, recommended \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q5_K_S.gguf) \| Q5_K_S \| 5.1 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q5_K_M.gguf) \| Q5_K_M \| 5.2 \| \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q6_K.gguf) \| Q6_K \| 6.0 \| very good quality \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.Q8_0.gguf) \| Q8_0 \| 7.8 \| fast, best quality \| \| [GGUF](https://huggingface.co/mradermacher/Antler-7B-evolve-GGUF/resolve/main/Antler-7B-evolve.f16.gguf) \| f16 \| 14.6 \| 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": ["mergekit", "merge"], "base_model": "Elizezen/Antler-7B-evolve", "quantized_by": "mradermacher"}	mradermacher/Antler-7B-evolve-GGUF	null	[ "transformers", "gguf", "mergekit", "merge", "en", "base_model:Elizezen/Antler-7B-evolve", "license:apache-2.0", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:34:35+00:00
null	null		{"license": "openrail"}	leeloli/mariah-by-leelo	null	[ "license:openrail", "region:us" ]	null	2024-05-01T20:35:27+00:00
null	null		{}	FanFierik/Zerbiian	null	[ "region:us" ]	null	2024-05-01T20:35:45+00:00
null	null		{"license": "apache-2.0"}	404-OS/Mixtral-8x7B-Instruct-v0.1-GGUF	null	[ "gguf", "license:apache-2.0", "region:us" ]	null	2024-05-01T20:36:35+00:00
null	null		{"license": "creativeml-openrail-m"}	Tinuva/Midkemia-Anime	null	[ "license:creativeml-openrail-m", "region:us" ]	null	2024-05-01T20:37:03+00:00
null	null		{}	LucaBia/test	null	[ "region:us" ]	null	2024-05-01T20:37:23+00:00
null	null		{"license": "openrail"}	Homiebear/Sindri	null	[ "license:openrail", "region:us" ]	null	2024-05-01T20:37:56+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. --> # distilbert-base-uncased-finetuned-clinc 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: 0.7898 - Accuracy: 0.9174 ## 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: 48 - eval_batch_size: 48 - 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 \| Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\| \| 4.3042 \| 1.0 \| 318 \| 3.2959 \| 0.7242 \| \| 2.6434 \| 2.0 \| 636 \| 1.8861 \| 0.8503 \| \| 1.5703 \| 3.0 \| 954 \| 1.1720 \| 0.8910 \| \| 1.0305 \| 4.0 \| 1272 \| 0.8763 \| 0.9139 \| \| 0.8107 \| 5.0 \| 1590 \| 0.7898 \| 0.9174 \| ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.0 - Datasets 2.19.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-clinc", "results": []}]}	joacorf33/distilbert-base-uncased-finetuned-clinc	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	2024-05-01T20:38:01+00:00
null	peft	# Model Card for Model ID Fine-tune Llama3-instruct методом ORPO на датасете SaigaSbs	{"library_name": "peft", "base_model": "meta-llama/Meta-Llama-3-8B-Instruct"}	mrvladd/OrpoLlama3-8B-VIKHR-instruct	null	[ "peft", "safetensors", "llama", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "4-bit", "region:us" ]	null	2024-05-01T20:39:31+00:00
fill-mask	transformers		{}	claudios/ContraBERT_C	null	[ "transformers", "safetensors", "roberta", "fill-mask", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:40:37+00:00
text-generation	mlx	# ahmetkca/Phi-3-mini-128k-instruct-mlx This model was converted to MLX format from [`microsoft/Phi-3-mini-128k-instruct`]() using mlx-lm version 0.12.1. Refer to the [original model card](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) for more details on the model. ## Use with mlx ```bash pip install mlx-lm ``` ```python from mlx_lm import load, generate model, tokenizer = load("ahmetkca/Phi-3-mini-128k-instruct-mlx") response = generate(model, tokenizer, prompt="hello", verbose=True) ```	{"language": ["en"], "license": "mit", "tags": ["nlp", "code", "mlx"], "license_link": "https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE", "pipeline_tag": "text-generation", "widget": [{"messages": [{"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}]}]}	ahmetkca/Phi-3-mini-128k-instruct-mlx	null	[ "mlx", "safetensors", "phi3", "nlp", "code", "text-generation", "conversational", "custom_code", "en", "license:mit", "region:us" ]	null	2024-05-01T20:42:22+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": "unsloth/llama-3-8b-bnb-4bit"}	Dabococo/OWAI3	null	[ "peft", "safetensors", "arxiv:1910.09700", "base_model:unsloth/llama-3-8b-bnb-4bit", "region:us" ]	null	2024-05-01T20:44:22+00:00
null	null		{}	Eswar1892/tuned-bert-test	null	[ "region:us" ]	null	2024-05-01T20:44:56+00:00
fill-mask	transformers		{}	claudios/ContraBERT_G	null	[ "transformers", "safetensors", "roberta", "fill-mask", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T20:45:52+00:00
null	null		{}	robsonferduda/bert_imdb_model	null	[ "region:us" ]	null	2024-05-01T20:48:24+00:00
null	null		{}	tarun1705/pdf_chat_bot	null	[ "region:us" ]	null	2024-05-01T20:48:28+00:00
text-generation	transformers		{}	TitanML/Mistral-7B-Instruct-v0.2-AWQ-4bit	null	[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-05-01T20:48:38+00:00
text-to-image	diffusers	<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - embracellm/sushi25_LoRA <Gallery /> ## Model description These are embracellm/sushi25_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a photo of Vegeterian Roll and Green Veggie Roll to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](embracellm/sushi25_LoRA/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]	{"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "text-to-image", "diffusers-training", "diffusers", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a photo of Vegeterian Roll and Green Veggie Roll", "widget": []}	embracellm/sushi25_LoRA	null	[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "dora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	null	2024-05-01T20:49:11+00:00
null	null		{"license": "llama3"}	Jobaar/Llama-3-8b-instruct-pretokenizerfix-GGUF	null	[ "license:llama3", "region:us" ]	null	2024-05-01T20:50:13+00:00
null	null		{}	jehad13/ASHI22	null	[ "region:us" ]	null	2024-05-01T20:50:59+00:00
text-generation	transformers	# Model Card for Model ID This is a finetuned version of StarCoderBase 1B using the [Fill-in-the-Middle objective](https://arxiv.org/abs/2207.14255) on [dataset](https://huggingface.co/datasets/xvadov01/cpp_emb_nl2pl) focused on embedded systems programming. ## 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] - Shared by [optional]: [More Information Needed] - Model type: Transformer decoder architecture with Multi-Query attention - Language(s) (NLP): English - License: MIT - Finetuned from model [optional]: [StarCoderBase 1B](https://huggingface.co/bigcode/starcoderbase-1b) ### 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: NVIDIA GeForce RTX 3090 - Hours used: 5h 25m - Carbon Emitted: 0.83 ## 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]	{"language": ["en"], "license": "mit", "library_name": "transformers", "metrics": ["bleu", "code_eval", "rouge", "chrf"], "base_model": "bigcode/starcoderbase-1b", "model-index": [{"name": "MicroCoderFIM-1B", "results": [{"task": {"type": "text-generation"}, "dataset": {"name": "HumanEval", "type": "openai_humaneval"}, "metrics": [{"type": "pass@1", "value": 65.46, "name": "pass@1", "verified": false}, {"type": "pass@10", "value": 90.36, "name": "pass@10", "verified": false}, {"type": "pass@100", "value": 94.43, "name": "pass@100", "verified": false}]}, {"task": {"type": "text-generation"}, "dataset": {"name": "xvadov01/cpp_emb_nl2pl", "type": "xvadov01/cpp_emb_nl2pl"}, "metrics": [{"type": "bleu", "value": 31.74, "name": "BLEU", "verified": false}, {"type": "codeBLEU", "value": 40.53, "name": "codeBLEU", "verified": false}, {"type": "chrf", "value": 51.54, "name": "chrf++", "verified": false}, {"type": "rouge", "value": 43.31, "name": "rouge-l", "verified": false}]}]}]}	xvadov01/microcoderfim-1B	null	[ "transformers", "safetensors", "gpt_bigcode", "text-generation", "en", "arxiv:2207.14255", "arxiv:1910.09700", "base_model:bigcode/starcoderbase-1b", "license:mit", "model-index", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:51:50+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": []}	OwOpeepeepoopoo/onetwothreefour	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T20:52:06+00:00
