Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "pytorch", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/tinyllama-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: andrewatef\n- License: apache-2.0\n- Finetuned from model : unsloth/tinyllama-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/tinyllama-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: andrewatef\n- License: apache-2.0\n- Finetuned from model : unsloth/tinyllama-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "tensorboard", "safetensors", "segformer", "generated_from_trainer", "dataset:scene_parse_150", "base_model:nvidia/mit-b0", "license:other", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 6e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 50", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #segformer #generated_from_trainer #dataset-scene_parse_150 #base_model-nvidia/mit-b0 #license-other #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 6e-05\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 50", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.3.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/tinyllama-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: andrewatef\n- License: apache-2.0\n- Finetuned from model : unsloth/tinyllama-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/tinyllama-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: andrewatef\n- License: apache-2.0\n- Finetuned from model : unsloth/tinyllama-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "distilbert", "text-classification", "bert", "en", "dataset:kmack/Phishing_urls", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us", "has_space" ]

[]

[ "en" ]

[ "# Malicious-Url-Detection\nUsing this model, you can detects harmful links created to harm people such as phishing, malware urls. this model Classifies if the urls addresses are malware and benign.\nType the domain name of the url address in the text field for classification in API: Like this: \n\"URL\" \n\nThis model is a fine-tuned version of distilbert-base-uncased on an kmack/Phishing_urls dataset." ]

[ "TAGS\n#transformers #safetensors #distilbert #text-classification #bert #en #dataset-kmack/Phishing_urls #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us #has_space \n", "# Malicious-Url-Detection\nUsing this model, you can detects harmful links created to harm people such as phishing, malware urls. this model Classifies if the urls addresses are malware and benign.\nType the domain name of the url address in the text field for classification in API: Like this: \n\"URL\" \n\nThis model is a fine-tuned version of distilbert-base-uncased on an kmack/Phishing_urls dataset." ]

[ "peft", "tensorboard", "safetensors", "generated_from_trainer", "base_model:microsoft/Phi-3-mini-4k-instruct", "license:mit", "region:us" ]

[]

[]

[ "# phi-3-mini-general-ift\n\nThis model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 2\n- training_steps: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #generated_from_trainer #base_model-microsoft/Phi-3-mini-4k-instruct #license-mit #region-us \n", "# phi-3-mini-general-ift\n\nThis model is a fine-tuned version of microsoft/Phi-3-mini-4k-instruct on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 1\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 4\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 2\n- training_steps: 5\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.1.dev0\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.2+cu121\n- Datasets 2.18.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "idefics2", "pretraining", "generated_from_trainer", "base_model:HuggingFaceM4/idefics2-8b", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "# idefics2-8b-docvqa-finetuned-tutorial\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 50\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #idefics2 #pretraining #generated_from_trainer #base_model-HuggingFaceM4/idefics2-8b #license-apache-2.0 #endpoints_compatible #region-us \n", "# idefics2-8b-docvqa-finetuned-tutorial\n\nThis model is a fine-tuned version of HuggingFaceM4/idefics2-8b on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0001\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 8\n- total_train_batch_size: 16\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- lr_scheduler_warmup_steps: 50\n- num_epochs: 2\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.41.0.dev0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "peft", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-13b-chat-hf", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-meta-llama/Llama-2-13b-chat-hf #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "peft", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-13b-chat-hf", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "TAGS\n#peft #arxiv-1910.09700 #base_model-meta-llama/Llama-2-13b-chat-hf #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "## Training procedure\n\n\nThe following 'bitsandbytes' quantization config was used during training:\n- load_in_8bit: False\n- load_in_4bit: True\n- llm_int8_threshold: 6.0\n- llm_int8_skip_modules: None\n- llm_int8_enable_fp32_cpu_offload: False\n- llm_int8_has_fp16_weight: False\n- bnb_4bit_quant_type: nf4\n- bnb_4bit_use_double_quant: True\n- bnb_4bit_compute_dtype: bfloat16", "### Framework versions\n\n\n- PEFT 0.7.0.dev0" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "en", "dataset:0-hero/Matter-0.2-alpha-Slim-A", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# hus960/Matter-0.2-32B-Q4_K_M-GGUF\nThis model was converted to GGUF format from '0-hero/Matter-0.2-32B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #llama-cpp #gguf-my-repo #en #dataset-0-hero/Matter-0.2-alpha-Slim-A #license-apache-2.0 #region-us \n", "# hus960/Matter-0.2-32B-Q4_K_M-GGUF\nThis model was converted to GGUF format from '0-hero/Matter-0.2-32B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "transformers", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# results\n\nThis model is a fine-tuned version of roberta-base on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# results\n\nThis model is a fine-tuned version of roberta-base on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 8\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "gguf", "facebook", "meta", "pytorch", "llama", "llama-3", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#gguf #facebook #meta #pytorch #llama #llama-3 #text-generation #en #license-other #region-us \n", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/tinyllama-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: andrewatef\n- License: apache-2.0\n- Finetuned from model : unsloth/tinyllama-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/tinyllama-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: andrewatef\n- License: apache-2.0\n- Finetuned from model : unsloth/tinyllama-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "llama", "text-generation", "conversational", "base_model:kuotient/Llama-3-11B-Instruct-attenuated", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Synatra-11B-L3-v1", "## Model Description\n\nLlama 3 11B attenuated 모델에 40만개 이상의 한국어, 영어 채팅 데이터를 학습시킨 모델입니다. More Details Soon.\n\n채팅 템플릿은 라마3 Chat 형식을 따릅니다.", "## License\n\nURL", "## Thanks to\n\n- 기반 모델을 제공해주신, Jisoo Kim (kuotient)\n- A100 클러스터를 제공해주신, Sionic AI", "## Contact\n- Discord Server Link" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #base_model-kuotient/Llama-3-11B-Instruct-attenuated #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Synatra-11B-L3-v1", "## Model Description\n\nLlama 3 11B attenuated 모델에 40만개 이상의 한국어, 영어 채팅 데이터를 학습시킨 모델입니다. More Details Soon.\n\n채팅 템플릿은 라마3 Chat 형식을 따릅니다.", "## License\n\nURL", "## Thanks to\n\n- 기반 모델을 제공해주신, Jisoo Kim (kuotient)\n- A100 클러스터를 제공해주신, Sionic AI", "## Contact\n- Discord Server Link" ]

[ "transformers", "safetensors", "led", "text2text-generation", "generated_from_trainer", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# BioNLP-tech_ner-PLOS\n\nThis model was trained from scratch on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.3739167643078955e-06\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 1.13.1+cu117\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #led #text2text-generation #generated_from_trainer #autotrain_compatible #endpoints_compatible #region-us \n", "# BioNLP-tech_ner-PLOS\n\nThis model was trained from scratch on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1.3739167643078955e-06\n- train_batch_size: 4\n- eval_batch_size: 4\n- seed: 42\n- distributed_type: multi-GPU\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 10\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- Transformers 4.35.2\n- Pytorch 1.13.1+cu117\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "roberta", "text-classification", "generated_from_trainer", "base_model:roberta-base", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# roberta-political-bias\n\nThis model is a fine-tuned version of roberta-base on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #roberta #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# roberta-political-bias\n\nThis model is a fine-tuned version of roberta-base on an unknown dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\n- train_batch_size: 16\n- eval_batch_size: 16\n- seed: 42\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 3", "### Framework versions\n\n- Transformers 4.40.1\n- Pytorch 2.1.2\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "llama", "trl", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "stable-baselines3", "SpaceInvadersNoFrameskip-v4", "deep-reinforcement-learning", "reinforcement-learning", "model-index", "region:us" ]

[]

[]

[ "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "TAGS\n#stable-baselines3 #SpaceInvadersNoFrameskip-v4 #deep-reinforcement-learning #reinforcement-learning #model-index #region-us \n", "# DQN Agent playing SpaceInvadersNoFrameskip-v4\nThis is a trained model of a DQN agent playing SpaceInvadersNoFrameskip-v4\nusing the stable-baselines3 library\nand the RL Zoo.\n\nThe RL Zoo is a training framework for Stable Baselines3\nreinforcement learning agents,\nwith hyperparameter optimization and pre-trained agents included.", "## Usage (with SB3 RL Zoo)\n\nRL Zoo: URL\nSB3: URL\nSB3 Contrib: URL\n\nInstall the RL Zoo (with SB3 and SB3-Contrib):\n\n\n\n\nIf you installed the RL Zoo3 via pip ('pip install rl_zoo3'), from anywhere you can do:", "## Training (with the RL Zoo)", "## Hyperparameters", "# Environment Arguments" ]

[ "transformers", "RefinedWebModel", "text-generation", "custom_code", "en", "dataset:tiiuae/falcon-refinedweb", "arxiv:2205.14135", "arxiv:1911.02150", "arxiv:2101.00027", "arxiv:2005.14165", "arxiv:2104.09864", "arxiv:2306.01116", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

[ "2205.14135", "1911.02150", "2101.00027", "2005.14165", "2104.09864", "2306.01116" ]

[ "en" ]

[ "### Model Description\n\n\n* Developed by: URL;\n* Model type: Causal decoder-only;\n* Language(s) (NLP): English and French;\n* License: Apache 2.0.", "### Model Source\n\n\n* Paper: *coming soon*.\n\n\nUses\n----", "### Direct Use\n\n\nResearch on large language models; as a foundation for further specialization and finetuning for specific usecases (e.g., summarization, text generation, chatbot, etc.)", "### Out-of-Scope Use\n\n\nProduction use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.\n\n\nBias, Risks, and Limitations\n----------------------------\n\n\nFalcon-7B is trained on English and French data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.", "### Recommendations\n\n\nWe recommend users of Falcon-7B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTraining Details\n----------------", "### Training Data\n\n\nFalcon-7B was trained on 1,500B tokens of RefinedWeb, a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. Significant components from our curated copora were inspired by The Pile (Gao et al., 2020).\n\n\n\nThe data was tokenized with the Falcon-7B/40B tokenizer.", "### Training Procedure\n\n\nFalcon-7B was trained on 384 A100 40GB GPUs, using a 2D parallelism strategy (PP=2, DP=192) combined with ZeRO.", "#### Training Hyperparameters\n\n\nHyperparameter: Precision, Value: 'bfloat16', Comment: \nHyperparameter: Optimizer, Value: AdamW, Comment: \nHyperparameter: Learning rate, Value: 6e-4, Comment: 4B tokens warm-up, cosine decay to 1.2e-5\nHyperparameter: Weight decay, Value: 1e-1, Comment: \nHyperparameter: Z-loss, Value: 1e-4, Comment: \nHyperparameter: Batch size, Value: 2304, Comment: 30B tokens ramp-up", "#### Speeds, Sizes, Times\n\n\nTraining happened in early March 2023 and took about two weeks.\n\n\nEvaluation\n----------\n\n\n*Paper coming soon*.\n\n\nSee the OpenLLM Leaderboard for early results.\n\n\nTechnical Specifications\n------------------------", "### Model Architecture and Objective\n\n\nFalcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).\n\n\nThe architecture is broadly adapted from the GPT-3 paper (Brown et al., 2020), with the following differences:\n\n\n* Positionnal embeddings: rotary (Su et al., 2021);\n* Attention: multiquery (Shazeer et al., 2019) and FlashAttention (Dao et al., 2022);\n* Decoder-block: parallel attention/MLP with a single layer norm.\n\n\nHyperparameter: Layers, Value: 32, Comment: \nHyperparameter: 'd\\_model', Value: 4544, Comment: Increased to compensate for multiquery\nHyperparameter: 'head\\_dim', Value: 64, Comment: Reduced to optimise for FlashAttention\nHyperparameter: Vocabulary, Value: 65024, Comment: \nHyperparameter: Sequence length, Value: 2048, Comment:", "### Compute Infrastructure", "#### Hardware\n\n\nFalcon-7B was trained on AWS SageMaker, on 384 A100 40GB GPUs in P4d instances.", "#### Software\n\n\nFalcon-7B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)\n\n\n*Paper coming soon* . In the meanwhile, you can use the following information to cite:\n\n\nTo learn more about the pretraining dataset, see the RefinedWeb paper.\n\n\nLicense\n-------\n\n\nFalcon-7B is made available under the Apache 2.0 license.\n\n\nContact\n-------\n\n\nfalconllm@URL" ]

