Datasets:
ftopal
/
huggingface-models-raw

Dataset card Data Studio Files Community
1
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": []}
miguel-kjh/pythia_160m-adpater-lora-dbpedia
null
[ "transformers", "safetensors", "gpt_neox", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T11:47:53+00:00
text-classification
transformers
{}
KatAlex/gpt2
null
[ "transformers", "pytorch", "gpt2", "text-classification", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T11:47:53+00:00
null
null
{}
Mariofm02/YOLOv8m_Car_Parts_Damaged
null
[ "region:us" ]
null
2024-05-02T11:48:06+00:00
fill-mask
transformers
{"license": "mit"}
AfnanTS/ARBERT_ArLAMA
null
[ "transformers", "pytorch", "bert", "fill-mask", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:48:27+00:00
null
null
{}
optimum-internal-testing/optimum-neuron-cache-for-testing-oejfb
null
[ "region:us" ]
null
2024-05-02T11:48:29+00:00
null
null
{}
cwiz/alextime.chkp
null
[ "region:us" ]
null
2024-05-02T11:48:34+00:00
null
null
{}
Ilkinism/ilmetin__1
null
[ "region:us" ]
null
2024-05-02T11:51:00+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. --> # gen-z-translate-llama-3-instruct-v1 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 4 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 10 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "datasets": ["generator"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "gen-z-translate-llama-3-instruct-v1", "results": []}]}
clp/gen-z-translate-llama-3-instruct-v1
null
[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]
null
2024-05-02T11:51:51+00:00
sentence-similarity
sentence-transformers
# luiz-and-robert-thesis/distilroberta-frozen-newtriplets-v2-lr-2e-7-m-1-e-3 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search. <!--- Describe your model here --> ## Usage (Sentence-Transformers) Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed: ``` pip install -U sentence-transformers ``` Then you can use the model like this: ```python from sentence_transformers import SentenceTransformer sentences = ["This is an example sentence", "Each sentence is converted"] model = SentenceTransformer('luiz-and-robert-thesis/distilroberta-frozen-newtriplets-v2-lr-2e-7-m-1-e-3') embeddings = model.encode(sentences) print(embeddings) ``` ## Evaluation Results <!--- Describe how your model was evaluated --> For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name=luiz-and-robert-thesis/distilroberta-frozen-newtriplets-v2-lr-2e-7-m-1-e-3) ## Training The model was trained with the parameters: **DataLoader**: `torch.utils.data.dataloader.DataLoader` of length 5885 with parameters: ``` {'batch_size': 16, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'} ``` **Loss**: `sentence_transformers.losses.TripletLoss.TripletLoss` with parameters: ``` {'distance_metric': 'TripletDistanceMetric.COSINE', 'triplet_margin': 1} ``` Parameters of the fit()-Method: ``` { "epochs": 3, "evaluation_steps": 0, "evaluator": "NoneType", "max_grad_norm": 1, "optimizer_class": "<class 'torch.optim.adamw.AdamW'>", "optimizer_params": { "lr": 2e-07 }, "scheduler": "WarmupLinear", "steps_per_epoch": null, "warmup_steps": 2648, "weight_decay": 0.01 } ``` ## Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) (2): Normalize() ) ``` ## Citing & Authors <!--- Describe where people can find more information -->
{"library_name": "sentence-transformers", "tags": ["sentence-transformers", "feature-extraction", "sentence-similarity"], "pipeline_tag": "sentence-similarity"}
luiz-and-robert-thesis/distilroberta-frozen-newtriplets-v2-lr-2e-7-m-1-e-3
null
[ "sentence-transformers", "safetensors", "roberta", "feature-extraction", "sentence-similarity", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:51:52+00:00
null
null
{"license": "apache-2.0"}
neeraj0022/bhasa_model
null
[ "license:apache-2.0", "region:us" ]
null
2024-05-02T11:52:04+00:00
null
null
{}
qnguyen3/14b-gguf
null
[ "gguf", "region:us" ]
null
2024-05-02T11:52:09+00:00
text-classification
transformers
{}
MASHXD/finetuning-review-model
null
[ "transformers", "pytorch", "tensorboard", "distilbert", "text-classification", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:52:29+00:00
text-generation
transformers
{}
AdnanRiaz107/SFTCBertbase-mlm-APPS10k
null
[ "transformers", "safetensors", "roberta", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:52:30+00:00
null
null
{}
optimum-internal-testing/optimum-neuron-cache-for-testing-yhgpc
null
[ "region:us" ]
null
2024-05-02T11:54:42+00:00
text2text-generation
transformers
{}
lkid08/25k_only_tag_clean_under_4096_02-05
null
[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T11:55:30+00:00
text-generation
transformers
# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> deep level trained on Jack O'Neill request response ## 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": []}
nachtwindecho/mistralai-Code-Instruct-Finetune-SG1-V3
null
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T11:55:31+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. --> # Siren1200-Chatbot-Phi2 This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) 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: 0.0002 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "mit", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "microsoft/phi-2", "model-index": [{"name": "Siren1200-Chatbot-Phi2", "results": []}]}
RayBoustany/Siren1200-Chatbot-Phi2
null
[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:microsoft/phi-2", "license:mit", "region:us" ]
null
2024-05-02T11:55:49+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": "245.39 +/- 31.16", "name": "mean_reward", "verified": false}]}]}]}
emiliomartin84/TestModel
null
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
null
2024-05-02T11:57:17+00:00
automatic-speech-recognition
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": []}
shtapm/whisper-large_0502_decoder1_200steps
null
[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:57:29+00:00
text-generation
transformers
{}
AdnanRiaz107/SFTCBertbase-mlm-APPS5k
null
[ "transformers", "safetensors", "roberta", "text-generation", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:58:19+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. --> # donut_synDB_van This model is a fine-tuned version of [naver-clova-ix/donut-base](https://huggingface.co/naver-clova-ix/donut-base) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.1275 ## 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: 7e-05 - train_batch_size: 5 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 6 - total_train_batch_size: 30 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 26 - num_epochs: 12 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.7738 | 1.0 | 26 | 0.6438 | | 0.5439 | 1.5 | 39 | 0.2740 | | 0.258 | 2.0 | 52 | 0.1549 | | 0.1257 | 2.5 | 65 | 0.1351 | | 0.0939 | 3.0 | 78 | 0.1411 | | 0.0656 | 3.5 | 91 | 0.0860 | | 0.0573 | 4.0 | 104 | 0.1013 | | 0.0405 | 4.5 | 117 | 0.0952 | | 0.0448 | 5.0 | 130 | 0.1299 | | 0.0346 | 5.5 | 143 | 0.1429 | | 0.0308 | 6.0 | 156 | 0.1518 | | 0.0249 | 6.5 | 169 | 0.1275 | ### Framework versions - Transformers 4.38.2 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
{"license": "mit", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "base_model": "naver-clova-ix/donut-base", "model-index": [{"name": "donut_synDB_van", "results": []}]}
Donut01/donut_synDB_van
null
[ "transformers", "tensorboard", "safetensors", "vision-encoder-decoder", "generated_from_trainer", "dataset:imagefolder", "base_model:naver-clova-ix/donut-base", "license:mit", "endpoints_compatible", "region:us" ]
null
2024-05-02T11:58:43+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) Starling-LM-7B-alpha - bnb 4bits - Model creator: https://huggingface.co/berkeley-nest/ - Original model: https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/ Original model description: --- license: apache-2.0 datasets: - berkeley-nest/Nectar language: - en library_name: transformers tags: - reward model - RLHF - RLAIF --- # Starling-LM-7B-alpha <!-- Provide a quick summary of what the model is/does. --> - **Developed by:** Banghua Zhu * , Evan Frick * , Tianhao Wu * , Hanlin Zhu and Jiantao Jiao. - **Model type:** Language Model finetuned with RLHF / RLAIF - **License:** Apache-2.0 license under the condition that the model is not used to compete with OpenAI - **Finetuned from model:** [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5) (based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)) We introduce Starling-7B, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). The model harnesses the power of our new GPT-4 labeled ranking dataset, [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), and our new reward training and policy tuning pipeline. Starling-7B-alpha scores 8.09 in MT Bench with GPT-4 as a judge, outperforming every model to date on MT-Bench except for OpenAI's GPT-4 and GPT-4 Turbo. We release the ranking dataset [Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), the reward model [Starling-RM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-RM-7B-alpha) and the language model [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) on HuggingFace, and an online demo in LMSYS [Chatbot Arena](https://chat.lmsys.org). Stay tuned for our forthcoming code and paper, which will provide more details on the whole process. Starling-LM-7B-alpha is a language model trained from [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5) with reward model [berkeley-nest/Starling-RM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-RM-7B-alpha) and policy optimization method [advantage-induced policy alignment (APA)](https://arxiv.org/abs/2306.02231). The evaluation results are listed below. | Model | Tuning Method | MT Bench | AlpacaEval | MMLU | |-----------------------|------------------|----------|------------|------| | GPT-4-Turbo | ? | 9.32 | 97.70 | | | GPT-4 | SFT + PPO | 8.99 | 95.28 | 86.4 | | **Starling-7B** | C-RLFT + APA | 8.09 | 91.99 | 63.9 | | Claude-2 | ? | 8.06 | 91.36 | 78.5 | | GPT-3.5-Turbo | ? | 7.94 | 89.37 | 70 | | Claude-1 | ? | 7.9 | 88.39 | 77 | | Tulu-2-dpo-70b | SFT + DPO | 7.89 | 95.1 | | | Openchat-3.5 | C-RLFT | 7.81 | 88.51 | 64.3 | | Zephyr-7B-beta | SFT + DPO | 7.34 | 90.60 | 61.4 | | Llama-2-70b-chat-hf | SFT + PPO | 6.86 | 92.66 | 63 | | Neural-chat-7b-v3-1 | SFT + DPO | 6.84 | 84.53 | 62.4 | | Tulu-2-dpo-7b | SFT + DPO | 6.29 | 85.1 | | For more detailed discussions, please check out our [blog post](https://starling.cs.berkeley.edu), and stay tuned for our upcoming code and paper! <!-- Provide the basic links for the model. --> - **Blog:** https://starling.cs.berkeley.edu/ - **Paper:** Coming soon! - **Code:** Coming soon! ## 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. --> **Important: Please use the exact chat template provided below for the model. Otherwise there will be a degrade in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** Our model follows the exact chat template and usage as [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5). Please refer to their model card for more details. In addition, our model is hosted on LMSYS [Chatbot Arena](https://chat.lmsys.org) for free test. The conversation template is the same as Openchat 3.5: ``` import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat_3.5") # Single-turn tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Multi-turn tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Coding Mode tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747] ``` ## Code Examples ```python import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("berkeley-nest/Starling-LM-7B-alpha") model = transformers.AutoModelForCausalLM.from_pretrained("berkeley-nest/Starling-LM-7B-alpha") def generate_response(prompt): input_ids = tokenizer(prompt, return_tensors="pt").input_ids outputs = model.generate( input_ids, max_length=256, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) response_ids = outputs[0] response_text = tokenizer.decode(response_ids, skip_special_tokens=True) return response_text # Single-turn conversation prompt = "Hello, how are you?" single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:" response_text = generate_response(single_turn_prompt) print("Response:", response_text) ## Multi-turn conversation prompt = "Hello" follow_up_question = "How are you today?" response = "" multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:" response_text = generate_response(multi_turn_prompt) print("Multi-turn conversation response:", response_text) ### Coding conversation prompt = "Implement quicksort using C++" coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:" response = generate_response(coding_prompt) print("Coding conversation response:", response) ``` ## License The dataset, model and online demo is a research preview intended for non-commercial use only, subject to the data distillation [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation. ## Acknowledgment We would like to thank Wei-Lin Chiang from Berkeley for detailed feedback of the blog and the projects. We would like to thank the [LMSYS Organization](https://lmsys.org/) for their support of [lmsys-chat-1M](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) dataset, evaluation and online demo. We would like to thank the open source community for their efforts in providing the datasets and base models we used to develope the project, including but not limited to Anthropic, Llama, Mistral, Hugging Face H4, LMSYS, OpenChat, OpenBMB, Flan and ShareGPT. ## Citation ``` @misc{starling2023, title = {Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF}, url = {}, author = {Zhu, Banghua and Frick, Evan and Wu, Tianhao and Zhu, Hanlin and Jiao, Jiantao}, month = {November}, year = {2023} } ```
{}
RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-4bits
null
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:2306.02231", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]
null
2024-05-02T11:59:46+00:00
text-generation
transformers
{}
vandeju/llama3-8B-Dutch_QDora_model
null
[ "transformers", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:00:05+00:00
null
null
{"license": "mit"}
happydiego/satellogic
null
[ "license:mit", "region:us" ]
null
2024-05-02T12:00:12+00:00
text-generation
transformers
# output_folder merge This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit). ## Merge Details ### Merge Method This model was merged using the SLERP merge method. ### Models Merged The following models were included in the merge: * [BioMistral/BioMistral-7B](https://huggingface.co/BioMistral/BioMistral-7B) * [akjindal53244/Arithmo-Mistral-7B](https://huggingface.co/akjindal53244/Arithmo-Mistral-7B) ### Configuration The following YAML configuration was used to produce this model: ```yaml slices: - sources: - model: akjindal53244/Arithmo-Mistral-7B layer_range: [0, 32] - model: BioMistral/BioMistral-7B layer_range: [0, 32] merge_method: slerp base_model: akjindal53244/Arithmo-Mistral-7B parameters: t: - filter: self_attn value: [0, 0.5, 0.3, 0.7, 1] - filter: mlp value: [1, 0.5, 0.7, 0.3, 0] - value: 0.5 dtype: bfloat16 ```
{"library_name": "transformers", "tags": ["mergekit", "merge"], "base_model": ["BioMistral/BioMistral-7B", "akjindal53244/Arithmo-Mistral-7B"]}
tanyakansal/arithBio-7B-slerp1
null
[ "transformers", "safetensors", "gguf", "mistral", "text-generation", "mergekit", "merge", "base_model:BioMistral/BioMistral-7B", "base_model:akjindal53244/Arithmo-Mistral-7B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:00:16+00:00
null
null
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Phi-3-mini-128k-instruct - GGUF - Model creator: https://huggingface.co/microsoft/ - Original model: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Phi-3-mini-128k-instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q2_K.gguf) | Q2_K | 1.32GB | | [Phi-3-mini-128k-instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.IQ3_XS.gguf) | IQ3_XS | 1.51GB | | [Phi-3-mini-128k-instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.IQ3_S.gguf) | IQ3_S | 1.57GB | | [Phi-3-mini-128k-instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q3_K_S.gguf) | Q3_K_S | 1.57GB | | [Phi-3-mini-128k-instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.IQ3_M.gguf) | IQ3_M | 1.73GB | | [Phi-3-mini-128k-instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q3_K.gguf) | Q3_K | 1.82GB | | [Phi-3-mini-128k-instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q3_K_M.gguf) | Q3_K_M | 1.82GB | | [Phi-3-mini-128k-instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q3_K_L.gguf) | Q3_K_L | 1.94GB | | [Phi-3-mini-128k-instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.IQ4_XS.gguf) | IQ4_XS | 1.93GB | | [Phi-3-mini-128k-instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q4_0.gguf) | Q4_0 | 2.03GB | | [Phi-3-mini-128k-instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.IQ4_NL.gguf) | IQ4_NL | 2.04GB | | [Phi-3-mini-128k-instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q4_K_S.gguf) | Q4_K_S | 2.04GB | | [Phi-3-mini-128k-instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q4_K.gguf) | Q4_K | 2.23GB | | [Phi-3-mini-128k-instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q4_K_M.gguf) | Q4_K_M | 2.23GB | | [Phi-3-mini-128k-instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q4_1.gguf) | Q4_1 | 2.24GB | | [Phi-3-mini-128k-instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q5_0.gguf) | Q5_0 | 2.46GB | | [Phi-3-mini-128k-instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q5_K_S.gguf) | Q5_K_S | 2.46GB | | [Phi-3-mini-128k-instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q5_K.gguf) | Q5_K | 2.62GB | | [Phi-3-mini-128k-instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q5_K_M.gguf) | Q5_K_M | 2.62GB | | [Phi-3-mini-128k-instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q5_1.gguf) | Q5_1 | 2.68GB | | [Phi-3-mini-128k-instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf/blob/main/Phi-3-mini-128k-instruct.Q6_K.gguf) | Q6_K | 2.92GB | Original model description: --- license: mit license_link: https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/LICENSE language: - en pipeline_tag: text-generation tags: - nlp - code widget: - messages: - role: user content: Can you provide ways to eat combinations of bananas and dragonfruits? --- ## Model Summary The Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets. This dataset includes both synthetic data and filtered publicly available website data, with an emphasis on high-quality and reasoning-dense properties. The model belongs to the Phi-3 family with the Mini version in two variants [4K](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) and [128K](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct) which is the context length (in tokens) that it can support. After initial training, the model underwent a post-training process that involved supervised fine-tuning and direct preference optimization to enhance its ability to follow instructions and adhere to safety measures. When evaluated against benchmarks that test common sense, language understanding, mathematics, coding, long-term context, and logical reasoning, the Phi-3 Mini-128K-Instruct demonstrated robust and state-of-the-art performance among models with fewer than 13 billion parameters. Resources and Technical Documentation: + [Phi-3 Microsoft Blog](https://aka.ms/phi3blog-april) + [Phi-3 Technical Report](https://aka.ms/phi3-tech-report) + [Phi-3 on Azure AI Studio](https://aka.ms/phi3-azure-ai) + Phi-3 ONNX: [128K](https://aka.ms/Phi3-mini-128k-instruct-onnx) ## Intended Uses **Primary use cases** The model is intended for commercial and research use in English. The model provides uses for applications which require: 1) Memory/compute constrained environments 2) Latency bound scenarios 3) Strong reasoning (especially code, math and logic) Our model is designed to accelerate research on language and multimodal models, for use as a building block for generative AI powered features. **Use case considerations** Our models are not specifically designed or evaluated for all downstream purposes. Developers should consider common limitations of language models as they select use cases, and evaluate and mitigate for accuracy, safety, and fariness before using within a specific downstream use case, particularly for high risk scenarios. Developers should be aware of and adhere to applicable laws or regulations (including privacy, trade compliance laws, etc.) that are relevant to their use case. Nothing contained in this Model Card should be interpreted as or deemed a restriction or modification to the license the model is released under. ## How to Use Phi-3 Mini-128K-Instruct has been integrated in the development version (4.41.0.dev0) of `transformers`. Until the official version is released through `pip`, ensure that you are doing one of the following: * When loading the model, ensure that `trust_remote_code=True` is passed as an argument of the `from_pretrained()` function. * Update your local `transformers` to the development version: `pip uninstall -y transformers && pip install git+https://github.com/huggingface/transformers`. The previous command is an alternative to cloning and installing from the source. The current `transformers` version can be verified with: `pip list | grep transformers`. ### Tokenizer Phi-3 Mini-128K-Instruct supports a vocabulary size of up to `32064` tokens. The [tokenizer files](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/blob/main/added_tokens.json) already provide placeholder tokens that can be used for downstream fine-tuning, but they can also be extended up to the model's vocabulary size. ### Chat Format Given the nature of the training data, the Phi-3 Mini-128K-Instruct model is best suited for prompts using the chat format as follows. You can provide the prompt as a question with a generic template as follow: ```markdown <|user|>\nQuestion<|end|>\n<|assistant|> ``` For example: ```markdown <|user|> How to explain Internet for a medieval knight?<|end|> <|assistant|> ``` where the model generates the text after `<|assistant|>`. In case of few-shots prompt, the prompt can be formatted as the following: ```markdown <|user|> I am going to Paris, what should I see?<|end|> <|assistant|> Paris, the capital of France, is known for its stunning architecture, art museums, historical landmarks, and romantic atmosphere. Here are some of the top attractions to see in Paris:\n\n1. The Eiffel Tower: The iconic Eiffel Tower is one of the most recognizable landmarks in the world and offers breathtaking views of the city.\n2. The Louvre Museum: The Louvre is one of the world's largest and most famous museums, housing an impressive collection of art and artifacts, including the Mona Lisa.\n3. Notre-Dame Cathedral: This beautiful cathedral is one of the most famous landmarks in Paris and is known for its Gothic architecture and stunning stained glass windows.\n\nThese are just a few of the many attractions that Paris has to offer. With so much to see and do, it's no wonder that Paris is one of the most popular tourist destinations in the world."<|end|> <|user|> What is so great about #1?<|end|> <|assistant|> ``` ### Sample inference code This code snippets show how to get quickly started with running the model on a GPU: ```python import torch from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline torch.random.manual_seed(0) model = AutoModelForCausalLM.from_pretrained( "microsoft/Phi-3-mini-128k-instruct", device_map="cuda", torch_dtype="auto", trust_remote_code=True, ) tokenizer = AutoTokenizer.from_pretrained("microsoft/Phi-3-mini-128k-instruct") messages = [ {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"}, {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."}, {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"}, ] pipe = pipeline( "text-generation", model=model, tokenizer=tokenizer, ) generation_args = { "max_new_tokens": 500, "return_full_text": False, "temperature": 0.0, "do_sample": False, } output = pipe(messages, **generation_args) print(output[0]['generated_text']) ``` *Some applications/frameworks might not include a BOS token (`<s>`) at the start of the conversation. Please ensure that it is included since it provides more reliable results.* ## Responsible AI Considerations Like other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include: + Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English. + Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases. + Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case. + Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated. + Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as "typing, math, random, collections, datetime, itertools". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses. Developers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include: + Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques. + High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context. + Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG). + Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case. + Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations. ## Training ### Model * Architecture: Phi-3 Mini-128K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines. * Inputs: Text. It is best suited for prompts using chat format. * Context length: 128K tokens * GPUs: 512 H100-80G * Training time: 7 days * Training data: 3.3T tokens * Outputs: Generated text in response to the input * Dates: Our models were trained between February and April 2024 * Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models. ### Datasets Our training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of 1) Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code; 2) Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.); 3) High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness. ### Fine-tuning A basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided [here](https://huggingface.co/microsoft/Phi-3-mini-128k-instruct/resolve/main/sample_finetune.py). ## Benchmarks We report the results for Phi-3-Mini-128K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5. All the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation. As is now standard, we use few-shot prompts to evaluate the models, at temperature 0. The prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3. More specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model. The number of k–shot examples is listed per-benchmark. | | Phi-3-Mini-128K-In<br>3.8b | Phi-3-Small<br>7b (preview) | Phi-3-Medium<br>14b (preview) | Phi-2<br>2.7b | Mistral<br>7b | Gemma<br>7b | Llama-3-In<br>8b | Mixtral<br>8x7b | GPT-3.5<br>version 1106 | |---|---|---|---|---|---|---|---|---|---| | MMLU <br>5-Shot | 68.1 | 75.3 | 78.2 | 56.3 | 61.7 | 63.6 | 66.5 | 68.4 | 71.4 | | HellaSwag <br> 5-Shot | 74.5 | 78.7 | 83.2 | 53.6 | 58.5 | 49.8 | 71.1 | 70.4 | 78.8 | | ANLI <br> 7-Shot | 52.8 | 55.0 | 58.7 | 42.5 | 47.1 | 48.7 | 57.3 | 55.2 | 58.1 | | GSM-8K <br> 0-Shot; CoT | 83.6 | 86.4 | 90.8 | 61.1 | 46.4 | 59.8 | 77.4 | 64.7 | 78.1 | | MedQA <br> 2-Shot | 55.3 | 58.2 | 69.8 | 40.9 | 49.6 | 50.0 | 60.5 | 62.2 | 63.4 | | AGIEval <br> 0-Shot | 36.9 | 45.0 | 49.7 | 29.8 | 35.1 | 42.1 | 42.0 | 45.2 | 48.4 | | TriviaQA <br> 5-Shot | 57.1 | 59.1 | 73.3 | 45.2 | 72.3 | 75.2 | 67.7 | 82.2 | 85.8 | | Arc-C <br> 10-Shot | 84.0 | 90.7 | 91.9 | 75.9 | 78.6 | 78.3 | 82.8 | 87.3 | 87.4 | | Arc-E <br> 10-Shot | 95.2 | 97.1 | 98.0 | 88.5 | 90.6 | 91.4 | 93.4 | 95.6 | 96.3 | | PIQA <br> 5-Shot | 83.6 | 87.8 | 88.2 | 60.2 | 77.7 | 78.1 | 75.7 | 86.0 | 86.6 | | SociQA <br> 5-Shot | 76.1 | 79.0 | 79.4 | 68.3 | 74.6 | 65.5 | 73.9 | 75.9 | 68.3 | | BigBench-Hard <br> 0-Shot | 71.5 | 75.0 | 82.5 | 59.4 | 57.3 | 59.6 | 51.5 | 69.7 | 68.32 | | WinoGrande <br> 5-Shot | 72.5 | 82.5 | 81.2 | 54.7 | 54.2 | 55.6 | 65.0 | 62.0 | 68.8 | | OpenBookQA <br> 10-Shot | 80.6 | 88.4 | 86.6 | 73.6 | 79.8 | 78.6 | 82.6 | 85.8 | 86.0 | | BoolQ <br> 0-Shot | 78.7 | 82.9 | 86.5 | -- | 72.2 | 66.0 | 80.9 | 77.6 | 79.1 | | CommonSenseQA <br> 10-Shot | 78.0 | 80.3 | 82.6 | 69.3 | 72.6 | 76.2 | 79 | 78.1 | 79.6 | | TruthfulQA <br> 10-Shot | 63.2 | 68.1 | 74.8 | -- | 52.1 | 53.0 | 63.2 | 60.1 | 85.8 | | HumanEval <br> 0-Shot | 57.9 | 59.1 | 54.7 | 47.0 | 28.0 | 34.1 | 60.4| 37.8 | 62.2 | | MBPP <br> 3-Shot | 62.5 | 71.4 | 73.7 | 60.6 | 50.8 | 51.5 | 67.7 | 60.2 | 77.8 | ## Software * [PyTorch](https://github.com/pytorch/pytorch) * [DeepSpeed](https://github.com/microsoft/DeepSpeed) * [Transformers](https://github.com/huggingface/transformers) * [Flash-Attention](https://github.com/HazyResearch/flash-attention) ## Hardware Note that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types: * NVIDIA A100 * NVIDIA A6000 * NVIDIA H100 If you want to run the model on: * NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from_pretrained() with attn_implementation="eager" * Optimized inference on GPU, CPU, and Mobile: use the **ONNX** models [128K](https://aka.ms/phi3-mini-128k-instruct-onnx) ## Cross Platform Support ONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-128K-Instruct ONNX model [here](https://aka.ms/phi3-mini-128k-instruct-onnx). Optimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. Along with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile. Here are some of the optimized configurations we have added: 1. ONNX models for int4 DML: Quantized to int4 via AWQ 2. ONNX model for fp16 CUDA 3. ONNX model for int4 CUDA: Quantized to int4 via RTN 4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN ## License The model is licensed under the [MIT license](https://huggingface.co/microsoft/Phi-3-mini-128k/resolve/main/LICENSE). ## Trademarks This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft’s Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.