null	null		{}	Anish13/part3	null	[ "region:us" ]	null	2024-05-01T20:52:26+00:00
reinforcement-learning	stable-baselines3	# PPO Agent playing LunarLander-v2 This is a trained model of a PPO agent playing LunarLander-v2 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3). ## Usage (with Stable-baselines3) TODO: Add your code ```python from stable_baselines3 import ... from huggingface_sb3 import load_from_hub ... ```	{"library_name": "stable-baselines3", "tags": ["LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "PPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "LunarLander-v2", "type": "LunarLander-v2"}, "metrics": [{"type": "mean_reward", "value": "259.14 +/- 20.87", "name": "mean_reward", "verified": false}]}]}]}	amc5/ppo-LunarLander-v2	null	[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-05-01T20:54:02+00:00
text-generation	transformers	Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Llama3-OpenBioLLM-8B - bnb 4bits - Model creator: https://huggingface.co/aaditya/ - Original model: https://huggingface.co/aaditya/Llama3-OpenBioLLM-8B/ Original model description: --- base_model: meta-llama/Meta-Llama-3-8B tags: - llama-3 - llama - Mixtral - instruct - finetune - chatml - DPO - RLHF - gpt4 - distillation model-index: - name: OpenBioLLM-8B results: [] license: llama3 language: - en widget: - example_title: OpenBioLLM-8B messages: - role: system content: >- You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. - role: user content: How long does it take for newborn jaundice to go away? output: text: >- Newborn jaundice, also known as neonatal jaundice, is a common condition in newborns where the yellowing of the skin and eyes occurs due to an elevated level of bilirubin in the blood. Bilirubin is a yellow pigment that forms when red blood cells break down. In most cases, newborn jaundice resolves on its own without any specific treatment. The duration of newborn jaundice can vary depending on several factors such as the underlying cause, gestational age at birth, and individual variations in bilirubin metabolism. Here are some general guidelines: 1. Physiological jaundice: This is the most common type of newborn jaundice and usually appears within 24-72 hours after birth. It tends to peak between the second and fifth day of life and gradually improves over the next week or two. By the time the baby is one week old, the jaundice should have mostly resolved. 2. Breast milk jaundice: This type of jaundice occurs in breastfed babies and may appear later than physiological jaundice, typically between the fifth and fourteenth day of life. It tends to persist for a longer duration but usually resolves within six weeks after birth. 3. Pathological jaundice: This type of jaundice is less common and occurs due to an underlying medical condition that affects bilirubin metabolism or liver function. The duration of pathological jaundice depends on the specific cause and may require treatment. It's important for parents to monitor their newborn's jaundice closely and seek medical advice if the jaundice progresses rapidly, becomes severe, or is accompanied by other symptoms such as poor feeding, lethargy, or excessive sleepiness. In these cases, further evaluation and management may be necessary. Remember that each baby is unique, and the timing of jaundice resolution can vary. If you have concerns about your newborn's jaundice, it's always best to consult with a healthcare professional for personalized advice and guidance. --- <div align="center"> <img width="260px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/BrQCb95lmEIFz79QAmoNA.png"></div> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/2FhDh8NDvMl7iSxbQz9BP.png) <div align="center"> <h1>Advancing Open-source Large Language Models in Medical Domain</h1> </div> <p align="center" style="margin-top: 0px;"> <a href="https://colab.research.google.com/drive/1F5oV20InEYeAJGmBwYF9NM_QhLmjBkKJ?usp=sharing"> <img src="https://colab.research.google.com/assets/colab-badge.svg" alt="OpenChat Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 10px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">Online Demo</span> </a> \| <a href="https://github.com/openlifescience-ai"> <img src="https://github.githubassets.com/assets/GitHub-Mark-ea2971cee799.png" alt="GitHub Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style=" margin-right: 5px;">GitHub</span> </a> \| <a href="#"> <img src="https://github.com/alpayariyak/openchat/blob/master/assets/arxiv-logomark-small-square-border.png?raw=true" alt="ArXiv Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text" style="margin-right: 5px;">Paper</span> </a> \| <a href="https://discord.gg/A5Fjf5zC69"> <img src="https://cloud.githubusercontent.com/assets/6291467/26705903/96c2d66e-477c-11e7-9f4e-f3c0efe96c9a.png" alt="Discord Logo" style="width:20px; vertical-align: middle; display: inline-block; margin-right: 5px; margin-left: 5px; margin-top: 0px; margin-bottom: 0px;"/> <span class="link-text">Discord</span> </a> </p> ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/KGmRE5w2sepNtwsEu8t7K.jpeg) Introducing OpenBioLLM-8B: A State-of-the-Art Open Source Biomedical Large Language Model OpenBioLLM-8B is an advanced open source language model designed specifically for the biomedical domain. Developed by Saama AI Labs, this model leverages cutting-edge techniques to achieve state-of-the-art performance on a wide range of biomedical tasks. 🏥 Biomedical Specialization: OpenBioLLM-8B is tailored for the unique language and knowledge requirements of the medical and life sciences fields. It was fine-tuned on a vast corpus of high-quality biomedical data, enabling it to understand and generate text with domain-specific accuracy and fluency. 🎓 Superior Performance: With 8 billion parameters, OpenBioLLM-8B outperforms other open source biomedical language models of similar scale. It has also demonstrated better results compared to larger proprietary & open-source models like GPT-3.5 and Meditron-70B on biomedical benchmarks. 🧠 Advanced Training Techniques: OpenBioLLM-8B builds upon the powerful foundations of the Meta-Llama-3-8B and [Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) models. It incorporates the DPO dataset and fine-tuning recipe along with a custom diverse medical instruction dataset. Key components of the training pipeline include: <div align="center"> <img width="1200px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/oPchsJsEpQoGcGXVbh7YS.png"> </div> - Policy Optimization: [Direct Preference Optimization: Your Language Model is Secretly a Reward Model (DPO)](https://arxiv.org/abs/2305.18290) - Ranking Dataset: [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar) - Fine-tuning dataset: Custom Medical Instruct dataset (We plan to release a sample training dataset in our upcoming paper; please stay updated) This combination of cutting-edge techniques enables OpenBioLLM-8B to align with key capabilities and preferences for biomedical applications. ⚙️ Release Details: - Model Size: 8 billion parameters - Quantization: Optimized quantized versions available [Here](https://huggingface.co/aaditya/OpenBioLLM-Llama3-8B-GGUF) - Language(s) (NLP): en - Developed By: [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) from Saama AI Labs - License: Meta-Llama License - Fine-tuned from models: [meta-llama/Meta-Llama-3-8B](meta-llama/Meta-Llama-3-8B) - Resources for more information: - Paper: Coming soon The model can be fine-tuned for more specialized tasks and datasets as needed. OpenBioLLM-8B represents an important step forward in