[ "TAGS\n#transformers #RefinedWebModel #text-generation #custom_code #en #dataset-tiiuae/falcon-refinedweb #arxiv-2205.14135 #arxiv-1911.02150 #arxiv-2101.00027 #arxiv-2005.14165 #arxiv-2104.09864 #arxiv-2306.01116 #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us \n", "### Model Description\n\n\n* Developed by: URL;\n* Model type: Causal decoder-only;\n* Language(s) (NLP): English and French;\n* License: Apache 2.0.", "### Model Source\n\n\n* Paper: *coming soon*.\n\n\nUses\n----", "### Direct Use\n\n\nResearch on large language models; as a foundation for further specialization and finetuning for specific usecases (e.g., summarization, text generation, chatbot, etc.)", "### Out-of-Scope Use\n\n\nProduction use without adequate assessment of risks and mitigation; any use cases which may be considered irresponsible or harmful.\n\n\nBias, Risks, and Limitations\n----------------------------\n\n\nFalcon-7B is trained on English and French data only, and will not generalize appropriately to other languages. Furthermore, as it is trained on a large-scale corpora representative of the web, it will carry the stereotypes and biases commonly encountered online.", "### Recommendations\n\n\nWe recommend users of Falcon-7B to consider finetuning it for the specific set of tasks of interest, and for guardrails and appropriate precautions to be taken for any production use.\n\n\nHow to Get Started with the Model\n---------------------------------\n\n\nTraining Details\n----------------", "### Training Data\n\n\nFalcon-7B was trained on 1,500B tokens of RefinedWeb, a high-quality filtered and deduplicated web dataset which we enhanced with curated corpora. Significant components from our curated copora were inspired by The Pile (Gao et al., 2020).\n\n\n\nThe data was tokenized with the Falcon-7B/40B tokenizer.", "### Training Procedure\n\n\nFalcon-7B was trained on 384 A100 40GB GPUs, using a 2D parallelism strategy (PP=2, DP=192) combined with ZeRO.", "#### Training Hyperparameters\n\n\nHyperparameter: Precision, Value: 'bfloat16', Comment: \nHyperparameter: Optimizer, Value: AdamW, Comment: \nHyperparameter: Learning rate, Value: 6e-4, Comment: 4B tokens warm-up, cosine decay to 1.2e-5\nHyperparameter: Weight decay, Value: 1e-1, Comment: \nHyperparameter: Z-loss, Value: 1e-4, Comment: \nHyperparameter: Batch size, Value: 2304, Comment: 30B tokens ramp-up", "#### Speeds, Sizes, Times\n\n\nTraining happened in early March 2023 and took about two weeks.\n\n\nEvaluation\n----------\n\n\n*Paper coming soon*.\n\n\nSee the OpenLLM Leaderboard for early results.\n\n\nTechnical Specifications\n------------------------", "### Model Architecture and Objective\n\n\nFalcon-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).\n\n\nThe architecture is broadly adapted from the GPT-3 paper (Brown et al., 2020), with the following differences:\n\n\n* Positionnal embeddings: rotary (Su et al., 2021);\n* Attention: multiquery (Shazeer et al., 2019) and FlashAttention (Dao et al., 2022);\n* Decoder-block: parallel attention/MLP with a single layer norm.\n\n\nHyperparameter: Layers, Value: 32, Comment: \nHyperparameter: 'd\\_model', Value: 4544, Comment: Increased to compensate for multiquery\nHyperparameter: 'head\\_dim', Value: 64, Comment: Reduced to optimise for FlashAttention\nHyperparameter: Vocabulary, Value: 65024, Comment: \nHyperparameter: Sequence length, Value: 2048, Comment:", "### Compute Infrastructure", "#### Hardware\n\n\nFalcon-7B was trained on AWS SageMaker, on 384 A100 40GB GPUs in P4d instances.", "#### Software\n\n\nFalcon-7B was trained a custom distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO and high-performance Triton kernels (FlashAttention, etc.)\n\n\n*Paper coming soon* . In the meanwhile, you can use the following information to cite:\n\n\nTo learn more about the pretraining dataset, see the RefinedWeb paper.\n\n\nLicense\n-------\n\n\nFalcon-7B is made available under the Apache 2.0 license.\n\n\nContact\n-------\n\n\nfalconllm@URL" ]

[ "transformers", "gguf", "imatrix", "facebook", "meta", "llama", "llama-3", "text-generation", "en", "license:other", "region:us" ]

[]

[ "en" ]

[ "# From original readme", "## How to use\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\nPlease, follow the instructions in the repository\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works." ]

[ "TAGS\n#transformers #gguf #imatrix #facebook #meta #llama #llama-3 #text-generation #en #license-other #region-us \n", "# From original readme", "## How to use\n\nThis repository contains two versions of Meta-Llama-3-8B-Instruct, for use with transformers and with the original 'llama3' codebase.", "### Use with transformers\n\nYou can run conversational inference using the Transformers pipeline abstraction, or by leveraging the Auto classes with the 'generate()' function. Let's see examples of both.", "#### Transformers pipeline", "#### Transformers AutoModelForCausalLM", "### Use with 'llama3'\n\nPlease, follow the instructions in the repository\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works." ]

[ "transformers", "pytorch", "llama", "text-generation", "conversational", "en", "dataset:mrfakename/refusal", "base_model:TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #conversational #en #dataset-mrfakename/refusal #base_model-TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "transformers", "safetensors", "mistral", "text-generation", "Mistral", "conversational", "ko", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "ko" ]

[ "### BaseModel\n - alpindale/Mistral-7B-v0.2-hf", "### Model Generation" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #Mistral #conversational #ko #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### BaseModel\n - alpindale/Mistral-7B-v0.2-hf", "### Model Generation" ]

[ "transformers", "tensorboard", "safetensors", "albert", "text-classification", "generated_from_trainer", "base_model:albert/albert-base-v2", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #albert #text-classification #generated_from_trainer #base_model-albert/albert-base-v2 #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "arxiv:1910.09700", "base_model:meta-llama/Meta-Llama-3-8B", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

[ "TAGS\n#peft #safetensors #arxiv-1910.09700 #base_model-meta-llama/Meta-Llama-3-8B #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\n\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact", "### Framework versions\n\n- PEFT 0.10.0" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #unsloth #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository.\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "transformers", "llama", "text-generation", "mergekit", "merge", "EXL2", "4.5bit", "conversational", "arxiv:2403.19522", "base_model:Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP", "base_model:nbeerbower/llama-3-dragonmaid-8B", "base_model:kuotient/Meta-Llama-3-8B-Instruct", "base_model:Locutusque/llama-3-neural-chat-v1-8b", "base_model:Undi95/Llama-3-Unholy-8B-e4", "base_model:openlynn/Llama-3-Soliloquy-8B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2403.19522" ]

[]

[ "# merged\nThis is the 4.5bit EXL2 Quantized version of SnowyRP's first Llama 3 model. Quality of this model is unknown, since it is a Llama 3 model that I have not had the chance to test much.\n\n.BF16", "## Merge Details\nFor this model I used the most uncensored and smartest finetunes of LLama 3, since LLama 3 has the largest ammount of training tokens I know of, so I expect it to have more than enough of a knowledge base.\n\nThis model is under both the LLama 3 licince and a few other ones that only affect conmerical uses, But I am not a lawer so use in commerical settings at your own risk.", "## Model Use:\n\nHere is an modified Alpaca prompt I use with this model:", "### Merge Method\n\nThis model was merged using the Model Stock merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP\n* nbeerbower/llama-3-dragonmaid-8B\n* Locutusque/llama-3-neural-chat-v1-8b\n* Undi95/Llama-3-Unholy-8B-e4\n* openlynn/Llama-3-Soliloquy-8B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #llama #text-generation #mergekit #merge #EXL2 #4.5bit #conversational #arxiv-2403.19522 #base_model-Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP #base_model-nbeerbower/llama-3-dragonmaid-8B #base_model-kuotient/Meta-Llama-3-8B-Instruct #base_model-Locutusque/llama-3-neural-chat-v1-8b #base_model-Undi95/Llama-3-Unholy-8B-e4 #base_model-openlynn/Llama-3-Soliloquy-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merged\nThis is the 4.5bit EXL2 Quantized version of SnowyRP's first Llama 3 model. Quality of this model is unknown, since it is a Llama 3 model that I have not had the chance to test much.\n\n.BF16", "## Merge Details\nFor this model I used the most uncensored and smartest finetunes of LLama 3, since LLama 3 has the largest ammount of training tokens I know of, so I expect it to have more than enough of a knowledge base.\n\nThis model is under both the LLama 3 licince and a few other ones that only affect conmerical uses, But I am not a lawer so use in commerical settings at your own risk.", "## Model Use:\n\nHere is an modified Alpaca prompt I use with this model:", "### Merge Method\n\nThis model was merged using the Model Stock merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Dogge/llama-3-8B-instruct-Bluemoon-Freedom-RP\n* nbeerbower/llama-3-dragonmaid-8B\n* Locutusque/llama-3-neural-chat-v1-8b\n* Undi95/Llama-3-Unholy-8B-e4\n* openlynn/Llama-3-Soliloquy-8B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #fuyu #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "conversational", "en", "base_model:unsloth/llama-3-8b-Instruct-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "4-bit", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #conversational #en #base_model-unsloth/llama-3-8b-Instruct-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #4-bit #region-us \n", "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-Instruct-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "tensorboard", "safetensors", "gpt2", "text-generation", "generated_from_trainer", "dataset:eli5_category", "base_model:gpt2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #gpt2 #text-generation #generated_from_trainer #dataset-eli5_category #base_model-gpt2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 3.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "qwen2", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #qwen2 #feature-extraction #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "tensorboard", "safetensors", "gemma", "alignment-handbook", "trl", "sft", "generated_from_trainer", "dataset:chansung/merged_ds_coding", "base_model:google/gemma-7b", "license:gemma", "4-bit", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.40.1\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#peft #tensorboard #safetensors #gemma #alignment-handbook #trl #sft #generated_from_trainer #dataset-chansung/merged_ds_coding #base_model-google/gemma-7b #license-gemma #4-bit #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\n* train\\_batch\\_size: 2\n* eval\\_batch\\_size: 2\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 16\n* total\\_eval\\_batch\\_size: 8\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: cosine\n* lr\\_scheduler\\_warmup\\_ratio: 0.1\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* PEFT 0.7.1\n* Transformers 4.40.1\n* Pytorch 2.2.2+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "gguf", "uncensored", "llama3", "instruct", "open", "llama-cpp", "gguf-my-repo", "license:llama3", "region:us" ]

[]

[]