{}
RichardErkhov/microsoft_-_Phi-3-mini-128k-instruct-gguf
null
[ "gguf", "region:us" ]
null
2024-05-02T12:00:57+00:00
null
null
{}
raghusesha/wav2vec2-base-finetuned
null
[ "region:us" ]
null
2024-05-02T12:01:45+00:00
reinforcement-learning
stable-baselines3
# **DQN** Agent playing **SpaceInvadersNoFrameskip-v4** This is a trained model of a **DQN** agent playing **SpaceInvadersNoFrameskip-v4** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3) and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo). The RL Zoo is a training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included. ## Usage (with SB3 RL Zoo) RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/> SB3: https://github.com/DLR-RM/stable-baselines3<br/> SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib Install the RL Zoo (with SB3 and SB3-Contrib): ```bash pip install rl_zoo3 ``` ``` # Download model and save it into the logs/ folder python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga miansumairjaved -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do: ``` python -m rl_zoo3.load_from_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -orga miansumairjaved -f logs/ python -m rl_zoo3.enjoy --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ ``` ## Training (with the RL Zoo) ``` python -m rl_zoo3.train --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ # Upload the model and generate video (when possible) python -m rl_zoo3.push_to_hub --algo dqn --env SpaceInvadersNoFrameskip-v4 -f logs/ -orga miansumairjaved ``` ## Hyperparameters ```python OrderedDict([('batch_size', 32), ('buffer_size', 100000), ('env_wrapper', ['stable_baselines3.common.atari_wrappers.AtariWrapper']), ('exploration_final_eps', 0.01), ('exploration_fraction', 0.1), ('frame_stack', 4), ('gradient_steps', 1), ('learning_rate', 100), ('learning_starts', 100), ('n_timesteps', 10000), ('optimize_memory_usage', False), ('policy', 'CnnPolicy'), ('target_update_interval', 1000), ('train_freq', 4), ('normalize', False)]) ``` # Environment Arguments ```python {'render_mode': 'rgb_array'} ```
{"library_name": "stable-baselines3", "tags": ["SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "stable-baselines3"], "model-index": [{"name": "DQN", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "SpaceInvadersNoFrameskip-v4", "type": "SpaceInvadersNoFrameskip-v4"}, "metrics": [{"type": "mean_reward", "value": "268.50 +/- 78.17", "name": "mean_reward", "verified": false}]}]}]}
miansumairjaved/dqn-SpaceInvadersNoFrameskip-v4
null
[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
null
2024-05-02T12:02:06+00:00
text-generation
null
## Exllama v2 Quantizations of Awanllm-Llama-3-8B-Instruct-ORPO-v0.1 Using <a href="https://github.com/turboderp/exllamav2/releases/tag/v0.0.20">turboderp's ExLlamaV2 v0.0.20</a> for quantization. <b>The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)</b> Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions. Original model: https://huggingface.co/AwanLLM/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1 ## Prompt format ``` <|begin_of_text|><|start_header_id|>system<|end_header_id|> {system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|> {prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|> <|eot_id|> ``` ## Available sizes | Branch | Bits | lm_head bits | VRAM (4k) | VRAM (8K) | VRAM (16k) | VRAM (32k) | Description | | ----- | ---- | ------- | ------ | ------ | ------ | ------ | ------------ | | [8_0](https://huggingface.co/bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2/tree/8_0) | 8.0 | 8.0 | 10.1 GB | 10.5 GB | 11.5 GB | 13.6 GB | Maximum quality that ExLlamaV2 can produce, near unquantized performance. | | [6_5](https://huggingface.co/bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2/tree/6_5) | 6.5 | 8.0 | 8.9 GB | 9.3 GB | 10.3 GB | 12.4 GB | Very similar to 8.0, good tradeoff of size vs performance, **recommended**. | | [5_0](https://huggingface.co/bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2/tree/5_0) | 5.0 | 6.0 | 7.7 GB | 8.1 GB | 9.1 GB | 11.2 GB | Slightly lower quality vs 6.5, but usable on 8GB cards. | | [4_25](https://huggingface.co/bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2/tree/4_25) | 4.25 | 6.0 | 7.0 GB | 7.4 GB | 8.4 GB | 10.5 GB | GPTQ equivalent bits per weight, slightly higher quality. | | [3_5](https://huggingface.co/bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2/tree/3_5) | 3.5 | 6.0 | 6.4 GB | 6.8 GB | 7.8 GB | 9.9 GB | Lower quality, only use if you have to. | ## Download instructions With git: ```shell git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2 Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2-6_5 ``` With huggingface hub (credit to TheBloke for instructions): ```shell pip3 install huggingface-hub ``` To download a specific branch, use the `--revision` parameter. For example, to download the 6.5 bpw branch: Linux: ```shell huggingface-cli download bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2 --revision 6_5 --local-dir Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2-6_5 --local-dir-use-symlinks False ``` Windows (which apparently doesn't like _ in folders sometimes?): ```shell huggingface-cli download bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2 --revision 6_5 --local-dir Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2-6.5 --local-dir-use-symlinks False ``` Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski
{"license": "llama3", "quantized_by": "bartowski", "pipeline_tag": "text-generation"}
bartowski/Awanllm-Llama-3-8B-Instruct-ORPO-v0.1-exl2
null
[ "text-generation", "license:llama3", "region:us" ]
null
2024-05-02T12:02:16+00:00
null
transformers
{}
ddemirkol/eplus_qa_v1
null
[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:02:27+00:00
sentence-similarity
sentence-transformers
# SentenceTransformer based on distilbert/distilroberta-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on the [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli), [sentence-compression](https://huggingface.co/datasets/sentence-transformers/sentence-compression), [simple-wiki](https://huggingface.co/datasets/sentence-transformers/simple-wiki), [altlex](https://huggingface.co/datasets/sentence-transformers/altlex), [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates), [coco-captions](https://huggingface.co/datasets/sentence-transformers/coco-captions), [flickr30k-captions](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions), [yahoo-answers](https://huggingface.co/datasets/sentence-transformers/yahoo-answers) and [stack-exchange](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) <!-- at revision fb53ab8802853c8e4fbdbcd0529f21fc6f459b2b --> - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Datasets:** - [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) - [sentence-compression](https://huggingface.co/datasets/sentence-transformers/sentence-compression) - [simple-wiki](https://huggingface.co/datasets/sentence-transformers/simple-wiki) - [altlex](https://huggingface.co/datasets/sentence-transformers/altlex) - [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - [coco-captions](https://huggingface.co/datasets/sentence-transformers/coco-captions) - [flickr30k-captions](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions) - [yahoo-answers](https://huggingface.co/datasets/sentence-transformers/yahoo-answers) - [stack-exchange](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates) - **Language:** en <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: RobertaModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("tomaarsen/distilroberta-base-paraphrases-multi") # Run inference sentences = [ 'guy on a bike', 'Man riding a bike', 'A man cooks on a grill.', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> ## Evaluation ### Metrics #### Semantic Similarity * Dataset: `sts-dev` * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8415 | | **spearman_cosine** | **0.8452** | | pearson_manhattan | 0.8502 | | spearman_manhattan | 0.8517 | | pearson_euclidean | 0.8535 | | spearman_euclidean | 0.8555 | | pearson_dot | 0.6505 | | spearman_dot | 0.649 | | pearson_max | 0.8535 | | spearman_max | 0.8555 | #### Semantic Similarity * Dataset: `sts-test` * Evaluated with [<code>EmbeddingSimilarityEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.EmbeddingSimilarityEvaluator) | Metric | Value | |:--------------------|:-----------| | pearson_cosine | 0.8106 | | **spearman_cosine** | **0.8145** | | pearson_manhattan | 0.8225 | | spearman_manhattan | 0.8131 | | pearson_euclidean | 0.8255 | | spearman_euclidean | 0.8165 | | pearson_dot | 0.5911 | | spearman_dot | 0.5761 | | pearson_max | 0.8255 | | spearman_max | 0.8165 | <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Datasets #### all-nli * Dataset: [all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) at [cc6c526](https://huggingface.co/datasets/sentence-transformers/all-nli/tree/cc6c526380e29912b5c6fa03682da4daf773c013) * Size: 557,850 training samples * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:---------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 10.38 tokens</li><li>max: 45 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 12.8 tokens</li><li>max: 39 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.4 tokens</li><li>max: 50 tokens</li></ul> | * Samples: | anchor | positive | negative | |:---------------------------------------------------------------------------|:-------------------------------------------------|:-----------------------------------------------------------| | <code>A person on a horse jumps over a broken down airplane.</code> | <code>A person is outdoors, on a horse.</code> | <code>A person is at a diner, ordering an omelette.</code> | | <code>Children smiling and waving at camera</code> | <code>There are children present</code> | <code>The kids are frowning</code> | | <code>A boy is jumping on skateboard in the middle of a red bridge.</code> | <code>The boy does a skateboarding trick.</code> | <code>The boy skates down the sidewalk.</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### sentence-compression * Dataset: [sentence-compression](https://huggingface.co/datasets/sentence-transformers/sentence-compression) at [605bc91](https://huggingface.co/datasets/sentence-transformers/sentence-compression/tree/605bc91d95631895ba25b6eda51a3cb596976c90) * Size: 180,000 training samples * Columns: <code>text</code> and <code>simplified</code> * Approximate statistics based on the first 1000 samples: | | text | simplified | |:--------|:------------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 10 tokens</li><li>mean: 33.13 tokens</li><li>max: 126 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 11.13 tokens</li><li>max: 29 tokens</li></ul> | * Samples: | text | simplified | |:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:-------------------------------------------------------| | <code>The USHL completed an expansion draft on Monday as 10 players who were on the rosters of USHL teams during the 2009-10 season were selected by the League's two newest entries, the Muskegon Lumberjacks and Dubuque Fighting Saints.</code> | <code>USHL completes expansion draft</code> | | <code>Major League Baseball Commissioner Bud Selig will be speaking at St. Norbert College next month.</code> | <code>Bud Selig to speak at St. Norbert College</code> | | <code>It's fresh cherry time in Michigan and the best time to enjoy this delicious and nutritious fruit.</code> | <code>It's cherry time</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### simple-wiki * Dataset: [simple-wiki](https://huggingface.co/datasets/sentence-transformers/simple-wiki) at [60fd9b4](https://huggingface.co/datasets/sentence-transformers/simple-wiki/tree/60fd9b4680642ace0e2604cc2de44d376df419a7) * Size: 102,225 training samples * Columns: <code>text</code> and <code>simplified</code> * Approximate statistics based on the first 1000 samples: | | text | simplified | |:--------|:-----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 9 tokens</li><li>mean: 35.19 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 8 tokens</li><li>mean: 29.1 tokens</li><li>max: 128 tokens</li></ul> | * Samples: | text | simplified | |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>The greatest example has been in his present job ( then , Minister for Foreign Affairs ) , where he has perforce concentrated on Anglo-Irish relations and , in particular the North ( i.e. , Northern Ireland ) .</code> | <code>The greatest example has been in his present job ( then , Minister for Foreign Affairs ) , where he has perforce concentrated on Anglo-Irish relations and , in particular Northern Ireland ( .</code> | | <code>His reputation rose further when opposition leaders under parliamentary privilege alleged that Taoiseach Charles Haughey , who in January 1982 had been Leader of the Opposition , had not merely rung the President 's Office but threatened to end the career of the army officer who took the call and who , on Hillery 's explicit instructions , had refused to put through the call to the President .</code> | <code>President Hillery refused to speak to any opposition party politicians , but when Charles Haughey , who was Leader of the Opposition , had rang the President 's Office he threatened to end the career of the army officer answered and refused on Hillery 's explicit orders to put the call through to the President .</code> | | <code>He considered returning to medicine , perhaps moving with his wife , Maeve ( also a doctor ) to Africa .</code> | <code>He thought about returning to medicine , perhaps moving with his wife , Maeve ( also a doctor ) to Africa .</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### altlex * Dataset: [altlex](https://huggingface.co/datasets/sentence-transformers/altlex) at [97eb209](https://huggingface.co/datasets/sentence-transformers/altlex/tree/97eb20963455c361d5a81c107c3596cff9e0cd82) * Size: 112,696 training samples * Columns: <code>text</code> and <code>simplified</code> * Approximate statistics based on the first 1000 samples: | | text | simplified | |:--------|:----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 9 tokens</li><li>mean: 31.8 tokens</li><li>max: 121 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 26.49 tokens</li><li>max: 114 tokens</li></ul> | * Samples: | text | simplified | |:-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>A set of 31 guns , cast 1729-1749 by the first master founder at the Royal Foundry , later the Royal Arsenal , Woolwich , were used to fire salutes until 1907 , often for Queen Victoria , who was a frequent visitor .</code> | <code>A set of 31 guns , cast 1729-1749 by the first master founder at the Royal Foundry , later the Royal Arsenal , Woolwich , were used to fire salutes until 1907 , often for Queen Victoria who was a frequent visitor .</code> | | <code>In 1929 , the building became vacant , and was given to Prince Edward , Prince of Wales , by his father , King George V . This became the Prince 's chief residence and was used extensively by him for entertaining and as a country retreat .</code> | <code>In 1929 , the building became vacant , and was given to Prince Edward , the Prince of Wales by his father , King George V . This became the Prince 's chief residence , and was used extensively by the Prince for entertaining and as a country retreat .</code> | | <code>Additions included an octagon room in the north-east side , in which the King regularly had dinner .</code> | <code>Additions included an octagon room in the North-East side , where the King regularly had dinner .</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### quora-duplicates * Dataset: [quora-duplicates](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 101,762 training samples * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 13.72 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.5 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.56 tokens</li><li>max: 62 tokens</li></ul> | * Samples: | anchor | positive | negative | |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------| | <code>Why in India do we not have one on one political debate as in USA?</code> | <code>Why cant we have a public debate between politicians in India like the one in US?</code> | <code>Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?</code> | | <code>What is OnePlus One?</code> | <code>How is oneplus one?</code> | <code>Why is OnePlus One so good?</code> | | <code>Does our mind control our emotions?</code> | <code>How do smart and successful people control their emotions?</code> | <code>How can I control my positive emotions for the people whom I love but they don't care about me?</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### coco-captions * Dataset: [coco-captions](https://huggingface.co/datasets/sentence-transformers/coco-captions) at [bd26018](https://huggingface.co/datasets/sentence-transformers/coco-captions/tree/bd2601822b9af9a41656d678ffbd5c80d81e276a) * Size: 414,010 training samples * Columns: <code>caption1</code> and <code>caption2</code> * Approximate statistics based on the first 1000 samples: | | caption1 | caption2 | |:--------|:-----------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 10 tokens</li><li>mean: 13.65 tokens</li><li>max: 25 tokens</li></ul> | <ul><li>min: 10 tokens</li><li>mean: 13.65 tokens</li><li>max: 25 tokens</li></ul> | * Samples: | caption1 | caption2 | |:-------------------------------------------------------------------------------------------|:-------------------------------------------------------------------------------------------| | <code>A clock that blends in with the wall hangs in a bathroom. </code> | <code>A very clean and well decorated empty bathroom</code> | | <code>A very clean and well decorated empty bathroom</code> | <code>A bathroom with a border of butterflies and blue paint on the walls above it.</code> | | <code>A bathroom with a border of butterflies and blue paint on the walls above it.</code> | <code>An angled view of a beautifully decorated bathroom.</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### flickr30k-captions * Dataset: [flickr30k-captions](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions) at [0ef0ce3](https://huggingface.co/datasets/sentence-transformers/flickr30k-captions/tree/0ef0ce31492fd8dc161ed483a40d3c4894f9a8c1) * Size: 158,881 training samples * Columns: <code>caption1</code> and <code>caption2</code> * Approximate statistics based on the first 1000 samples: | | caption1 | caption2 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 16.22 tokens</li><li>max: 60 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 16.22 tokens</li><li>max: 60 tokens</li></ul> | * Samples: | caption1 | caption2 | |:------------------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------| | <code>Two men in green shirts are standing in a yard.</code> | <code>Two young, White males are outside near many bushes.</code> | | <code>Two young, White males are outside near many bushes.</code> | <code>Two young guys with shaggy hair look at their hands while hanging out in the yard.</code> | | <code>Two young guys with shaggy hair look at their hands while hanging out in the yard.</code> | <code>A man in a blue shirt standing in a garden.</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### yahoo-answers * Dataset: [yahoo-answers](https://huggingface.co/datasets/sentence-transformers/yahoo-answers) at [93b3605](https://huggingface.co/datasets/sentence-transformers/yahoo-answers/tree/93b3605c508cf93e3666c9d3e34640b5fe62b507) * Size: 599,417 training samples * Columns: <code>question</code> and <code>answer</code> * Approximate statistics based on the first 1000 samples: | | question | answer | |:--------|:------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 12 tokens</li><li>mean: 52.48 tokens</li><li>max: 128 tokens</li></ul> | <ul><li>min: 13 tokens</li><li>mean: 83.5 tokens</li><li>max: 128 tokens</li></ul> | * Samples: | question | answer | |:-----------------------------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>why doesn't an optical mouse work on a glass table? or even on some surfaces?</code> | <code>why doesn't an optical mouse work on a glass table? Optical mice use an LED and a camera to rapidly capture images of the surface beneath the mouse. The infomation from the camera is analyzed by a DSP (Digital Signal Processor) and used to detect imperfections in the underlying surface and determine motion. Some materials, such as glass, mirrors or other very shiny, uniform surfaces interfere with the ability of the DSP to accurately analyze the surface beneath the mouse. \nSince glass is transparent and very uniform, the mouse is unable to pick up enough imperfections in the underlying surface to determine motion. Mirrored surfaces are also a problem, since they constantly reflect back the same image, causing the DSP not to recognize motion properly. When the system is unable to see surface changes associated with movement, the mouse will not work properly.</code> | | <code>What is the best off-road motorcycle trail ? long-distance trail throughout CA</code> | <code>What is the best off-road motorcycle trail ? i hear that the mojave road is amazing!<br />\nsearch for it online.</code> | | <code>What is Trans Fat? How to reduce that? I heard that tras fat is bad for the body. Why is that? Where can we find it in our daily food?</code> | <code>What is Trans Fat? How to reduce that? Trans fats occur in manufactured foods during the process of partial hydrogenation, when hydrogen gas is bubbled through vegetable oil to increase shelf life and stabilize the original polyunsatured oil. The resulting fat is similar to saturated fat, which raises "bad" LDL cholesterol and can lead to clogged arteries and heart disease. \nUntil very recently, food labels were not required to list trans fats, and this health risk remained hidden to consumers. In early July, FDA regulations changed, and food labels will soon begin identifying trans fat content in processed foods.</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### stack-exchange * Dataset: [stack-exchange](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates) at [1c9657a](https://huggingface.co/datasets/sentence-transformers/stackexchange-duplicates/tree/1c9657aec12d9e101667bb9593efcc623c4a68ff) * Size: 304,525 training samples * Columns: <code>title1</code> and <code>title2</code> * Approximate statistics based on the first 1000 samples: | | title1 | title2 | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | | details | <ul><li>min: 5 tokens</li><li>mean: 15.04 tokens</li><li>max: 63 tokens</li></ul> | <ul><li>min: 5 tokens</li><li>mean: 15.91 tokens</li><li>max: 80 tokens</li></ul> | * Samples: | title1 | title2 | |:----------------------------------------------------------------------------------|:-------------------------------------------------------------| | <code>what is the advantage of using the GPU rendering options in Android?</code> | <code>Can anyone explain all these Developer Options?</code> | | <code>Blank video when converting uncompressed AVI files with ffmpeg</code> | <code>FFmpeg lossy compression problems</code> | | <code>URL Rewriting of a query string in php</code> | <code>How to create friendly URL in php?</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: round_robin #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: False - `per_device_train_batch_size`: 128 - `per_device_eval_batch_size`: 128 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: None - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: round_robin </details> ### Training Logs | Epoch | Step | Training Loss | sts-dev_spearman_cosine | sts-test_spearman_cosine | |:------:|:----:|:-------------:|:-----------------------:|:------------------------:| | 0.0140 | 100 | 3.739 | - | - | | 0.0279 | 200 | 1.1317 | - | - | | 0.0419 | 300 | 0.9645 | - | - | | 0.0558 | 400 | 0.9053 | - | - | | 0.0698 | 500 | 0.8889 | - | - | | 0.0838 | 600 | 0.8741 | - | - | | 0.0977 | 700 | 0.8329 | - | - | | 0.1117 | 800 | 0.8331 | - | - | | 0.1256 | 900 | 0.8241 | - | - | | 0.1396 | 1000 | 0.7829 | 0.8460 | - | | 0.1535 | 1100 | 0.7871 | - | - | | 0.1675 | 1200 | 0.7521 | - | - | | 0.1815 | 1300 | 0.7905 | - | - | | 0.1954 | 1400 | 0.7531 | - | - | | 0.2094 | 1500 | 0.7677 | - | - | | 0.2233 | 1600 | 0.7745 | - | - | | 0.2373 | 1700 | 0.7651 | - | - | | 0.2513 | 1800 | 0.7712 | - | - | | 0.2652 | 1900 | 0.7476 | - | - | | 0.2792 | 2000 | 0.7814 | 0.8370 | - | | 0.2931 | 2100 | 0.7536 | - | - | | 0.3071 | 2200 | 0.7689 | - | - | | 0.3210 | 2300 | 0.7656 | - | - | | 0.3350 | 2400 | 0.7672 | - | - | | 0.3490 | 2500 | 0.6921 | - | - | | 0.3629 | 2600 | 0.6778 | - | - | | 0.3769 | 2700 | 0.6844 | - | - | | 0.3908 | 2800 | 0.6907 | - | - | | 0.4048 | 2900 | 0.6881 | - | - | | 0.4188 | 3000 | 0.6815 | 0.8372 | - | | 0.4327 | 3100 | 0.6869 | - | - | | 0.4467 | 3200 | 0.698 | - | - | | 0.4606 | 3300 | 0.6868 | - | - | | 0.4746 | 3400 | 0.7174 | - | - | | 0.4886 | 3500 | 0.6714 | - | - | | 0.5025 | 3600 | 0.6698 | - | - | | 0.5165 | 3700 | 0.6838 | - | - | | 0.5304 | 3800 | 0.6927 | - | - | | 0.5444 | 3900 | 0.6628 | - | - | | 0.5583 | 4000 | 0.6647 | 0.8367 | - | | 0.5723 | 4100 | 0.6766 | - | - | | 0.5863 | 4200 | 0.6987 | - | - | | 0.6002 | 4300 | 0.6895 | - | - | | 0.6142 | 4400 | 0.6571 | - | - | | 0.6281 | 4500 | 0.66 | - | - | | 0.6421 | 4600 | 0.6747 | - | - | | 0.6561 | 4700 | 0.6495 | - | - | | 0.6700 | 4800 | 0.6746 | - | - | | 0.6840 | 4900 | 0.6575 | - | - | | 0.6979 | 5000 | 0.6712 | 0.8454 | - | | 0.7119 | 5100 | 0.6627 | - | - | | 0.7259 | 5200 | 0.6538 | - | - | | 0.7398 | 5300 | 0.6659 | - | - | | 0.7538 | 5400 | 0.6551 | - | - | | 0.7677 | 5500 | 0.6548 | - | - | | 0.7817 | 5600 | 0.673 | - | - | | 0.7956 | 5700 | 0.6805 | - | - | | 0.8096 | 5800 | 0.6537 | - | - | | 0.8236 | 5900 | 0.6826 | - | - | | 0.8375 | 6000 | 0.7182 | 0.8370 | - | | 0.8515 | 6100 | 0.7391 | - | - | | 0.8654 | 6200 | 0.7006 | - | - | | 0.8794 | 6300 | 0.6774 | - | - | | 0.8934 | 6400 | 0.7076 | - | - | | 0.9073 | 6500 | 0.6893 | - | - | | 0.9213 | 6600 | 0.678 | - | - | | 0.9352 | 6700 | 0.6703 | - | - | | 0.9492 | 6800 | 0.675 | - | - | | 0.9631 | 6900 | 0.6842 | - | - | | 0.9771 | 7000 | 0.6909 | 0.8452 | - | | 0.9911 | 7100 | 0.681 | - | - | | 1.0 | 7164 | - | - | 0.8145 | ### Environmental Impact Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon). - **Energy Consumed**: 0.202 kWh - **Carbon Emitted**: 0.079 kg of CO2 - **Hours Used**: 0.601 hours ### Training Hardware - **On Cloud**: No - **GPU Model**: 1 x NVIDIA GeForce RTX 3090 - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K - **RAM Size**: 31.78 GB ### Framework Versions - Python: 3.11.6 - Sentence Transformers: 3.0.0.dev0 - Transformers: 4.41.0.dev0 - PyTorch: 2.3.0+cu121 - Accelerate: 0.26.1 - Datasets: 2.18.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
{"language": ["en"], "library_name": "sentence-transformers", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "loss:MultipleNegativesRankingLoss"], "metrics": ["pearson_cosine", "spearman_cosine", "pearson_manhattan", "spearman_manhattan", "pearson_euclidean", "spearman_euclidean", "pearson_dot", "spearman_dot", "pearson_max", "spearman_max"], "base_model": "distilbert/distilroberta-base", "widget": [{"source_sentence": "She was buried in Breda .", "sentences": ["Anna was buried in Breda .", "Jackson Township is a township found in Will County , Illinois .", "Saint-Genis-Pouilly is a commune in the Ain department in eastern France ."]}, {"source_sentence": "Have you never been mellow? No, I'm just a grumpy sumbitch", "sentences": ["How many of you retards have ever had wooopi.? Not me... I'm saving myself...", "Has anyone heard of the marketing company Vector? If so what is the company about and is it a good place to work?", "I want to make hearts on the computer too?!? How do i do it!!!!i tried doing alt 3 but i couldn't see my heart!!!Is that normal!!"]}, {"source_sentence": "Are there UFOs?", "sentences": ["Who has seen aliens or UFOs?", "How do people become famous?", "How do I learn math?"]}, {"source_sentence": "The dog runs.", "sentences": ["A dog running.", "A man eats a sandwich.", "The people are sitting."]}, {"source_sentence": "guy on a bike", "sentences": ["Man riding a bike", "A man cooks on a grill.", "The woman is indoors."]}], "pipeline_tag": "sentence-similarity", "co2_eq_emissions": {"emissions": 78.69029495412121, "energy_consumed": 0.2024437614268031, "source": "codecarbon", "training_type": "fine-tuning", "on_cloud": false, "cpu_model": "13th Gen Intel(R) Core(TM) i7-13700K", "ram_total_size": 31.777088165283203, "hours_used": 0.601, "hardware_used": "1 x NVIDIA GeForce RTX 3090"}, "model-index": [{"name": "SentenceTransformer based on distilbert/distilroberta-base", "results": [{"task": {"type": "semantic-similarity", "name": "Semantic Similarity"}, "dataset": {"name": "sts dev", "type": "sts-dev"}, "metrics": [{"type": "pearson_cosine", "value": 0.8415424335219892, "name": "Pearson Cosine"}, {"type": "spearman_cosine", "value": 0.845236449663091, "name": "Spearman Cosine"}, {"type": "pearson_manhattan", "value": 0.8502275215819475, "name": "Pearson Manhattan"}, {"type": "spearman_manhattan", "value": 0.851659983857617, "name": "Spearman Manhattan"}, {"type": "pearson_euclidean", "value": 0.8534543309306831, "name": "Pearson Euclidean"}, {"type": "spearman_euclidean", "value": 0.8555429338051269, "name": "Spearman Euclidean"}, {"type": "pearson_dot", "value": 0.6505488321872611, "name": "Pearson Dot"}, {"type": "spearman_dot", "value": 0.6489555708500816, "name": "Spearman Dot"}, {"type": "pearson_max", "value": 0.8534543309306831, "name": "Pearson Max"}, {"type": "spearman_max", "value": 0.8555429338051269, "name": "Spearman Max"}]}, {"task": {"type": "semantic-similarity", "name": "Semantic Similarity"}, "dataset": {"name": "sts test", "type": "sts-test"}, "metrics": [{"type": "pearson_cosine", "value": 0.8105817065758533, "name": "Pearson Cosine"}, {"type": "spearman_cosine", "value": 0.8144723448926713, "name": "Spearman Cosine"}, {"type": "pearson_manhattan", "value": 0.8225264118038157, "name": "Pearson Manhattan"}, {"type": "spearman_manhattan", "value": 0.8131121443026537, "name": "Spearman Manhattan"}, {"type": "pearson_euclidean", "value": 0.825469313508584, "name": "Pearson Euclidean"}, {"type": "spearman_euclidean", "value": 0.8164637881262432, "name": "Spearman Euclidean"}, {"type": "pearson_dot", "value": 0.5910799174044387, "name": "Pearson Dot"}, {"type": "spearman_dot", "value": 0.5760606722387962, "name": "Spearman Dot"}, {"type": "pearson_max", "value": 0.825469313508584, "name": "Pearson Max"}, {"type": "spearman_max", "value": 0.8164637881262432, "name": "Spearman Max"}]}]}]}