democratizing advanced language AI for the biomedical community. By leveraging state-of-the-art architectures and training techniques from leading open source efforts like Llama-3, we have created a powerful tool to accelerate innovation and discovery in healthcare and the life sciences. We are excited to share OpenBioLLM-8B with researchers and developers around the world. ### Use with transformers Important: Please use the exact chat template provided by Llama-3 instruct version. Otherwise there will be a degradation in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less. See the snippet below for usage with Transformers: ```python import transformers import torch model_id = "aaditya/OpenBioLLM-Llama3-8B" pipeline = transformers.pipeline( "text-generation", model=model_id, model_kwargs={"torch_dtype": torch.bfloat16}, device="auto", ) messages = [ {"role": "system", "content": "You are an expert and experienced from the healthcare and biomedical domain with extensive medical knowledge and practical experience. Your name is OpenBioLLM, and you were developed by Saama AI Labs. who's willing to help answer the user's query with explanation. In your explanation, leverage your deep medical expertise such as relevant anatomical structures, physiological processes, diagnostic criteria, treatment guidelines, or other pertinent medical concepts. Use precise medical terminology while still aiming to make the explanation clear and accessible to a general audience."}, {"role": "user", "content": "How can i split a 3mg or 4mg waefin pill so i can get a 2.5mg pill?"}, ] prompt = pipeline.tokenizer.apply_chat_template( messages, tokenize=False, add_generation_prompt=True ) terminators = [ pipeline.tokenizer.eos_token_id, pipeline.tokenizer.convert_tokens_to_ids("<\|eot_id\|>") ] outputs = pipeline( prompt, max_new_tokens=256, eos_token_id=terminators, do_sample=True, temperature=0.0, top_p=0.9, ) print(outputs[0]["generated_text"][len(prompt):]) ``` ## Training procedure ### Training hyperparameters <details> <summary>Click to see details</summary> - learning_rate: 0.0002 - lr_scheduler: cosine - train_batch_size: 12 - eval_batch_size: 8 - GPU: H100 80GB SXM5 - num_devices: 1 - optimizer: adamw_bnb_8bit - lr_scheduler_warmup_steps: 100 - num_epochs: 4 </details> ### Peft hyperparameters <details> <summary>Click to see details</summary> - adapter: qlora - lora_r: 128 - lora_alpha: 256 - lora_dropout: 0.05 - lora_target_linear: true -lora_target_modules: - q_proj - v_proj - k_proj - o_proj - gate_proj - down_proj - up_proj </details> ### Training results ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.1 - Axolotl - Lm harness for evaluation # Benchmark Results 🔥 OpenBioLLM-8B demonstrates superior performance compared to larger models, such as GPT-3.5, Meditron-70B across 9 diverse biomedical datasets, achieving state-of-the-art results with an average score of 72.50%, despite having a significantly smaller parameter count. The model's strong performance in domain-specific tasks, such as Clinical KG, Medical Genetics, and PubMedQA, highlights its ability to effectively capture and apply biomedical knowledge. 🚨 The GPT-4, Med-PaLM-1, and Med-PaLM-2 results are taken from their official papers. Since Med-PaLM doesn't provide zero-shot accuracy, we are using 5-shot accuracy from their paper for comparison. All results presented are in the zero-shot setting, except for Med-PaLM-2 and Med-PaLM-1, which use 5-shot accuracy. \| \| Clinical KG \| Medical Genetics \| Anatomy \| Pro Medicine \| College Biology \| College Medicine \| MedQA 4 opts \| PubMedQA \| MedMCQA \| Avg \| \|--------------------\|-------------\|------------------\|---------\|--------------\|-----------------\|------------------\|--------------\|----------\|---------\|-------\| \| OpenBioLLM-70B \| 92.93 \| 93.197 \| 83.904 \| 93.75 \| 93.827 \| 85.749 \| 78.162 \| 78.97 \| 74.014 \| 86.05588 \| \| Med-PaLM-2 (5-shot) \| 88.3 \| 90 \| 77.8 \| 95.2 \| 94.4 \| 80.9 \| 79.7 \| 79.2 \| 71.3 \| 84.08 \| \| GPT-4 \| 86.04 \| 91 \| 80 \| 93.01 \| 95.14 \| 76.88 \| 78.87 \| 75.2 \| 69.52 \| 82.85 \| \| Med-PaLM-1 (Flan-PaLM, 5-shot) \| 80.4 \| 75 \| 63.7 \| 83.8 \| 88.9 \| 76.3 \| 67.6 \| 79 \| 57.6 \| 74.7 \| \| OpenBioLLM-8B \| 76.101 \| 86.1 \| 69.829 \| 78.21 \| 84.213 \| 68.042 \| 58.993 \| 74.12 \| 56.913 \| 72.502 \| \| Gemini-1.0 \| 76.7 \| 75.8 \| 66.7 \| 77.7 \| 88 \| 69.2 \| 58 \| 70.7 \| 54.3 \| 70.79 \| \| GPT-3.5 Turbo 1106 \| 74.71 \| 74 \| 72.79 \| 72.79 \| 72.91 \| 64.73 \| 57.71 \| 72.66 \| 53.79 \| 66 \| \| Meditron-70B \| 66.79 \| 69 \| 53.33 \| 71.69 \| 76.38 \| 63 \| 57.1 \| 76.6 \| 46.85 \| 64.52 \| \| gemma-7b \| 69.81 \| 70 \| 59.26 \| 66.18 \| 79.86 \| 60.12 \| 47.21 \| 76.2 \| 48.96 \| 64.18 \| \| Mistral-7B-v0.1 \| 68.68 \| 71 \| 55.56 \| 68.38 \| 68.06 \| 59.54 \| 50.82 \| 75.4 \| 48.2 \| 62.85 \| \| Apollo-7B \| 62.26 \| 72 \| 61.48 \| 69.12 \| 70.83 \| 55.49 \| 55.22 \| 39.8 \| 53.77 \| 60 \| \| MedAlpaca-7b \| 57.36 \| 69 \| 57.04 \| 67.28 \| 65.28 \| 54.34 \| 41.71 \| 72.8 \| 37.51 \| 58.03 \| \| BioMistral-7B \| 59.9 \| 64 \| 56.5 \| 60.4 \| 59 \| 54.7 \| 50.6 \| 77.5 \| 48.1 \| 57.3 \| \| AlpaCare-llama2-7b \| 49.81 \| 49 \| 45.92 \| 33.82 \| 50 \| 43.35 \| 29.77 \| 72.2 \| 34.42 \| 45.36 \| \| ClinicalGPT \| 30.56 \| 27 \| 30.37 \| 19.48 \| 25 \| 24.27 \| 26.08 \| 63.8 \| 28.18 \| 30.52 \| <div align="center"> <img width="1600px" src="https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_SzdcJSBjZyo8RS1bTEkP.png"> </div> ## Detailed Medical Subjectwise accuracy ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/UXF-V0col0Z0sS6BGPBkE.png) # Use Cases & Examples 🚨 Below results are from the quantized version of OpenBioLLM-70B # Summarize Clinical Notes OpenBioLLM-70B can efficiently analyze and summarize complex clinical notes, EHR data, and discharge summaries, extracting key information and generating concise, structured summaries ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/xdwdBgOxNi_TfML0hKlI8.png) # Answer Medical Questions OpenBioLLM-70B can provide answers to a wide range of medical questions. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/zO95GlwOQEZqCKQF69mE6.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/OKBczKw7gWeW5xsuDpc27.png) <details> <summary>Click to see details</summary> ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/eJGHT5khppYvJb8fQ-YW4.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Cnbwrqa_-ORHRuNRC2P6Y.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/J9DhdcvukAc9mnnW9fj2C.png) </details> # Clinical Entity Recognition OpenBioLLM-70B can perform advanced clinical entity recognition by identifying and extracting key medical concepts, such as diseases, symptoms, medications, procedures, and anatomical structures, from unstructured clinical text. By leveraging its deep understanding of medical terminology and context, the model can accurately annotate and categorize clinical entities, enabling more efficient information retrieval, data analysis, and knowledge discovery from electronic health records, research articles, and other biomedical text sources. This capability can support various downstream applications, such as clinical decision support, pharmacovigilance, and medical research. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/_69BW4k9LVABFwtxixL45.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/DKy5wYCoPhoPPUc1-x8_J.png) ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/7WD9zCCBZT4-4XlfnIQjl.png) # Biomarkers Extraction ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/ZttoM4AiteT7gFYVhjIpN.png) # Classification OpenBioLLM-70B can perform various biomedical classification tasks, such as disease prediction, sentiment analysis, medical document categorization ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/Bf5MW1d75qT-1F_TR_hC0.png) # De-Identification OpenBioLLM-70B can detect and remove personally identifiable information (PII) from medical records, ensuring patient privacy and compliance with data protection regulations like HIPAA. ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5f3fe13d79c1ba4c353d0c19/hKX4kzm--Tw5bj6K78msy.png) Advisory Notice! While OpenBioLLM-70B & 8B leverages high-quality data sources, its outputs may still contain inaccuracies, biases, or misalignments that could pose risks if relied upon for medical decision-making without further testing and refinement. The model's performance has not yet been rigorously evaluated in randomized controlled trials or real-world healthcare environments. Therefore, we strongly advise against using OpenBioLLM-70B & 8B for any direct patient care, clinical decision support, or other professional medical purposes at this time. Its use should be limited to research, development, and exploratory applications by qualified individuals who understand its limitations. OpenBioLLM-70B & 8B are intended solely as a research tool to assist healthcare professionals and should never be considered a replacement for the professional judgment and expertise of a qualified medical doctor. Appropriately adapting and validating OpenBioLLM-70B & 8B for specific medical use cases would require significant additional work, potentially including: - Thorough testing and evaluation in relevant clinical scenarios - Alignment with evidence-based guidelines and best practices - Mitigation of potential biases and failure modes - Integration with human oversight and interpretation - Compliance with regulatory and ethical standards Always consult a qualified healthcare provider for personal medical needs. # Citation If you find OpenBioLLM-70B & 8B useful in your work, please cite the model as follows: ``` @misc{OpenBioLLMs, author = {Ankit Pal, Malaikannan Sankarasubbu}, title = {OpenBioLLMs: Advancing Open-Source Large Language Models for Healthcare and Life Sciences}, year = {2024}, publisher = {Hugging Face}, journal = {Hugging Face repository}, howpublished = {\url{https://huggingface.co/aaditya/OpenBioLLM-Llama3-70B}} } ``` The accompanying paper is currently in progress and will be released soon. <div align="center"> <h2> 💌 Contact </h2> </div> We look forward to hearing you and collaborating on this exciting project! Contributors: - [Ankit Pal (Aaditya Ura)](https://aadityaura.github.io/) [aadityaura at gmail dot com] - Saama AI Labs - Note: I am looking for a funded PhD opportunity, especially if it fits my Responsible Generative AI, Multimodal LLMs, Geometric Deep Learning, and Healthcare AI skillset. # References We thank the [Meta Team](meta-llama/Meta-Llama-3-70B-Instruct) for their amazing models! Result sources - [1] GPT-4 [Capabilities of GPT-4 on Medical Challenge Problems] (https://arxiv.org/abs/2303.13375) - [2] Med-PaLM-1 [Large Language Models Encode Clinical Knowledge](https://arxiv.org/abs/2212.13138) - [3] Med-PaLM-2 [Towards Expert-Level Medical Question Answering with Large Language Models](https://arxiv.org/abs/2305.09617) - [4] Gemini-1.0 [Gemini Goes to Med School](https://arxiv.org/abs/2402.07023)	{}	RichardErkhov/aaditya_-_Llama3-OpenBioLLM-8B-4bits	null	[ "transformers", "safetensors", "llama", "text-generation", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]	null	2024-05-01T20:54:49+00:00
null	null		{}	FanFierik/MrPeto	null	[ "region:us" ]	null	2024-05-01T20:56:17+00:00
null	peft	## 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 ### Framework versions - PEFT 0.4.0	{"library_name": "peft"}	YasaminAbb/Llama-2-7b-CNN_Q_lora_Summarizer	null	[ "peft", "region:us" ]	null	2024-05-01T20:58:21+00:00
text-to-image	diffusers	<!-- This model card has been generated automatically according to the information the training script had access to. You should probably proofread and complete it, then remove this comment. --> # SDXL LoRA DreamBooth - phn91/books_LoRA <Gallery /> ## Model description These are phn91/books_LoRA LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0. The weights were trained using [DreamBooth](https://dreambooth.github.io/). LoRA for the text encoder was enabled: False. Special VAE used for training: madebyollin/sdxl-vae-fp16-fix. ## Trigger words You should use a cover of TOK book to trigger the image generation. ## Download model Weights for this model are available in Safetensors format. [Download](phn91/books_LoRA/tree/main) them in the Files & versions tab. ## Intended uses & limitations #### How to use ```python # TODO: add an example code snippet for running this diffusion pipeline ``` #### Limitations and bias [TODO: provide examples of latent issues and potential remediations] ## Training details [TODO: describe the data used to train the model]	{"license": "openrail++", "library_name": "diffusers", "tags": ["text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "text-to-image", "diffusers-training", "diffusers", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers"], "base_model": "stabilityai/stable-diffusion-xl-base-1.0", "instance_prompt": "a cover of TOK book", "widget": []}	phn91/books_LoRA	null	[ "diffusers", "tensorboard", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:openrail++", "region:us" ]	null	2024-05-01T20:58:42+00:00
reinforcement-learning	null	# PPO Agent Playing CartPole-v1 This is a trained model of a PPO agent playing CartPole-v1. # Hyperparameters	{"tags": ["CartPole-v1", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course"], "model-index": [{"name": "PPO", "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}]}]}]}	Joalbom14/ppo-CartPole-v1	null	[ "tensorboard", "CartPole-v1", "ppo", "deep-reinforcement-learning", "reinforcement-learning", "custom-implementation", "deep-rl-course", "model-index", "region:us" ]	null	2024-05-01T20:58:45+00:00
text-classification	transformers		{}	Youssef1234/roberta-base-sarcasm-detection-1-v2	null	[ "transformers", "safetensors", "roberta", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T21:00:10+00:00
text-generation	transformers		{}	cclabadmin/deepseek_base_system	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T21:01:15+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. --> # swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000-finetuned-leukemia-1000 This model is a fine-tuned version of [DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000](https://huggingface.co/DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.0056 - Accuracy: 1.0 ## 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 \| \|:-------------:\|:------:\|:----:\|:---------------:\|:--------:\| \| 0.5471 \| 0.9825 \| 14 \| 0.1240 \| 0.955 \| \| 0.1792 \| 1.9649 \| 28 \| 0.0493 \| 0.985 \| \| 0.0936 \| 2.9474 \| 42 \| 0.1210 \| 0.965 \| \| 0.0907 \| 4.0 \| 57 \| 0.0056 \| 1.0 \| \| 0.0441 \| 4.9825 \| 71 \| 0.0165 \| 0.995 \| \| 0.0341 \| 5.9649 \| 85 \| 0.0059 \| 0.995 \| \| 0.0406 \| 6.9474 \| 99 \| 0.0018 \| 1.0 \| \| 0.013 \| 8.0 \| 114 \| 0.0200 \| 0.995 \| \| 0.0342 \| 8.9825 \| 128 \| 0.0030 \| 1.0 \| \| 0.0246 \| 9.8246 \| 140 \| 0.0026 \| 1.0 \| ### Framework versions - Transformers 4.40.0.dev0 - Pytorch 2.2.2+cpu - Datasets 2.19.0 - Tokenizers 0.15.2	{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy"], "base_model": "DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000", "model-index": [{"name": "swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000-finetuned-leukemia-1000", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 1.0, "name": "Accuracy"}]}]}]}	DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000-finetuned-leukemia-1000	null	[ "transformers", "tensorboard", "safetensors", "swin", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:DouglasBraga/swin-tiny-patch4-window7-224-finetuned-eurosat-leukemia-3000", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]	null	2024-05-01T21:03:37+00:00