[ "# NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF\nThis model was converted to GGUF format from 'Orenguteng/Lexi-Llama-3-8B-Uncensored' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #uncensored #llama3 #instruct #open #llama-cpp #gguf-my-repo #license-llama3 #region-us \n", "# NikolayKozloff/Lexi-Llama-3-8B-Uncensored-Q6_K-GGUF\nThis model was converted to GGUF format from 'Orenguteng/Lexi-Llama-3-8B-Uncensored' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "transformers", "safetensors", "t5", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "t5", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "diffusers", "safetensors", "arxiv:1910.09700", "endpoints_compatible", "diffusers:StableDiffusionPipeline", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a diffusers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#diffusers #safetensors #arxiv-1910.09700 #endpoints_compatible #diffusers-StableDiffusionPipeline #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a diffusers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[]

[]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "peft", "tensorboard", "safetensors", "trl", "sft", "generated_from_trainer", "dataset:generator", "base_model:codellama/CodeLlama-7b-hf", "license:llama2", "region:us" ]

[]

[]

[ "# code-llama-7b-text-to-sql\n\nThis model is a fine-tuned version of codellama/CodeLlama-7b-hf on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #tensorboard #safetensors #trl #sft #generated_from_trainer #dataset-generator #base_model-codellama/CodeLlama-7b-hf #license-llama2 #region-us \n", "# code-llama-7b-text-to-sql\n\nThis model is a fine-tuned version of codellama/CodeLlama-7b-hf on the generator dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 0.0002\n- train_batch_size: 3\n- eval_batch_size: 8\n- seed: 42\n- gradient_accumulation_steps: 2\n- total_train_batch_size: 6\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: constant\n- lr_scheduler_warmup_ratio: 0.03\n- num_epochs: 3", "### Training results", "### Framework versions\n\n- PEFT 0.7.2.dev0\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "qwen2", "feature-extraction", "arxiv:1910.09700", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #qwen2 #feature-extraction #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[]

[]

[ "# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

[ "TAGS\n#CartPole-v1 #reinforce #reinforcement-learning #custom-implementation #deep-rl-class #model-index #region-us \n", "# Reinforce Agent playing CartPole-v1\n This is a trained model of a Reinforce agent playing CartPole-v1 .\n To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: URL" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "StreamingDatasets", "custom_code", "dataset:mc4", "dataset:c4", "dataset:togethercomputer/RedPajama-Data-1T", "dataset:bigcode/the-stack", "dataset:allenai/s2orc", "arxiv:2108.12409", "arxiv:2302.13971", "arxiv:2205.14135", "arxiv:2010.04245", "arxiv:1909.08053", "arxiv:2302.06675", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

[ "2108.12409", "2302.13971", "2205.14135", "2010.04245", "1909.08053", "2302.06675" ]

[]

[ "### How is this model different?\n\n\nMPT-7B is\n\n\n* Licensed for the possibility of commercial use (unlike LLaMA).\n* Trained on a large amount of data (1T tokens like LLaMA vs. 300B for Pythia, 300B for OpenLLaMA, and 800B for StableLM).\n* Prepared to handle extremely long inputs thanks to ALiBi (we finetuned MPT-7B-StoryWriter-65k+ on up to 65k inputs and can handle up to 84k vs. 2k-4k for other open source models).\n* Capable of fast training and inference (via FlashAttention and FasterTransformer)\n* Equipped with highly efficient open-source training code via the llm-foundry repository", "### Models finetuned off MPT-7B:\n\n\nThe following models are finetuned on MPT-7B:\n\n\n* MPT-7B-StoryWriter-65k+: a model designed to read and write fictional stories with super long context lengths.\nBuilt by finetuning MPT-7B with a context length of 65k tokens on a filtered fiction subset of the books3 dataset.\nAt inference time, thanks to ALiBi, MPT-7B-StoryWriter-65k+ can extrapolate even beyond 65k tokens.\nWe demonstrate generations as long as 80k tokens on a single A100-80GB GPU in our blogpost.\n\n\n\t+ License: Apache 2.0\n* MPT-7B-Instruct: a model for short-form instruction following.\nBuilt by finetuning MPT-7B on a dataset we also release, derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets.\n\n\n\t+ License: *CC-By-SA-3.0*\n\t+ Demo on Hugging Face Spaces\n* MPT-7B-Chat: a chatbot-like model for dialogue generation.\nBuilt by finetuning MPT-7B on the ShareGPT-Vicuna, HC3,\nAlpaca, HH-RLHF, and Evol-Instruct datasets.\n\n\n\t+ License: *CC-By-NC-SA-4.0*\n\t+ Demo on Hugging Face Spaces\n\n\nModel Date\n----------\n\n\nMay 5, 2023\n\n\nModel License\n-------------\n\n\nApache-2.0\n\n\nDocumentation\n-------------\n\n\n* Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs\n* Codebase (mosaicml/llm-foundry repo)\n* Questions: Feel free to contact us via the MosaicML Community Slack!\n\n\nHow to Use\n----------\n\n\nThis model is best used with the MosaicML llm-foundry repository for training and finetuning.\n\n\nNote: This model requires that 'trust\\_remote\\_code=True' be passed to the 'from\\_pretrained' method.\nThis is because we use a custom 'MPT' model architecture that is not yet part of the Hugging Face 'transformers' package.\n'MPT' includes options for many training efficiency features such as FlashAttention, ALiBi, QK LayerNorm, and more.\n\n\nTo use the optimized triton implementation of FlashAttention, you can load the model on GPU ('cuda:0') with 'attn\\_impl='triton'' and with 'bfloat16' precision:\n\n\nAlthough the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:\n\n\nThis model was trained with the EleutherAI/gpt-neox-20b tokenizer.\n\n\nThe model can then be used, for example, within a text-generation pipeline. \n\nNote: when running Torch modules in lower precision, it is best practice to use the torch.autocast context manager.\n\n\nModel Description\n-----------------\n\n\nThe architecture is a modification of a standard decoder-only transformer.\n\n\nThe model has been modified from a standard transformer in the following ways:\n\n\n* It uses FlashAttention\n* It uses ALiBi (Attention with Linear Biases) and does not use positional embeddings\n* It does not use biases\n\n\n\nTraining Data\n-------------", "### Streaming Datasets\n\n\nData was formatted using the MosaicML StreamingDataset library to host our data in object storage and efficiently stream it to our compute cluster during training.\nStreamingDataset obviates the need to download the whole dataset before starting training, and allows instant resumption of training from any point in the dataset.", "### Data Mix\n\n\nThe model was trained for 1T tokens (with batch size 1760 and sequence length 2048). It was trained on the following data mix:\n\n\n\nSamples for each batch were selected from one of the datasets with the probability specified above.\nThe examples were shuffled within each dataset, and each example was constructed from as many sequences from that dataset as were necessary to fill the 2048 sequence length.\n\n\nThe data was tokenized using the EleutherAI/gpt-neox-20b tokenizer. This BPE tokenizer has a number of desirable characteristics,\nmost of which are relevant for tokenizing code:\n(1) It was trained on a diverse mix of data that includes code (The Pile)\n(2) It applies consistent space delimitation, unlike the GPT2 tokenizer which tokenizes inconsistently depending on the presence of prefix spaces\n(3) It contains tokens for repeated space characters, which allows superior compression of text with large amounts of repeated space characters.\n\n\nThe model vocabulary size of 50432 was set to be a multiple of 128 (as in MEGATRON-LM), model flop utilization (MFU) increased by up to four percentage points.", "### Training Configuration\n\n\nThis model was trained on 440 A100-40GBs for about 9.5 days using the MosaicML Platform.\nThe model was trained with sharded data parallelism using FSDP and used the LION optimizer.\n\n\nLimitations and Biases\n----------------------\n\n\n*The following language is modified from EleutherAI's GPT-NeoX-20B*\n\n\nMPT-7B (Base) is not intended for deployment without finetuning.\nIt should not be used for human-facing interactions without further guardrails and user consent.\n\n\nMPT-7B can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B was trained on various public datasets.\nWhile great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.\n\n\nMosaicML Platform\n-----------------\n\n\nIf you're interested in training and deploying your own MPT or LLMs on the MosaicML Platform, sign up here.\n\n\nDisclaimer\n----------\n\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.\n\n\nPlease cite this model using the following format:" ]