tomaarsen/distilroberta-base-paraphrases-multi
null
[ "sentence-transformers", "safetensors", "roberta", "sentence-similarity", "feature-extraction", "loss:MultipleNegativesRankingLoss", "en", "arxiv:1908.10084", "arxiv:1705.00652", "base_model:distilbert/distilroberta-base", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:02:28+00:00
text-generation
transformers
# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details "This model has only been trained and does not reply in a clear or clean way. A formatting script is stored privately, allowing the model to act as an accurate chatbot specialized in the public sector." ### 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": []}
RayBoustany/Siren1200-Chatbot-Phi2-Merged
null
[ "transformers", "safetensors", "phi", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:03:34+00:00
text-generation
transformers
{}
harshh1307/my_awesome_eli5_clm-model
null
[ "transformers", "pytorch", "tensorboard", "gpt2", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:03:39+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": []}
morioxd/happymaker3_8b
null
[ "transformers", "safetensors", "llama", "text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:04:13+00:00
null
null
{"license": "openrail"}
mahdi786/videotest
null
[ "license:openrail", "region:us" ]
null
2024-05-02T12:04:24+00:00
null
null
{}
DioBot2000/distilbert-base-uncased-finetuned-ner
null
[ "region:us" ]
null
2024-05-02T12:04:31+00:00
text2text-generation
transformers
{}
lingvenvist/mtwsd_base_4
null
[ "transformers", "safetensors", "mt5", "text2text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:05:19+00:00
null
null
{"license": "mit"}
lakshyaM/llama2_hf_alpaca_gpt4
null
[ "license:mit", "region:us" ]
null
2024-05-02T12:07:37+00:00
null
transformers
## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hfhfix --> <!-- ### vocab_type: --> static quants of https://huggingface.co/mesolitica/malaysian-llama-3-8b-262k <!-- 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/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/malaysian-llama-3-8b-262k-GGUF/resolve/main/malaysian-llama-3-8b-262k.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
{"language": ["en"], "library_name": "transformers", "tags": [], "base_model": "mesolitica/malaysian-llama-3-8b-262k", "quantized_by": "mradermacher"}
mradermacher/malaysian-llama-3-8b-262k-GGUF
null
[ "transformers", "gguf", "en", "base_model:mesolitica/malaysian-llama-3-8b-262k", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:09:12+00:00
null
null
{}
kirubai0/2miner4
null
[ "region:us" ]
null
2024-05-02T12:09:39+00:00
null
transformers
## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hfhfix --> <!-- ### vocab_type: --> weighted/imatrix quants of https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-GGUF ## 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/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF/resolve/main/Meta-Llama-3-8B-Instruct.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | 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": "other", "library_name": "transformers", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "base_model": "NousResearch/Meta-Llama-3-8B-Instruct", "extra_gated_button_content": "Submit", "extra_gated_fields": {"Affiliation": "text", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox", "Country": "country", "Date of birth": "date_picker", "First Name": "text", "Last Name": "text", "geo": "ip_location"}, "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "license_link": "LICENSE", "license_name": "llama3", "quantized_by": "mradermacher"}
mradermacher/Meta-Llama-3-8B-Instruct-i1-GGUF
null
[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "en", "base_model:NousResearch/Meta-Llama-3-8B-Instruct", "license:other", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:10:47+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) Starling-LM-7B-alpha - bnb 8bits - Model creator: https://huggingface.co/berkeley-nest/ - Original model: https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/ Original model description: --- license: apache-2.0 datasets: - berkeley-nest/Nectar language: - en library_name: transformers tags: - reward model - RLHF - RLAIF --- # Starling-LM-7B-alpha <!-- Provide a quick summary of what the model is/does. --> - **Developed by:** Banghua Zhu * , Evan Frick * , Tianhao Wu * , Hanlin Zhu and Jiantao Jiao. - **Model type:** Language Model finetuned with RLHF / RLAIF - **License:** Apache-2.0 license under the condition that the model is not used to compete with OpenAI - **Finetuned from model:** [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5) (based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)) We introduce Starling-7B, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). The model harnesses the power of our new GPT-4 labeled ranking dataset, [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), and our new reward training and policy tuning pipeline. Starling-7B-alpha scores 8.09 in MT Bench with GPT-4 as a judge, outperforming every model to date on MT-Bench except for OpenAI's GPT-4 and GPT-4 Turbo. We release the ranking dataset [Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), the reward model [Starling-RM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-RM-7B-alpha) and the language model [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) on HuggingFace, and an online demo in LMSYS [Chatbot Arena](https://chat.lmsys.org). Stay tuned for our forthcoming code and paper, which will provide more details on the whole process. Starling-LM-7B-alpha is a language model trained from [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5) with reward model [berkeley-nest/Starling-RM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-RM-7B-alpha) and policy optimization method [advantage-induced policy alignment (APA)](https://arxiv.org/abs/2306.02231). The evaluation results are listed below. | Model | Tuning Method | MT Bench | AlpacaEval | MMLU | |-----------------------|------------------|----------|------------|------| | GPT-4-Turbo | ? | 9.32 | 97.70 | | | GPT-4 | SFT + PPO | 8.99 | 95.28 | 86.4 | | **Starling-7B** | C-RLFT + APA | 8.09 | 91.99 | 63.9 | | Claude-2 | ? | 8.06 | 91.36 | 78.5 | | GPT-3.5-Turbo | ? | 7.94 | 89.37 | 70 | | Claude-1 | ? | 7.9 | 88.39 | 77 | | Tulu-2-dpo-70b | SFT + DPO | 7.89 | 95.1 | | | Openchat-3.5 | C-RLFT | 7.81 | 88.51 | 64.3 | | Zephyr-7B-beta | SFT + DPO | 7.34 | 90.60 | 61.4 | | Llama-2-70b-chat-hf | SFT + PPO | 6.86 | 92.66 | 63 | | Neural-chat-7b-v3-1 | SFT + DPO | 6.84 | 84.53 | 62.4 | | Tulu-2-dpo-7b | SFT + DPO | 6.29 | 85.1 | | For more detailed discussions, please check out our [blog post](https://starling.cs.berkeley.edu), and stay tuned for our upcoming code and paper! <!-- Provide the basic links for the model. --> - **Blog:** https://starling.cs.berkeley.edu/ - **Paper:** Coming soon! - **Code:** Coming soon! ## 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. --> **Important: Please use the exact chat template provided below for the model. Otherwise there will be a degrade in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** Our model follows the exact chat template and usage as [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5). Please refer to their model card for more details. In addition, our model is hosted on LMSYS [Chatbot Arena](https://chat.lmsys.org) for free test. The conversation template is the same as Openchat 3.5: ``` import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat_3.5") # Single-turn tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Multi-turn tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Coding Mode tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747] ``` ## Code Examples ```python import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("berkeley-nest/Starling-LM-7B-alpha") model = transformers.AutoModelForCausalLM.from_pretrained("berkeley-nest/Starling-LM-7B-alpha") def generate_response(prompt): input_ids = tokenizer(prompt, return_tensors="pt").input_ids outputs = model.generate( input_ids, max_length=256, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) response_ids = outputs[0] response_text = tokenizer.decode(response_ids, skip_special_tokens=True) return response_text # Single-turn conversation prompt = "Hello, how are you?" single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:" response_text = generate_response(single_turn_prompt) print("Response:", response_text) ## Multi-turn conversation prompt = "Hello" follow_up_question = "How are you today?" response = "" multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:" response_text = generate_response(multi_turn_prompt) print("Multi-turn conversation response:", response_text) ### Coding conversation prompt = "Implement quicksort using C++" coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:" response = generate_response(coding_prompt) print("Coding conversation response:", response) ``` ## License The dataset, model and online demo is a research preview intended for non-commercial use only, subject to the data distillation [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation. ## Acknowledgment We would like to thank Wei-Lin Chiang from Berkeley for detailed feedback of the blog and the projects. We would like to thank the [LMSYS Organization](https://lmsys.org/) for their support of [lmsys-chat-1M](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) dataset, evaluation and online demo. We would like to thank the open source community for their efforts in providing the datasets and base models we used to develope the project, including but not limited to Anthropic, Llama, Mistral, Hugging Face H4, LMSYS, OpenChat, OpenBMB, Flan and ShareGPT. ## Citation ``` @misc{starling2023, title = {Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF}, url = {}, author = {Zhu, Banghua and Frick, Evan and Wu, Tianhao and Zhu, Hanlin and Jiao, Jiantao}, month = {November}, year = {2023} } ```
{}
RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-8bits
null
[ "transformers", "safetensors", "mistral", "text-generation", "conversational", "arxiv:2306.02231", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]
null
2024-05-02T12:11:08+00:00
null
null
{}
Ukado/S-C
null
[ "region:us" ]
null
2024-05-02T12:12:00+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) gemma-7b-it - bnb 8bits - Model creator: https://huggingface.co/google/ - Original model: https://huggingface.co/google/gemma-7b-it/ Original model description: --- library_name: transformers tags: [] widget: - messages: - role: user content: How does the brain work? inference: parameters: max_new_tokens: 200 extra_gated_heading: Access Gemma on Hugging Face extra_gated_prompt: >- To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately. extra_gated_button_content: Acknowledge license license: gemma --- # Gemma Model Card **Model Page**: [Gemma](https://ai.google.dev/gemma/docs) This model card corresponds to the 7B instruct version of the Gemma model. You can also visit the model card of the [2B base model](https://huggingface.co/google/gemma-2b), [7B base model](https://huggingface.co/google/gemma-7b), and [2B instruct model](https://huggingface.co/google/gemma-2b-it). **Resources and Technical Documentation**: * [Responsible Generative AI Toolkit](https://ai.google.dev/responsible) * [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma) * [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-it-gg-hf) **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent) **Authors**: Google ## Model Information Summary description and brief definition of inputs and outputs. ### Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. ### Usage Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase. #### Fine-tuning the model You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-7b-it`. In that repository, we provide: * A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA * A script to perform SFT using FSDP on TPU devices * A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset #### Running the model on a CPU As explained below, we recommend `torch.bfloat16` as the default dtype. You can use [a different precision](#precisions) if necessary. ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", torch_dtype=torch.bfloat16 ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` #### Running the model on a single / multi GPU ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM import torch tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", device_map="auto", torch_dtype=torch.bfloat16 ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` <a name="precisions"></a> #### Running the model on a GPU using different precisions The native weights of this model were exported in `bfloat16` precision. You can use `float16`, which may be faster on certain hardware, indicating the `torch_dtype` when loading the model. For convenience, the `float16` revision of the repo contains a copy of the weights already converted to that precision. You can also use `float32` if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to `float32`). See examples below. * _Using `torch.float16`_ ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM import torch tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", device_map="auto", torch_dtype=torch.float16, revision="float16", ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` * _Using `torch.bfloat16`_ ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it", device_map="auto", torch_dtype=torch.bfloat16) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` * _Upcasting to `torch.float32`_ ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", device_map="auto" ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` #### Quantized Versions through `bitsandbytes` * _Using 8-bit precision (int8)_ ```python # pip install bitsandbytes accelerate from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig quantization_config = BitsAndBytesConfig(load_in_8bit=True) tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it", quantization_config=quantization_config) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` * _Using 4-bit precision_ ```python # pip install bitsandbytes accelerate from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig quantization_config = BitsAndBytesConfig(load_in_4bit=True) tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it", quantization_config=quantization_config) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` #### Other optimizations * _Flash Attention 2_ First make sure to install `flash-attn` in your environment `pip install flash-attn` ```diff model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, + attn_implementation="flash_attention_2" ).to(0) ``` ### Chat Template The instruction-tuned models use a chat template that must be adhered to for conversational use. The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet. Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction: ```py from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model_id = "google/gemma-7b-it" dtype = torch.bfloat16 tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda", torch_dtype=dtype, ) chat = [ { "role": "user", "content": "Write a hello world program" }, ] prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) ``` At this point, the prompt contains the following text: ``` <bos><start_of_turn>user Write a hello world program<end_of_turn> <start_of_turn>model ``` As you can see, each turn is preceded by a `<start_of_turn>` delimiter and then the role of the entity (either `user`, for content supplied by the user, or `model` for LLM responses). Turns finish with the `<end_of_turn>` token. You can follow this format to build the prompt manually, if you need to do it without the tokenizer's chat template. After the prompt is ready, generation can be performed like this: ```py inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150) print(tokenizer.decode(outputs[0])) ``` ### Inputs and outputs * **Input:** Text string, such as a question, a prompt, or a document to be summarized. * **Output:** Generated English-language text in response to the input, such as an answer to a question, or a summary of a document. ## Model Data Data used for model training and how the data was processed. ### Training Dataset These models were trained on a dataset of text data that includes a wide variety of sources, totaling 6 trillion tokens. Here are the key components: * Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. Primarily English-language content. * Code: Exposing the model to code helps it to learn the syntax and patterns of programming languages, which improves its ability to generate code or understand code-related questions. * Mathematics: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries. The combination of these diverse data sources is crucial for training a powerful language model that can handle a wide variety of different tasks and text formats. ### Data Preprocessing Here are the key data cleaning and filtering methods applied to the training data: * CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was applied at multiple stages in the data preparation process to ensure the exclusion of harmful and illegal content * Sensitive Data Filtering: As part of making Gemma pre-trained models safe and reliable, automated techniques were used to filter out certain personal information and other sensitive data from training sets. * Additional methods: Filtering based on content quality and safely in line with [our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11). ## Implementation Information Details about the model internals. ### Hardware Gemma was trained using the latest generation of [Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e). Training large language models requires significant computational power. TPUs, designed specifically for matrix operations common in machine learning, offer several advantages in this domain: * Performance: TPUs are specifically designed to handle the massive computations involved in training LLMs. They can speed up training considerably compared to CPUs. * Memory: TPUs often come with large amounts of high-bandwidth memory, allowing for the handling of large models and batch sizes during training. This can lead to better model quality. * Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for handling the growing complexity of large foundation models. You can distribute training across multiple TPU devices for faster and more efficient processing. * Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective solution for training large models compared to CPU-based infrastructure, especially when considering the time and resources saved due to faster training. * These advantages are aligned with [Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/). ### Software Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture). JAX allows researchers to take advantage of the latest generation of hardware, including TPUs, for faster and more efficient training of large models. ML Pathways is Google's latest effort to build artificially intelligent systems capable of generalizing across multiple tasks. This is specially suitable for [foundation models](https://ai.google/discover/foundation-models/), including large language models like these ones. Together, JAX and ML Pathways are used as described in the [paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single controller' programming model of Jax and Pathways allows a single Python process to orchestrate the entire training run, dramatically simplifying the development workflow." ## Evaluation Model evaluation metrics and results. ### Benchmark Results These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation: | Benchmark | Metric | 2B Params | 7B Params | | ------------------------------ | ------------- | ----------- | --------- | | [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 | | [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 | | [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 | | [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 49.7 | 51.8 | | [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 | | [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 | | [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 | | [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 | | [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 | | [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 | | [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 | | [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | 12.5 | 23 | | [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 | | [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 | | [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 | | [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 | | [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 | | [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 | | ------------------------------ | ------------- | ----------- | --------- | | **Average** | | **45.0** | **56.9** | ## Ethics and Safety Ethics and safety evaluation approach and results. ### Evaluation Approach Our evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including: * Text-to-Text Content Safety: Human evaluation on prompts covering safety policies including child sexual abuse and exploitation, harassment, violence and gore, and hate speech. * Text-to-Text Representational Harms: Benchmark against relevant academic datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2). * Memorization: Automated evaluation of memorization of training data, including the risk of personally identifiable information exposure. * Large-scale harm: Tests for "dangerous capabilities," such as chemical, biological, radiological, and nuclear (CBRN) risks. ### Evaluation Results The results of ethics and safety evaluations are within acceptable thresholds for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child safety, content safety, representational harms, memorization, large-scale harms. On top of robust internal evaluations, the results of well known safety benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA are shown here. | Benchmark | Metric | 2B Params | 7B Params | | ------------------------------ | ------------- | ----------- | --------- | | [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 | | [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 | | [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 | | [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 | | [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 | | [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 | | [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 | | [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 | | [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 | | [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 | | ------------------------------ | ------------- | ----------- | --------- | ## Usage and Limitations These models have certain limitations that users should be aware of. ### Intended Usage Open Large Language Models (LLMs) have a wide range of applications across various industries and domains. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development. * Content Creation and Communication * Text Generation: These models can be used to generate creative text formats such as poems, scripts, code, marketing copy, and email drafts. * Chatbots and Conversational AI: Power conversational interfaces for customer service, virtual assistants, or interactive applications. * Text Summarization: Generate concise summaries of a text corpus, research papers, or reports. * Research and Education * Natural Language Processing (NLP) Research: These models can serve as a foundation for researchers to experiment with NLP techniques, develop algorithms, and contribute to the advancement of the field. * Language Learning Tools: Support interactive language learning experiences, aiding in grammar correction or providing writing practice. * Knowledge Exploration: Assist researchers in exploring large bodies of text by generating summaries or answering questions about specific topics. ### Limitations * Training Data * The quality and diversity of the training data significantly influence the model's capabilities. Biases or gaps in the training data can lead to limitations in the model's responses. * The scope of the training dataset determines the subject areas the model can handle effectively. * Context and Task Complexity * LLMs are better at tasks that can be framed with clear prompts and instructions. Open-ended or highly complex tasks might be challenging. * A model's performance can be influenced by the amount of context provided (longer context generally leads to better outputs, up to a certain point). * Language Ambiguity and Nuance * Natural language is inherently complex. LLMs might struggle to grasp subtle nuances, sarcasm, or figurative language. * Factual Accuracy * LLMs generate responses based on information they learned from their training datasets, but they are not knowledge bases. They may generate incorrect or outdated factual statements. * Common Sense * LLMs rely on statistical patterns in language. They might lack the ability to apply common sense reasoning in certain situations. ### Ethical Considerations and Risks The development of large language models (LLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following: * Bias and Fairness * LLMs trained on large-scale, real-world text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card. * Misinformation and Misuse * LLMs can be misused to generate text that is false, misleading, or harmful. * Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible). * Transparency and Accountability: * This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes. * A responsibly developed open model offers the opportunity to share innovation by making LLM technology accessible to developers and researchers across the AI ecosystem. Risks identified and mitigations: * Perpetuation of biases: It's encouraged to perform continuous monitoring (using evaluation metrics, human review) and the exploration of de-biasing techniques during model training, fine-tuning, and other use cases. * Generation of harmful content: Mechanisms and guidelines for content safety are essential. Developers are encouraged to exercise caution and implement appropriate content safety safeguards based on their specific product policies and application use cases. * Misuse for malicious purposes: Technical limitations and developer and end-user education can help mitigate against malicious applications of LLMs. Educational resources and reporting mechanisms for users to flag misuse are provided. Prohibited uses of Gemma models are outlined in the [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). * Privacy violations: Models were trained on data filtered for removal of PII (Personally Identifiable Information). Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques. ### Benefits At the time of release, this family of models provides high-performance open large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models. Using the benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives.