text-generation	transformers		{}	YasaminAbb/Llama-2-7b-CNN_adaptor_qlora_Summarizer	null	[ "transformers", "pytorch", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T21:03:51+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. --> # Mistral-7B-Instruct-v0.2-miracl-raft-sft-v2.0 This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the nthakur/miracl-raft-sft-instruct-v0.2 dataset. It achieves the following results on the evaluation set: - Loss: 1.2086 ## 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: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 3 - gradient_accumulation_steps: 2 - total_train_batch_size: 24 - total_eval_batch_size: 12 - 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 \| \|:-------------:\|:------:\|:----:\|:---------------:\| \| 1.3095 \| 0.0987 \| 200 \| 1.2800 \| \| 1.249 \| 0.1975 \| 400 \| 1.2516 \| \| 1.2514 \| 0.2962 \| 600 \| 1.2369 \| \| 1.275 \| 0.3950 \| 800 \| 1.2263 \| \| 1.1984 \| 0.4937 \| 1000 \| 1.2197 \| \| 1.1556 \| 0.5924 \| 1200 \| 1.2149 \| \| 1.2386 \| 0.6912 \| 1400 \| 1.2116 \| \| 1.2661 \| 0.7899 \| 1600 \| 1.2096 \| \| 1.2752 \| 0.8887 \| 1800 \| 1.2088 \| \| 1.2701 \| 0.9874 \| 2000 \| 1.2086 \| ### Framework versions - PEFT 0.7.1 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1	{"license": "apache-2.0", "library_name": "peft", "tags": ["alignment-handbook", "trl", "sft", "generated_from_trainer"], "datasets": ["nthakur/miracl-raft-sft-instruct-v0.2"], "base_model": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "Mistral-7B-Instruct-v0.2-miracl-raft-sft-v2.0", "results": []}]}	nthakur/Mistral-7B-Instruct-v0.2-miracl-raft-sft-v2.0	null	[ "peft", "safetensors", "mistral", "alignment-handbook", "trl", "sft", "generated_from_trainer", "dataset:nthakur/miracl-raft-sft-instruct-v0.2", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]	null	2024-05-01T21:04:24+00:00
null	null		{}	toretto14/finetuning-sentiment-model-3000-samples	null	[ "region:us" ]	null	2024-05-01T21:04:52+00:00
null	transformers		{}	baseten/medusa-vicuna-0.10.0.dev2024042300	null	[ "transformers", "endpoints_compatible", "region:us" ]	null	2024-05-01T21:05:20+00:00
text-generation	null	<div align="center"> <h1>Llama-3-8B-Instruct-80K-QLoRA</h1> <a href="https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/longllm_qlora">[Data&Code]</a> </div> We extend the context length of Llama-3-8B-Instruct to 80K using QLoRA and 3.5K long-context training data synthesized from GPT-4. The entire training cycle is super efficient, which takes 8 hours on a 8xA800 (80G) machine. Yet, the resulted model achieves remarkable performance on a series of downstream long-context evaluation benchmarks. # Evaluation All the following evaluation results can be reproduced following instructions [here](https://github.com/FlagOpen/FlagEmbedding/tree/master/Long_LLM/longllm_qlora). ## Needle in a Haystack We evaluate the model on the Needle-In-A-HayStack task using the official setting. The blue vertical line indicates the training context length, i.e. 80K. <img src="data/needle.png"></img> ## LongBench We evaluate the model on [LongBench](https://arxiv.org/abs/2308.14508) using 32K context length and the official prompt template. For [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), we use 8K context length. \|Model\|Single-Doc QA\|Multi-Doc QA\|Summarization\|Few-Shot Learning\|Synthetic\|Code\|Avg\| \|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\| \|[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)\|37.33\|36.04\|26.83\|69.56\|37.75\|53.24\|43.20\| \|[gradientai/Llama-3-8B-Instruct-262k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k)\|37.29\|31.20\|26.18\|67.25\|44.25\|62.71\|43.73\| \|[Llama-3-8B-Instruct-80K-QLoRA]()\|43.57\|43.07\|28.93\|69.15\|48.50\|51.95\|47.19\| ## InfiniteBench We evaluate the model on [InfiniteBench](https://arxiv.org/pdf/2402.13718.pdf) using 80K context length and the official prompt template. The results of GPT-4 is copied from the [paper](https://arxiv.org/pdf/2402.13718.pdf). For [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), we use 8K context length. \|Model\|LongBookQA Eng\|LongBookSum Eng\| \|:-:\|:-:\|:-:\| \|GPT-4\|22.22\|14.73\| \|[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)\|7.00\|16.40\| \|[gradientai/Llama-3-8B-Instruct-262k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k)\|20.30\|10.34\| \|[Llama-3-8B-Instruct-80K-QLoRA]()\|30.92\|14.73\| ## Topic Retrieval We evaluate the model on [Topic Retrieval](https://lmsys.org/blog/2023-06-29-longchat/) task with `[5,10,15,20,25,30,40,50,60,70]` topics. <img src="data/topic.png"></img> ## MMLU We evaluate the model's zero-shot performance on MMLU benchmark as a reflection of its short-context capability. \|Model\|STEM\|Social Sciences\|Humanities\|Others\|Avg\| \|:-:\|:-:\|:-:\|:-:\|:-:\|:-:\| \|[Llama-2-7B-Chat](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)\|35.92\|54.37\|51.74\|51.42\|47.22\| \|[Mistral-7B-v0.2-Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2)\|48.79\|69.95\|64.99\|61.64\|60.10\| \|[meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)\|53.87\|75.66\|69.44\|69.75\|65.91\| \|[gradientai/Llama-3-8B-Instruct-262k](https://huggingface.co/NousResearch/Yarn-Mistral-7b-128k)\|52.10\|73.26\|67.15\|69.80\|64.34\| \|[Llama-3-8B-Instruct-80K-QLoRA]()\|53.10\|73.24\|67.32\|68.79\|64.44\| # Environment ```bash torch==2.2.2 flash_attn==2.5.6 transformers==4.39.3 peft==0.10.0 ``` # Usage ```python import json import torch from transformers import AutoModelForCausalLM, AutoTokenizer from peft import PeftModel model_id = "meta-llama/Meta-Llama-3-8B-Instruct" peft_id = "namespace-Pt/Llama-3-8B-Instruct-80K-QLoRA" torch_dtype = torch.bfloat16 # place the model on GPU device_map = {"": "cuda"} tokenizer = AutoTokenizer.from_pretrained(model_id) base_model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.bfloat16, device_map=device_map, attn_implementation="flash_attention_2", # NOTE: expand rope base rope_theta=200e6, ) model = PeftModel.from_pretrained( base_model, peft_id, torch_dtype=torch.bfloat16, device_map=device_map, ) # NOTE: merge LoRA weights model = model.merge_and_unload().eval() with torch.no_grad(): # short context messages = [{"role": "user", "content": "Tell me about yourself."}] inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to("cuda") outputs = model.generate(inputs, max_new_tokens=50)[:, inputs["input_ids"].shape[1]:] print(f"Input Length: {inputs['input_ids'].shape[1]}") print(f"Output: {tokenizer.decode(outputs[0])}") # long context with open("data/narrativeqa.json", encoding="utf-8") as f: example = json.load(f) messages = [{"role": "user", "content": example["context"]}] inputs = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt", return_dict=True).to("cuda") outputs = model.generate(inputs, do_sample=False, top_p=1, temperature=1, max_new_tokens=20)[:, inputs["input_ids"].shape[1]:] print(""20) print(f"Input Length: {inputs['input_ids'].shape[1]}") print(f"Answers: {example['answer']}") print(f"Prediction: {tokenizer.decode(outputs[0])}") ``` You may observe messages like: `This is a friendly reminder - the current text generation call will exceed the model's predefined maximum length (8192). Depending on the model, you may observe exceptions, performance degradation, or nothing at all.` or `Setting pad_token_id to eos_token_id:128001 for open-end generation`. They do not matter. Just ignore them.	{"license": "mit", "pipeline_tag": "text-generation"}	dhruvabansal/Llama-3-8B-Instruct-80K-QLoRA	null	[ "safetensors", "text-generation", "conversational", "arxiv:2308.14508", "arxiv:2402.13718", "license:mit", "region:us" ]	null	2024-05-01T21:09:02+00:00
null	null		{}	thenam/video_mamba-finetuned-ucf101-subset	null	[ "tensorboard", "safetensors", "region:us" ]	null	2024-05-01T21:09:59+00:00