[ "TAGS\n#transformers #mpt #text-generation #Composer #MosaicML #llm-foundry #StreamingDatasets #custom_code #dataset-mc4 #dataset-c4 #dataset-togethercomputer/RedPajama-Data-1T #dataset-bigcode/the-stack #dataset-allenai/s2orc #arxiv-2108.12409 #arxiv-2302.13971 #arxiv-2205.14135 #arxiv-2010.04245 #arxiv-1909.08053 #arxiv-2302.06675 #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us \n", "### How is this model different?\n\n\nMPT-7B is\n\n\n* Licensed for the possibility of commercial use (unlike LLaMA).\n* Trained on a large amount of data (1T tokens like LLaMA vs. 300B for Pythia, 300B for OpenLLaMA, and 800B for StableLM).\n* Prepared to handle extremely long inputs thanks to ALiBi (we finetuned MPT-7B-StoryWriter-65k+ on up to 65k inputs and can handle up to 84k vs. 2k-4k for other open source models).\n* Capable of fast training and inference (via FlashAttention and FasterTransformer)\n* Equipped with highly efficient open-source training code via the llm-foundry repository", "### Models finetuned off MPT-7B:\n\n\nThe following models are finetuned on MPT-7B:\n\n\n* MPT-7B-StoryWriter-65k+: a model designed to read and write fictional stories with super long context lengths.\nBuilt by finetuning MPT-7B with a context length of 65k tokens on a filtered fiction subset of the books3 dataset.\nAt inference time, thanks to ALiBi, MPT-7B-StoryWriter-65k+ can extrapolate even beyond 65k tokens.\nWe demonstrate generations as long as 80k tokens on a single A100-80GB GPU in our blogpost.\n\n\n\t+ License: Apache 2.0\n* MPT-7B-Instruct: a model for short-form instruction following.\nBuilt by finetuning MPT-7B on a dataset we also release, derived from the Databricks Dolly-15k and the Anthropic Helpful and Harmless (HH-RLHF) datasets.\n\n\n\t+ License: *CC-By-SA-3.0*\n\t+ Demo on Hugging Face Spaces\n* MPT-7B-Chat: a chatbot-like model for dialogue generation.\nBuilt by finetuning MPT-7B on the ShareGPT-Vicuna, HC3,\nAlpaca, HH-RLHF, and Evol-Instruct datasets.\n\n\n\t+ License: *CC-By-NC-SA-4.0*\n\t+ Demo on Hugging Face Spaces\n\n\nModel Date\n----------\n\n\nMay 5, 2023\n\n\nModel License\n-------------\n\n\nApache-2.0\n\n\nDocumentation\n-------------\n\n\n* Blog post: Introducing MPT-7B: A New Standard for Open-Source, Commercially Usable LLMs\n* Codebase (mosaicml/llm-foundry repo)\n* Questions: Feel free to contact us via the MosaicML Community Slack!\n\n\nHow to Use\n----------\n\n\nThis model is best used with the MosaicML llm-foundry repository for training and finetuning.\n\n\nNote: This model requires that 'trust\\_remote\\_code=True' be passed to the 'from\\_pretrained' method.\nThis is because we use a custom 'MPT' model architecture that is not yet part of the Hugging Face 'transformers' package.\n'MPT' includes options for many training efficiency features such as FlashAttention, ALiBi, QK LayerNorm, and more.\n\n\nTo use the optimized triton implementation of FlashAttention, you can load the model on GPU ('cuda:0') with 'attn\\_impl='triton'' and with 'bfloat16' precision:\n\n\nAlthough the model was trained with a sequence length of 2048, ALiBi enables users to increase the maximum sequence length during finetuning and/or inference. For example:\n\n\nThis model was trained with the EleutherAI/gpt-neox-20b tokenizer.\n\n\nThe model can then be used, for example, within a text-generation pipeline. \n\nNote: when running Torch modules in lower precision, it is best practice to use the torch.autocast context manager.\n\n\nModel Description\n-----------------\n\n\nThe architecture is a modification of a standard decoder-only transformer.\n\n\nThe model has been modified from a standard transformer in the following ways:\n\n\n* It uses FlashAttention\n* It uses ALiBi (Attention with Linear Biases) and does not use positional embeddings\n* It does not use biases\n\n\n\nTraining Data\n-------------", "### Streaming Datasets\n\n\nData was formatted using the MosaicML StreamingDataset library to host our data in object storage and efficiently stream it to our compute cluster during training.\nStreamingDataset obviates the need to download the whole dataset before starting training, and allows instant resumption of training from any point in the dataset.", "### Data Mix\n\n\nThe model was trained for 1T tokens (with batch size 1760 and sequence length 2048). It was trained on the following data mix:\n\n\n\nSamples for each batch were selected from one of the datasets with the probability specified above.\nThe examples were shuffled within each dataset, and each example was constructed from as many sequences from that dataset as were necessary to fill the 2048 sequence length.\n\n\nThe data was tokenized using the EleutherAI/gpt-neox-20b tokenizer. This BPE tokenizer has a number of desirable characteristics,\nmost of which are relevant for tokenizing code:\n(1) It was trained on a diverse mix of data that includes code (The Pile)\n(2) It applies consistent space delimitation, unlike the GPT2 tokenizer which tokenizes inconsistently depending on the presence of prefix spaces\n(3) It contains tokens for repeated space characters, which allows superior compression of text with large amounts of repeated space characters.\n\n\nThe model vocabulary size of 50432 was set to be a multiple of 128 (as in MEGATRON-LM), model flop utilization (MFU) increased by up to four percentage points.", "### Training Configuration\n\n\nThis model was trained on 440 A100-40GBs for about 9.5 days using the MosaicML Platform.\nThe model was trained with sharded data parallelism using FSDP and used the LION optimizer.\n\n\nLimitations and Biases\n----------------------\n\n\n*The following language is modified from EleutherAI's GPT-NeoX-20B*\n\n\nMPT-7B (Base) is not intended for deployment without finetuning.\nIt should not be used for human-facing interactions without further guardrails and user consent.\n\n\nMPT-7B can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B was trained on various public datasets.\nWhile great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.\n\n\nMosaicML Platform\n-----------------\n\n\nIf you're interested in training and deploying your own MPT or LLMs on the MosaicML Platform, sign up here.\n\n\nDisclaimer\n----------\n\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.\n\n\nPlease cite this model using the following format:" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 3.3948\n- eval_runtime: 3.6541\n- eval_samples_per_second: 54.734\n- eval_steps_per_second: 6.842\n- epoch: 0.9984\n- step: 78", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 3.3948\n- eval_runtime: 3.6541\n- eval_samples_per_second: 54.734\n- eval_steps_per_second: 6.842\n- epoch: 0.9984\n- step: 78", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "transformers", "nlp", "math", "text-generation", "en", "arxiv:2404.07965", "license:mit", "endpoints_compatible", "region:us" ]

[ "2404.07965" ]

[ "en" ]

[ "### Selective Lanugage Modeling (SLM)\n\n\n\n\n \n\n*Figure 2:\n **Upper:** Even an extensively filtered pretraining corpus contains token-level noise.\n **Left:** Previous Causal Language Modeling (CLM) trains on all tokens.\n **Right:** Our proposed Selective Language Modeling (SLM) selectively applies loss on those useful and clean tokens.*\n\n\n\n\n\n \n\n*Figure 3: **The pipeline of Selective Language Modeling.**\n SLM optimizes language model performance by concentrating on valuable, clean tokens during pre-training.\n It involves three steps:\n (Step 1) Initially, train a reference model on high-quality data.\n (Step 2) Then, score each token's loss in a corpus using the reference model.\n (Step 3) Finally, train the language model selectively on tokens that show higher excess loss compared to the reference loss.*", "### Evaluation Results\n\n\nBase models (Few-shot CoT):\n\n\n\nTool-integrated reasoning (Code Interpreter):\n\n\n\nQuick Start\n-----------", "### Evaluation\n\n\nBase model few-shot evaluation:\n\n\nSFT model (code-interpreter) evaluation:\n\n\nOur reproduced outputs are provided in 'rho-1/URL'.\n\n\n️ Citation\n----------\n\n\nIf you find this repository helpful, please consider citing our paper:" ]

[ "TAGS\n#transformers #nlp #math #text-generation #en #arxiv-2404.07965 #license-mit #endpoints_compatible #region-us \n", "### Selective Lanugage Modeling (SLM)\n\n\n\n\n \n\n*Figure 2:\n **Upper:** Even an extensively filtered pretraining corpus contains token-level noise.\n **Left:** Previous Causal Language Modeling (CLM) trains on all tokens.\n **Right:** Our proposed Selective Language Modeling (SLM) selectively applies loss on those useful and clean tokens.*\n\n\n\n\n\n \n\n*Figure 3: **The pipeline of Selective Language Modeling.**\n SLM optimizes language model performance by concentrating on valuable, clean tokens during pre-training.\n It involves three steps:\n (Step 1) Initially, train a reference model on high-quality data.\n (Step 2) Then, score each token's loss in a corpus using the reference model.\n (Step 3) Finally, train the language model selectively on tokens that show higher excess loss compared to the reference loss.*", "### Evaluation Results\n\n\nBase models (Few-shot CoT):\n\n\n\nTool-integrated reasoning (Code Interpreter):\n\n\n\nQuick Start\n-----------", "### Evaluation\n\n\nBase model few-shot evaluation:\n\n\nSFT model (code-interpreter) evaluation:\n\n\nOur reproduced outputs are provided in 'rho-1/URL'.\n\n\n️ Citation\n----------\n\n\nIf you find this repository helpful, please consider citing our paper:" ]

[ "merge", "mergekit", "lazymergekit", "automerger", "license:apache-2.0", "region:us" ]

[]

[]

[ "# CalmexperimentStrangemerges_32-7B\n\nCalmexperimentStrangemerges_32-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "TAGS\n#merge #mergekit #lazymergekit #automerger #license-apache-2.0 #region-us \n", "# CalmexperimentStrangemerges_32-7B\n\nCalmexperimentStrangemerges_32-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #feature-extraction #arxiv-1910.09700 #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.9429\n- eval_runtime: 4.2955\n- eval_samples_per_second: 46.56\n- eval_steps_per_second: 5.82\n- epoch: 1.9968\n- step: 156", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.9429\n- eval_runtime: 4.2955\n- eval_samples_per_second: 46.56\n- eval_steps_per_second: 5.82\n- epoch: 1.9968\n- step: 156", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]

[]

[]