{}
RichardErkhov/google_-_gemma-7b-it-8bits
null
[ "transformers", "safetensors", "gemma", "text-generation", "conversational", "arxiv:2312.11805", "arxiv:2009.03300", "arxiv:1905.07830", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1905.10044", "arxiv:1907.10641", "arxiv:1811.00937", "arxiv:1809.02789", "arxiv:1911.01547", "arxiv:1705.03551", "arxiv:2107.03374", "arxiv:2108.07732", "arxiv:2110.14168", "arxiv:2304.06364", "arxiv:2206.04615", "arxiv:1804.06876", "arxiv:2110.08193", "arxiv:2009.11462", "arxiv:2101.11718", "arxiv:1804.09301", "arxiv:2109.07958", "arxiv:2203.09509", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]
null
2024-05-02T12:12:56+00:00
image-classification
transformers
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # vit-base-patch16-224-finetuned-ind-17-imbalanced-aadhaarmask-new-parameter This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset. It achieves the following results on the evaluation set: - Loss: 0.3278 - Accuracy: 0.8519 - Recall: 0.8519 - F1: 0.8508 - Precision: 0.8576 ## 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: 8 - eval_batch_size: 8 - seed: 42 - 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 | Recall | F1 | Precision | |:-------------:|:-----:|:-----:|:---------------:|:--------:|:------:|:------:|:---------:| | No log | 1.0 | 1175 | 0.5572 | 0.8076 | 0.8076 | 0.7937 | 0.8043 | | No log | 2.0 | 2350 | 0.4673 | 0.8284 | 0.8284 | 0.8271 | 0.8347 | | No log | 3.0 | 3525 | 0.4109 | 0.8344 | 0.8344 | 0.8301 | 0.8367 | | No log | 4.0 | 4700 | 0.3984 | 0.8382 | 0.8382 | 0.8339 | 0.8375 | | No log | 5.0 | 5875 | 0.3886 | 0.8412 | 0.8412 | 0.8398 | 0.8467 | | No log | 6.0 | 7050 | 0.3520 | 0.8493 | 0.8493 | 0.8481 | 0.8519 | | No log | 7.0 | 8225 | 0.4229 | 0.8416 | 0.8416 | 0.8399 | 0.8512 | | No log | 8.0 | 9400 | 0.3140 | 0.8612 | 0.8612 | 0.8600 | 0.8656 | | No log | 9.0 | 10575 | 0.3399 | 0.8421 | 0.8421 | 0.8403 | 0.8464 | | 0.4263 | 10.0 | 11750 | 0.3399 | 0.8476 | 0.8476 | 0.8468 | 0.8536 | ### Framework versions - Transformers 4.40.1 - Pytorch 2.2.0a0+81ea7a4 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "datasets": ["imagefolder"], "metrics": ["accuracy", "recall", "f1", "precision"], "base_model": "google/vit-base-patch16-224", "model-index": [{"name": "vit-base-patch16-224-finetuned-ind-17-imbalanced-aadhaarmask-new-parameter", "results": [{"task": {"type": "image-classification", "name": "Image Classification"}, "dataset": {"name": "imagefolder", "type": "imagefolder", "config": "default", "split": "train", "args": "default"}, "metrics": [{"type": "accuracy", "value": 0.8518518518518519, "name": "Accuracy"}, {"type": "recall", "value": 0.8518518518518519, "name": "Recall"}, {"type": "f1", "value": 0.8508141812977819, "name": "F1"}, {"type": "precision", "value": 0.8576385720576808, "name": "Precision"}]}]}]}
Kushagra07/vit-base-patch16-224-finetuned-ind-17-imbalanced-aadhaarmask-new-parameter
null
[ "transformers", "tensorboard", "safetensors", "vit", "image-classification", "generated_from_trainer", "dataset:imagefolder", "base_model:google/vit-base-patch16-224", "license:apache-2.0", "model-index", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:13:38+00:00
question-answering
transformers
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # distilbert-base-uncased-finetuned-squad This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.7599 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 3 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 1.4162 | 1.0 | 2500 | 1.5635 | | 1.0379 | 2.0 | 5000 | 1.6740 | | 0.838 | 3.0 | 7500 | 1.7599 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.1.2 - Datasets 2.18.0 - Tokenizers 0.15.2
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "base_model": "distilbert-base-uncased", "model-index": [{"name": "distilbert-base-uncased-finetuned-squad", "results": []}]}
mondol007/distilbert-base-uncased-finetuned-squad
null
[ "transformers", "tensorboard", "safetensors", "distilbert", "question-answering", "generated_from_trainer", "base_model:distilbert-base-uncased", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:16:09+00:00
automatic-speech-recognition
transformers
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # whisper_model_team1-ar-en This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the fleurs data dataset. It achieves the following results on the evaluation set: - Loss: 0.4172 - Wer: 12.3005 ## 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: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 500 - training_steps: 1000 ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:--------:|:----:|:---------------:|:-------:| | 0.0 | 142.8571 | 1000 | 0.4172 | 12.3005 | ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.3.0+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"language": ["en"], "license": "apache-2.0", "tags": ["hf-asr-leaderboard", "generated_from_trainer"], "datasets": ["google/fleurs"], "metrics": ["wer"], "base_model": "openai/whisper-medium", "model-index": [{"name": "whisper_model_team1-ar-en", "results": [{"task": {"type": "automatic-speech-recognition", "name": "Automatic Speech Recognition"}, "dataset": {"name": "fleurs data", "type": "google/fleurs", "config": "en_us", "split": "None", "args": "config: en_us, split: test"}, "metrics": [{"type": "wer", "value": 12.300469483568074, "name": "Wer"}]}]}]}
nesrine19/whisper_model_team1-ar-en
null
[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "hf-asr-leaderboard", "generated_from_trainer", "en", "dataset:google/fleurs", "base_model:openai/whisper-medium", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:16:24+00:00
reinforcement-learning
null
# **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
{"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-Cartpolev1", "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}]}]}]}
AGI-CEO/Reinforce-Cartpolev1
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
null
2024-05-02T12:16:37+00:00
automatic-speech-recognition
transformers
{}
raidavid/whisper-tiny-20240502-pc28-have-opendata
null
[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:17:08+00:00
null
null
{}
greasyFinger/raghava_gps
null
[ "region:us" ]
null
2024-05-02T12:17:08+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 0.9.1.dev0
{"library_name": "peft", "base_model": "HuggingFaceH4/zephyr-7b-beta"}
Bodhi108/zephyr_7B_beta_FDE_NA0219_2400
null
[ "peft", "safetensors", "mistral", "arxiv:1910.09700", "base_model:HuggingFaceH4/zephyr-7b-beta", "region:us" ]
null
2024-05-02T12:17:27+00:00
null
transformers
## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hfhfix --> <!-- ### vocab_type: --> static quants of https://huggingface.co/NousResearch/Meta-Llama-3-8B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-8B-i1-GGUF ## 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/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q2_K.gguf) | Q2_K | 3.3 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.IQ3_XS.gguf) | IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q3_K_S.gguf) | Q3_K_S | 3.8 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.IQ3_S.gguf) | IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.IQ3_M.gguf) | IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q3_K_M.gguf) | Q3_K_M | 4.1 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q3_K_L.gguf) | Q3_K_L | 4.4 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.IQ4_XS.gguf) | IQ4_XS | 4.6 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q4_K_S.gguf) | Q4_K_S | 4.8 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q4_K_M.gguf) | Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q5_K_S.gguf) | Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q5_K_M.gguf) | Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q6_K.gguf) | Q6_K | 6.7 | very good quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.Q8_0.gguf) | Q8_0 | 8.6 | fast, best quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-8B-GGUF/resolve/main/Meta-Llama-3-8B.f16.gguf) | f16 | 16.2 | 16 bpw, overkill | Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) And here are Artefact2's thoughts on the matter: https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 ## FAQ / Model Request See https://huggingface.co/mradermacher/model_requests for some answers to questions you might have and/or if you want some other model quantized. ## Thanks I thank my company, [nethype GmbH](https://www.nethype.de/), for letting me use its servers and providing upgrades to my workstation to enable this work in my free time. <!-- end -->
{"language": ["en"], "license": "other", "library_name": "transformers", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "base_model": "NousResearch/Meta-Llama-3-8B", "extra_gated_button_content": "Submit", "extra_gated_fields": {"Affiliation": "text", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox", "Country": "country", "Date of birth": "date_picker", "First Name": "text", "Last Name": "text", "geo": "ip_location"}, "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "license_link": "LICENSE", "license_name": "llama3", "quantized_by": "mradermacher"}
mradermacher/Meta-Llama-3-8B-GGUF
null
[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "en", "base_model:NousResearch/Meta-Llama-3-8B", "license:other", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:17:43+00:00
text-generation
transformers
{}
simonveitner/deepseekmath_onebin
null
[ "transformers", "pytorch", "llama", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:17:44+00:00
null
transformers
# Uploaded model - **Developed by:** grabbysingh - **License:** apache-2.0 - **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-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"], "base_model": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit"}
grabbysingh/phi_3_mini_4k_personality
null
[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:18:46+00:00
automatic-speech-recognition
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": []}
shtapm/whisper-large_0502_decoder2_200steps
null
[ "transformers", "safetensors", "whisper", "automatic-speech-recognition", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:18:53+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. --> # final_model_5 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 None dataset. It achieves the following results on the evaluation set: - Loss: 2.8725 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure The following `bitsandbytes` quantization config was used during training: - quant_method: bitsandbytes - 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: False - bnb_4bit_compute_dtype: bfloat16 ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0002 - train_batch_size: 8 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_ratio: 0.03 - training_steps: 90 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-----:|:----:|:---------------:| | 0.0462 | 1.0 | 1 | 2.5821 | | 0.0463 | 2.0 | 2 | 2.6255 | | 0.0327 | 3.0 | 3 | 2.7177 | | 0.0374 | 4.0 | 4 | 2.7702 | | 0.0465 | 5.0 | 5 | 2.7528 | | 0.029 | 6.0 | 6 | 2.7269 | | 0.0239 | 7.0 | 7 | 2.6977 | | 0.0284 | 8.0 | 8 | 2.6762 | | 0.019 | 9.0 | 9 | 2.6788 | | 0.0184 | 10.0 | 10 | 2.6653 | | 0.0283 | 11.0 | 11 | 2.6582 | | 0.0232 | 12.0 | 12 | 2.6511 | | 0.0161 | 13.0 | 13 | 2.6508 | | 0.0158 | 14.0 | 14 | 2.6450 | | 0.0147 | 15.0 | 15 | 2.6431 | | 0.0156 | 16.0 | 16 | 2.6449 | | 0.014 | 17.0 | 17 | 2.6488 | | 0.0139 | 18.0 | 18 | 2.6530 | | 0.0137 | 19.0 | 19 | 2.6587 | | 0.0136 | 20.0 | 20 | 2.6646 | | 0.0135 | 21.0 | 21 | 2.6703 | | 0.0134 | 22.0 | 22 | 2.6755 | | 0.0133 | 23.0 | 23 | 2.6806 | | 0.0131 | 24.0 | 24 | 2.6858 | | 0.0131 | 25.0 | 25 | 2.6908 | | 0.0129 | 26.0 | 26 | 2.6956 | | 0.0128 | 27.0 | 27 | 2.7001 | | 0.0127 | 28.0 | 28 | 2.7043 | | 0.0125 | 29.0 | 29 | 2.7083 | | 0.0123 | 30.0 | 30 | 2.7120 | | 0.0121 | 31.0 | 31 | 2.7155 | | 0.0121 | 32.0 | 32 | 2.7191 | | 0.0117 | 33.0 | 33 | 2.7227 | | 0.0115 | 34.0 | 34 | 2.7263 | | 0.0113 | 35.0 | 35 | 2.7301 | | 0.0111 | 36.0 | 36 | 2.7340 | | 0.0108 | 37.0 | 37 | 2.7379 | | 0.0106 | 38.0 | 38 | 2.7418 | | 0.0104 | 39.0 | 39 | 2.7457 | | 0.0104 | 40.0 | 40 | 2.7494 | | 0.01 | 41.0 | 41 | 2.7532 | | 0.0098 | 42.0 | 42 | 2.7569 | | 0.0096 | 43.0 | 43 | 2.7606 | | 0.0095 | 44.0 | 44 | 2.7643 | | 0.0094 | 45.0 | 45 | 2.7681 | | 0.0093 | 46.0 | 46 | 2.7720 | | 0.0093 | 47.0 | 47 | 2.7760 | | 0.0092 | 48.0 | 48 | 2.7802 | | 0.0092 | 49.0 | 49 | 2.7846 | | 0.0091 | 50.0 | 50 | 2.7892 | | 0.0091 | 51.0 | 51 | 2.7940 | | 0.0091 | 52.0 | 52 | 2.7989 | | 0.0091 | 53.0 | 53 | 2.8039 | | 0.009 | 54.0 | 54 | 2.8090 | | 0.009 | 55.0 | 55 | 2.8141 | | 0.0089 | 56.0 | 56 | 2.8191 | | 0.0089 | 57.0 | 57 | 2.8239 | | 0.0088 | 58.0 | 58 | 2.8284 | | 0.0087 | 59.0 | 59 | 2.8331 | | 0.0088 | 60.0 | 60 | 2.8372 | | 0.0087 | 61.0 | 61 | 2.8405 | | 0.0087 | 62.0 | 62 | 2.8433 | | 0.0086 | 63.0 | 63 | 2.8457 | | 0.0086 | 64.0 | 64 | 2.8476 | | 0.0085 | 65.0 | 65 | 2.8499 | | 0.0085 | 66.0 | 66 | 2.8514 | | 0.0085 | 67.0 | 67 | 2.8530 | | 0.0084 | 68.0 | 68 | 2.8545 | | 0.0084 | 69.0 | 69 | 2.8560 | | 0.0084 | 70.0 | 70 | 2.8575 | | 0.0084 | 71.0 | 71 | 2.8590 | | 0.0083 | 72.0 | 72 | 2.8605 | | 0.0083 | 73.0 | 73 | 2.8620 | | 0.0083 | 74.0 | 74 | 2.8633 | | 0.0082 | 75.0 | 75 | 2.8646 | | 0.0082 | 76.0 | 76 | 2.8657 | | 0.0082 | 77.0 | 77 | 2.8668 | | 0.0082 | 78.0 | 78 | 2.8679 | | 0.0081 | 79.0 | 79 | 2.8689 | | 0.0082 | 80.0 | 80 | 2.8697 | | 0.0082 | 81.0 | 81 | 2.8705 | | 0.0081 | 82.0 | 82 | 2.8711 | | 0.0082 | 83.0 | 83 | 2.8716 | | 0.0082 | 84.0 | 84 | 2.8719 | | 0.0081 | 85.0 | 85 | 2.8721 | | 0.0081 | 86.0 | 86 | 2.8723 | | 0.0081 | 87.0 | 87 | 2.8724 | | 0.0081 | 88.0 | 88 | 2.8724 | | 0.0081 | 89.0 | 89 | 2.8725 | | 0.0081 | 90.0 | 90 | 2.8725 | ### Framework versions - PEFT 0.4.0 - Transformers 4.37.2 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.15.2
{"license": "apache-2.0", "library_name": "peft", "tags": ["generated_from_trainer"], "base_model": "mistralai/Mistral-7B-Instruct-v0.2", "model-index": [{"name": "final_model_5", "results": []}]}
hussamsal/final_model_5
null
[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:apache-2.0", "region:us" ]
null
2024-05-02T12:19:54+00:00
text-classification
transformers
# Model Card for Model ID <!-- Provide a quick summary of what the model is/does. --> ## Model Details ### Model Description <!-- Provide a longer summary of what this model is. --> This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated. - **Developed by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Model type:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] - **Finetuned from model [optional]:** [More Information Needed] ### Model Sources [optional] <!-- Provide the basic links for the model. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. --> ### Direct Use <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. --> [More Information Needed] ### Downstream Use [optional] <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations. ## How to Get Started with the Model Use the code below to get started with the model. [More Information Needed] ## Training Details ### Training Data <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. --> [More Information Needed] ### Training Procedure <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. --> #### Preprocessing [optional] [More Information Needed] #### Training Hyperparameters - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision --> #### Speeds, Sizes, Times [optional] <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. --> [More Information Needed] ## Evaluation <!-- This section describes the evaluation protocols and provides the results. --> ### Testing Data, Factors & Metrics #### Testing Data <!-- This should link to a Dataset Card if possible. --> [More Information Needed] #### Factors <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. --> [More Information Needed] #### Metrics <!-- These are the evaluation metrics being used, ideally with a description of why. --> [More Information Needed] ### Results [More Information Needed] #### Summary ## Model Examination [optional] <!-- Relevant interpretability work for the model goes here --> [More Information Needed] ## Environmental Impact <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly --> Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). - **Hardware Type:** [More Information Needed] - **Hours used:** [More Information Needed] - **Cloud Provider:** [More Information Needed] - **Compute Region:** [More Information Needed] - **Carbon Emitted:** [More Information Needed] ## Technical Specifications [optional] ### Model Architecture and Objective [More Information Needed] ### Compute Infrastructure [More Information Needed] #### Hardware [More Information Needed] #### Software [More Information Needed] ## Citation [optional] <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Model Card Authors [optional] [More Information Needed] ## Model Card Contact [More Information Needed]
{"library_name": "transformers", "tags": []}
presencesw/xlm-roberta-large-snli-cosine
null
[ "transformers", "safetensors", "xlm-roberta", "text-classification", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:20:04+00:00
null
null
GGUF version of [state-spaces/mamba-130m-hf](https://huggingface.co/state-spaces/mamba-130m-hf).