null	null		{"license": "llama3"}	404-OS/Meta-Llama-3-70B-Instruct-GGUF	null	[ "gguf", "license:llama3", "region:us" ]	null	2024-05-01T21:10:50+00:00
text-generation	transformers	# Model Card for Model ID The LLM is designed to perform a wide range of natural language processing tasks, including but not limited to text generation,language translation, and question answering. It is suitable for both research and practical applications in industries such as healthcare ## 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"}	skumar9/Llama-medx_v3	null	[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T21:15:07+00:00
null	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. --> # segformer-b0-scene-parse-150 This model is a fine-tuned version of [nvidia/mit-b0](https://huggingface.co/nvidia/mit-b0) on the scene_parse_150 dataset. It achieves the following results on the evaluation set: - Loss: 2.6113 - Mean Iou: 0.0736 - Mean Accuracy: 0.1203 - Overall Accuracy: 0.5421 - Per Category Iou: [0.5290430214500985, 0.5487400784041843, 0.6619536389625599, 0.12631756630031135, 0.667709713836941, 0.40753243770811803, 0.43861790085568836, 0.2038499011376336, 0.0, 0.5802379269854258, nan, 0.0, 0.00029880390554281244, nan, 0.0, 0.0, 0.0, 0.0, 0.09049022128181297, 0.013685578172368991, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] - Per Category Accuracy: [0.8874631796148624, 0.983710303861092, 0.7448862590316111, 0.2007511401234016, 0.7139033574305619, 0.4423744868961162, 0.9995063516092938, 0.24030097792490754, 0.0, 0.9445905269349203, nan, 0.0, 0.008382642998027613, nan, 0.0, 0.0, 0.0, 0.0, 0.1936439422792095, 0.014002126905352711, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] ## 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: 6e-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: 50 ### Training results \| Training Loss \| Epoch \| Step \| Validation Loss \| Mean Iou \| Mean Accuracy \| Overall Accuracy \| Per Category Iou \| Per Category Accuracy \| \|:-------------:\|:-----:\|:----:\|:---------------:\|:--------:\|:-------------:\|:----------------:\|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:\|:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:\| \| 3.688 \| 2.0 \| 20 \| 3.7364 \| 0.0346 \| 0.0861 \| 0.4498 \| [0.5445246383770482, 0.3339450224958781, 0.6477979381753378, 0.10257270193325284, 0.13740277950687013, 0.2923593294882429, 0.43092224064007706, 0.026117754709241787, 0.0, 0.005411154124303399, 0.0, 0.0, 0.00734193624418125, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan] \| [0.8893084874357328, 0.9828649760109665, 0.8347679477531192, 0.13674525817957814, 0.13756412443091617, 0.6296927193259435, 0.7657144737708155, 0.027961220801594407, 0.0, 0.0055011590492336435, nan, 0.0, 0.15359960552268245, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 3.7673 \| 4.0 \| 40 \| 3.3319 \| 0.0410 \| 0.0896 \| 0.4550 \| [0.5255379142235984, 0.4766923289947383, 0.6000659367831092, 0.15913063179699638, 0.06135603646286638, 0.41507875949869866, 0.30641540161693714, 0.018372174182791114, 0.0, 0.011133745984486406, 0.0, 0.0, 0.00875771914347582, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan] \| [0.9774421533982581, 0.9831711217729038, 0.7054588559044208, 0.19539578924359394, 0.06150697332686075, 0.659947152377312, 0.8668794839728823, 0.020006080362119344, 0.0, 0.012291111649309761, nan, 0.0, 0.2692307692307692, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 3.7122 \| 6.0 \| 60 \| 3.2402 \| 0.0443 \| 0.0910 \| 0.4546 \| [0.5331449211884658, 0.5096587066477429, 0.6099317893720195, 0.14884262629203668, 0.08252191804159513, 0.3571447073044379, 0.33233355888038185, 0.028218781439403234, 0.0, 0.002750710600238395, nan, 0.0, 0.0074093852212802885, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan] \| [0.9426190137773182, 0.9779392277815856, 0.6853559512543321, 0.20316551909147815, 0.08261719518755166, 0.6874262543001014, 0.9401917549748788, 0.029135068488523316, 0.0, 0.0028543749783759473, nan, 0.0, 0.27366863905325445, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 3.143 \| 8.0 \| 80 \| 3.1031 \| 0.0455 \| 0.0882 \| 0.4551 \| [0.5392500200116639, 0.48507061997757955, 0.6790375440779921, 0.1510979736066201, 0.00970230519949094, 0.3460482632178782, 0.3786052241483176, 0.020821731071342484, 0.0, 0.02180300246395096, nan, 0.0, 0.0050370065789473685, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.924504119472041, 0.9866072652501714, 0.793015015810366, 0.2001053185887309, 0.00970230519949094, 0.5802934871121599, 0.9203909695254393, 0.02115459320688432, 0.0, 0.02227277445247898, nan, 0.0, 0.21745562130177515, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 3.1285 \| 10.0 \| 100 \| 3.0147 \| 0.0500 \| 0.0913 \| 0.4611 \| [0.5279775078771491, 0.5364035087719298, 0.6043004425059568, 0.1730750274860674, 0.17374020964800652, 0.387475578195804, 0.3233683054665244, 0.01362610439408305, 0.0, 0.008417588706600533, nan, 0.0, 0.0037462710727747843, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.9493973954938221, 0.983541238291067, 0.6766255284925728, 0.22679265154450703, 0.17374932759548145, 0.6295182224585778, 0.9756192544812304, 0.013714594558075903, 0.0, 0.009159948794242811, nan, 0.0, 0.1997041420118343, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.8777 \| 12.0 \| 120 \| 2.9980 \| 0.0536 \| 0.0926 \| 0.4650 \| [0.5277860922742017, 0.5356964379392906, 0.6723194548091409, 0.16953697019696815, 0.160576759075821, 0.3962510676086133, 0.35413202469902266, 0.018904785563312085, 0.0, 0.053459190509525856, nan, 0.0, 0.0036004154325499096, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| [0.903107861060329, 0.9845236463331049, 0.7711195160316143, 0.2123461205997198, 0.160576759075821, 0.5821215495321822, 0.9824096623445008, 0.0189589068860101, 0.0, 0.06142960938310902, nan, 0.0, 0.23076923076923078, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 3.0064 \| 14.0 \| 140 \| 2.8058 \| 0.0535 \| 0.0922 \| 0.4725 \| [0.5285329801601095, 0.5389589846425947, 0.6267061964393704, 0.17138776663586305, 0.2829107624610388, 0.40535877972665385, 0.33534470954395235, 0.01581797414891082, 0.0, 0.03735375580814578, nan, 0.0, 0.0011804184557652358, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.9427660502570688, 0.9886086360520905, 0.6861731162409118, 0.222967400916073, 0.2834267046274551, 0.6540724245093315, 0.9940378244366923, 0.01625652372185721, 0.0, 0.04269452997958689, nan, 0.0, 0.05645956607495069, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 3.1326 \| 16.0 \| 160 \| 2.9155 \| 0.0667 \| 0.1085 \| 0.5287 \| [0.5650188259280788, 0.5972000938824537, 0.7776175430657293, 0.1623852681406223, 0.3029858842065839, 0.34448445497571384, 0.44026591674601356, 0.017794429429186426, 0.0, 0.5729181020623766, nan, 0.0, 0.002365010699951322, nan, 0.0, 0.0, 0.0, 0.0, 0.018022446137462112, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| [0.9480544623120997, 0.9882522275531186, 0.9213228383079194, 0.22359335101890768, 0.3078038284417271, 0.4602562611137886, 0.9814991553127537, 0.018570439306163124, 0.0, 0.7552070719302495, nan, 0.0, 0.1269723865877712, nan, 0.0, 0.0, 0.0, 0.0, 0.018619609834539377, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.7144 \| 18.0 \| 180 \| 2.8128 \| 0.0655 \| 0.1073 \| 0.5217 \| [0.5524650907618421, 0.6138029030754759, 0.7354998896490841, 0.1507244937059166, 0.33346080305927345, 0.41254446585088406, 0.41290332894102816, 0.01273833072055287, 0.0, 0.4977908947460698, nan, 0.0, 0.0016595586871870943, nan, 0.0, 0.0, 0.0, 0.0, 0.012172477821332784, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| [0.9328214830099347, 0.980982408042038, 0.8611045615893698, 0.21104454181446045, 0.33750114800771464, 0.5213384740664417, 0.991712192018254, 0.013106558346141503, 0.0, 0.7367487804034183, nan, 0.0, 0.08826429980276135, nan, 0.0, 0.0, 0.0, 0.0, 