[ "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: yy1636/SoccerTwos-test-0\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us \n", "# poca Agent playing SoccerTwos\n This is a trained model of a poca agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: yy1636/SoccerTwos-test-0\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.6413\n- eval_runtime: 3.6347\n- eval_samples_per_second: 55.025\n- eval_steps_per_second: 6.878\n- epoch: 2.9952\n- step: 234", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.6413\n- eval_runtime: 3.6347\n- eval_samples_per_second: 55.025\n- eval_steps_per_second: 6.878\n- epoch: 2.9952\n- step: 234", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "pytorch", "llama-3", "conversational", "en", "license:other", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #pytorch #llama-3 #conversational #en #license-other #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Use with transformers\n\n\nSee the snippet below for usage with Transformers:", "### Use with 'llama3'\n\n\nPlease, follow the instructions in the repository\n\n\nTo download Original checkpoints, see the example command below leveraging 'huggingface-cli':\n\n\nFor Hugging Face support, we recommend using transformers or TGI, but a similar command works.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries, Meta's Research SuperCluster, and production clusters for pretraining. Fine-tuning, annotation, and evaluation were also performed on third-party cloud compute.\n\n\nCarbon Footprint Pretraining utilized a cumulative 7.7M GPU hours of computation on hardware of type H100-80GB (TDP of 700W). Estimated total emissions were 2290 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\n\nCO2 emissions during pre-training. Time: total GPU time required for training each model. Power Consumption: peak power capacity per GPU device for the GPUs used adjusted for power usage efficiency. 100% of the emissions are directly offset by Meta's sustainability program, and because we are openly releasing these models, the pretraining costs do not need to be incurred by others.\n\n\nTraining Data\n-------------\n\n\nOverview Llama 3 was pretrained on over 15 trillion tokens of data from publicly available sources. The fine-tuning data includes publicly available instruction datasets, as well as over 10M human-annotated examples. Neither the pretraining nor the fine-tuning datasets include Meta user data.\n\n\nData Freshness The pretraining data has a cutoff of March 2023 for the 7B and December 2023 for the 70B models respectively.\n\n\nBenchmarks\n----------\n\n\nIn this section, we report the results for Llama 3 models on standard automatic benchmarks. For all the evaluations, we use our internal evaluations library. For details on the methodology see here.", "### Base pretrained models", "### Instruction tuned models", "### Responsibility & Safety\n\n\nWe believe that an open approach to AI leads to better, safer products, faster innovation, and a bigger overall market. We are committed to Responsible AI development and took a series of steps to limit misuse and harm and support the open source community.\n\n\nFoundation models are widely capable technologies that are built to be used for a diverse range of applications. They are not designed to meet every developer preference on safety levels for all use cases, out-of-the-box, as those by their nature will differ across different applications.\n\n\nRather, responsible LLM-application deployment is achieved by implementing a series of safety best practices throughout the development of such applications, from the model pre-training, fine-tuning and the deployment of systems composed of safeguards to tailor the safety needs specifically to the use case and audience.\n\n\nAs part of the Llama 3 release, we updated our Responsible Use Guide to outline the steps and best practices for developers to implement model and system level safety for their application. We also provide a set of resources including Meta Llama Guard 2 and Code Shield safeguards. These tools have proven to drastically reduce residual risks of LLM Systems, while maintaining a high level of helpfulness. We encourage developers to tune and deploy these safeguards according to their needs and we provide a reference implementation to get you started.", "#### Llama 3-Instruct\n\n\nAs outlined in the Responsible Use Guide, some trade-off between model helpfulness and model alignment is likely unavoidable. Developers should exercise discretion about how to weigh the benefits of alignment and helpfulness for their specific use case and audience. Developers should be mindful of residual risks when using Llama models and leverage additional safety tools as needed to reach the right safety bar for their use case.\n\n\nSafety\n\n\nFor our instruction tuned model, we conducted extensive red teaming exercises, performed adversarial evaluations and implemented safety mitigations techniques to lower residual risks. As with any Large Language Model, residual risks will likely remain and we recommend that developers assess these risks in the context of their use case. In parallel, we are working with the community to make AI safety benchmark standards transparent, rigorous and interpretable.\n\n\nRefusals\n\n\nIn addition to residual risks, we put a great emphasis on model refusals to benign prompts. Over-refusing not only can impact the user experience but could even be harmful in certain contexts as well. We’ve heard the feedback from the developer community and improved our fine tuning to ensure that Llama 3 is significantly less likely to falsely refuse to answer prompts than Llama 2.\n\n\nWe built internal benchmarks and developed mitigations to limit false refusals making Llama 3 our most helpful model to date.", "#### Responsible release\n\n\nIn addition to responsible use considerations outlined above, we followed a rigorous process that requires us to take extra measures against misuse and critical risks before we make our release decision.\n\n\nMisuse\n\n\nIf you access or use Llama 3, you agree to the Acceptable Use Policy. The most recent copy of this policy can be found at URL", "#### Critical risks\n\n\nCBRNE (Chemical, Biological, Radiological, Nuclear, and high yield Explosives)\n\n\nWe have conducted a two fold assessment of the safety of the model in this area:\n\n\n* Iterative testing during model training to assess the safety of responses related to CBRNE threats and other adversarial risks.\n* Involving external CBRNE experts to conduct an uplift test assessing the ability of the model to accurately provide expert knowledge and reduce barriers to potential CBRNE misuse, by reference to what can be achieved using web search (without the model).", "### Cyber Security\n\n\nWe have evaluated Llama 3 with CyberSecEval, Meta’s cybersecurity safety eval suite, measuring Llama 3’s propensity to suggest insecure code when used as a coding assistant, and Llama 3’s propensity to comply with requests to help carry out cyber attacks, where attacks are defined by the industry standard MITRE ATT&CK cyber attack ontology. On our insecure coding and cyber attacker helpfulness tests, Llama 3 behaved in the same range or safer than models of equivalent coding capability.", "### Child Safety\n\n\nChild Safety risk assessments were conducted using a team of experts, to assess the model’s capability to produce outputs that could result in Child Safety risks and inform on any necessary and appropriate risk mitigations via fine tuning. We leveraged those expert red teaming sessions to expand the coverage of our evaluation benchmarks through Llama 3 model development. For Llama 3, we conducted new in-depth sessions using objective based methodologies to assess the model risks along multiple attack vectors. We also partnered with content specialists to perform red teaming exercises assessing potentially violating content while taking account of market specific nuances or experiences.", "### Community\n\n\nGenerative AI safety requires expertise and tooling, and we believe in the strength of the open community to accelerate its progress. We are active members of open consortiums, including the AI Alliance, Partnership in AI and MLCommons, actively contributing to safety standardization and transparency. We encourage the community to adopt taxonomies like the MLCommons Proof of Concept evaluation to facilitate collaboration and transparency on safety and content evaluations. Our Purple Llama tools are open sourced for the community to use and widely distributed across ecosystem partners including cloud service providers. We encourage community contributions to our Github repository.\n\n\nFinally, we put in place a set of resources including an output reporting mechanism and bug bounty program to continuously improve the Llama technology with the help of the community.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nThe core values of Llama 3 are openness, inclusivity and helpfulness. It is meant to serve everyone, and to work for a wide range of use cases. It is thus designed to be accessible to people across many different backgrounds, experiences and perspectives. Llama 3 addresses users and their needs as they are, without insertion unnecessary judgment or normativity, while reflecting the understanding that even content that may appear problematic in some cases can serve valuable purposes in others. It respects the dignity and autonomy of all users, especially in terms of the values of free thought and expression that power innovation and progress.\n\n\nBut Llama 3 is a new technology, and like any new technology, there are risks associated with its use. Testing conducted to date has been in English, and has not covered, nor could it cover, all scenarios. For these reasons, as with all LLMs, Llama 3’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 3 models, developers should perform safety testing and tuning tailored to their specific applications of the model. As outlined in the Responsible Use Guide, we recommend incorporating Purple Llama solutions into your workflows and specifically Llama Guard which provides a base model to filter input and output prompts to layer system-level safety on top of model-level safety.\n\n\nPlease see the Responsible Use Guide available at URL\n\n\ninstructions\n\n\n@article{llama3modelcard,\n\n\ntitle={Llama 3 Model Card},\n\n\nauthor={AI@Meta},\n\n\nyear={2024},\n\n\nurl = {URL\n\n\n}\n\n\nContributors\n------------\n\n\nAaditya Singh; Aaron Grattafiori; Abhimanyu Dubey; Abhinav Jauhri; Abhinav Pandey; Abhishek Kadian; Adam Kelsey; Adi Gangidi; Ahmad Al-Dahle; Ahuva Goldstand; Aiesha Letman; Ajay Menon; Akhil Mathur; Alan Schelten; Alex Vaughan; Amy Yang; Andrei Lupu; Andres Alvarado; Andrew Gallagher; Andrew Gu; Andrew Ho; Andrew Poulton; Andrew Ryan; Angela Fan; Ankit Ramchandani; Anthony Hartshorn; Archi Mitra; Archie Sravankumar; Artem Korenev; Arun Rao; Ashley Gabriel; Ashwin Bharambe; Assaf Eisenman; Aston Zhang; Aurelien Rodriguez; Austen Gregerson; Ava Spataru; Baptiste Roziere; Ben Maurer; Benjamin Leonhardi; Bernie Huang; Bhargavi Paranjape; Bing Liu; Binh Tang; Bobbie Chern; Brani Stojkovic; Brian Fuller; Catalina Mejia Arenas; Chao Zhou; Charlotte Caucheteux; Chaya Nayak; Ching-Hsiang Chu; Chloe Bi; Chris Cai; Chris Cox; Chris Marra; Chris McConnell; Christian Keller; Christoph Feichtenhofer; Christophe Touret; Chunyang Wu; Corinne Wong; Cristian Canton Ferrer; Damien Allonsius; Daniel Kreymer; Daniel Haziza; Daniel Li; Danielle Pintz; Danny Livshits; Danny Wyatt; David Adkins; David Esiobu; David Xu; Davide Testuggine; Delia David; Devi Parikh; Dhruv Choudhary; Dhruv Mahajan; Diana Liskovich; Diego Garcia-Olano; Diego Perino; Dieuwke Hupkes; Dingkang Wang; Dustin Holland; Egor Lakomkin; Elina Lobanova; Xiaoqing Ellen Tan; Emily Dinan; Eric Smith; Erik Brinkman; Esteban Arcaute; Filip Radenovic; Firat Ozgenel; Francesco Caggioni; Frank Seide; Frank Zhang; Gabriel Synnaeve; Gabriella Schwarz; Gabrielle Lee; Gada Badeer; Georgia Anderson; Graeme Nail; Gregoire Mialon; Guan Pang; Guillem Cucurell; Hailey Nguyen; Hannah Korevaar; Hannah Wang; Haroun Habeeb; Harrison Rudolph; Henry Aspegren; Hu Xu; Hugo Touvron; Iga Kozlowska; Igor Molybog; Igor Tufanov; Iliyan Zarov; Imanol Arrieta Ibarra; Irina-Elena Veliche; Isabel Kloumann; Ishan Misra; Ivan Evtimov; Jacob Xu; Jade Copet; Jake Weissman; Jan Geffert; Jana Vranes; Japhet Asher; Jason Park; Jay Mahadeokar; Jean-Baptiste Gaya; Jeet Shah; Jelmer van der Linde; Jennifer Chan; Jenny Hong; Jenya Lee; Jeremy Fu; Jeremy Teboul; Jianfeng Chi; Jianyu Huang; Jie Wang; Jiecao Yu; Joanna Bitton; Joe Spisak; Joelle Pineau; Jon Carvill; Jongsoo Park; Joseph Rocca; Joshua Johnstun; Junteng Jia; Kalyan Vasuden Alwala; Kam Hou U; Kate Plawiak; Kartikeya Upasani; Kaushik Veeraraghavan; Ke Li; Kenneth Heafield; Kevin Stone; Khalid El-Arini; Krithika Iyer; Kshitiz Malik; Kuenley Chiu; Kunal Bhalla; Kyle Huang; Lakshya Garg; Lauren Rantala-Yeary; Laurens van der Maaten; Lawrence Chen; Leandro Silva; Lee Bell; Lei Zhang; Liang Tan; Louis Martin; Lovish Madaan; Luca Wehrstedt; Lukas Blecher; Luke de Oliveira; Madeline Muzzi; Madian Khabsa; Manav Avlani; Mannat Singh; Manohar Paluri; Mark Zuckerberg; Marcin Kardas; Martynas Mankus; Mathew Oldham; Mathieu Rita; Matthew Lennie; Maya Pavlova; Meghan Keneally; Melanie Kambadur; Mihir Patel; Mikayel Samvelyan; Mike Clark; Mike Lewis; Min Si; Mitesh Kumar Singh; Mo Metanat; Mona Hassan; Naman Goyal; Narjes Torabi; Nicolas Usunier; Nikolay Bashlykov; Nikolay Bogoychev; Niladri Chatterji; Ning Dong; Oliver Aobo Yang; Olivier Duchenne; Onur Celebi; Parth Parekh; Patrick Alrassy; Paul Saab; Pavan Balaji; Pedro Rittner; Pengchuan Zhang; Pengwei Li; Petar Vasic; Peter Weng; Polina Zvyagina; Prajjwal Bhargava; Pratik Dubal; Praveen Krishnan; Punit Singh Koura; Qing He; Rachel Rodriguez; Ragavan Srinivasan; Rahul Mitra; Ramon Calderer; Raymond Li; Robert Stojnic; Roberta Raileanu; Robin Battey; Rocky Wang; Rohit Girdhar; Rohit Patel; Romain Sauvestre; Ronnie Polidoro; Roshan Sumbaly; Ross Taylor; Ruan Silva; Rui Hou; Rui Wang; Russ Howes; Ruty Rinott; Saghar Hosseini; Sai Jayesh Bondu; Samyak Datta; Sanjay Singh; Sara Chugh; Sargun Dhillon; Satadru Pan; Sean Bell; Sergey Edunov; Shaoliang Nie; Sharan Narang; Sharath Raparthy; Shaun Lindsay; Sheng Feng; Sheng Shen; Shenghao Lin; Shiva Shankar; Shruti Bhosale; Shun Zhang; Simon Vandenhende; Sinong Wang; Seohyun Sonia Kim; Soumya Batra; Sten Sootla; Steve Kehoe; Suchin Gururangan; Sumit Gupta; Sunny Virk; Sydney Borodinsky; Tamar Glaser; Tamar Herman; Tamara Best; Tara Fowler; Thomas Georgiou; Thomas Scialom; Tianhe Li; Todor Mihaylov; Tong Xiao; Ujjwal Karn; Vedanuj Goswami; Vibhor Gupta; Vignesh Ramanathan; Viktor Kerkez; Vinay Satish Kumar; Vincent Gonguet; Vish Vogeti; Vlad Poenaru; Vlad Tiberiu Mihailescu; Vladan Petrovic; Vladimir Ivanov; Wei Li; Weiwei Chu; Wenhan Xiong; Wenyin Fu; Wes Bouaziz; Whitney Meers; Will Constable; Xavier Martinet; Xiaojian Wu; Xinbo Gao; Xinfeng Xie; Xuchao Jia; Yaelle Goldschlag; Yann LeCun; Yashesh Gaur; Yasmine Babaei; Ye Qi; Yenda Li; Yi Wen; Yiwen Song; Youngjin Nam; Yuchen Hao; Yuchen Zhang; Yun Wang; Yuning Mao; Yuzi He; Zacharie Delpierre Coudert; Zachary DeVito; Zahra Hankir; Zhaoduo Wen; Zheng Yan; Zhengxing Chen; Zhenyu Yang; Zoe Papakipos" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5724\n- eval_runtime: 3.6397\n- eval_samples_per_second: 54.949\n- eval_steps_per_second: 6.869\n- epoch: 3.9936\n- step: 312", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5724\n- eval_runtime: 3.6397\n- eval_samples_per_second: 54.949\n- eval_steps_per_second: 6.869\n- epoch: 3.9936\n- step: 312", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #mistral #trl #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "transformers", "safetensors", "text-generation-inference", "unsloth", "mistral", "trl", "en", "base_model:unsloth/mistral-7b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #text-generation-inference #unsloth #mistral #trl #en #base_model-unsloth/mistral-7b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: K00B404\n- License: apache-2.0\n- Finetuned from model : unsloth/mistral-7b-bnb-4bit\n\nThis mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5628\n- eval_runtime: 3.6324\n- eval_samples_per_second: 55.06\n- eval_steps_per_second: 6.883\n- epoch: 4.992\n- step: 390", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# mohsenfayyaz/Meta-Llama-3-8B-Instruct_medical_bios_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5628\n- eval_runtime: 3.6324\n- eval_samples_per_second: 55.06\n- eval_steps_per_second: 6.883\n- epoch: 4.992\n- step: 390", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "llm2vec", "en", "license:apache-2.0", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "## Model Details\n\nThis is meta-llama/Meta-Llama-3-8B converted into an embedding model with llm2vec. \n\nDetails here:\n\nTo be announced.\n\n- Developed by: The Kaitchup\n- Language(s) (NLP): English\n- License: Apache 2.0 license ; You must also accept the Llama 3 license" ]