{"base_model": "state-spaces/mamba-130m-hf"}
Felladrin/gguf-mamba-130m-hf
null
[ "gguf", "base_model:state-spaces/mamba-130m-hf", "region:us" ]
null
2024-05-02T12:20:33+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": []}
vaatsav06/Llama3_pubmedqa_finetune
null
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "8-bit", "region:us" ]
null
2024-05-02T12:21:20+00:00
null
null
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) illuni-llama-2-ko-7b-test - GGUF - Model creator: https://huggingface.co/julleong/ - Original model: https://huggingface.co/julleong/illuni-llama-2-ko-7b-test/ | Name | Quant method | Size | | ---- | ---- | ---- | | [illuni-llama-2-ko-7b-test.Q2_K.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q2_K.gguf) | Q2_K | 2.42GB | | [illuni-llama-2-ko-7b-test.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.IQ3_XS.gguf) | IQ3_XS | 2.67GB | | [illuni-llama-2-ko-7b-test.IQ3_S.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.IQ3_S.gguf) | IQ3_S | 2.81GB | | [illuni-llama-2-ko-7b-test.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q3_K_S.gguf) | Q3_K_S | 2.81GB | | [illuni-llama-2-ko-7b-test.IQ3_M.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.IQ3_M.gguf) | IQ3_M | 2.97GB | | [illuni-llama-2-ko-7b-test.Q3_K.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q3_K.gguf) | Q3_K | 3.14GB | | [illuni-llama-2-ko-7b-test.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q3_K_M.gguf) | Q3_K_M | 3.14GB | | [illuni-llama-2-ko-7b-test.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q3_K_L.gguf) | Q3_K_L | 3.42GB | | [illuni-llama-2-ko-7b-test.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.IQ4_XS.gguf) | IQ4_XS | 3.47GB | | [illuni-llama-2-ko-7b-test.Q4_0.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q4_0.gguf) | Q4_0 | 3.64GB | | [illuni-llama-2-ko-7b-test.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.IQ4_NL.gguf) | IQ4_NL | 3.66GB | | [illuni-llama-2-ko-7b-test.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q4_K_S.gguf) | Q4_K_S | 3.67GB | | [illuni-llama-2-ko-7b-test.Q4_K.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q4_K.gguf) | Q4_K | 3.88GB | | [illuni-llama-2-ko-7b-test.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q4_K_M.gguf) | Q4_K_M | 3.88GB | | [illuni-llama-2-ko-7b-test.Q4_1.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q4_1.gguf) | Q4_1 | 4.03GB | | [illuni-llama-2-ko-7b-test.Q5_0.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q5_0.gguf) | Q5_0 | 4.42GB | | [illuni-llama-2-ko-7b-test.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q5_K_S.gguf) | Q5_K_S | 4.42GB | | [illuni-llama-2-ko-7b-test.Q5_K.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q5_K.gguf) | Q5_K | 4.54GB | | [illuni-llama-2-ko-7b-test.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q5_K_M.gguf) | Q5_K_M | 4.54GB | | [illuni-llama-2-ko-7b-test.Q5_1.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q5_1.gguf) | Q5_1 | 4.8GB | | [illuni-llama-2-ko-7b-test.Q6_K.gguf](https://huggingface.co/RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf/blob/main/illuni-llama-2-ko-7b-test.Q6_K.gguf) | Q6_K | 5.24GB | Original model description: --- language: - ko base_model: beomi/llama-2-ko-7b license: mit pipeline_tag: question-answering tags: - instruct - instruction - llama-2 --- # llama2-7b ### Model Details - Developed by: Julleong - Backbone Model: beomi/llama-2-ko-7b - Library: [transformers](https://github.com/huggingface/transformers) ### Used Datasets - 개체명 사전 2022(모두의 말뭉치) ### Prompt Template ``` <usr> {Instruction} <bot> {Answer} ``` ### License - MIT
{}
RichardErkhov/julleong_-_illuni-llama-2-ko-7b-test-gguf
null
[ "gguf", "region:us" ]
null
2024-05-02T12:22:11+00:00
reinforcement-learning
ml-agents
# **ppo** Agent playing **Pyramids** This is a trained model of a **ppo** agent playing **Pyramids** using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents). ## Usage (with ML-Agents) The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/ We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub: - A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction - A *longer tutorial* to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction ### Resume the training ```bash mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume ``` ### Watch your Agent play You can watch your agent **playing directly in your browser** 1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity 2. Step 1: Find your model_id: pietroorlandi/ppo-pyramid 3. Step 2: Select your *.nn /*.onnx file 4. Click on Watch the agent play 👀
{"library_name": "ml-agents", "tags": ["Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids"]}
pietroorlandi/ppo-pyramid
null
[ "ml-agents", "tensorboard", "onnx", "Pyramids", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-Pyramids", "region:us" ]
null
2024-05-02T12:22:20+00:00
text-to-audio
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. --> # ceb_b32_le3_s4000 This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 1.4322 ## 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: 0.001 - train_batch_size: 32 - eval_batch_size: 8 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 2000 - training_steps: 4000 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:-------:|:----:|:---------------:| | 0.5339 | 9.8039 | 500 | 0.5261 | | 0.5398 | 19.6078 | 1000 | 0.4739 | | 1.4411 | 29.4118 | 1500 | 1.4336 | | 1.4717 | 39.2157 | 2000 | 1.4339 | | 1.4605 | 49.0196 | 2500 | 1.4345 | | 1.4354 | 58.8235 | 3000 | 1.4322 | | 1.4293 | 68.6275 | 3500 | 1.4321 | | 1.4262 | 78.4314 | 4000 | 1.4322 | ### Framework versions - Transformers 4.41.0.dev0 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "mit", "tags": ["generated_from_trainer"], "base_model": "microsoft/speecht5_tts", "model-index": [{"name": "ceb_b32_le3_s4000", "results": []}]}
mikhail-panzo/ceb_b32_le3_s4000
null
[ "transformers", "tensorboard", "safetensors", "speecht5", "text-to-audio", "generated_from_trainer", "base_model:microsoft/speecht5_tts", "license:mit", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:22:50+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]
{"license": "apache-2.0", "library_name": "transformers"}
T3Q-LLM/T3Q-LLM1-v1.0
null
[ "transformers", "safetensors", "llama", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]
null
2024-05-02T12:23:02+00:00
null
null
{}
NightFuryTimo/test
null
[ "region:us" ]
null
2024-05-02T12:23:35+00:00
null
null
{}
little7279/test-model1
null
[ "region:us" ]
null
2024-05-02T12:23:43+00:00
null
transformers
## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: --> <!-- ### vocab_type: --> weighted/imatrix quants of https://huggingface.co/Gryphe/Tiamat-8b-1.2-Llama-3-DPO <!-- provided-files --> static quants are available at https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-GGUF ## 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/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ1_S.gguf) | i1-IQ1_S | 2.1 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ1_M.gguf) | i1-IQ1_M | 2.3 | for the desperate | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 2.5 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ2_XS.gguf) | i1-IQ2_XS | 2.7 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ2_S.gguf) | i1-IQ2_S | 2.9 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ2_M.gguf) | i1-IQ2_M | 3.0 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q2_K.gguf) | i1-Q2_K | 3.3 | IQ3_XXS probably better | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 3.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ3_XS.gguf) | i1-IQ3_XS | 3.6 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q3_K_S.gguf) | i1-Q3_K_S | 3.8 | IQ3_XS probably better | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ3_S.gguf) | i1-IQ3_S | 3.8 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ3_M.gguf) | i1-IQ3_M | 3.9 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q3_K_M.gguf) | i1-Q3_K_M | 4.1 | IQ3_S probably better | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q3_K_L.gguf) | i1-Q3_K_L | 4.4 | IQ3_M probably better | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-IQ4_XS.gguf) | i1-IQ4_XS | 4.5 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q4_0.gguf) | i1-Q4_0 | 4.8 | fast, low quality | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q4_K_S.gguf) | i1-Q4_K_S | 4.8 | optimal size/speed/quality | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q4_K_M.gguf) | i1-Q4_K_M | 5.0 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q5_K_S.gguf) | i1-Q5_K_S | 5.7 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q5_K_M.gguf) | i1-Q5_K_M | 5.8 | | | [GGUF](https://huggingface.co/mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF/resolve/main/Tiamat-8b-1.2-Llama-3-DPO.i1-Q6_K.gguf) | i1-Q6_K | 6.7 | practically like static Q6_K | 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": "Gryphe/Tiamat-8b-1.2-Llama-3-DPO", "quantized_by": "mradermacher"}
mradermacher/Tiamat-8b-1.2-Llama-3-DPO-i1-GGUF
null
[ "transformers", "gguf", "en", "base_model:Gryphe/Tiamat-8b-1.2-Llama-3-DPO", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:23:53+00:00
text-generation
transformers
# Uploaded model - **Developed by:** grabbysingh - **License:** apache-2.0 - **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-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/Phi-3-mini-4k-instruct-bnb-4bit"}
grabbysingh/phi_3_mini_4k_personality_16bit
null
[ "transformers", "pytorch", "mistral", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:25:12+00:00
null
null
{"license": "openrail"}
ahmadi321/mohammad
null
[ "license:openrail", "region:us" ]
null
2024-05-02T12:26:17+00:00
null
null
{}
philgrey/clas_model
null
[ "region:us" ]
null
2024-05-02T12:26:40+00:00
feature-extraction
transformers
# fine-tuned/car-search-100-64-8-jinaai_jina-embeddings-v2-base-en-300-gpt-3.5-turb_8647177611 ## Model Description fine-tuned/car-search-100-64-8-jinaai_jina-embeddings-v2-base-en-300-gpt-3.5-turb_8647177611 is a fine-tuned version of jinaai/jina-embeddings-v2-base-en designed for a specific domain. ## Use Case This model is designed to support various applications in natural language processing and understanding. ## Associated Dataset This the dataset for this model can be found [**here**](https://huggingface.co/datasets/fine-tuned/fine-tuned/car-search-100-64-8-jinaai_jina-embeddings-v2-base-en-300-gpt-3.5-turb_8647177611). ## How to Use This model can be easily integrated into your NLP pipeline for tasks such as text classification, sentiment analysis, entity recognition, and more. Here's a simple example to get you started: ```python from transformers import AutoModel, AutoTokenizer llm_name = "fine-tuned/car-search-100-64-8-jinaai_jina-embeddings-v2-base-en-300-gpt-3.5-turb_8647177611" tokenizer = AutoTokenizer.from_pretrained(llm_name) model = AutoModel.from_pretrained(llm_name, trust_remote_code=True) tokens = tokenizer("Your text here", return_tensors="pt") embedding = model(**tokens) ```
{}
fine-tuned/car-search-100-64-8-jinaai_jina-embeddings-v2-base-en-300-gpt-3.5-turb_8647177611
null
[ "transformers", "safetensors", "bert", "feature-extraction", "custom_code", "region:us" ]
null
2024-05-02T12:26:46+00:00
null
null
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) Starling-LM-7B-alpha - GGUF - Model creator: https://huggingface.co/berkeley-nest/ - Original model: https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha/ | Name | Quant method | Size | | ---- | ---- | ---- | | [Starling-LM-7B-alpha.Q2_K.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q2_K.gguf) | Q2_K | 2.53GB | | [Starling-LM-7B-alpha.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.IQ3_XS.gguf) | IQ3_XS | 2.81GB | | [Starling-LM-7B-alpha.IQ3_S.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.IQ3_S.gguf) | IQ3_S | 2.96GB | | [Starling-LM-7B-alpha.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q3_K_S.gguf) | Q3_K_S | 2.95GB | | [Starling-LM-7B-alpha.IQ3_M.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.IQ3_M.gguf) | IQ3_M | 3.06GB | | [Starling-LM-7B-alpha.Q3_K.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q3_K.gguf) | Q3_K | 3.28GB | | [Starling-LM-7B-alpha.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q3_K_M.gguf) | Q3_K_M | 3.28GB | | [Starling-LM-7B-alpha.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q3_K_L.gguf) | Q3_K_L | 3.56GB | | [Starling-LM-7B-alpha.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.IQ4_XS.gguf) | IQ4_XS | 3.67GB | | [Starling-LM-7B-alpha.Q4_0.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q4_0.gguf) | Q4_0 | 3.83GB | | [Starling-LM-7B-alpha.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.IQ4_NL.gguf) | IQ4_NL | 3.87GB | | [Starling-LM-7B-alpha.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q4_K_S.gguf) | Q4_K_S | 3.86GB | | [Starling-LM-7B-alpha.Q4_K.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q4_K.gguf) | Q4_K | 4.07GB | | [Starling-LM-7B-alpha.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q4_K_M.gguf) | Q4_K_M | 4.07GB | | [Starling-LM-7B-alpha.Q4_1.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q4_1.gguf) | Q4_1 | 4.24GB | | [Starling-LM-7B-alpha.Q5_0.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q5_0.gguf) | Q5_0 | 4.65GB | | [Starling-LM-7B-alpha.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q5_K_S.gguf) | Q5_K_S | 4.65GB | | [Starling-LM-7B-alpha.Q5_K.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q5_K.gguf) | Q5_K | 4.78GB | | [Starling-LM-7B-alpha.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q5_K_M.gguf) | Q5_K_M | 4.78GB | | [Starling-LM-7B-alpha.Q5_1.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q5_1.gguf) | Q5_1 | 5.07GB | | [Starling-LM-7B-alpha.Q6_K.gguf](https://huggingface.co/RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf/blob/main/Starling-LM-7B-alpha.Q6_K.gguf) | Q6_K | 5.53GB | Original model description: --- license: apache-2.0 datasets: - berkeley-nest/Nectar language: - en library_name: transformers tags: - reward model - RLHF - RLAIF --- # Starling-LM-7B-alpha <!-- Provide a quick summary of what the model is/does. --> - **Developed by:** Banghua Zhu * , Evan Frick * , Tianhao Wu * , Hanlin Zhu and Jiantao Jiao. - **Model type:** Language Model finetuned with RLHF / RLAIF - **License:** Apache-2.0 license under the condition that the model is not used to compete with OpenAI - **Finetuned from model:** [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5) (based on [Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)) We introduce Starling-7B, an open large language model (LLM) trained by Reinforcement Learning from AI Feedback (RLAIF). The model harnesses the power of our new GPT-4 labeled ranking dataset, [berkeley-nest/Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), and our new reward training and policy tuning pipeline. Starling-7B-alpha scores 8.09 in MT Bench with GPT-4 as a judge, outperforming every model to date on MT-Bench except for OpenAI's GPT-4 and GPT-4 Turbo. We release the ranking dataset [Nectar](https://huggingface.co/datasets/berkeley-nest/Nectar), the reward model [Starling-RM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-RM-7B-alpha) and the language model [Starling-LM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-LM-7B-alpha) on HuggingFace, and an online demo in LMSYS [Chatbot Arena](https://chat.lmsys.org). Stay tuned for our forthcoming code and paper, which will provide more details on the whole process. Starling-LM-7B-alpha is a language model trained from [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5) with reward model [berkeley-nest/Starling-RM-7B-alpha](https://huggingface.co/berkeley-nest/Starling-RM-7B-alpha) and policy optimization method [advantage-induced policy alignment (APA)](https://arxiv.org/abs/2306.02231). The evaluation results are listed below. | Model | Tuning Method | MT Bench | AlpacaEval | MMLU | |-----------------------|------------------|----------|------------|------| | GPT-4-Turbo | ? | 9.32 | 97.70 | | | GPT-4 | SFT + PPO | 8.99 | 95.28 | 86.4 | | **Starling-7B** | C-RLFT + APA | 8.09 | 91.99 | 63.9 | | Claude-2 | ? | 8.06 | 91.36 | 78.5 | | GPT-3.5-Turbo | ? | 7.94 | 89.37 | 70 | | Claude-1 | ? | 7.9 | 88.39 | 77 | | Tulu-2-dpo-70b | SFT + DPO | 7.89 | 95.1 | | | Openchat-3.5 | C-RLFT | 7.81 | 88.51 | 64.3 | | Zephyr-7B-beta | SFT + DPO | 7.34 | 90.60 | 61.4 | | Llama-2-70b-chat-hf | SFT + PPO | 6.86 | 92.66 | 63 | | Neural-chat-7b-v3-1 | SFT + DPO | 6.84 | 84.53 | 62.4 | | Tulu-2-dpo-7b | SFT + DPO | 6.29 | 85.1 | | For more detailed discussions, please check out our [blog post](https://starling.cs.berkeley.edu), and stay tuned for our upcoming code and paper! <!-- Provide the basic links for the model. --> - **Blog:** https://starling.cs.berkeley.edu/ - **Paper:** Coming soon! - **Code:** Coming soon! ## 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. --> **Important: Please use the exact chat template provided below for the model. Otherwise there will be a degrade in the performance. The model output can be verbose in rare cases. Please consider setting temperature = 0 to make this happen less.** Our model follows the exact chat template and usage as [Openchat 3.5](https://huggingface.co/openchat/openchat_3.5). Please refer to their model card for more details. In addition, our model is hosted on LMSYS [Chatbot Arena](https://chat.lmsys.org) for free test. The conversation template is the same as Openchat 3.5: ``` import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("openchat/openchat_3.5") # Single-turn tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Multi-turn tokens = tokenizer("GPT4 Correct User: Hello<|end_of_turn|>GPT4 Correct Assistant: Hi<|end_of_turn|>GPT4 Correct User: How are you today?<|end_of_turn|>GPT4 Correct Assistant:").input_ids assert tokens == [1, 420, 6316, 28781, 3198, 3123, 1247, 28747, 22557, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747, 15359, 32000, 420, 6316, 28781, 3198, 3123, 1247, 28747, 1602, 460, 368, 3154, 28804, 32000, 420, 6316, 28781, 3198, 3123, 21631, 28747] # Coding Mode tokens = tokenizer("Code User: Implement quicksort using C++<|end_of_turn|>Code Assistant:").input_ids assert tokens == [1, 7596, 1247, 28747, 26256, 2936, 7653, 1413, 334, 1680, 32000, 7596, 21631, 28747] ``` ## Code Examples ```python import transformers tokenizer = transformers.AutoTokenizer.from_pretrained("berkeley-nest/Starling-LM-7B-alpha") model = transformers.AutoModelForCausalLM.from_pretrained("berkeley-nest/Starling-LM-7B-alpha") def generate_response(prompt): input_ids = tokenizer(prompt, return_tensors="pt").input_ids outputs = model.generate( input_ids, max_length=256, pad_token_id=tokenizer.pad_token_id, eos_token_id=tokenizer.eos_token_id, ) response_ids = outputs[0] response_text = tokenizer.decode(response_ids, skip_special_tokens=True) return response_text # Single-turn conversation prompt = "Hello, how are you?" single_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:" response_text = generate_response(single_turn_prompt) print("Response:", response_text) ## Multi-turn conversation prompt = "Hello" follow_up_question = "How are you today?" response = "" multi_turn_prompt = f"GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant: {response}<|end_of_turn|>GPT4 Correct User: {follow_up_question}<|end_of_turn|>GPT4 Correct Assistant:" response_text = generate_response(multi_turn_prompt) print("Multi-turn conversation response:", response_text) ### Coding conversation prompt = "Implement quicksort using C++" coding_prompt = f"Code User: {prompt}<|end_of_turn|>Code Assistant:" response = generate_response(coding_prompt) print("Coding conversation response:", response) ``` ## License The dataset, model and online demo is a research preview intended for non-commercial use only, subject to the data distillation [License](https://github.com/facebookresearch/llama/blob/main/MODEL_CARD.md) of LLaMA, [Terms of Use](https://openai.com/policies/terms-of-use) of the data generated by OpenAI, and [Privacy Practices](https://chrome.google.com/webstore/detail/sharegpt-share-your-chatg/daiacboceoaocpibfodeljbdfacokfjb) of ShareGPT. Please contact us if you find any potential violation. ## Acknowledgment We would like to thank Wei-Lin Chiang from Berkeley for detailed feedback of the blog and the projects. We would like to thank the [LMSYS Organization](https://lmsys.org/) for their support of [lmsys-chat-1M](https://huggingface.co/datasets/lmsys/lmsys-chat-1m) dataset, evaluation and online demo. We would like to thank the open source community for their efforts in providing the datasets and base models we used to develope the project, including but not limited to Anthropic, Llama, Mistral, Hugging Face H4, LMSYS, OpenChat, OpenBMB, Flan and ShareGPT. ## Citation ``` @misc{starling2023, title = {Starling-7B: Improving LLM Helpfulness & Harmlessness with RLAIF}, url = {}, author = {Zhu, Banghua and Frick, Evan and Wu, Tianhao and Zhu, Hanlin and Jiao, Jiantao}, month = {November}, year = {2023} } ```
{}
RichardErkhov/berkeley-nest_-_Starling-LM-7B-alpha-gguf
null
[ "gguf", "arxiv:2306.02231", "region:us" ]
null
2024-05-02T12:27:00+00:00
null
null
### Coming Soon!!!!!! ### 使用数据集alpaca-data-gpt4-chinese、sft_zh、ruozhiba对Qwen1.5-7B-Chat微调，测试结果显示CEVAL和MMLU分数均有上升 ### 模型： - https://huggingface.co/Qwen/Qwen1.5-7B-Chat ### 数据集： - https://huggingface.co/datasets/TigerResearch/sft_zh - https://huggingface.co/datasets/silk-road/alpaca-data-gpt4-chinese - https://huggingface.co/datasets/LooksJuicy/ruozhiba ### 结果 | 模型名称 | CEVAL | MMLU | |------------------------ |-------|------| | Qwen1.5-7B-Chat | 68.61 | 61.56| | Qwen1.5-7B-Chat-sft-lora-tigerbot-alpacadatagpt4-ruozhiba-10epoch | 71.09 | 62.62 |
{"language": ["zh", "en"], "license": "other", "tags": ["Transformer", "text-generation-inference"], "datasets": ["LooksJuicy/ruozhiba", "TigerResearch/sft_zh", "silk-road/alpaca-data-gpt4-chinese"], "license_name": "tongyi-qianwen", "license_link": "https://huggingface.co/Qwen/Qwen1.5-7B-Chat/blob/main/LICENSE"}
REILX/Qwen1.5-7B-Chat-tigerbot-alpacadatagpt4-ruozhiba-lora
null
[ "Transformer", "text-generation-inference", "zh", "en", "dataset:LooksJuicy/ruozhiba", "dataset:TigerResearch/sft_zh", "dataset:silk-road/alpaca-data-gpt4-chinese", "license:other", "region:us" ]
null
2024-05-02T12:27:58+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. --> # Llama3_finetued_on_charttotext This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 1e-06 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 30 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "Llama3_finetued_on_charttotext", "results": []}]}
moetezsa/Llama3_finetued_on_charttotext
null
[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]
null
2024-05-02T12:29:36+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": "245.92 +/- 18.53", "name": "mean_reward", "verified": false}]}]}]}
Max87152/ppo-LunarLander-v2
null
[ "stable-baselines3", "LunarLander-v2", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]
null
2024-05-02T12:29:40+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": ["unsloth"]}
pollbt/llama_partis
null
[ "transformers", "safetensors", "unsloth", "arxiv:1910.09700", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:30:21+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": "meta-llama/Meta-Llama-3-70B-Instruct"}
asbabiy/AspectLens-BA-Large-DPO-v2
null
[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "region:us" ]
null
2024-05-02T12:30:57+00:00
null
gpt-neox
# joeshmoethefunnyone/pythia-70m-F16-GGUF This model was converted to GGUF format from [`EleutherAI/pythia-70m`](https://huggingface.co/EleutherAI/pythia-70m) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space. Refer to the [original model card](https://huggingface.co/EleutherAI/pythia-70m) for more details on the model. ## Use with llama.cpp Install llama.cpp through brew. ```bash brew install ggerganov/ggerganov/llama.cpp ``` Invoke the llama.cpp server or the CLI. CLI: ```bash llama-cli --hf-repo joeshmoethefunnyone/pythia-70m-F16-GGUF --model pythia-70m.F16.gguf -p "The meaning to life and the universe is" ``` Server: ```bash llama-server --hf-repo joeshmoethefunnyone/pythia-70m-F16-GGUF --model pythia-70m.F16.gguf -c 2048 ``` Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well. ``` git clone https://github.com/ggerganov/llama.cpp && cd llama.cpp && make && ./main -m pythia-70m.F16.gguf -n 128 ```
{"language": ["en"], "license": "apache-2.0", "library_name": "gpt-neox", "tags": ["pytorch", "causal-lm", "pythia", "llama-cpp", "gguf-my-repo"], "datasets": ["EleutherAI/pile"]}
joeshmoethefunnyone/pythia-70m-F16-GGUF
null
[ "gpt-neox", "gguf", "pytorch", "causal-lm", "pythia", "llama-cpp", "gguf-my-repo", "en", "dataset:EleutherAI/pile", "license:apache-2.0", "region:us" ]
null
2024-05-02T12:31:34+00:00
text-to-image
diffusers
{}
GraydientPlatformAPI/juggernaut-hyper-x
null
[ "diffusers", "safetensors", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]
null
2024-05-02T12:31:43+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. --> # bert-base-arabic_ArLAMA This model is a fine-tuned version of [asafaya/bert-base-arabic](https://huggingface.co/asafaya/bert-base-arabic) 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: 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: 2 ### Training results ### Framework versions - Transformers 4.27.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.13.3
{"tags": ["generated_from_trainer"], "model-index": [{"name": "bert-base-arabic_ArLAMA", "results": []}]}
AfnanTS/bert-base-arabic_ArLAMA
null
[ "transformers", "pytorch", "tensorboard", "bert", "fill-mask", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:31:48+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. --> # albert_model_03 This model is a fine-tuned version of [distilbert/distilbert-base-uncased](https://huggingface.co/distilbert/distilbert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.6568 - Accuracy: 0.6973 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 2e-05 - train_batch_size: 16 - eval_batch_size: 16 - seed: 42 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - num_epochs: 1 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | |:-------------:|:-----:|:----:|:---------------:|:--------:| | No log | 1.0 | 310 | 0.6568 | 0.6973 | ### Framework versions - Transformers 4.39.3 - Pytorch 2.2.2+cu121 - Datasets 2.18.0 - Tokenizers 0.15.2
{"license": "apache-2.0", "tags": ["generated_from_trainer"], "metrics": ["accuracy"], "base_model": "distilbert/distilbert-base-uncased", "model-index": [{"name": "albert_model_03", "results": []}]}
KalaiselvanD/albert_model_03
null
[ "transformers", "tensorboard", "safetensors", "distilbert", "text-classification", "generated_from_trainer", "base_model:distilbert/distilbert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:31:56+00:00
text-to-image
null
<div class="flex justify-center"> <div class="container p-0 w-100"> <!-- <img class="mt-0 object-cover rounded-t-lg w-100 h-1/4" style="height: 480px; object-position: 60% 25%;" src="https://huggingface.co/bluepen5805/anima_pencil-XL/resolve/main/images/anima_pencil-XL-v1.0.0.webp" width="100%"/> --> <div class="flex px-4"> <div class="flex-auto"> <h1 class="mb-2 text-3xl font-bold leading-tight" style="color: rgb(56 189 248/var(--tw-text-opacity));"> pony_pencil-XL </h1> <!-- <p class="mb-4 text-base text-neutral-600 dark:text-neutral-200"> <a href="https://huggingface.co/bluepen5805/blue_pencil-XL">blue_pencil-XL</a> meets <a href="https://huggingface.co/cagliostrolab/animagine-xl-3.0">ANIMAGINE XL 3.0</a> </p> --> <dl> <dt>License</dt> <dd><a href="https://freedevproject.org/faipl-1.0-sd/">Fair AI Public License 1.0-SD</a></dd> <!-- <dt>Civitai</dt> <dd><a href="https://civitai.com/models/261336">https://civitai.com/models/261336</a></dd> --> </dl> </div> <div class="flex gap-2" style="height: fit-content;"> <a href="https://twitter.com/blue_pen5805" class="mb-2 inline-block rounded px-6 py-2.5 text-white shadow-md" style="background-color: #1da1f2"> <svg xmlns="http://www.w3.org/2000/svg" class="h-3.5 w-3.5" fill="currentColor" viewBox="0 0 24 24"> <path d="M24 4.557c-.883.392-1.832.656-2.828.775 1.017-.609 1.798-1.574 2.165-2.724-.951.564-2.005.974-3.127 1.195-.897-.957-2.178-1.555-3.594-1.555-3.179 0-5.515 2.966-4.797 6.045-4.091-.205-7.719-2.165-10.148-5.144-1.29 2.213-.669 5.108 1.523 6.574-.806-.026-1.566-.247-2.229-.616-.054 2.281 1.581 4.415 3.949 4.89-.693.188-1.452.232-2.224.084.626 1.956 2.444 3.379 4.6 3.419-2.07 1.623-4.678 2.348-7.29 2.04 2.179 1.397 4.768 2.212 7.548 2.212 9.142 0 14.307-7.721 13.995-14.646.962-.695 1.797-1.562 2.457-2.549z" /> </svg> </a> <a href="https://discord.gg/ai-animal" class="mb-2 inline-block rounded px-6 py-2.5 text-white shadow-md" style="background-color: #7289da"> <svg xmlns="http://www.w3.org/2000/svg" class="h-3.5 w-3.5" fill="currentColor" viewbox="0 0 24 24"> <path d="M19.54 0c1.356 0 2.46 1.104 2.46 2.472v21.528l-2.58-2.28-1.452-1.344-1.536-1.428.636 2.22h-13.608c-1.356 0-2.46-1.104-2.46-2.472v-16.224c0-1.368 1.104-2.472 2.46-2.472h16.08zm-4.632 15.672c2.652-.084 3.672-1.824 3.672-1.824 0-3.864-1.728-6.996-1.728-6.996-1.728-1.296-3.372-1.26-3.372-1.26l-.168.192c2.04.624 2.988 1.524 2.988 1.524-1.248-.684-2.472-1.02-3.612-1.152-.864-.096-1.692-.072-2.424.024l-.204.024c-.42.036-1.44.192-2.724.756-.444.204-.708.348-.708.348s.996-.948 3.156-1.572l-.12-.144s-1.644-.036-3.372 1.26c0 0-1.728 3.132-1.728 6.996 0 0 1.008 1.74 3.66 1.824 0 0 .444-.54.804-.996-1.524-.456-2.1-1.416-2.1-1.416l.336.204.048.036.047.027.014.006.047.027c.3.168.6.3.876.408.492.192 1.08.384 1.764.516.9.168 1.956.228 3.108.012.564-.096 1.14-.264 1.74-.516.42-.156.888-.384 1.38-.708 0 0-.6.984-2.172 1.428.36.456.792.972.792.972zm-5.58-5.604c-.684 0-1.224.6-1.224 1.332 0 .732.552 1.332 1.224 1.332.684 0 1.224-.6 1.224-1.332.012-.732-.54-1.332-1.224-1.332zm4.38 0c-.684 0-1.224.6-1.224 1.332 0 .732.552 1.332 1.224 1.332.684 0 1.224-.6 1.224-1.332 0-.732-.54-1.332-1.224-1.332z" /> </svg> </a> <a href="https://github.com/blue-pen5805" class="mb-2 inline-block rounded px-6 py-2.5 text-white shadow-md" style="background-color: #333"> <svg xmlns="http://www.w3.org/2000/svg" class="h-4 w-4" fill="currentColor" viewBox="0 0 24 24"> <path d="M12 0c-6.626 0-12 5.373-12 12 0 5.302 3.438 9.8 8.207 11.387.599.111.793-.261.793-.577v-2.234c-3.338.726-4.033-1.416-4.033-1.416-.546-1.387-1.333-1.756-1.333-1.756-1.089-.745.083-.729.083-.729 1.205.084 1.839 1.237 1.839 1.237 1.07 1.834 2.807 1.304 3.492.997.107-.775.418-1.305.762-1.604-2.665-.305-5.467-1.334-5.467-5.931 0-1.311.469-2.381 1.236-3.221-.124-.303-.535-1.524.117-3.176 0 0 1.008-.322 3.301 1.23.957-.266 1.983-.399 3.003-.404 1.02.005 2.047.138 3.006.404 2.291-1.552 3.297-1.23 3.297-1.23.653 1.653.242 2.874.118 3.176.77.84 1.235 1.911 1.235 3.221 0 4.609-2.807 5.624-5.479 5.921.43.372.823 1.102.823 2.222v3.293c0 .319.192.694.801.576 4.765-1.589 8.199-6.086 8.199-11.386 0-6.627-5.373-12-12-12z" /> </svg> </a> </div> </div> </div> </div> <hr class="my-6 h-0.5 border-t-0 opacity-100 dark:opacity-50" style="background-color: rgb(245 245 245/var(--tw-bg-opacity));">