0.012483602048157082, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.4557 \| 20.0 \| 200 \| 2.7736 \| 0.0682 \| 0.1060 \| 0.5110 \| [0.5257654123854485, 0.49916072032990944, 0.691302319713901, 0.16502411260023553, 0.4853489054904903, 0.43901126595556283, 0.40272463999149793, 0.02759797239386494, 0.0, 0.49948775570904524, nan, 0.0, 0.0004708915852130899, nan, 0.0, 0.0, 0.0, 0.0, 0.013085843130938959, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| [0.8908205125691684, 0.990568882796436, 0.7610874431133663, 0.23391655985772056, 0.4879819992390349, 0.5355641234440696, 0.9976798525636806, 0.02855236711875285, 0.0, 0.6536518700480919, nan, 0.0, 0.025394477317554242, nan, 0.0, 0.0, 0.0, 0.0, 0.013753120900512039, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.5213 \| 22.0 \| 220 \| 2.7816 \| 0.0703 \| 0.1111 \| 0.5308 \| [0.5440689431008583, 0.5184614355283469, 0.7194621233455365, 0.14283249480665577, 0.5286864033952694, 0.40737848639516144, 0.43636924218300244, 0.02685888809199552, 0.0, 0.5743388972243061, nan, 0.0, 0.0004980711948825627, nan, 0.0, 0.0, 0.0, 0.0, 0.03960361492026938, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| [0.9106410300395528, 0.9914233493260224, 0.8251783712900548, 0.20562957663914475, 0.5360736824151459, 0.4768500822628089, 0.9936593606704842, 0.028147009644129917, 0.0, 0.847628273881604, nan, 0.0, 0.02514792899408284, nan, 0.0, 0.0, 0.0, 0.0, 0.048030129914095894, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.3498 \| 24.0 \| 240 \| 2.8055 \| 0.0692 \| 0.1101 \| 0.5283 \| [0.5700983103439244, 0.5810995149835441, 0.7491326423543071, 0.1240946184313396, 0.46232141249694586, 0.36068291626629134, 0.38788266907223296, 0.03186517833361582, 0.0, 0.5432235417864263, nan, 0.0, 0.0012461256580441108, nan, 0.0, 0.0, 0.0, 0.0, 0.06565315645819271, 0.0, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| [0.9068033779180614, 0.9810372401188028, 0.8878061542536183, 0.19082535992130914, 0.47168684973563024, 0.44289797749821347, 0.9999835450536432, 0.03334065228773625, 0.0, 0.7683371968307788, nan, 0.0, 0.05818540433925049, nan, 0.0, 0.0, 0.0, 0.0, 0.09466378909060133, 0.0, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.0242 \| 26.0 \| 260 \| 2.7994 \| 0.0699 \| 0.1134 \| 0.5315 \| [0.5398820820142047, 0.5841360097383234, 0.6863650158642571, 0.13203471242169898, 0.561555007673149, 0.335132764480906, 0.41699745360784646, 0.0548605767469129, 0.0, 0.6124071574265139, nan, 0.0, 0.0007264457850352168, nan, 0.0, 0.0, 0.0, 0.0, 0.06054418749167739, 0.0004430856484558465, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.901414490935201, 0.980123372172721, 0.8035121944917266, 0.2119387562470814, 0.5857135359949619, 0.43177172485998705, 0.9997202659119331, 0.0632188761464016, 0.0, 0.8907639345396672, nan, 0.0, 0.028353057199211044, nan, 0.0, 0.0, 0.0, 0.0, 0.11544158097414413, 0.00044310528181495923, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.4443 \| 28.0 \| 280 \| 2.6896 \| 0.0714 \| 0.1164 \| 0.5428 \| [0.5469046938577081, 0.5971152147997704, 0.723692066206046, 0.13746607589754425, 0.5629920030963811, 0.3715061908991171, 0.44461751048568626, 0.07683866327567158, 0.0, 0.5431491849626494, nan, 0.0, 0.0004744943060683272, nan, 0.0, 0.0, 0.0, 0.0, 0.06503724784464719, 0.0008862105636299185, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.9097637123770408, 0.9887365775645419, 0.8339217136563449, 0.206841733981142, 0.591611015626025, 0.47270370431921294, 0.9989139735404463, 0.08751498978161366, 0.0, 0.9289001141749992, nan, 0.0, 0.01799802761341223, nan, 0.0, 0.0, 0.0, 0.0, 0.13152215310397358, 0.0008862105636299185, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.1037 \| 30.0 \| 300 \| 2.6889 \| 0.0685 \| 0.1145 \| 0.5224 \| [0.5223163875923119, 0.5210373476872969, 0.6803276632393397, 0.13057052026422494, 0.5740544653330374, 0.35095013636902644, 0.4567682610233347, 0.05511532093488891, 0.0, 0.6137970209543044, 0.0, 0.0, 0.0006255149055625057, nan, 0.0, 0.0, 0.0, 0.0, 0.13225938107699325, 0.0010191421481744063, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8479030147379565, 0.9911994516792324, 0.7883865674871692, 0.2044472264449015, 0.5939267111874992, 0.3934738171605205, 0.9988316988086618, 0.06044048845575692, 0.0, 0.9252932221568695, nan, 0.0, 0.030325443786982247, nan, 0.0, 0.0, 0.0, 0.0, 0.23312597858744868, 0.0010191421481744063, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 1.8701 \| 32.0 \| 320 \| 2.6938 \| 0.0711 \| 0.1169 \| 0.5325 \| [0.5220021689921465, 0.5421127667517733, 0.6725032126454334, 0.12156799020006125, 0.6249390708777544, 0.4247157491838343, 0.4400857868916276, 0.07354098385704354, 0.0, 0.5968861021705961, nan, 0.0, 0.0005501396053191993, nan, 0.0, 0.0, 0.0, 0.0, 0.09409925919582067, 0.008277493102089082, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8787684224456087, 0.988626913411012, 0.753868614081723, 0.1932596103212217, 0.656030648525958, 0.5015870905555648, 0.9983325654358367, 0.08129106355667404, 0.0, 0.9271528907033872, nan, 0.0, 0.022928994082840236, nan, 0.0, 0.0, 0.0, 0.0, 0.18598451187000126, 0.008374689826302729, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 1.7081 \| 34.0 \| 340 \| 2.6581 \| 0.0710 \| 0.1139 \| 0.5231 \| [0.5137814638944675, 0.4451227485208068, 0.6731168529064608, 0.15325710146427277, 0.5410841491752695, 0.3646819876053656, 0.46368211580433943, 0.11745800999066493, 0.0, 0.659651835131876, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.11052066091703691, 0.007176190895482962, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8601560547171754, 0.9955129083847384, 0.7570371470929275, 0.23543672439317614, 0.5590731969718836, 0.4073089259302345, 0.9904835560236074, 0.13919806779603763, 0.0, 0.9226464380860119, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.16105962506876562, 0.007222616093583835, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 1.8887 \| 36.0 \| 360 \| 2.6809 \| 0.0720 \| 0.1170 \| 0.5252 \| [0.5222722059173355, 0.5376719226742726, 0.6748048560072764, 0.1262832911769082, 0.5959977891113735, 0.4117124930548968, 0.44974482107832237, 0.07852803433426613, 0.0, 0.6013350360526654, nan, 0.0, 0.000693721817551162, nan, 0.0, 0.0, 0.0, 0.0, 0.09746794642217606, 0.00839597344938239, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8447147737353637, 0.9879872058487549, 0.7452480079584763, 0.20239053324987333, 0.6224825830829583, 0.5049025310355143, 0.9986122995239035, 0.09147567010657523, 0.0, 0.9327059474795004, nan, 0.0, 0.029092702169625246, nan, 0.0, 0.0, 0.0, 0.0, 0.2303330371122678, 0.008463310882665722, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.2154 \| 38.0 \| 380 \| 2.6333 \| 0.0768 \| 0.1216 \| 0.5451 \| [0.5252281150749047, 0.5341900701796827, 0.6816421675527212, 0.13850695747889213, 0.6025770795168752, 0.4379378827163899, 0.4565431330116538, 0.20476580846775436, 0.0, 0.6824203660312836, nan, 0.0, 0.0005496042849148613, nan, 0.0, 0.0, 0.0, 0.0, 0.10153206390895163, 0.01417452932736206, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8932000529331328, 0.9888142563399589, 0.7470858217029976, 0.21629059981916998, 0.6365604376861412, 0.5277117644126104, 0.9974604532789223, 0.2805495971760096, 0.0, 0.9320918243780922, nan, 0.0, 0.013560157790927022, nan, 0.0, 0.0, 0.0, 0.0, 0.19630993186915494, 0.01444523218716767, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.165 \| 40.0 \| 400 \| 2.6768 \| 0.0740 \| 0.1184 \| 0.5356 \| [0.5278760892435632, 0.5692884784938572, 0.6663932751441061, 0.12705388928304587, 0.6648403827891007, 0.40507117829025496, 0.4290532186233388, 0.10117158896753722, 0.0, 0.6410734319073539, nan, 0.0, 0.0008257131539452909, nan, 0.0, 0.0, 0.0, 0.0, 0.07810178626956432, 0.0068164826949294165, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8779548205909886, 0.985419236920265, 0.7479255959975065, 0.20105914731685992, 0.7164355344467915, 