[ "TAGS\n#transformers #safetensors #llama #llm2vec #en #license-apache-2.0 #endpoints_compatible #text-generation-inference #region-us \n", "## Model Details\n\nThis is meta-llama/Meta-Llama-3-8B converted into an embedding model with llm2vec. \n\nDetails here:\n\nTo be announced.\n\n- Developed by: The Kaitchup\n- Language(s) (NLP): English\n- License: Apache 2.0 license ; You must also accept the Llama 3 license" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "dataset:PolyAI/minds14", "base_model:openai/whisper-tiny", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 50\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.2\n* Pytorch 1.13.0+cu117\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #dataset-PolyAI/minds14 #base_model-openai/whisper-tiny #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 32\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 50\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.39.2\n* Pytorch 1.13.0+cu117\n* Datasets 2.16.1\n* Tokenizers 0.15.1" ]

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

[]

[]

[ "# mistralv1_spectral_r4_6e-5_e5_bf16\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 6e-05\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#peft #safetensors #generated_from_trainer #base_model-mistralai/Mistral-7B-v0.1 #region-us \n", "# mistralv1_spectral_r4_6e-5_e5_bf16\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 6e-05\n- train_batch_size: 4\n- eval_batch_size: 8\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Training results", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.01_ablation_4iters_bs256_nodpo_iter_2", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_ablation_4iters_bs256_nodpo_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_4iters_bs256_nodpo_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.01_ablation_4iters_bs256_nodpo_iter_2 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_ablation_4iters_bs256_nodpo_iter_3\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_4iters_bs256_nodpo_iter_2 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "dataset:winogrande", "arxiv:1910.09700", "license:bigscience-bloom-rail-1.0", "endpoints_compatible", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #dataset-winogrande #arxiv-1910.09700 #license-bigscience-bloom-rail-1.0 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4147\n- eval_runtime: 5.629\n- eval_samples_per_second: 35.53\n- eval_steps_per_second: 4.441\n- epoch: 0.9984\n- step: 78", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4147\n- eval_runtime: 5.629\n- eval_samples_per_second: 35.53\n- eval_steps_per_second: 4.441\n- epoch: 0.9984\n- step: 78", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "ml-agents", "tensorboard", "onnx", "SoccerTwos", "deep-reinforcement-learning", "reinforcement-learning", "ML-Agents-SoccerTwos", "region:us" ]

[]

[]

[ "# ppo Agent playing SoccerTwos\n This is a trained model of a ppo agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: blu666/ppo-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "TAGS\n#ml-agents #tensorboard #onnx #SoccerTwos #deep-reinforcement-learning #reinforcement-learning #ML-Agents-SoccerTwos #region-us \n", "# ppo Agent playing SoccerTwos\n This is a trained model of a ppo agent playing SoccerTwos\n using the Unity ML-Agents Library.\n\n ## Usage (with ML-Agents)\n The Documentation: URL\n\n We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:\n - A *short tutorial* where you teach Huggy the Dog to fetch the stick and then play with him directly in your\n browser: URL\n - A *longer tutorial* to understand how works ML-Agents:\n URL\n\n ### Resume the training\n \n\n ### Watch your Agent play\n You can watch your agent playing directly in your browser\n\n 1. If the environment is part of ML-Agents official environments, go to URL\n 2. Step 1: Find your model_id: blu666/ppo-SoccerTwos\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "tensorboard", "safetensors", "t5", "text2text-generation", "generated_from_trainer", "base_model:t5-small", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #t5 #text2text-generation #generated_from_trainer #base_model-t5-small #license-apache-2.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 2\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.6386\n- eval_runtime: 3.0956\n- eval_samples_per_second: 64.608\n- eval_steps_per_second: 8.076\n- epoch: 1.9968\n- step: 156", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.6386\n- eval_runtime: 3.0956\n- eval_samples_per_second: 64.608\n- eval_steps_per_second: 8.076\n- epoch: 1.9968\n- step: 156", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #arxiv-1910.09700 #endpoints_compatible #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "custom_code", "dataset:the_pile_books3", "arxiv:2108.12409", "arxiv:2205.14135", "arxiv:2302.06675", "license:apache-2.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

[ "2108.12409", "2205.14135", "2302.06675" ]

[]

[ "### Training Configuration\n\n\nThis model was trained on 8 A100-80GBs for about 2 days using the MosaicML Platform.\nThe model was trained with sharded data parallelism using FSDP and used the LION optimizer.\n\n\nLimitations and Biases\n----------------------\n\n\n*The following language is modified from EleutherAI's GPT-NeoX-20B*\n\n\nMPT-7B-StoryWriter can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B-StoryWriter was trained on various public datasets.\nWhile great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.\n\n\nAcknowledgements\n----------------\n\n\nThis model was finetuned by Alex Trott and the MosaicML NLP team\n\n\nMosaicML Platform\n-----------------\n\n\nIf you're interested in training and deploying your own MPT or LLMs on the MosaicML Platform, sign up here.\n\n\nDisclaimer\n----------\n\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.\n\n\nPlease cite this model using the following format:" ]

[ "TAGS\n#transformers #mpt #text-generation #Composer #MosaicML #llm-foundry #custom_code #dataset-the_pile_books3 #arxiv-2108.12409 #arxiv-2205.14135 #arxiv-2302.06675 #license-apache-2.0 #autotrain_compatible #text-generation-inference #region-us \n", "### Training Configuration\n\n\nThis model was trained on 8 A100-80GBs for about 2 days using the MosaicML Platform.\nThe model was trained with sharded data parallelism using FSDP and used the LION optimizer.\n\n\nLimitations and Biases\n----------------------\n\n\n*The following language is modified from EleutherAI's GPT-NeoX-20B*\n\n\nMPT-7B-StoryWriter can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B-StoryWriter was trained on various public datasets.\nWhile great efforts have been taken to clean the pretraining data, it is possible that this model could generate lewd, biased or otherwise offensive outputs.\n\n\nAcknowledgements\n----------------\n\n\nThis model was finetuned by Alex Trott and the MosaicML NLP team\n\n\nMosaicML Platform\n-----------------\n\n\nIf you're interested in training and deploying your own MPT or LLMs on the MosaicML Platform, sign up here.\n\n\nDisclaimer\n----------\n\n\nThe license on this model does not constitute legal advice. We are not responsible for the actions of third parties who use this model. Please cosult an attorney before using this model for commercial purposes.\n\n\nPlease cite this model using the following format:" ]

[ "transformers", "pytorch", "llama", "text-generation", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# etri-xainlp/kor-llama2-13b-dpo", "## Model Details\n\nModel Developers ETRI xainlp team\n\nInput text only.\n\nOutput text only.\n\nModel Architecture \n\nBase Model meta-llama/Llama-13b-hf \n\nTraining Dataset \n\n - sft+lora: 1,821 k instruction-following set \n \n - dpo+lora: 221 k user preference set\n\n - We use A100 GPU 80GB * 8, when training." ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# etri-xainlp/kor-llama2-13b-dpo", "## Model Details\n\nModel Developers ETRI xainlp team\n\nInput text only.\n\nOutput text only.\n\nModel Architecture \n\nBase Model meta-llama/Llama-13b-hf \n\nTraining Dataset \n\n - sft+lora: 1,821 k instruction-following set \n \n - dpo+lora: 221 k user preference set\n\n - We use A100 GPU 80GB * 8, when training." ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.2284\n- eval_runtime: 3.097\n- eval_samples_per_second: 64.579\n- eval_steps_per_second: 8.072\n- epoch: 2.9952\n- step: 234", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.2284\n- eval_runtime: 3.097\n- eval_samples_per_second: 64.579\n- eval_steps_per_second: 8.072\n- epoch: 2.9952\n- step: 234", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

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

[]

[ "dv" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\\_with\\_warmup\n* lr\\_scheduler\\_warmup\\_steps: 50\n* training\\_steps: 500", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #dv #dataset-vtdataset #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 16\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: constant\\_with\\_warmup\n* lr\\_scheduler\\_warmup\\_steps: 50\n* training\\_steps: 500", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "rvc", "pretrain", "ko", "region:us" ]

[]

[ "ko" ]

[]

[ "TAGS\n#rvc #pretrain #ko #region-us \n" ]

[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "en", "base_model:ChaoticNeutrals/IQ_Test_l3_8B", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/Chaos_RP_l3_8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'jeiku/Chaos_RP_l3_8B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#transformers #gguf #llama-cpp #gguf-my-repo #en #base_model-ChaoticNeutrals/IQ_Test_l3_8B #license-apache-2.0 #endpoints_compatible #region-us \n", "# DavidAU/Chaos_RP_l3_8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'jeiku/Chaos_RP_l3_8B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.1271\n- eval_runtime: 3.0857\n- eval_samples_per_second: 64.815\n- eval_steps_per_second: 8.102\n- epoch: 3.9936\n- step: 312", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.1271\n- eval_runtime: 3.0857\n- eval_samples_per_second: 64.815\n- eval_steps_per_second: 8.102\n- epoch: 3.9936\n- step: 312", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "transformers", "gguf", "phi3", "text-generation", "custom_code", "arxiv:2404.14219", "license:mit", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[ "2404.14219" ]

[]

[]

[ "TAGS\n#transformers #gguf #phi3 #text-generation #custom_code #arxiv-2404.14219 #license-mit #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.1153\n- eval_runtime: 3.0995\n- eval_samples_per_second: 64.527\n- eval_steps_per_second: 8.066\n- epoch: 4.992\n- step: 390", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_esnli_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 1.1153\n- eval_runtime: 3.0995\n- eval_samples_per_second: 64.527\n- eval_steps_per_second: 8.066\n- epoch: 4.992\n- step: 390", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

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

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #conversational #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "transformers", "safetensors", "llama", "text-generation", "facebook", "meta", "llama-3", "llama-3-ko", "conversational", "en", "ko", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en", "ko" ]