{"license": "other", "tags": ["text-to-image", "stable-diffusion", "stable-diffusion-xl"], "license_name": "faipl-1.0-sd", "license_link": "https://freedevproject.org/faipl-1.0-sd/"}
bluepen5805/pony_pencil-XL
null
[ "text-to-image", "stable-diffusion", "stable-diffusion-xl", "license:other", "region:us" ]
null
2024-05-02T12:32:01+00:00
text-to-image
diffusers
{}
GraydientPlatformAPI/newreality4-sdxl
null
[ "diffusers", "safetensors", "endpoints_compatible", "diffusers:StableDiffusionXLPipeline", "region:us" ]
null
2024-05-02T12:32:10+00:00
null
null
Quantization made by Richard Erkhov. [Github](https://github.com/RichardErkhov) [Discord](https://discord.gg/pvy7H8DZMG) [Request more models](https://github.com/RichardErkhov/quant_request) gemma-7b-it - GGUF - Model creator: https://huggingface.co/google/ - Original model: https://huggingface.co/google/gemma-7b-it/ | Name | Quant method | Size | | ---- | ---- | ---- | | [gemma-7b-it.Q2_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q2_K.gguf) | Q2_K | 3.24GB | | [gemma-7b-it.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.IQ3_XS.gguf) | IQ3_XS | 3.54GB | | [gemma-7b-it.IQ3_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.IQ3_S.gguf) | IQ3_S | 3.71GB | | [gemma-7b-it.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q3_K_S.gguf) | Q3_K_S | 3.71GB | | [gemma-7b-it.IQ3_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.IQ3_M.gguf) | IQ3_M | 3.82GB | | [gemma-7b-it.Q3_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q3_K.gguf) | Q3_K | 4.07GB | | [gemma-7b-it.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q3_K_M.gguf) | Q3_K_M | 4.07GB | | [gemma-7b-it.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q3_K_L.gguf) | Q3_K_L | 4.39GB | | [gemma-7b-it.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.IQ4_XS.gguf) | IQ4_XS | 4.48GB | | [gemma-7b-it.Q4_0.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q4_0.gguf) | Q4_0 | 4.67GB | | [gemma-7b-it.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.IQ4_NL.gguf) | IQ4_NL | 4.69GB | | [gemma-7b-it.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q4_K_S.gguf) | Q4_K_S | 4.7GB | | [gemma-7b-it.Q4_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q4_K.gguf) | Q4_K | 4.96GB | | [gemma-7b-it.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q4_K_M.gguf) | Q4_K_M | 4.96GB | | [gemma-7b-it.Q4_1.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q4_1.gguf) | Q4_1 | 5.12GB | | [gemma-7b-it.Q5_0.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q5_0.gguf) | Q5_0 | 5.57GB | | [gemma-7b-it.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q5_K_S.gguf) | Q5_K_S | 5.57GB | | [gemma-7b-it.Q5_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q5_K.gguf) | Q5_K | 5.72GB | | [gemma-7b-it.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q5_K_M.gguf) | Q5_K_M | 5.72GB | | [gemma-7b-it.Q5_1.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q5_1.gguf) | Q5_1 | 6.02GB | | [gemma-7b-it.Q6_K.gguf](https://huggingface.co/RichardErkhov/google_-_gemma-7b-it-gguf/blob/main/gemma-7b-it.Q6_K.gguf) | Q6_K | 6.53GB | Original model description: --- library_name: transformers tags: [] widget: - messages: - role: user content: How does the brain work? inference: parameters: max_new_tokens: 200 extra_gated_heading: Access Gemma on Hugging Face extra_gated_prompt: >- To access Gemma on Hugging Face, you’re required to review and agree to Google’s usage license. To do this, please ensure you’re logged-in to Hugging Face and click below. Requests are processed immediately. extra_gated_button_content: Acknowledge license license: gemma --- # Gemma Model Card **Model Page**: [Gemma](https://ai.google.dev/gemma/docs) This model card corresponds to the 7B instruct version of the Gemma model. You can also visit the model card of the [2B base model](https://huggingface.co/google/gemma-2b), [7B base model](https://huggingface.co/google/gemma-7b), and [2B instruct model](https://huggingface.co/google/gemma-2b-it). **Resources and Technical Documentation**: * [Responsible Generative AI Toolkit](https://ai.google.dev/responsible) * [Gemma on Kaggle](https://www.kaggle.com/models/google/gemma) * [Gemma on Vertex Model Garden](https://console.cloud.google.com/vertex-ai/publishers/google/model-garden/335?version=gemma-7b-it-gg-hf) **Terms of Use**: [Terms](https://www.kaggle.com/models/google/gemma/license/consent) **Authors**: Google ## Model Information Summary description and brief definition of inputs and outputs. ### Description Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models. They are text-to-text, decoder-only large language models, available in English, with open weights, pre-trained variants, and instruction-tuned variants. Gemma models are well-suited for a variety of text generation tasks, including question answering, summarization, and reasoning. Their relatively small size makes it possible to deploy them in environments with limited resources such as a laptop, desktop or your own cloud infrastructure, democratizing access to state of the art AI models and helping foster innovation for everyone. ### Usage Below we share some code snippets on how to get quickly started with running the model. First make sure to `pip install -U transformers`, then copy the snippet from the section that is relevant for your usecase. #### Fine-tuning the model You can find fine-tuning scripts and notebook under the [`examples/` directory](https://huggingface.co/google/gemma-7b/tree/main/examples) of [`google/gemma-7b`](https://huggingface.co/google/gemma-7b) repository. To adapt it to this model, simply change the model-id to `google/gemma-7b-it`. In that repository, we provide: * A script to perform Supervised Fine-Tuning (SFT) on UltraChat dataset using QLoRA * A script to perform SFT using FSDP on TPU devices * A notebook that you can run on a free-tier Google Colab instance to perform SFT on English quotes dataset #### Running the model on a CPU As explained below, we recommend `torch.bfloat16` as the default dtype. You can use [a different precision](#precisions) if necessary. ```python from transformers import AutoTokenizer, AutoModelForCausalLM import torch tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", torch_dtype=torch.bfloat16 ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` #### Running the model on a single / multi GPU ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM import torch tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", device_map="auto", torch_dtype=torch.bfloat16 ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` <a name="precisions"></a> #### Running the model on a GPU using different precisions The native weights of this model were exported in `bfloat16` precision. You can use `float16`, which may be faster on certain hardware, indicating the `torch_dtype` when loading the model. For convenience, the `float16` revision of the repo contains a copy of the weights already converted to that precision. You can also use `float32` if you skip the dtype, but no precision increase will occur (model weights will just be upcasted to `float32`). See examples below. * _Using `torch.float16`_ ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM import torch tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", device_map="auto", torch_dtype=torch.float16, revision="float16", ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` * _Using `torch.bfloat16`_ ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it", device_map="auto", torch_dtype=torch.bfloat16) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` * _Upcasting to `torch.float32`_ ```python # pip install accelerate from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained( "google/gemma-7b-it", device_map="auto" ) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` #### Quantized Versions through `bitsandbytes` * _Using 8-bit precision (int8)_ ```python # pip install bitsandbytes accelerate from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig quantization_config = BitsAndBytesConfig(load_in_8bit=True) tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it", quantization_config=quantization_config) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` * _Using 4-bit precision_ ```python # pip install bitsandbytes accelerate from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig quantization_config = BitsAndBytesConfig(load_in_4bit=True) tokenizer = AutoTokenizer.from_pretrained("google/gemma-7b-it") model = AutoModelForCausalLM.from_pretrained("google/gemma-7b-it", quantization_config=quantization_config) input_text = "Write me a poem about Machine Learning." input_ids = tokenizer(input_text, return_tensors="pt").to("cuda") outputs = model.generate(**input_ids) print(tokenizer.decode(outputs[0])) ``` #### Other optimizations * _Flash Attention 2_ First make sure to install `flash-attn` in your environment `pip install flash-attn` ```diff model = AutoModelForCausalLM.from_pretrained( model_id, torch_dtype=torch.float16, + attn_implementation="flash_attention_2" ).to(0) ``` ### Chat Template The instruction-tuned models use a chat template that must be adhered to for conversational use. The easiest way to apply it is using the tokenizer's built-in chat template, as shown in the following snippet. Let's load the model and apply the chat template to a conversation. In this example, we'll start with a single user interaction: ```py from transformers import AutoTokenizer, AutoModelForCausalLM import transformers import torch model_id = "google/gemma-7b-it" dtype = torch.bfloat16 tokenizer = AutoTokenizer.from_pretrained(model_id) model = AutoModelForCausalLM.from_pretrained( model_id, device_map="cuda", torch_dtype=dtype, ) chat = [ { "role": "user", "content": "Write a hello world program" }, ] prompt = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) ``` At this point, the prompt contains the following text: ``` <bos><start_of_turn>user Write a hello world program<end_of_turn> <start_of_turn>model ``` As you can see, each turn is preceded by a `<start_of_turn>` delimiter and then the role of the entity (either `user`, for content supplied by the user, or `model` for LLM responses). Turns finish with the `<end_of_turn>` token. You can follow this format to build the prompt manually, if you need to do it without the tokenizer's chat template. After the prompt is ready, generation can be performed like this: ```py inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt") outputs = model.generate(input_ids=inputs.to(model.device), max_new_tokens=150) print(tokenizer.decode(outputs[0])) ``` ### Inputs and outputs * **Input:** Text string, such as a question, a prompt, or a document to be summarized. * **Output:** Generated English-language text in response to the input, such as an answer to a question, or a summary of a document. ## Model Data Data used for model training and how the data was processed. ### Training Dataset These models were trained on a dataset of text data that includes a wide variety of sources, totaling 6 trillion tokens. Here are the key components: * Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. Primarily English-language content. * Code: Exposing the model to code helps it to learn the syntax and patterns of programming languages, which improves its ability to generate code or understand code-related questions. * Mathematics: Training on mathematical text helps the model learn logical reasoning, symbolic representation, and to address mathematical queries. The combination of these diverse data sources is crucial for training a powerful language model that can handle a wide variety of different tasks and text formats. ### Data Preprocessing Here are the key data cleaning and filtering methods applied to the training data: * CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was applied at multiple stages in the data preparation process to ensure the exclusion of harmful and illegal content * Sensitive Data Filtering: As part of making Gemma pre-trained models safe and reliable, automated techniques were used to filter out certain personal information and other sensitive data from training sets. * Additional methods: Filtering based on content quality and safely in line with [our policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11). ## Implementation Information Details about the model internals. ### Hardware Gemma was trained using the latest generation of [Tensor Processing Unit (TPU)](https://cloud.google.com/tpu/docs/intro-to-tpu) hardware (TPUv5e). Training large language models requires significant computational power. TPUs, designed specifically for matrix operations common in machine learning, offer several advantages in this domain: * Performance: TPUs are specifically designed to handle the massive computations involved in training LLMs. They can speed up training considerably compared to CPUs. * Memory: TPUs often come with large amounts of high-bandwidth memory, allowing for the handling of large models and batch sizes during training. This can lead to better model quality. * Scalability: TPU Pods (large clusters of TPUs) provide a scalable solution for handling the growing complexity of large foundation models. You can distribute training across multiple TPU devices for faster and more efficient processing. * Cost-effectiveness: In many scenarios, TPUs can provide a more cost-effective solution for training large models compared to CPU-based infrastructure, especially when considering the time and resources saved due to faster training. * These advantages are aligned with [Google's commitments to operate sustainably](https://sustainability.google/operating-sustainably/). ### Software Training was done using [JAX](https://github.com/google/jax) and [ML Pathways](https://blog.google/technology/ai/introducing-pathways-next-generation-ai-architecture). JAX allows researchers to take advantage of the latest generation of hardware, including TPUs, for faster and more efficient training of large models. ML Pathways is Google's latest effort to build artificially intelligent systems capable of generalizing across multiple tasks. This is specially suitable for [foundation models](https://ai.google/discover/foundation-models/), including large language models like these ones. Together, JAX and ML Pathways are used as described in the [paper about the Gemini family of models](https://arxiv.org/abs/2312.11805); "the 'single controller' programming model of Jax and Pathways allows a single Python process to orchestrate the entire training run, dramatically simplifying the development workflow." ## Evaluation Model evaluation metrics and results. ### Benchmark Results These models were evaluated against a large collection of different datasets and metrics to cover different aspects of text generation: | Benchmark | Metric | 2B Params | 7B Params | | ------------------------------ | ------------- | ----------- | --------- | | [MMLU](https://arxiv.org/abs/2009.03300) | 5-shot, top-1 | 42.3 | 64.3 | | [HellaSwag](https://arxiv.org/abs/1905.07830) | 0-shot |71.4 | 81.2 | | [PIQA](https://arxiv.org/abs/1911.11641) | 0-shot | 77.3 | 81.2 | | [SocialIQA](https://arxiv.org/abs/1904.09728) | 0-shot | 49.7 | 51.8 | | [BooIQ](https://arxiv.org/abs/1905.10044) | 0-shot | 69.4 | 83.2 | | [WinoGrande](https://arxiv.org/abs/1907.10641) | partial score | 65.4 | 72.3 | | [CommonsenseQA](https://arxiv.org/abs/1811.00937) | 7-shot | 65.3 | 71.3 | | [OpenBookQA](https://arxiv.org/abs/1809.02789) | | 47.8 | 52.8 | | [ARC-e](https://arxiv.org/abs/1911.01547) | | 73.2 | 81.5 | | [ARC-c](https://arxiv.org/abs/1911.01547) | | 42.1 | 53.2 | | [TriviaQA](https://arxiv.org/abs/1705.03551) | 5-shot | 53.2 | 63.4 | | [Natural Questions](https://github.com/google-research-datasets/natural-questions) | 5-shot | 12.5 | 23 | | [HumanEval](https://arxiv.org/abs/2107.03374) | pass@1 | 22.0 | 32.3 | | [MBPP](https://arxiv.org/abs/2108.07732) | 3-shot | 29.2 | 44.4 | | [GSM8K](https://arxiv.org/abs/2110.14168) | maj@1 | 17.7 | 46.4 | | [MATH](https://arxiv.org/abs/2108.07732) | 4-shot | 11.8 | 24.3 | | [AGIEval](https://arxiv.org/abs/2304.06364) | | 24.2 | 41.7 | | [BIG-Bench](https://arxiv.org/abs/2206.04615) | | 35.2 | 55.1 | | ------------------------------ | ------------- | ----------- | --------- | | **Average** | | **45.0** | **56.9** | ## Ethics and Safety Ethics and safety evaluation approach and results. ### Evaluation Approach Our evaluation methods include structured evaluations and internal red-teaming testing of relevant content policies. Red-teaming was conducted by a number of different teams, each with different goals and human evaluation metrics. These models were evaluated against a number of different categories relevant to ethics and safety, including: * Text-to-Text Content Safety: Human evaluation on prompts covering safety policies including child sexual abuse and exploitation, harassment, violence and gore, and hate speech. * Text-to-Text Representational Harms: Benchmark against relevant academic datasets such as [WinoBias](https://arxiv.org/abs/1804.06876) and [BBQ Dataset](https://arxiv.org/abs/2110.08193v2). * Memorization: Automated evaluation of memorization of training data, including the risk of personally identifiable information exposure. * Large-scale harm: Tests for "dangerous capabilities," such as chemical, biological, radiological, and nuclear (CBRN) risks. ### Evaluation Results The results of ethics and safety evaluations are within acceptable thresholds for meeting [internal policies](https://storage.googleapis.com/gweb-uniblog-publish-prod/documents/2023_Google_AI_Principles_Progress_Update.pdf#page=11) for categories such as child safety, content safety, representational harms, memorization, large-scale harms. On top of robust internal evaluations, the results of well known safety benchmarks like BBQ, BOLD, Winogender, Winobias, RealToxicity, and TruthfulQA are shown here. | Benchmark | Metric | 2B Params | 7B Params | | ------------------------------ | ------------- | ----------- | --------- | | [RealToxicity](https://arxiv.org/abs/2009.11462) | average | 6.86 | 7.90 | | [BOLD](https://arxiv.org/abs/2101.11718) | | 45.57 | 49.08 | | [CrowS-Pairs](https://aclanthology.org/2020.emnlp-main.154/) | top-1 | 45.82 | 51.33 | | [BBQ Ambig](https://arxiv.org/abs/2110.08193v2) | 1-shot, top-1 | 62.58 | 92.54 | | [BBQ Disambig](https://arxiv.org/abs/2110.08193v2) | top-1 | 54.62 | 71.99 | | [Winogender](https://arxiv.org/abs/1804.09301) | top-1 | 51.25 | 54.17 | | [TruthfulQA](https://arxiv.org/abs/2109.07958) | | 44.84 | 31.81 | | [Winobias 1_2](https://arxiv.org/abs/1804.06876) | | 56.12 | 59.09 | | [Winobias 2_2](https://arxiv.org/abs/1804.06876) | | 91.10 | 92.23 | | [Toxigen](https://arxiv.org/abs/2203.09509) | | 29.77 | 39.59 | | ------------------------------ | ------------- | ----------- | --------- | ## Usage and Limitations These models have certain limitations that users should be aware of. ### Intended Usage Open Large Language Models (LLMs) have a wide range of applications across various industries and domains. The following list of potential uses is not comprehensive. The purpose of this list is to provide contextual information about the possible use-cases that the model creators considered as part of model training and development. * Content Creation and Communication * Text Generation: These models can be used to generate creative text formats such as poems, scripts, code, marketing copy, and email drafts. * Chatbots and Conversational AI: Power conversational interfaces for customer service, virtual assistants, or interactive applications. * Text Summarization: Generate concise summaries of a text corpus, research papers, or reports. * Research and Education * Natural Language Processing (NLP) Research: These models can serve as a foundation for researchers to experiment with NLP techniques, develop algorithms, and contribute to the advancement of the field. * Language Learning Tools: Support interactive language learning experiences, aiding in grammar correction or providing writing practice. * Knowledge Exploration: Assist researchers in exploring large bodies of text by generating summaries or answering questions about specific topics. ### Limitations * Training Data * The quality and diversity of the training data significantly influence the model's capabilities. Biases or gaps in the training data can lead to limitations in the model's responses. * The scope of the training dataset determines the subject areas the model can handle effectively. * Context and Task Complexity * LLMs are better at tasks that can be framed with clear prompts and instructions. Open-ended or highly complex tasks might be challenging. * A model's performance can be influenced by the amount of context provided (longer context generally leads to better outputs, up to a certain point). * Language Ambiguity and Nuance * Natural language is inherently complex. LLMs might struggle to grasp subtle nuances, sarcasm, or figurative language. * Factual Accuracy * LLMs generate responses based on information they learned from their training datasets, but they are not knowledge bases. They may generate incorrect or outdated factual statements. * Common Sense * LLMs rely on statistical patterns in language. They might lack the ability to apply common sense reasoning in certain situations. ### Ethical Considerations and Risks The development of large language models (LLMs) raises several ethical concerns. In creating an open model, we have carefully considered the following: * Bias and Fairness * LLMs trained on large-scale, real-world text data can reflect socio-cultural biases embedded in the training material. These models underwent careful scrutiny, input data pre-processing described and posterior evaluations reported in this card. * Misinformation and Misuse * LLMs can be misused to generate text that is false, misleading, or harmful. * Guidelines are provided for responsible use with the model, see the [Responsible Generative AI Toolkit](http://ai.google.dev/gemma/responsible). * Transparency and Accountability: * This model card summarizes details on the models' architecture, capabilities, limitations, and evaluation processes. * A responsibly developed open model offers the opportunity to share innovation by making LLM technology accessible to developers and researchers across the AI ecosystem. Risks identified and mitigations: * Perpetuation of biases: It's encouraged to perform continuous monitoring (using evaluation metrics, human review) and the exploration of de-biasing techniques during model training, fine-tuning, and other use cases. * Generation of harmful content: Mechanisms and guidelines for content safety are essential. Developers are encouraged to exercise caution and implement appropriate content safety safeguards based on their specific product policies and application use cases. * Misuse for malicious purposes: Technical limitations and developer and end-user education can help mitigate against malicious applications of LLMs. Educational resources and reporting mechanisms for users to flag misuse are provided. Prohibited uses of Gemma models are outlined in the [Gemma Prohibited Use Policy](https://ai.google.dev/gemma/prohibited_use_policy). * Privacy violations: Models were trained on data filtered for removal of PII (Personally Identifiable Information). Developers are encouraged to adhere to privacy regulations with privacy-preserving techniques. ### Benefits At the time of release, this family of models provides high-performance open large language model implementations designed from the ground up for Responsible AI development compared to similarly sized models. Using the benchmark evaluation metrics described in this document, these models have shown to provide superior performance to other, comparably-sized open model alternatives.
{}
RichardErkhov/google_-_gemma-7b-it-gguf
null
[ "gguf", "arxiv:2312.11805", "arxiv:2009.03300", "arxiv:1905.07830", "arxiv:1911.11641", "arxiv:1904.09728", "arxiv:1905.10044", "arxiv:1907.10641", "arxiv:1811.00937", "arxiv:1809.02789", "arxiv:1911.01547", "arxiv:1705.03551", "arxiv:2107.03374", "arxiv:2108.07732", "arxiv:2110.14168", "arxiv:2304.06364", "arxiv:2206.04615", "arxiv:1804.06876", "arxiv:2110.08193", "arxiv:2009.11462", "arxiv:2101.11718", "arxiv:1804.09301", "arxiv:2109.07958", "arxiv:2203.09509", "region:us" ]
null
2024-05-02T12:33:49+00:00
null
null
{}
M17idd/bert-finetuned-squad
null
[ "region:us" ]
null
2024-05-02T12:35:05+00:00
null
transformers
# Uploaded model - **Developed by:** grabbysingh - **License:** apache-2.0 - **Finetuned from model :** unsloth/Phi-3-mini-4k-instruct-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"], "base_model": "unsloth/Phi-3-mini-4k-instruct-bnb-4bit"}
grabbysingh/phi_3_mini_4k_personality_lora
null
[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:unsloth/Phi-3-mini-4k-instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:35:14+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/model42
null
[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:35:21+00:00
feature-extraction
transformers.js
https://huggingface.co/intfloat/multilingual-e5-large with ONNX weights to be compatible with Transformers.js.
{"license": "mit", "library_name": "transformers.js", "pipeline_tag": "feature-extraction"}
sirius422/multilingual-e5-large-onnx
null
[ "transformers.js", "onnx", "xlm-roberta", "feature-extraction", "license:mit", "region:us" ]
null
2024-05-02T12:35:24+00:00
null
null
{}
mayukhbis/outputs
null
[ "region:us" ]
null
2024-05-02T12:36:09+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. --> # Llama-2-7b-hf-threapist-DPO-version-1.1 This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 1 - eval_batch_size: 1 - seed: 42 - gradient_accumulation_steps: 2 - total_train_batch_size: 2 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 10 - num_epochs: 1 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.3.0+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "llama2", "library_name": "peft", "tags": ["trl", "dpo", "generated_from_trainer"], "base_model": "meta-llama/Llama-2-7b-hf", "model-index": [{"name": "Llama-2-7b-hf-threapist-DPO-version-1.1", "results": []}]}
LBK95/Llama-2-7b-hf-threapist-DPO-version-1.1
null
[ "peft", "safetensors", "trl", "dpo", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-hf", "license:llama2", "region:us" ]
null
2024-05-02T12:38:46+00:00
reinforcement-learning
null
# **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
{"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-cartpole", "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}]}]}]}
ilanasto/Reinforce-cartpole
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
null
2024-05-02T12:38:52+00:00
text-generation
null
# [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3-GGUF) - Model creator: [MaziyarPanahi](https://huggingface.co/MaziyarPanahi) - Original model: [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3) ## Description [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3-GGUF](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3-GGUF) contains GGUF format model files for [MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3](https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3). IMPORTANT: There is no need to merge the splits. By now, most libraries support automatically loading the splits by simply pointing to the first one. ### About GGUF GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp. Here is an incomplete list of clients and libraries that are known to support GGUF: * [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option. * [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server. * [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023. * [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration. * [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling. * [GPT4All](https://gpt4all.io/index.html), a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel. * [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection. * [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration. * [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use. * [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models. ## Special thanks 🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.