0.4591677330364117, 0.9992485574497028, 0.11901464353877075, 0.0, 0.9341677334532748, nan, 0.0, 0.03648915187376726, nan, 0.0, 0.0, 0.0, 0.0, 0.1913164910498921, 0.006868131868131868, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 1.2369 \| 42.0 \| 420 \| 2.6011 \| 0.0710 \| 0.1176 \| 0.5262 \| [0.5217002173573326, 0.4466952295821389, 0.6968318877081771, 0.12430322276679455, 0.6455977631611362, 0.3588564016319882, 0.4613312255214674, 0.09666473429951691, 0.0, 0.6157443403347276, nan, 0.0, 0.00031487885450387244, nan, 0.0, 0.0, 0.0, 0.0, 0.14433419494705244, 0.004342431761786601, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8099430968823365, 0.9932922092757597, 0.7953179353179999, 0.20184406887438275, 0.6876697411406605, 0.3953932827015439, 0.9956010443405955, 0.10561251203405003, 0.0, 0.9384492959208387, nan, 0.0, 0.014053254437869823, nan, 0.0, 0.0, 0.0, 0.0, 0.2930049511235242, 0.004342431761786601, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.0646 \| 44.0 \| 440 \| 2.6161 \| 0.0735 \| 0.1194 \| 0.5376 \| [0.5279592791205597, 0.45058932822388664, 0.6806860497007157, 0.13310259368457036, 0.644979894834519, 0.36316445830085736, 0.4712505349431339, 0.1986756411001919, 0.0, 0.5762290959386395, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.12794710297063153, 0.013649929775280898, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8548186305022276, 0.9928901073794837, 0.7775760883959342, 0.21664828559221835, 0.6839567561894015, 0.38716700181144365, 0.996582856139889, 0.23082574695559646, 0.0, 0.9513372314292634, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.2243662985061995, 0.013780574264445232, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 1.4952 \| 46.0 \| 460 \| 2.6179 \| 0.0757 \| 0.1228 \| 0.5461 \| [0.5273642894171665, 0.5466249103683828, 0.6675992691908981, 0.13401316608104666, 0.6815742503569728, 0.407689227072487, 0.4726095863202416, 0.204243653857898, 0.0, 0.5548311233425068, nan, 0.0, 0.0006031411591568891, nan, 0.0, 0.0, 0.0, 0.0, 0.09452166802943582, 0.022502134927412466, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8725389769201739, 0.9857756454192369, 0.7529771613690905, 0.22471608691764286, 0.7515120901612459, 0.44832399913582505, 0.998414840167621, 0.25419291637813096, 0.0, 0.959095941597758, nan, 0.0, 0.01849112426035503, nan, 0.0, 0.0, 0.0, 0.0, 0.22013456899834963, 0.023351648351648352, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 2.265 \| 48.0 \| 480 \| 2.6001 \| 0.0729 \| 0.1221 \| 0.5456 \| [0.5282490432130446, 0.5826753468354156, 0.6669979775630499, 0.12854484974911204, 0.6845652266387938, 0.4169519406037434, 0.4559235232159879, 0.20162061028629885, 0.0, 0.5345489350594105, nan, 0.0, 0.000965970715835141, nan, 0.0, 0.0, 0.0, 0.0, 0.08393083087304935, 0.016724410796013518, 0.0, nan, 0.0, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8828315305027177, 0.9798903358464702, 0.7477834803476665, 0.2038808906375749, 0.7389889660058515, 0.4675768201685141, 0.9995502314662454, 0.2529937338490381, 0.0, 0.9564751063903401, nan, 0.0, 0.028106508875739646, nan, 0.0, 0.0, 0.0, 0.0, 0.193686259574288, 0.017325416518964906, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| \| 1.8367 \| 50.0 \| 500 \| 2.6113 \| 0.0736 \| 0.1203 \| 0.5421 \| [0.5290430214500985, 0.5487400784041843, 0.6619536389625599, 0.12631756630031135, 0.667709713836941, 0.40753243770811803, 0.43861790085568836, 0.2038499011376336, 0.0, 0.5802379269854258, nan, 0.0, 0.00029880390554281244, nan, 0.0, 0.0, 0.0, 0.0, 0.09049022128181297, 0.013685578172368991, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan] \| [0.8874631796148624, 0.983710303861092, 0.7448862590316111, 0.2007511401234016, 0.7139033574305619, 0.4423744868961162, 0.9995063516092938, 0.24030097792490754, 0.0, 0.9445905269349203, nan, 0.0, 0.008382642998027613, nan, 0.0, 0.0, 0.0, 0.0, 0.1936439422792095, 0.014002126905352711, 0.0, nan, 0.0, nan, nan, 0.0, 0.0, 0.0, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, 0.0, nan, 0.0, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, 0.0, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, 0.0, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, 0.0, 0.0, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, 0.0, 0.0, nan, nan, nan, 0.0, 0.0, nan, 0.0, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan, nan] \| ### Framework versions - Transformers 4.35.2 - Pytorch 2.1.0+cu121 - Datasets 2.19.0 - Tokenizers 0.15.1	{"license": "other", "tags": ["generated_from_trainer"], "datasets": ["scene_parse_150"], "base_model": "nvidia/mit-b0", "model-index": [{"name": "segformer-b0-scene-parse-150", "results": []}]}	serbest/segformer-b0-scene-parse-150	null	[ "transformers", "tensorboard", "safetensors", "segformer", "generated_from_trainer", "dataset:scene_parse_150", "base_model:nvidia/mit-b0", "license:other", "endpoints_compatible", "region:us" ]	null	2024-05-01T21:16:16+00:00
null	null		{"license": "unknown"}	Thatsnazzyartist22/FileName2	null	[ "license:unknown", "region:us" ]	null	2024-05-01T21:17:40+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": "microsoft/Phi-3-mini-4k-instruct"}	Entreprenerdly/phi-3_fined-tune2	null	[ "peft", "tensorboard", "safetensors", "arxiv:1910.09700", "base_model:microsoft/Phi-3-mini-4k-instruct", "region:us" ]	null	2024-05-01T21:18:43+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. --> # 0.0001_withdpo_4iters_bs256_5102lr_iter_4 This model is a fine-tuned version of [ShenaoZ/0.0001_withdpo_4iters_bs256_511lr_iter_3](https://huggingface.co/ShenaoZ/0.0001_withdpo_4iters_bs256_511lr_iter_3) 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: 2e-08 - 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": "ShenaoZ/0.0001_withdpo_4iters_bs256_511lr_iter_3", "model-index": [{"name": "0.0001_withdpo_4iters_bs256_5102lr_iter_4", "results": []}]}	ShenaoZ/0.0001_withdpo_4iters_bs256_5102lr_iter_4	null	[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.0001_withdpo_4iters_bs256_511lr_iter_3", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]	null	2024-05-01T21:19:08+00:00
null	null		{}	zbin1234/zbin	null	[ "region:us" ]	null	2024-05-01T21:19:35+00:00
null	null		{}	Aleksrrrrr/Miner2	null	[ "region:us" ]	null	2024-05-01T21:20:05+00:00
reinforcement-learning	sample-factory	A(n) APPO model trained on the doom_health_gathering_supreme environment. This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory. Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/ ## Downloading the model After installing Sample-Factory, download the model with: ``` python -m sample_factory.huggingface.load_from_hub -r pdejong/rl_course_vizdoom_health_gathering_supreme ``` ## Using the model To run the model after download, use the `enjoy` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme ``` You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag. See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details ## Training with this model To continue training with this model, use the `train` script corresponding to this environment: ``` python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000 ``` Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.	{"library_name": "sample-factory", "tags": ["deep-reinforcement-learning", "reinforcement-learning", "sample-factory"], "model-index": [{"name": "APPO", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "doom_health_gathering_supreme", "type": "doom_health_gathering_supreme"}, "metrics": [{"type": "mean_reward", "value": "8.94 +/- 3.74", "name": "mean_reward", "verified": false}]}]}]}	pdejong/rl_course_vizdoom_health_gathering_supreme	null	[ "sample-factory", "tensorboard", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]	null	2024-05-01T21:21:06+00:00

Subsets and Splits

No saved queries yet

Save your SQL queries to embed, download, and access them later. Queries will appear here once saved.