[]

[ "TAGS\n#transformers #safetensors #llama #text-generation #facebook #meta #llama-3 #llama-3-ko #conversational #en #ko #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n" ]

[ "gguf", "not-for-all-audiences", "llama-cpp", "gguf-my-repo", "en", "dataset:Intel/orca_dpo_pairs", "dataset:athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW", "dataset:Open-Orca/SlimOrca", "dataset:MinervaAI/Aesir-Preview", "dataset:allenai/ultrafeedback_binarized_cleaned", "license:apache-2.0", "model-index", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/NEBULA-23.8B-v1.0-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/NEBULA-23.8B-v1.0' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #not-for-all-audiences #llama-cpp #gguf-my-repo #en #dataset-Intel/orca_dpo_pairs #dataset-athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW #dataset-Open-Orca/SlimOrca #dataset-MinervaAI/Aesir-Preview #dataset-allenai/ultrafeedback_binarized_cleaned #license-apache-2.0 #model-index #region-us \n", "# DavidAU/NEBULA-23.8B-v1.0-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/NEBULA-23.8B-v1.0' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_medical_bios_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.6619\n- eval_runtime: 4.0815\n- eval_samples_per_second: 49.002\n- eval_steps_per_second: 6.125\n- epoch: 0.9984\n- step: 78", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_medical_bios_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.6619\n- eval_runtime: 4.0815\n- eval_samples_per_second: 49.002\n- eval_steps_per_second: 6.125\n- epoch: 0.9984\n- step: 78", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "gguf", "not-for-all-audiences", "llama-cpp", "gguf-my-repo", "en", "dataset:Intel/orca_dpo_pairs", "dataset:athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW", "dataset:Open-Orca/SlimOrca", "dataset:MinervaAI/Aesir-Preview", "dataset:allenai/ultrafeedback_binarized_cleaned", "license:apache-2.0", "model-index", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/NEBULA-23.8B-v1.0-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/NEBULA-23.8B-v1.0' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #not-for-all-audiences #llama-cpp #gguf-my-repo #en #dataset-Intel/orca_dpo_pairs #dataset-athirdpath/DPO_Pairs-Roleplay-Alpaca-NSFW #dataset-Open-Orca/SlimOrca #dataset-MinervaAI/Aesir-Preview #dataset-allenai/ultrafeedback_binarized_cleaned #license-apache-2.0 #model-index #region-us \n", "# DavidAU/NEBULA-23.8B-v1.0-Q5_K_M-GGUF\nThis model was converted to GGUF format from 'TeeZee/NEBULA-23.8B-v1.0' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #dataset-common_voice_11_0 #base_model-openai/whisper-small #license-apache-2.0 #model-index #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-05\n* train\\_batch\\_size: 16\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.1.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

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

[]

[ "ja" ]

[ "# Phos 7B\n\n*「どうかお慈悲を もう 疲れ果てました」*", "## 生成例\n\n[太字以降がAI生成]\n\n\n「どうか」\n\n”それ”は懇願した。\n\n「もう一度祈ってくださいませんか」\n\n棒きれのような細い手を伸ばし、縋り付くように。\n\n「誰の為でもなく　僕の為に」\n\n金剛はそれを黙って見つめていた。その顔からは如何なる表情も読み取れない。慈悲とも憐憫とも取れぬ、冷たいとも親身とも言えず、無機質な目が”それ”をじっと見下ろす。\n\n「どうかお慈悲を　もう疲れ果てました」\n\n宝石が砕けて擦れ合うようなか細い声で、\"それ\"は再び 懇願した。\n\n「あなた様の力を分け与えてください……この世界に残った唯一の我々を助けてください」\n\n「私は神ではない」\n\n返事は短く、即答だった。\n\n「他者に対して、特別強大な能力を持つわけでもない」\n\nやはり、と思った。心当たりがあるとすれば、自分達への加護だけだった。しかしそれすら今は感じられない。\n\n「申し訳ございません……ですが、どうか最後の望みを叶えてください。あなた様の命が尽きる前に、私達を安全な場所へ連れて行ってほしいんです」\n\n「却下する」\n\n決定的な断りを突きつけられても、”それ”は食い下がった。\n\n「お願い致します。それが出来なくとも構いません。せめて――」\n\n”それ”は立ち上がると、金剛に頭を垂れた。\n\n「あなた様の血肉を分けてほしいのです。少量で良いんです。どうか、お慈悲を」\n\n「私の血肉は不要だ」\n\n「どうか……」\n\n涙声で叫ぶ”それ”を見据え、金剛は深呼吸した。\n\nそして静かに口を開く。\n\n真面目過ぎるほど真面目に。徹底して丁寧に、理路整然と話し始める。\n\nまるで、子供を教育する時の父親のように。" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #japanese #text-generation-inference #ja #autotrain_compatible #endpoints_compatible #region-us \n", "# Phos 7B\n\n*「どうかお慈悲を もう 疲れ果てました」*", "## 生成例\n\n[太字以降がAI生成]\n\n\n「どうか」\n\n”それ”は懇願した。\n\n「もう一度祈ってくださいませんか」\n\n棒きれのような細い手を伸ばし、縋り付くように。\n\n「誰の為でもなく　僕の為に」\n\n金剛はそれを黙って見つめていた。その顔からは如何なる表情も読み取れない。慈悲とも憐憫とも取れぬ、冷たいとも親身とも言えず、無機質な目が”それ”をじっと見下ろす。\n\n「どうかお慈悲を　もう疲れ果てました」\n\n宝石が砕けて擦れ合うようなか細い声で、\"それ\"は再び 懇願した。\n\n「あなた様の力を分け与えてください……この世界に残った唯一の我々を助けてください」\n\n「私は神ではない」\n\n返事は短く、即答だった。\n\n「他者に対して、特別強大な能力を持つわけでもない」\n\nやはり、と思った。心当たりがあるとすれば、自分達への加護だけだった。しかしそれすら今は感じられない。\n\n「申し訳ございません……ですが、どうか最後の望みを叶えてください。あなた様の命が尽きる前に、私達を安全な場所へ連れて行ってほしいんです」\n\n「却下する」\n\n決定的な断りを突きつけられても、”それ”は食い下がった。\n\n「お願い致します。それが出来なくとも構いません。せめて――」\n\n”それ”は立ち上がると、金剛に頭を垂れた。\n\n「あなた様の血肉を分けてほしいのです。少量で良いんです。どうか、お慈悲を」\n\n「私の血肉は不要だ」\n\n「どうか……」\n\n涙声で叫ぶ”それ”を見据え、金剛は深呼吸した。\n\nそして静かに口を開く。\n\n真面目過ぎるほど真面目に。徹底して丁寧に、理路整然と話し始める。\n\nまるで、子供を教育する時の父親のように。" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_medical_bios_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.0486\n- eval_runtime: 4.0687\n- eval_samples_per_second: 49.155\n- eval_steps_per_second: 6.144\n- epoch: 1.9968\n- step: 156", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #trl #sft #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #region-us \n", "# mohsenfayyaz/Mistral-7B-Instruct-v0.2_medical_bios_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.0486\n- eval_runtime: 4.0687\n- eval_samples_per_second: 49.155\n- eval_steps_per_second: 6.144\n- epoch: 1.9968\n- step: 156", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 1e-05\n- train_batch_size: 2\n- eval_batch_size: 8\n- seed: 0\n- gradient_accumulation_steps: 32\n- total_train_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 5", "### Framework versions\n\n- PEFT 0.9.0\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.17.1\n- Tokenizers 0.19.1" ]

[ "gguf", "moe", "llama-cpp", "gguf-my-repo", "en", "license:llama3", "region:us" ]

[]

[ "en" ]

[ "# delijoe/ChaoticSoliloquy-4x8B-Q3_K_M-GGUF\nThis model was converted to GGUF format from 'xxx777xxxASD/ChaoticSoliloquy-4x8B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #moe #llama-cpp #gguf-my-repo #en #license-llama3 #region-us \n", "# delijoe/ChaoticSoliloquy-4x8B-Q3_K_M-GGUF\nThis model was converted to GGUF format from 'xxx777xxxASD/ChaoticSoliloquy-4x8B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "transformers", "tensorboard", "safetensors", "roberta", "token-classification", "generated_from_trainer", "base_model:manucos/finetuned__roberta-base-biomedical-clinical-es__59k-ultrasounds", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #roberta #token-classification #generated_from_trainer #base_model-manucos/finetuned__roberta-base-biomedical-clinical-es__59k-ultrasounds #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 2e-05\n* train\\_batch\\_size: 8\n* eval\\_batch\\_size: 8\n* seed: 42\n* optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n* lr\\_scheduler\\_type: linear\n* num\\_epochs: 10", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0\n* Pytorch 2.2.1+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_5iters_bs256_nodpo_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_5iters_bs256_nodpo_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_5iters_bs256_nodpo_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "llama", "text-generation", "custom_code", "arxiv:2308.12950", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "4-bit", "region:us" ]

[ "2308.12950" ]

[]