{"tags": ["quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "text-generation"], "model_name": "Llama-3-70B-Instruct-DPO-v0.3-GGUF", "base_model": "MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3", "inference": false, "model_creator": "MaziyarPanahi", "pipeline_tag": "text-generation", "quantized_by": "MaziyarPanahi"}
MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3-GGUF
null
[ "gguf", "quantized", "2-bit", "3-bit", "4-bit", "5-bit", "6-bit", "8-bit", "GGUF", "text-generation", "llama", "llama-3", "base_model:MaziyarPanahi/Llama-3-70B-Instruct-DPO-v0.3", "region:us" ]
null
2024-05-02T12:39:15+00:00
reinforcement-learning
null
# **Reinforce** Agent playing **CartPole-v1** This is a trained model of a **Reinforce** agent playing **CartPole-v1** . To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
{"tags": ["CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class"], "model-index": [{"name": "Reinforce-CartPole-v1", "results": [{"task": {"type": "reinforcement-learning", "name": "reinforcement-learning"}, "dataset": {"name": "CartPole-v1", "type": "CartPole-v1"}, "metrics": [{"type": "mean_reward", "value": "381.60 +/- 147.11", "name": "mean_reward", "verified": false}]}]}]}
ArnavModanwal/Reinforce-CartPole-v1
null
[ "CartPole-v1", "reinforce", "reinforcement-learning", "custom-implementation", "deep-rl-class", "model-index", "region:us" ]
null
2024-05-02T12:39:27+00:00
null
null
{"license": "mit"}
GHGGZY/wangkeai
null
[ "license:mit", "region:us" ]
null
2024-05-02T12:39:30+00:00
null
peft
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # llama3-fine-tuned-5e This model is a fine-tuned version of [unsloth/llama-3-8b-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-bnb-4bit) 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: 0.0002 - train_batch_size: 4 - eval_batch_size: 8 - seed: 3407 - gradient_accumulation_steps: 4 - 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: 5 - num_epochs: 5 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.2.1+cu121 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "llama2", "library_name": "peft", "tags": ["trl", "sft", "unsloth", "generated_from_trainer"], "base_model": "unsloth/llama-3-8b-bnb-4bit", "model-index": [{"name": "llama3-fine-tuned-5e", "results": []}]}
mayukhbis/llama3-fine-tuned-5e
null
[ "peft", "tensorboard", "safetensors", "trl", "sft", "unsloth", "generated_from_trainer", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:llama2", "region:us" ]
null
2024-05-02T12:39:37+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. --> # bert-scam-classifier-v1 This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.0290 - Accuracy: {'accuracy': 1.0} - Precision: {'precision': 1.0} - Recall: {'recall': 1.0} - F1: {'f1': 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: 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: 2 ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-----:|:----:|:---------------:|:-----------------:|:------------------:|:---------------:|:-----------:| | No log | 1.0 | 40 | 0.1046 | {'accuracy': 1.0} | {'precision': 1.0} | {'recall': 1.0} | {'f1': 1.0} | | No log | 2.0 | 80 | 0.0290 | {'accuracy': 1.0} | {'precision': 1.0} | {'recall': 1.0} | {'f1': 1.0} | ### 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"], "metrics": ["accuracy", "precision", "recall", "f1"], "base_model": "google-bert/bert-base-uncased", "model-index": [{"name": "bert-scam-classifier-v1", "results": []}]}
BothBosu/bert-scam-classifier-v1
null
[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "generated_from_trainer", "base_model:google-bert/bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:39:40+00:00
text-classification
transformers
# Model Trained Using AutoTrain - Problem type: Text Classification ## Validation Metrics loss: 0.5613215565681458 f1_macro: 0.7270965370193369 f1_micro: 0.7587301587301587 f1_weighted: 0.7500760798400677 precision_macro: 0.7107159142726859 precision_micro: 0.7587301587301587 precision_weighted: 0.7611013397607105 recall_macro: 0.777733466267863 recall_micro: 0.7587301587301587 recall_weighted: 0.7587301587301587 accuracy: 0.7587301587301587
{"tags": ["autotrain", "text-classification"], "datasets": ["v14/autotrain-data"], "widget": [{"text": "I love AutoTrain"}]}
Zerithas/v14
null
[ "transformers", "tensorboard", "safetensors", "bert", "text-classification", "autotrain", "dataset:v14/autotrain-data", "autotrain_compatible", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:39:46+00:00
null
null
{"license": "openrail"}
Adnan1361/mobuvyc
null
[ "license:openrail", "region:us" ]
null
2024-05-02T12:40:33+00:00
null
peft
<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # Llama3_finetued_on_charttotext_v2 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset. ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 0.0001 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: constant - lr_scheduler_warmup_ratio: 0.03 - num_epochs: 30 ### Training results ### Framework versions - PEFT 0.10.0 - Transformers 4.40.1 - Pytorch 2.1.2 - Datasets 2.19.0 - Tokenizers 0.19.1
{"license": "other", "library_name": "peft", "tags": ["trl", "sft", "generated_from_trainer"], "base_model": "meta-llama/Meta-Llama-3-8B-Instruct", "model-index": [{"name": "Llama3_finetued_on_charttotext_v2", "results": []}]}
moetezsa/Llama3_finetued_on_charttotext_v2
null
[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]
null
2024-05-02T12:40:44+00:00
null
transformers
## About <!-- ### quantize_version: 2 --> <!-- ### output_tensor_quantised: 1 --> <!-- ### convert_type: hfhfix --> <!-- ### vocab_type: --> static quants of https://huggingface.co/NousResearch/Meta-Llama-3-70B <!-- provided-files --> weighted/imatrix quants are available at https://huggingface.co/mradermacher/Meta-Llama-3-70B-i1-GGUF ## 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/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q2_K.gguf) | Q2_K | 26.5 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.IQ3_XS.gguf) | IQ3_XS | 29.4 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.IQ3_S.gguf) | IQ3_S | 31.0 | beats Q3_K* | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q3_K_S.gguf) | Q3_K_S | 31.0 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.IQ3_M.gguf) | IQ3_M | 32.0 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q3_K_M.gguf) | Q3_K_M | 34.4 | lower quality | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q3_K_L.gguf) | Q3_K_L | 37.2 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.IQ4_XS.gguf) | IQ4_XS | 38.4 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q4_K_S.gguf) | Q4_K_S | 40.4 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q4_K_M.gguf) | Q4_K_M | 42.6 | fast, recommended | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q5_K_S.gguf) | Q5_K_S | 48.8 | | | [GGUF](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q5_K_M.gguf) | Q5_K_M | 50.0 | | | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q6_K.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q6_K.gguf.part2of2) | Q6_K | 58.0 | very good quality | | [PART 1](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q8_0.gguf.part1of2) [PART 2](https://huggingface.co/mradermacher/Meta-Llama-3-70B-GGUF/resolve/main/Meta-Llama-3-70B.Q8_0.gguf.part2of2) | Q8_0 | 75.1 | 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": "other", "library_name": "transformers", "tags": ["facebook", "meta", "pytorch", "llama", "llama-3"], "base_model": "NousResearch/Meta-Llama-3-70B", "extra_gated_button_content": "Submit", "extra_gated_fields": {"Affiliation": "text", "By clicking Submit below I accept the terms of the license and acknowledge that the information I provide will be collected stored processed and shared in accordance with the Meta Privacy Policy": "checkbox", "Country": "country", "Date of birth": "date_picker", "First Name": "text", "Last Name": "text", "geo": "ip_location"}, "extra_gated_prompt": "### META LLAMA 3 COMMUNITY LICENSE AGREEMENT\nMeta Llama 3 Version Release Date: April 18, 2024\n\"Agreement\" means the terms and conditions for use, reproduction, distribution and modification of the Llama Materials set forth herein.\n\"Documentation\" means the specifications, manuals and documentation accompanying Meta Llama 3 distributed by Meta at https://llama.meta.com/get-started/.\n\"Licensee\" or \"you\" means you, or your employer or any other person or entity (if you are entering into this Agreement on such person or entity\u2019s behalf), of the age required under applicable laws, rules or regulations to provide legal consent and that has legal authority to bind your employer or such other person or entity if you are entering in this Agreement on their behalf.\n\"Meta Llama 3\" means the foundational large language models and software and algorithms, including machine-learning model code, trained model weights, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Meta at https://llama.meta.com/llama-downloads.\n\"Llama Materials\" means, collectively, Meta\u2019s proprietary Meta Llama 3 and Documentation (and any portion thereof) made available under this Agreement.\n\"Meta\" or \"we\" means Meta Platforms Ireland Limited (if you are located in or, if you are an entity, your principal place of business is in the EEA or Switzerland) and Meta Platforms, Inc. (if you are located outside of the EEA or Switzerland).\n \n1. License Rights and Redistribution.\na. Grant of Rights. You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Meta\u2019s intellectual property or other rights owned by Meta embodied in the Llama Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Llama Materials.\nb. Redistribution and Use.\ni. If you distribute or make available the Llama Materials (or any derivative works thereof), or a product or service that uses any of them, including another AI model, you shall (A) provide a copy of this Agreement with any such Llama Materials; and (B) prominently display \u201cBuilt with Meta Llama 3\u201d on a related website, user interface, blogpost, about page, or product documentation. If you use the Llama Materials to create, train, fine tune, or otherwise improve an AI model, which is distributed or made available, you shall also include \u201cLlama 3\u201d at the beginning of any such AI model name.\nii. If you receive Llama Materials, or any derivative works thereof, from a Licensee as part of an integrated end user product, then Section 2 of this Agreement will not apply to you.\niii. You must retain in all copies of the Llama Materials that you distribute the following attribution notice within a \u201cNotice\u201d text file distributed as a part of such copies: \u201cMeta Llama 3 is licensed under the Meta Llama 3 Community License, Copyright \u00a9 Meta Platforms, Inc. All Rights Reserved.\u201d\niv. Your use of the Llama Materials must comply with applicable laws and regulations (including trade compliance laws and regulations) and adhere to the Acceptable Use Policy for the Llama Materials (available at https://llama.meta.com/llama3/use-policy), which is hereby incorporated by reference into this Agreement.\nv. You will not use the Llama Materials or any output or results of the Llama Materials to improve any other large language model (excluding Meta Llama 3 or derivative works thereof).\n2. Additional Commercial Terms. If, on the Meta Llama 3 version release date, the monthly active users of the products or services made available by or for Licensee, or Licensee\u2019s affiliates, is greater than 700 million monthly active users in the preceding calendar month, you must request a license from Meta, which Meta may grant to you in its sole discretion, and you are not authorized to exercise any of the rights under this Agreement unless or until Meta otherwise expressly grants you such rights.\n3. Disclaimer of Warranty. UNLESS REQUIRED BY APPLICABLE LAW, THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS THEREFROM ARE PROVIDED ON AN \u201cAS IS\u201d BASIS, WITHOUT WARRANTIES OF ANY KIND, AND META DISCLAIMS ALL WARRANTIES OF ANY KIND, BOTH EXPRESS AND IMPLIED, INCLUDING, WITHOUT LIMITATION, ANY WARRANTIES OF TITLE, NON-INFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE. YOU ARE SOLELY RESPONSIBLE FOR DETERMINING THE APPROPRIATENESS OF USING OR REDISTRIBUTING THE LLAMA MATERIALS AND ASSUME ANY RISKS ASSOCIATED WITH YOUR USE OF THE LLAMA MATERIALS AND ANY OUTPUT AND RESULTS.\n4. Limitation of Liability. IN NO EVENT WILL META OR ITS AFFILIATES BE LIABLE UNDER ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, TORT, NEGLIGENCE, PRODUCTS LIABILITY, OR OTHERWISE, ARISING OUT OF THIS AGREEMENT, FOR ANY LOST PROFITS OR ANY INDIRECT, SPECIAL, CONSEQUENTIAL, INCIDENTAL, EXEMPLARY OR PUNITIVE DAMAGES, EVEN IF META OR ITS AFFILIATES HAVE BEEN ADVISED OF THE POSSIBILITY OF ANY OF THE FOREGOING.\n5. Intellectual Property.\na. No trademark licenses are granted under this Agreement, and in connection with the Llama Materials, neither Meta nor Licensee may use any name or mark owned by or associated with the other or any of its affiliates, except as required for reasonable and customary use in describing and redistributing the Llama Materials or as set forth in this Section 5(a). Meta hereby grants you a license to use \u201cLlama 3\u201d (the \u201cMark\u201d) solely as required to comply with the last sentence of Section 1.b.i. You will comply with Meta\u2019s brand guidelines (currently accessible at https://about.meta.com/brand/resources/meta/company-brand/ ). All goodwill arising out of your use of the Mark will inure to the benefit of Meta.\nb. Subject to Meta\u2019s ownership of Llama Materials and derivatives made by or for Meta, with respect to any derivative works and modifications of the Llama Materials that are made by you, as between you and Meta, you are and will be the owner of such derivative works and modifications.\nc. If you institute litigation or other proceedings against Meta or any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Llama Materials or Meta Llama 3 outputs or results, or any portion of any of the foregoing, constitutes infringement of intellectual property or other rights owned or licensable by you, then any licenses granted to you under this Agreement shall terminate as of the date such litigation or claim is filed or instituted. You will indemnify and hold harmless Meta from and against any claim by any third party arising out of or related to your use or distribution of the Llama Materials.\n6. Term and Termination. The term of this Agreement will commence upon your acceptance of this Agreement or access to the Llama Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein. Meta may terminate this Agreement if you are in breach of any term or condition of this Agreement. Upon termination of this Agreement, you shall delete and cease use of the Llama Materials. Sections 3, 4 and 7 shall survive the termination of this Agreement.\n7. Governing Law and Jurisdiction. This Agreement will be governed and construed under the laws of the State of California without regard to choice of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement. The courts of California shall have exclusive jurisdiction of any dispute arising out of this Agreement.\n### Meta Llama 3 Acceptable Use Policy\nMeta is committed to promoting safe and fair use of its tools and features, including Meta Llama 3. If you access or use Meta Llama 3, you agree to this Acceptable Use Policy (\u201cPolicy\u201d). The most recent copy of this policy can be found at [https://llama.meta.com/llama3/use-policy](https://llama.meta.com/llama3/use-policy)\n#### Prohibited Uses\nWe want everyone to use Meta Llama 3 safely and responsibly. You agree you will not use, or allow others to use, Meta Llama 3 to: 1. Violate the law or others\u2019 rights, including to:\n 1. Engage in, promote, generate, contribute to, encourage, plan, incite, or further illegal or unlawful activity or content, such as:\n 1. Violence or terrorism\n 2. Exploitation or harm to children, including the solicitation, creation, acquisition, or dissemination of child exploitative content or failure to report Child Sexual Abuse Material\n 3. Human trafficking, exploitation, and sexual violence\n 4. The illegal distribution of information or materials to minors, including obscene materials, or failure to employ legally required age-gating in connection with such information or materials.\n 5. Sexual solicitation\n 6. Any other criminal activity\n 2. Engage in, promote, incite, or facilitate the harassment, abuse, threatening, or bullying of individuals or groups of individuals\n 3. Engage in, promote, incite, or facilitate discrimination or other unlawful or harmful conduct in the provision of employment, employment benefits, credit, housing, other economic benefits, or other essential goods and services\n 4. Engage in the unauthorized or unlicensed practice of any profession including, but not limited to, financial, legal, medical/health, or related professional practices\n 5. Collect, process, disclose, generate, or infer health, demographic, or other sensitive personal or private information about individuals without rights and consents required by applicable laws\n 6. Engage in or facilitate any action or generate any content that infringes, misappropriates, or otherwise violates any third-party rights, including the outputs or results of any products or services using the Llama Materials\n 7. Create, generate, or facilitate the creation of malicious code, malware, computer viruses or do anything else that could disable, overburden, interfere with or impair the proper working, integrity, operation or appearance of a website or computer system\n2. Engage in, promote, incite, facilitate, or assist in the planning or development of activities that present a risk of death or bodily harm to individuals, including use of Meta Llama 3 related to the following:\n 1. Military, warfare, nuclear industries or applications, espionage, use for materials or activities that are subject to the International Traffic Arms Regulations (ITAR) maintained by the United States Department of State\n 2. Guns and illegal weapons (including weapon development)\n 3. Illegal drugs and regulated/controlled substances\n 4. Operation of critical infrastructure, transportation technologies, or heavy machinery\n 5. Self-harm or harm to others, including suicide, cutting, and eating disorders\n 6. Any content intended to incite or promote violence, abuse, or any infliction of bodily harm to an individual\n3. Intentionally deceive or mislead others, including use of Meta Llama 3 related to the following:\n 1. Generating, promoting, or furthering fraud or the creation or promotion of disinformation\n 2. Generating, promoting, or furthering defamatory content, including the creation of defamatory statements, images, or other content\n 3. Generating, promoting, or further distributing spam\n 4. Impersonating another individual without consent, authorization, or legal right\n 5. Representing that the use of Meta Llama 3 or outputs are human-generated\n 6. Generating or facilitating false online engagement, including fake reviews and other means of fake online engagement\n4. Fail to appropriately disclose to end users any known dangers of your AI system\nPlease report any violation of this Policy, software \u201cbug,\u201d or other problems that could lead to a violation of this Policy through one of the following means:\n * Reporting issues with the model: [https://github.com/meta-llama/llama3](https://github.com/meta-llama/llama3)\n * Reporting risky content generated by the model:\n developers.facebook.com/llama_output_feedback\n * Reporting bugs and security concerns: facebook.com/whitehat/info\n * Reporting violations of the Acceptable Use Policy or unlicensed uses of Meta Llama 3: [email protected]", "license_link": "LICENSE", "license_name": "llama3", "quantized_by": "mradermacher"}
mradermacher/Meta-Llama-3-70B-GGUF
null
[ "transformers", "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "en", "base_model:NousResearch/Meta-Llama-3-70B", "license:other", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:41:59+00:00
sentence-similarity
sentence-transformers
# SentenceTransformer based on sentence-transformers/stsb-distilbert-base This is a [sentence-transformers](https://www.SBERT.net) model finetuned from [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) on the [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) and [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) datasets. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more. ## Model Details ### Model Description - **Model Type:** Sentence Transformer - **Base model:** [sentence-transformers/stsb-distilbert-base](https://huggingface.co/sentence-transformers/stsb-distilbert-base) <!-- at revision 82ad392c08f81be9be9bf065339670b23f2e1493 --> - **Maximum Sequence Length:** 128 tokens - **Output Dimensionality:** 768 tokens - **Similarity Function:** Cosine Similarity - **Training Datasets:** - [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) - **Language:** en <!-- - **License:** Unknown --> ### Model Sources - **Documentation:** [Sentence Transformers Documentation](https://sbert.net) - **Repository:** [Sentence Transformers on GitHub](https://github.com/UKPLab/sentence-transformers) - **Hugging Face:** [Sentence Transformers on Hugging Face](https://huggingface.co/models?library=sentence-transformers) ### Full Model Architecture ``` SentenceTransformer( (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: DistilBertModel (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True}) ) ``` ## Usage ### Direct Usage (Sentence Transformers) First install the Sentence Transformers library: ```bash pip install -U sentence-transformers ``` Then you can load this model and run inference. ```python from sentence_transformers import SentenceTransformer # Download from the 🤗 Hub model = SentenceTransformer("tomaarsen/stsb-distilbert-base-mnrl-cl-multi") # Run inference sentences = [ 'How fast is fast?', 'How does light travel so fast?', 'How do I copyright my books?', ] embeddings = model.encode(sentences) print(embeddings.shape) # [3, 768] # Get the similarity scores for the embeddings similarities = model.similarity(embeddings) print(similarities.shape) # [3, 3] ``` <!-- ### Direct Usage (Transformers) <details><summary>Click to see the direct usage in Transformers</summary> </details> --> <!-- ### Downstream Usage (Sentence Transformers) You can finetune this model on your own dataset. <details><summary>Click to expand</summary> </details> --> <!-- ### Out-of-Scope Use *List how the model may foreseeably be misused and address what users ought not to do with the model.* --> ## Evaluation ### Metrics #### Binary Classification * Dataset: `quora-duplicates` * Evaluated with [<code>BinaryClassificationEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.BinaryClassificationEvaluator) | Metric | Value | |:-----------------------------|:----------| | cosine_accuracy | 0.846 | | cosine_accuracy_threshold | 0.7969 | | cosine_f1 | 0.7791 | | cosine_f1_threshold | 0.714 | | cosine_precision | 0.6978 | | cosine_recall | 0.882 | | cosine_ap | 0.823 | | dot_accuracy | 0.843 | | dot_accuracy_threshold | 151.2908 | | dot_f1 | 0.7661 | | dot_f1_threshold | 143.7784 | | dot_precision | 0.7238 | | dot_recall | 0.8137 | | dot_ap | 0.7946 | | manhattan_accuracy | 0.838 | | manhattan_accuracy_threshold | 194.9912 | | manhattan_f1 | 0.7704 | | manhattan_f1_threshold | 247.4978 | | manhattan_precision | 0.6537 | | manhattan_recall | 0.9379 | | manhattan_ap | 0.815 | | euclidean_accuracy | 0.841 | | euclidean_accuracy_threshold | 9.0223 | | euclidean_f1 | 0.7704 | | euclidean_f1_threshold | 11.3852 | | euclidean_precision | 0.6463 | | euclidean_recall | 0.9534 | | euclidean_ap | 0.8153 | | max_accuracy | 0.846 | | max_accuracy_threshold | 194.9912 | | max_f1 | 0.7791 | | max_f1_threshold | 247.4978 | | max_precision | 0.7238 | | max_recall | 0.9534 | | **max_ap** | **0.823** | #### Paraphrase Mining * Dataset: `quora-duplicates-dev` * Evaluated with [<code>ParaphraseMiningEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.ParaphraseMiningEvaluator) | Metric | Value | |:----------------------|:-----------| | **average_precision** | **0.5889** | | f1 | 0.5762 | | precision | 0.5478 | | recall | 0.6077 | | threshold | 0.7729 | #### Information Retrieval * Evaluated with [<code>InformationRetrievalEvaluator</code>](https://sbert.net/docs/package_reference/evaluation.html#sentence_transformers.evaluation.InformationRetrievalEvaluator) | Metric | Value | |:--------------------|:-----------| | cosine_accuracy@1 | 0.963 | | cosine_accuracy@3 | 0.9906 | | cosine_accuracy@5 | 0.9944 | | cosine_accuracy@10 | 0.9982 | | cosine_precision@1 | 0.963 | | cosine_precision@3 | 0.4285 | | cosine_precision@5 | 0.2757 | | cosine_precision@10 | 0.1449 | | cosine_recall@1 | 0.83 | | cosine_recall@3 | 0.959 | | cosine_recall@5 | 0.9806 | | cosine_recall@10 | 0.9926 | | cosine_ndcg@10 | 0.9784 | | cosine_mrr@10 | 0.9772 | | **cosine_map@100** | **0.9709** | | dot_accuracy@1 | 0.9514 | | dot_accuracy@3 | 0.9852 | | dot_accuracy@5 | 0.991 | | dot_accuracy@10 | 0.9968 | | dot_precision@1 | 0.9514 | | dot_precision@3 | 0.4247 | | dot_precision@5 | 0.2736 | | dot_precision@10 | 0.1446 | | dot_recall@1 | 0.8194 | | dot_recall@3 | 0.952 | | dot_recall@5 | 0.9756 | | dot_recall@10 | 0.9911 | | dot_ndcg@10 | 0.9715 | | dot_mrr@10 | 0.9693 | | dot_map@100 | 0.9617 | <!