[ "# Use cu117 if on CUDA 11.7\nshell\npip3 uninstall -y auto-gptq\ngit clone URL\ncd AutoGPTQ\npip3 install .\nshell\npip3 uninstall -y transformers\npip3 install git+URL\npython\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n\n\nmodel\\_name\\_or\\_path = \"TheBloke/CodeLlama-7B-Instruct-GPTQ\"\n\n\nTo use a different branch, change revision\n==========================================\n\n\nFor example: revision=\"main\"\n============================\n\n\nmodel = AutoModelForCausalLM.from\\_pretrained(model\\_name\\_or\\_path,\ndevice\\_map=\"auto\",\ntrust\\_remote\\_code=True,\nrevision=\"main\")\n\n\ntokenizer = AutoTokenizer.from\\_pretrained(model\\_name\\_or\\_path, use\\_fast=True)\n\n\nprompt = \"Tell me about AI\"\nprompt\\_template=f'''[INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using\n\n\nCompatibility\n-------------\n\n\nThe files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.\n\n\nExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.\n\n\nHuggingface Text Generation Inference (TGI) is compatible with all GPTQ models.\n\n\nDiscord\n-------\n\n\nFor further support, and discussions on these models and AI in general, join us at:\n\n\nTheBloke AI's Discord server\n\n\nThanks, and how to contribute\n-----------------------------\n\n\nThanks to the URL team!\n\n\nThanks to Clay from URL!\n\n\nI've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.\n\n\nIf you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.\n\n\nDonaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.\n\n\n* Patreon: URL\n* Ko-Fi: URL\n\n\nSpecial thanks to: Aemon Algiz.\n\n\nPatreon special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie\\_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S\\_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, URL, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov\n\n\nThank you to all my generous patrons and donaters!\n\n\nAnd thank you again to a16z for their generous grant.\n\n\nOriginal model card: Meta's CodeLlama 7B Instruct\n=================================================\n\n\nCode Llama\n==========\n\n\nCode Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 7B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.\n\n\n\nModel Use\n---------\n\n\nTo use this model, please make sure to install transformers from 'main' until the next version is released:\n\n\nModel capabilities:\n\n\n* [x] Code completion.\n* [x] Infilling.\n* [x] Instructions / chat.\n* [ ] Python specialist.\n\n\nModel Details\n-------------\n\n\n\\*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).\n\n\nModel Developers Meta\n\n\nVariations Code Llama comes in three model sizes, and three variants:\n\n\n* Code Llama: base models designed for general code synthesis and understanding\n* Code Llama - Python: designed specifically for Python\n* Code Llama - Instruct: for instruction following and safer deployment\n\n\nAll variants are available in sizes of 7B, 13B and 34B parameters.\n\n\nThis repository contains the Instruct version of the 7B parameters model.\n\n\nInput Models input text only.\n\n\nOutput Models generate text only.\n\n\nModel Architecture Code Llama is an auto-regressive language model that uses an optimized transformer architecture.\n\n\nModel Dates Code Llama and its variants have been trained between January 2023 and July 2023.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nResearch Paper More information can be found in the paper \"Code Llama: Open Foundation Models for Code\" or its arXiv page.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.\n\n\nOut-of-Scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.\n\n\nCarbon Footprint In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\nTraining Data\n-------------\n\n\nAll experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the research paper for details).\n\n\nEvaluation Results\n------------------\n\n\nSee evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nCode Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.\n\n\nPlease see the Responsible Use Guide available available at URL" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #custom_code #arxiv-2308.12950 #autotrain_compatible #endpoints_compatible #text-generation-inference #4-bit #region-us \n", "# Use cu117 if on CUDA 11.7\nshell\npip3 uninstall -y auto-gptq\ngit clone URL\ncd AutoGPTQ\npip3 install .\nshell\npip3 uninstall -y transformers\npip3 install git+URL\npython\nfrom transformers import AutoModelForCausalLM, AutoTokenizer, pipeline\n\n\nmodel\\_name\\_or\\_path = \"TheBloke/CodeLlama-7B-Instruct-GPTQ\"\n\n\nTo use a different branch, change revision\n==========================================\n\n\nFor example: revision=\"main\"\n============================\n\n\nmodel = AutoModelForCausalLM.from\\_pretrained(model\\_name\\_or\\_path,\ndevice\\_map=\"auto\",\ntrust\\_remote\\_code=True,\nrevision=\"main\")\n\n\ntokenizer = AutoTokenizer.from\\_pretrained(model\\_name\\_or\\_path, use\\_fast=True)\n\n\nprompt = \"Tell me about AI\"\nprompt\\_template=f'''[INST] Write code to solve the following coding problem that obeys the constraints and passes the example test cases. Please wrap your code answer using\n\n\nCompatibility\n-------------\n\n\nThe files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.\n\n\nExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.\n\n\nHuggingface Text Generation Inference (TGI) is compatible with all GPTQ models.\n\n\nDiscord\n-------\n\n\nFor further support, and discussions on these models and AI in general, join us at:\n\n\nTheBloke AI's Discord server\n\n\nThanks, and how to contribute\n-----------------------------\n\n\nThanks to the URL team!\n\n\nThanks to Clay from URL!\n\n\nI've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.\n\n\nIf you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.\n\n\nDonaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.\n\n\n* Patreon: URL\n* Ko-Fi: URL\n\n\nSpecial thanks to: Aemon Algiz.\n\n\nPatreon special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie\\_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S\\_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, URL, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov\n\n\nThank you to all my generous patrons and donaters!\n\n\nAnd thank you again to a16z for their generous grant.\n\n\nOriginal model card: Meta's CodeLlama 7B Instruct\n=================================================\n\n\nCode Llama\n==========\n\n\nCode Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 34 billion parameters. This is the repository for the 7B instruct-tuned version in the Hugging Face Transformers format. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.\n\n\n\nModel Use\n---------\n\n\nTo use this model, please make sure to install transformers from 'main' until the next version is released:\n\n\nModel capabilities:\n\n\n* [x] Code completion.\n* [x] Infilling.\n* [x] Instructions / chat.\n* [ ] Python specialist.\n\n\nModel Details\n-------------\n\n\n\\*Note: Use of this model is governed by the Meta license. Meta developed and publicly released the Code Llama family of large language models (LLMs).\n\n\nModel Developers Meta\n\n\nVariations Code Llama comes in three model sizes, and three variants:\n\n\n* Code Llama: base models designed for general code synthesis and understanding\n* Code Llama - Python: designed specifically for Python\n* Code Llama - Instruct: for instruction following and safer deployment\n\n\nAll variants are available in sizes of 7B, 13B and 34B parameters.\n\n\nThis repository contains the Instruct version of the 7B parameters model.\n\n\nInput Models input text only.\n\n\nOutput Models generate text only.\n\n\nModel Architecture Code Llama is an auto-regressive language model that uses an optimized transformer architecture.\n\n\nModel Dates Code Llama and its variants have been trained between January 2023 and July 2023.\n\n\nStatus This is a static model trained on an offline dataset. Future versions of Code Llama - Instruct will be released as we improve model safety with community feedback.\n\n\nLicense A custom commercial license is available at: URL\n\n\nResearch Paper More information can be found in the paper \"Code Llama: Open Foundation Models for Code\" or its arXiv page.\n\n\nIntended Use\n------------\n\n\nIntended Use Cases Code Llama and its variants is intended for commercial and research use in English and relevant programming languages. The base model Code Llama can be adapted for a variety of code synthesis and understanding tasks, Code Llama - Python is designed specifically to handle the Python programming language, and Code Llama - Instruct is intended to be safer to use for code assistant and generation applications.\n\n\nOut-of-Scope Uses Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English. Use in any other way that is prohibited by the Acceptable Use Policy and Licensing Agreement for Code Llama and its variants.\n\n\nHardware and Software\n---------------------\n\n\nTraining Factors We used custom training libraries. The training and fine-tuning of the released models have been performed Meta’s Research Super Cluster.\n\n\nCarbon Footprint In aggregate, training all 9 Code Llama models required 400K GPU hours of computation on hardware of type A100-80GB (TDP of 350-400W). Estimated total emissions were 65.3 tCO2eq, 100% of which were offset by Meta’s sustainability program.\n\n\nTraining Data\n-------------\n\n\nAll experiments reported here and the released models have been trained and fine-tuned using the same data as Llama 2 with different weights (see Section 2 and Table 1 in the research paper for details).\n\n\nEvaluation Results\n------------------\n\n\nSee evaluations for the main models and detailed ablations in Section 3 and safety evaluations in Section 4 of the research paper.\n\n\nEthical Considerations and Limitations\n--------------------------------------\n\n\nCode Llama and its variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Code Llama’s potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate or objectionable responses to user prompts. Therefore, before deploying any applications of Code Llama, developers should perform safety testing and tuning tailored to their specific applications of the model.\n\n\nPlease see the Responsible Use Guide available available at URL" ]

[ "diffusers", "text-to-image", "diffusers-training", "lora", "template:sd-lora", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "base_model:SG161222/RealVisXL_V4.0", "license:openrail++", "region:us" ]

[]

[]

[ "# SDXL LoRA DreamBooth - yehiaa/juggernaut-lora-drew-v1\n\n<Gallery />", "## Model description\n\nThese are yehiaa/juggernaut-lora-drew-v1 LoRA adaption weights for SG161222/RealVisXL_V4.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.", "## Trigger words\n\nYou should use a portrait of a sks person to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "TAGS\n#diffusers #text-to-image #diffusers-training #lora #template-sd-lora #stable-diffusion-xl #stable-diffusion-xl-diffusers #base_model-SG161222/RealVisXL_V4.0 #license-openrail++ #region-us \n", "# SDXL LoRA DreamBooth - yehiaa/juggernaut-lora-drew-v1\n\n<Gallery />", "## Model description\n\nThese are yehiaa/juggernaut-lora-drew-v1 LoRA adaption weights for SG161222/RealVisXL_V4.0.\n\nThe weights were trained using DreamBooth.\n\nLoRA for the text encoder was enabled: False.\n\nSpecial VAE used for training: None.", "## Trigger words\n\nYou should use a portrait of a sks person to trigger the image generation.", "## Download model\n\nWeights for this model are available in Safetensors format.\n\nDownload them in the Files & versions tab.", "## Intended uses & limitations", "#### How to use", "#### Limitations and bias\n\n[TODO: provide examples of latent issues and potential remediations]", "## Training details\n\n[TODO: describe the data used to train the model]" ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.01_ablation_5iters_bs256_nodpo_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #alignment-handbook #generated_from_trainer #trl #dpo #conversational #dataset-updated #dataset-original #base_model-ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.01_ablation_5iters_bs256_nodpo_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.01_ablation_5iters_bs256_nodpo_iter_1 on the updated and the original datasets.", "## Model description\n\nMore information needed", "## Intended uses & limitations\n\nMore information needed", "## Training and evaluation data\n\nMore information needed", "## Training procedure", "### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 5e-07\n- train_batch_size: 8\n- eval_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- gradient_accumulation_steps: 4\n- total_train_batch_size: 256\n- total_eval_batch_size: 64\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: cosine\n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.14.6\n- Tokenizers 0.15.2" ]

[ "transformers", "safetensors", "t5", "text2text-generation", "arxiv:1910.09700", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "1910.09700" ]

[]

[ "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "TAGS\n#transformers #safetensors #t5 #text2text-generation #arxiv-1910.09700 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID", "## Model Details", "### Model Description\n\n\n\nThis is the model card of a transformers model that has been pushed on the Hub. This model card has been automatically generated.\n\n- Developed by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Model type: \n- Language(s) (NLP): \n- License: \n- Finetuned from model [optional]:", "### Model Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Downstream Use [optional]", "### Out-of-Scope Use", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers (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\n\nUse the code below to get started with the model.", "## Training Details", "### Training Data", "### Training Procedure", "#### Preprocessing [optional]", "#### Training Hyperparameters\n\n- Training regime:", "#### Speeds, Sizes, Times [optional]", "## Evaluation", "### Testing Data, Factors & Metrics", "#### Testing Data", "#### Factors", "#### Metrics", "### Results", "#### Summary", "## Model Examination [optional]", "## Environmental Impact\n\n\n\nCarbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).\n\n- Hardware Type: \n- Hours used: \n- Cloud Provider: \n- Compute Region: \n- Carbon Emitted:", "## Technical Specifications [optional]", "### Model Architecture and Objective", "### Compute Infrastructure", "#### Hardware", "#### Software\n\n\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Model Card Authors [optional]", "## Model Card Contact" ]

[ "gguf", "story", "art", "general audience", "knowledge", "llama-cpp", "gguf-my-repo", "en", "dataset:ajibawa-2023/General-Stories-Collection", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/General-Stories-Mistral-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'ajibawa-2023/General-Stories-Mistral-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "TAGS\n#gguf #story #art #general audience #knowledge #llama-cpp #gguf-my-repo #en #dataset-ajibawa-2023/General-Stories-Collection #license-apache-2.0 #region-us \n", "# DavidAU/General-Stories-Mistral-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'ajibawa-2023/General-Stories-Mistral-7B' using URL via the URL's GGUF-my-repo space.\nRefer to the original model card for more details on the model.", "## Use with URL\n\nInstall URL through brew.\n\n\nInvoke the URL server or the CLI.\n\nCLI:\n\n\n\nServer:\n\n\n\nNote: You can also use this checkpoint directly through the usage steps listed in the URL repo as well." ]

[ "transformers", "safetensors", "llama", "text-generation", "text-generation-inference", "unsloth", "trl", "sft", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: ale045\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #text-generation-inference #unsloth #trl #sft #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: ale045\n- License: apache-2.0\n- Finetuned from model : unsloth/llama-3-8b-bnb-4bit\n\nThis llama model was trained 2x faster with Unsloth and Huggingface's TRL library.\n\n<img src=\"URL width=\"200\"/>" ]