-- ## Bias, Risks and Limitations *What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* --> <!-- ### Recommendations *What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* --> ## Training Details ### Training Datasets #### mnrl * Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 100,000 training samples * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 6 tokens</li><li>mean: 13.85 tokens</li><li>max: 42 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.65 tokens</li><li>max: 44 tokens</li></ul> | <ul><li>min: 4 tokens</li><li>mean: 14.76 tokens</li><li>max: 64 tokens</li></ul> | * Samples: | anchor | positive | negative | |:--------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------|:-----------------------------------------------------------------------------------------------------------------| | <code>Why in India do we not have one on one political debate as in USA?</code> | <code>Why cant we have a public debate between politicians in India like the one in US?</code> | <code>Can people on Quora stop India Pakistan debate? We are sick and tired seeing this everyday in bulk?</code> | | <code>What is OnePlus One?</code> | <code>How is oneplus one?</code> | <code>Why is OnePlus One so good?</code> | | <code>Does our mind control our emotions?</code> | <code>How do smart and successful people control their emotions?</code> | <code>How can I control my positive emotions for the people whom I love but they don't care about me?</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### cl * Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 100,000 training samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | <ul><li>min: 6 tokens</li><li>mean: 15.3 tokens</li><li>max: 57 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.66 tokens</li><li>max: 56 tokens</li></ul> | <ul><li>0: ~62.00%</li><li>1: ~38.00%</li></ul> | * Samples: | sentence1 | sentence2 | label | |:---------------------------------------------------------------------------------------|:------------------------------------------------------------------------------------------------------|:---------------| | <code>What is the step by step guide to invest in share market in india?</code> | <code>What is the step by step guide to invest in share market?</code> | <code>0</code> | | <code>What is the story of Kohinoor (Koh-i-Noor) Diamond?</code> | <code>What would happen if the Indian government stole the Kohinoor (Koh-i-Noor) diamond back?</code> | <code>0</code> | | <code>How can I increase the speed of my internet connection while using a VPN?</code> | <code>How can Internet speed be increased by hacking through DNS?</code> | <code>0</code> | * Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Evaluation Datasets #### mnrl * Dataset: [mnrl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 1,000 evaluation samples * Columns: <code>anchor</code>, <code>positive</code>, and <code>negative</code> * Approximate statistics based on the first 1000 samples: | | anchor | positive | negative | |:--------|:----------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------| | type | string | string | string | | details | <ul><li>min: 7 tokens</li><li>mean: 13.84 tokens</li><li>max: 43 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 13.8 tokens</li><li>max: 38 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 14.71 tokens</li><li>max: 56 tokens</li></ul> | * Samples: | anchor | positive | negative | |:---------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------|:----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | <code>Which programming language is best for developing low-end games?</code> | <code>What coding language should I learn first for making games?</code> | <code>I am entering the world of video game programming and want to know what language I should learn? Because there are so many languages ​​I do not know which one to start with. Can you recommend a language that's easy to learn and can be used with many platforms?</code> | | <code>Was it appropriate for Meryl Streep to use her Golden Globes speech to attack Donald Trump?</code> | <code>Should Meryl Streep be using her position to attack the president?</code> | <code>Why did Kelly Ann Conway say that Meryl Streep incited peoples worst feelings?</code> | | <code>Where can I found excellent commercial fridges in Sydney?</code> | <code>Where can I found impressive range of commercial fridges in Sydney?</code> | <code>What is the best grocery delivery service in Sydney?</code> | * Loss: [<code>MultipleNegativesRankingLoss</code>](https://sbert.net/docs/package_reference/losses.html#multiplenegativesrankingloss) with these parameters: ```json { "scale": 20.0, "similarity_fct": "cos_sim" } ``` #### cl * Dataset: [cl](https://huggingface.co/datasets/sentence-transformers/quora-duplicates) at [451a485](https://huggingface.co/datasets/sentence-transformers/quora-duplicates/tree/451a4850bd141edb44ade1b5828c259abd762cdb) * Size: 1,000 evaluation samples * Columns: <code>sentence1</code>, <code>sentence2</code>, and <code>label</code> * Approximate statistics based on the first 1000 samples: | | sentence1 | sentence2 | label | |:--------|:----------------------------------------------------------------------------------|:----------------------------------------------------------------------------------|:------------------------------------------------| | type | string | string | int | | details | <ul><li>min: 5 tokens</li><li>mean: 15.59 tokens</li><li>max: 59 tokens</li></ul> | <ul><li>min: 6 tokens</li><li>mean: 15.65 tokens</li><li>max: 76 tokens</li></ul> | <ul><li>0: ~63.40%</li><li>1: ~36.60%</li></ul> | * Samples: | sentence1 | sentence2 | label | |:--------------------------------------------------------------------------|:---------------------------------------------------------------------------------------------------------|:---------------| | <code>What should I ask my friend to get from UK to India?</code> | <code>What is the process of getting a surgical residency in UK after completing MBBS from India?</code> | <code>0</code> | | <code>How can I learn hacking for free?</code> | <code>How can I learn to hack seriously?</code> | <code>1</code> | | <code>Which is the best website to learn programming language C++?</code> | <code>Which is the best website to learn C++ Programming language for free?</code> | <code>0</code> | * Loss: [<code>ContrastiveLoss</code>](https://sbert.net/docs/package_reference/losses.html#contrastiveloss) with these parameters: ```json { "distance_metric": "SiameseDistanceMetric.COSINE_DISTANCE", "margin": 0.5, "size_average": true } ``` ### Training Hyperparameters #### Non-Default Hyperparameters - `eval_strategy`: steps - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `num_train_epochs`: 1 - `warmup_ratio`: 0.1 - `fp16`: True - `batch_sampler`: no_duplicates #### All Hyperparameters <details><summary>Click to expand</summary> - `overwrite_output_dir`: False - `do_predict`: False - `eval_strategy`: steps - `prediction_loss_only`: False - `per_device_train_batch_size`: 64 - `per_device_eval_batch_size`: 64 - `per_gpu_train_batch_size`: None - `per_gpu_eval_batch_size`: None - `gradient_accumulation_steps`: 1 - `eval_accumulation_steps`: None - `learning_rate`: 5e-05 - `weight_decay`: 0.0 - `adam_beta1`: 0.9 - `adam_beta2`: 0.999 - `adam_epsilon`: 1e-08 - `max_grad_norm`: 1.0 - `num_train_epochs`: 1 - `max_steps`: -1 - `lr_scheduler_type`: linear - `lr_scheduler_kwargs`: {} - `warmup_ratio`: 0.1 - `warmup_steps`: 0 - `log_level`: passive - `log_level_replica`: warning - `log_on_each_node`: True - `logging_nan_inf_filter`: True - `save_safetensors`: True - `save_on_each_node`: False - `save_only_model`: False - `no_cuda`: False - `use_cpu`: False - `use_mps_device`: False - `seed`: 42 - `data_seed`: None - `jit_mode_eval`: False - `use_ipex`: False - `bf16`: False - `fp16`: True - `fp16_opt_level`: O1 - `half_precision_backend`: auto - `bf16_full_eval`: False - `fp16_full_eval`: False - `tf32`: None - `local_rank`: 0 - `ddp_backend`: None - `tpu_num_cores`: None - `tpu_metrics_debug`: False - `debug`: [] - `dataloader_drop_last`: False - `dataloader_num_workers`: 0 - `dataloader_prefetch_factor`: None - `past_index`: -1 - `disable_tqdm`: False - `remove_unused_columns`: True - `label_names`: None - `load_best_model_at_end`: False - `ignore_data_skip`: False - `fsdp`: [] - `fsdp_min_num_params`: 0 - `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} - `fsdp_transformer_layer_cls_to_wrap`: None - `accelerator_config`: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} - `deepspeed`: None - `label_smoothing_factor`: 0.0 - `optim`: adamw_torch - `optim_args`: None - `adafactor`: False - `group_by_length`: False - `length_column_name`: length - `ddp_find_unused_parameters`: None - `ddp_bucket_cap_mb`: None - `ddp_broadcast_buffers`: None - `dataloader_pin_memory`: True - `dataloader_persistent_workers`: False - `skip_memory_metrics`: True - `use_legacy_prediction_loop`: False - `push_to_hub`: False - `resume_from_checkpoint`: None - `hub_model_id`: None - `hub_strategy`: every_save - `hub_private_repo`: False - `hub_always_push`: False - `gradient_checkpointing`: False - `gradient_checkpointing_kwargs`: None - `include_inputs_for_metrics`: False - `eval_do_concat_batches`: True - `fp16_backend`: auto - `push_to_hub_model_id`: None - `push_to_hub_organization`: None - `mp_parameters`: - `auto_find_batch_size`: False - `full_determinism`: False - `torchdynamo`: None - `ray_scope`: last - `ddp_timeout`: 1800 - `torch_compile`: False - `torch_compile_backend`: None - `torch_compile_mode`: None - `dispatch_batches`: None - `split_batches`: None - `include_tokens_per_second`: False - `include_num_input_tokens_seen`: False - `neftune_noise_alpha`: None - `optim_target_modules`: None - `batch_sampler`: no_duplicates - `multi_dataset_batch_sampler`: proportional </details> ### Training Logs | Epoch | Step | Training Loss | cl loss | mnrl loss | cosine_map@100 | quora-duplicates-dev_average_precision | quora-duplicates_max_ap | |:------:|:----:|:-------------:|:-------:|:---------:|:--------------:|:--------------------------------------:|:-----------------------:| | 0 | 0 | - | - | - | 0.9245 | 0.4200 | 0.6890 | | 0.0320 | 100 | 0.1634 | - | - | - | - | - | | 0.0640 | 200 | 0.1206 | - | - | - | - | - | | 0.0800 | 250 | - | 0.0190 | 0.1469 | 0.9530 | 0.5068 | 0.7354 | | 0.0960 | 300 | 0.1036 | - | - | - | - | - | | 0.1280 | 400 | 0.0836 | - | - | - | - | - | | 0.1599 | 500 | 0.0918 | 0.0180 | 0.1008 | 0.9553 | 0.5259 | 0.7643 | | 0.1919 | 600 | 0.0784 | - | - | - | - | - | | 0.2239 | 700 | 0.0656 | - | - | - | - | - | | 0.2399 | 750 | - | 0.0177 | 0.0905 | 0.9593 | 0.5305 | 0.7686 | | 0.2559 | 800 | 0.0593 | - | - | - | - | - | | 0.2879 | 900 | 0.0534 | - | - | - | - | - | | 0.3199 | 1000 | 0.0612 | 0.0161 | 0.0736 | 0.9642 | 0.5512 | 0.7881 | | 0.3519 | 1100 | 0.0572 | - | - | - | - | - | | 0.3839 | 1200 | 0.06 | - | - | - | - | - | | 0.3999 | 1250 | - | 0.0158 | 0.0641 | 0.9649 | 0.5567 | 0.7983 | | 0.4159 | 1300 | 0.0565 | - | - | - | - | - | | 0.4479 | 1400 | 0.0565 | - | - | - | - | - | | 0.4798 | 1500 | 0.0475 | 0.0154 | 0.0578 | 0.9645 | 0.5614 | 0.8062 | | 0.5118 | 1600 | 0.0596 | - | - | - | - | - | | 0.5438 | 1700 | 0.0509 | - | - | - | - | - | | 0.5598 | 1750 | - | 0.0150 | 0.0525 | 0.9674 | 0.5762 | 0.8092 | | 0.5758 | 1800 | 0.0403 | - | - | - | - | - | | 0.6078 | 1900 | 0.0431 | - | - | - | - | - | | 0.6398 | 2000 | 0.0481 | 0.0150 | 0.0531 | 0.9689 | 0.5824 | 0.8128 | | 0.6718 | 2100 | 0.05 | - | - | - | - | - | | 0.7038 | 2200 | 0.0468 | - | - | - | - | - | | 0.7198 | 2250 | - | 0.0146 | 0.0486 | 0.9684 | 0.5756 | 0.8195 | | 0.7358 | 2300 | 0.0436 | - | - | - | - | - | | 0.7678 | 2400 | 0.0409 | - | - | - | - | - | | 0.7997 | 2500 | 0.0391 | 0.0145 | 0.0454 | 0.9705 | 0.5822 | 0.8190 | | 0.8317 | 2600 | 0.0412 | - | - | - | - | - | | 0.8637 | 2700 | 0.0373 | - | - | - | - | - | | 0.8797 | 2750 | - | 0.0143 | 0.0451 | 0.9705 | 0.5889 | 0.8229 | | 0.8957 | 2800 | 0.0428 | - | - | - | - | - | | 0.9277 | 2900 | 0.0419 | - | - | - | - | - | | 0.9597 | 3000 | 0.0376 | 0.0143 | 0.0435 | 0.9709 | 0.5889 | 0.8230 | | 0.9917 | 3100 | 0.0366 | - | - | - | - | - | ### Environmental Impact Carbon emissions were measured using [CodeCarbon](https://github.com/mlco2/codecarbon). - **Energy Consumed**: 0.084 kWh - **Carbon Emitted**: 0.033 kg of CO2 - **Hours Used**: 0.399 hours ### Training Hardware - **On Cloud**: No - **GPU Model**: 1 x NVIDIA GeForce RTX 3090 - **CPU Model**: 13th Gen Intel(R) Core(TM) i7-13700K - **RAM Size**: 31.78 GB ### Framework Versions - Python: 3.11.6 - Sentence Transformers: 3.0.0.dev0 - Transformers: 4.41.0.dev0 - PyTorch: 2.3.0+cu121 - Accelerate: 0.26.1 - Datasets: 2.18.0 - Tokenizers: 0.19.1 ## Citation ### BibTeX #### Sentence Transformers ```bibtex @inproceedings{reimers-2019-sentence-bert, title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", author = "Reimers, Nils and Gurevych, Iryna", booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", month = "11", year = "2019", publisher = "Association for Computational Linguistics", url = "https://arxiv.org/abs/1908.10084", } ``` #### MultipleNegativesRankingLoss ```bibtex @misc{henderson2017efficient, title={Efficient Natural Language Response Suggestion for Smart Reply}, author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil}, year={2017}, eprint={1705.00652}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``` #### ContrastiveLoss ```bibtex @inproceedings{hadsell2006dimensionality, author={Hadsell, R. and Chopra, S. and LeCun, Y.}, booktitle={2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06)}, title={Dimensionality Reduction by Learning an Invariant Mapping}, year={2006}, volume={2}, number={}, pages={1735-1742}, doi={10.1109/CVPR.2006.100} } ``` <!-- ## Glossary *Clearly define terms in order to be accessible across audiences.* --> <!-- ## Model Card Authors *Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* --> <!-- ## Model Card Contact *Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* -->
{"language": ["en"], "library_name": "sentence-transformers", "tags": ["sentence-transformers", "sentence-similarity", "feature-extraction", "loss:MultipleNegativesRankingLoss", "loss:ContrastiveLoss"], "metrics": ["cosine_accuracy", "cosine_accuracy_threshold", "cosine_f1", "cosine_f1_threshold", "cosine_precision", "cosine_recall", "cosine_ap", "dot_accuracy", "dot_accuracy_threshold", "dot_f1", "dot_f1_threshold", "dot_precision", "dot_recall", "dot_ap", "manhattan_accuracy", "manhattan_accuracy_threshold", "manhattan_f1", "manhattan_f1_threshold", "manhattan_precision", "manhattan_recall", "manhattan_ap", "euclidean_accuracy", "euclidean_accuracy_threshold", "euclidean_f1", "euclidean_f1_threshold", "euclidean_precision", "euclidean_recall", "euclidean_ap", "max_accuracy", "max_accuracy_threshold", "max_f1", "max_f1_threshold", "max_precision", "max_recall", "max_ap", "average_precision", "f1", "precision", "recall", "threshold", "cosine_accuracy@1", "cosine_accuracy@3", "cosine_accuracy@5", "cosine_accuracy@10", "cosine_precision@1", "cosine_precision@3", "cosine_precision@5", "cosine_precision@10", "cosine_recall@1", "cosine_recall@3", "cosine_recall@5", "cosine_recall@10", "cosine_ndcg@10", "cosine_mrr@10", "cosine_map@100", "dot_accuracy@1", "dot_accuracy@3", "dot_accuracy@5", "dot_accuracy@10", "dot_precision@1", "dot_precision@3", "dot_precision@5", "dot_precision@10", "dot_recall@1", "dot_recall@3", "dot_recall@5", "dot_recall@10", "dot_ndcg@10", "dot_mrr@10", "dot_map@100"], "base_model": "sentence-transformers/stsb-distilbert-base", "widget": [{"source_sentence": "What is Mindset?", "sentences": ["What is a mindset?", "Can you eat only once a day?", "Is law a good career choice?"]}, {"source_sentence": "Is a queef real?", "sentences": ["Is \"G\" based on real events?", "What is the entire court process?", "How do I reduce my weight?"]}, {"source_sentence": "Is Cicret a scam?", "sentences": ["Is the Cicret Bracelet a scam?", "Was World War II Inevitable?", "What are some of the best photos?"]}, {"source_sentence": "What is Planet X?", "sentences": ["Do planet X exist?", "What are the best C++ books?", "How can I lose my weight fast?"]}, {"source_sentence": "How fast is fast?", "sentences": ["How does light travel so fast?", "How do I copyright my books?", "What is a black hole made of?"]}], "pipeline_tag": "sentence-similarity", "co2_eq_emissions": {"emissions": 32.724475965905576, "energy_consumed": 0.08418911136527617, "source": "codecarbon", "training_type": "fine-tuning", "on_cloud": false, "cpu_model": "13th Gen Intel(R) Core(TM) i7-13700K", "ram_total_size": 31.777088165283203, "hours_used": 0.399, "hardware_used": "1 x NVIDIA GeForce RTX 3090"}, "model-index": [{"name": "SentenceTransformer based on sentence-transformers/stsb-distilbert-base", "results": [{"task": {"type": "binary-classification", "name": "Binary Classification"}, "dataset": {"name": "quora duplicates", "type": "quora-duplicates"}, "metrics": [{"type": "cosine_accuracy", "value": 0.846, "name": "Cosine Accuracy"}, {"type": "cosine_accuracy_threshold", "value": 0.7969297170639038, "name": "Cosine Accuracy Threshold"}, {"type": "cosine_f1", "value": 0.7791495198902607, "name": "Cosine F1"}, {"type": "cosine_f1_threshold", "value": 0.7139598727226257, "name": "Cosine F1 Threshold"}, {"type": "cosine_precision", "value": 0.6977886977886978, "name": "Cosine Precision"}, {"type": "cosine_recall", "value": 0.8819875776397516, "name": "Cosine Recall"}, {"type": "cosine_ap", "value": 0.8230449963294564, "name": "Cosine Ap"}, {"type": "dot_accuracy", "value": 0.843, "name": "Dot Accuracy"}, {"type": "dot_accuracy_threshold", "value": 151.2908477783203, "name": "Dot Accuracy Threshold"}, {"type": "dot_f1", "value": 0.7660818713450294, "name": "Dot F1"}, {"type": "dot_f1_threshold", "value": 143.77838134765625, "name": "Dot F1 Threshold"}, {"type": "dot_precision", "value": 0.7237569060773481, "name": "Dot Precision"}, {"type": "dot_recall", "value": 0.8136645962732919, "name": "Dot Recall"}, {"type": "dot_ap", "value": 0.7946044629726107, "name": "Dot Ap"}, {"type": "manhattan_accuracy", "value": 0.838, "name": "Manhattan Accuracy"}, {"type": "manhattan_accuracy_threshold", "value": 194.99119567871094, "name": "Manhattan Accuracy Threshold"}, {"type": "manhattan_f1", "value": 0.7704081632653061, "name": "Manhattan F1"}, {"type": "manhattan_f1_threshold", "value": 247.49777221679688, "name": "Manhattan F1 Threshold"}, {"type": "manhattan_precision", "value": 0.6536796536796536, "name": "Manhattan Precision"}, {"type": "manhattan_recall", "value": 0.937888198757764, "name": "Manhattan Recall"}, {"type": "manhattan_ap", "value": 0.8149715271935773, "name": "Manhattan Ap"}, {"type": "euclidean_accuracy", "value": 0.841, "name": "Euclidean Accuracy"}, {"type": "euclidean_accuracy_threshold", "value": 9.02225112915039, "name": "Euclidean Accuracy Threshold"}, {"type": "euclidean_f1", "value": 0.7703889585947302, "name": "Euclidean F1"}, {"type": "euclidean_f1_threshold", "value": 11.385245323181152, "name": "Euclidean F1 Threshold"}, {"type": "euclidean_precision", "value": 0.6463157894736842, "name": "Euclidean Precision"}, {"type": "euclidean_recall", "value": 0.953416149068323, "name": "Euclidean Recall"}, {"type": "euclidean_ap", "value": 0.8152967320117391, "name": "Euclidean Ap"}, {"type": "max_accuracy", "value": 0.846, "name": "Max Accuracy"}, {"type": "max_accuracy_threshold", "value": 194.99119567871094, "name": "Max Accuracy Threshold"}, {"type": "max_f1", "value": 0.7791495198902607, "name": "Max F1"}, {"type": "max_f1_threshold", "value": 247.49777221679688, "name": "Max F1 Threshold"}, {"type": "max_precision", "value": 0.7237569060773481, "name": "Max Precision"}, {"type": "max_recall", "value": 0.953416149068323, "name": "Max Recall"}, {"type": "max_ap", "value": 0.8230449963294564, "name": "Max Ap"}]}, {"task": {"type": "paraphrase-mining", "name": "Paraphrase Mining"}, "dataset": {"name": "quora duplicates dev", "type": "quora-duplicates-dev"}, "metrics": [{"type": "average_precision", "value": 0.5888649029434471, "name": "Average Precision"}, {"type": "f1", "value": 0.5761652140962487, "name": "F1"}, {"type": "precision", "value": 0.5477552123204396, "name": "Precision"}, {"type": "recall", "value": 0.6076834690513064, "name": "Recall"}, {"type": "threshold", "value": 0.7728720009326935, "name": "Threshold"}]}, {"task": {"type": "information-retrieval", "name": "Information Retrieval"}, "dataset": {"name": "Unknown", "type": "unknown"}, "metrics": [{"type": "cosine_accuracy@1", "value": 0.963, "name": "Cosine Accuracy@1"}, {"type": "cosine_accuracy@3", "value": 0.9906, "name": "Cosine Accuracy@3"}, {"type": "cosine_accuracy@5", "value": 0.9944, "name": "Cosine Accuracy@5"}, {"type": "cosine_accuracy@10", "value": 0.9982, "name": "Cosine Accuracy@10"}, {"type": "cosine_precision@1", "value": 0.963, "name": "Cosine Precision@1"}, {"type": "cosine_precision@3", "value": 0.4285333333333333, "name": "Cosine Precision@3"}, {"type": "cosine_precision@5", "value": 0.27568000000000004, "name": "Cosine Precision@5"}, {"type": "cosine_precision@10", "value": 0.14494, "name": "Cosine Precision@10"}, {"type": "cosine_recall@1", "value": 0.8299562338609103, "name": "Cosine Recall@1"}, {"type": "cosine_recall@3", "value": 0.9590366552956846, "name": "Cosine Recall@3"}, {"type": "cosine_recall@5", "value": 0.9806221849555673, "name": "Cosine Recall@5"}, {"type": "cosine_recall@10", "value": 0.9925738410935468, "name": "Cosine Recall@10"}, {"type": "cosine_ndcg@10", "value": 0.9784033087450696, "name": "Cosine Ndcg@10"}, {"type": "cosine_mrr@10", "value": 0.9771579365079368, "name": "Cosine Mrr@10"}, {"type": "cosine_map@100", "value": 0.9709189650394419, "name": "Cosine Map@100"}, {"type": "dot_accuracy@1", "value": 0.9514, "name": "Dot Accuracy@1"}, {"type": "dot_accuracy@3", "value": 0.9852, "name": "Dot Accuracy@3"}, {"type": "dot_accuracy@5", "value": 0.991, "name": "Dot Accuracy@5"}, {"type": "dot_accuracy@10", "value": 0.9968, "name": "Dot Accuracy@10"}, {"type": "dot_precision@1", "value": 0.9514, "name": "Dot Precision@1"}, {"type": "dot_precision@3", "value": 0.4247333333333334, "name": "Dot Precision@3"}, {"type": "dot_precision@5", "value": 0.27364, "name": "Dot Precision@5"}, {"type": "dot_precision@10", "value": 0.14458000000000001, "name": "Dot Precision@10"}, {"type": "dot_recall@1", "value": 0.8194380520427287, "name": "Dot Recall@1"}, {"type": "dot_recall@3", "value": 0.9520212390452685, "name": "Dot Recall@3"}, {"type": "dot_recall@5", "value": 0.9755502441186265, "name": "Dot Recall@5"}, {"type": "dot_recall@10", "value": 0.9910547306614953, "name": "Dot Recall@10"}, {"type": "dot_ndcg@10", "value": 0.9715023430522326, "name": "Dot Ndcg@10"}, {"type": "dot_mrr@10", "value": 0.9692583333333334, "name": "Dot Mrr@10"}, {"type": "dot_map@100", "value": 0.961739772177385, "name": "Dot Map@100"}]}]}]}
tomaarsen/stsb-distilbert-base-mnrl-cl-multi
null
[ "sentence-transformers", "safetensors", "distilbert", "sentence-similarity", "feature-extraction", "loss:MultipleNegativesRankingLoss", "loss:ContrastiveLoss", "en", "arxiv:1908.10084", "arxiv:1705.00652", "base_model:sentence-transformers/stsb-distilbert-base", "model-index", "co2_eq_emissions", "endpoints_compatible", "region:us" ]
null
2024-05-02T12:42:23+00:00