Datasets:

---

ftopal

/

huggingface-models

like 0

[ "transformers", "gguf", "mergekit", "merge", "llama-cpp", "gguf-my-repo", "base_model:mlabonne/AlphaMonarch-7B", "base_model:Kukedlc/NeuralMaths-Experiment-7b", "endpoints_compatible", "region:us" ]

[]

[]

[ "# DavidAU/NeuralMathsRolePlay-7b-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralMathsRolePlay-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#transformers #gguf #mergekit #merge #llama-cpp #gguf-my-repo #base_model-mlabonne/AlphaMonarch-7B #base_model-Kukedlc/NeuralMaths-Experiment-7b #endpoints_compatible #region-us \n", "# DavidAU/NeuralMathsRolePlay-7b-Q6_K-GGUF\nThis model was converted to GGUF format from 'Kukedlc/NeuralMathsRolePlay-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", "gguf", "llama", "text-generation-inference", "unsloth", "en", "base_model:unsloth/llama-3-8b-bnb-4bit", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: zsdizital\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 #gguf #llama #text-generation-inference #unsloth #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: zsdizital\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\"/>" ]

[ "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_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: 1.6975\n- eval_runtime: 4.0953\n- eval_samples_per_second: 48.836\n- eval_steps_per_second: 6.105\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_medical_bios_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: 1.6975\n- eval_runtime: 4.0953\n- eval_samples_per_second: 48.836\n- eval_steps_per_second: 6.105\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", "pytorch", "llama", "text-generation", "llama-3", "Mixtral", "instruct", "finetune", "chatml", "DPO", "RLHF", "gpt4", "distillation", "conversational", "en", "arxiv:2305.18290", "arxiv:2303.13375", "arxiv:2212.13138", "arxiv:2305.09617", "arxiv:2402.07023", "base_model:meta-llama/Meta-Llama-3-70B-Instruct", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us", "has_space" ]

[ "2305.18290", "2303.13375", "2212.13138", "2305.09617", "2402.07023" ]

[ "en" ]

[]

[ "TAGS\n#transformers #pytorch #llama #text-generation #llama-3 #Mixtral #instruct #finetune #chatml #DPO #RLHF #gpt4 #distillation #conversational #en #arxiv-2305.18290 #arxiv-2303.13375 #arxiv-2212.13138 #arxiv-2305.09617 #arxiv-2402.07023 #base_model-meta-llama/Meta-Llama-3-70B-Instruct #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us #has_space \n" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: Teera\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 #text-generation-inference #unsloth #llama #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: Teera\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\"/>" ]

[ "transformers", "mpt", "text-generation", "Composer", "MosaicML", "llm-foundry", "custom_code", "dataset:jeffwan/sharegpt_vicuna", "dataset:Hello-SimpleAI/HC3", "dataset:tatsu-lab/alpaca", "dataset:Anthropic/hh-rlhf", "dataset:victor123/evol_instruct_70k", "arxiv:2205.14135", "arxiv:2108.12409", "arxiv:2010.04245", "license:cc-by-nc-sa-4.0", "autotrain_compatible", "text-generation-inference", "region:us" ]

[ "2205.14135", "2108.12409", "2010.04245" ]

[]

[ "### Example Dialogue\n\n\nSamIAm85:\n\n\n\n> \n> I want you to come up with a tweet based on this summary of the article:\n> \"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.\n> MPT-7B is a transformer trained from scratch on IT tokens of text and code.\n> It is open source and it matches the quality of LLaMA-7B.\n> MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.\n> Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.\n> For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!\n> \n> \n> \n\n\nMPT-7B-Instruct:\n\n\n\n> \n> Here's my suggestion for a tweet:\n> \"Exciting news! @MosaicML has launched #MPT\\_7B - a new standard for open-source LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: URL\n> \n> \n> \n\n\nSamIAm85:\n\n\n\n> \n> Is there anything you want to say to MosaicML about this exciting news?\n> \n> \n> \n\n\nMPT-7B-Instruct:\n\n\n\n> \n> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.\n> This new version of MPT-7B is truly impressive and I look forward to seeing what innovative applications developers will create using these powerful tools.\n> Thank you for your hard work and dedication to advancing Al research and development.\n> \n> \n> \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", "### Training Configuration\n\n\nThis model was trained on 8 A100-80GBs for about 8.2 hours, followed by training for 6.7 hours on 32 A100-40GBs using the MosaicML Platform.\nThe model was trained with sharded data parallelism using FSDP and used the AdamW 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-Chat can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B-Chat 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 Sam Havens and the MosaicML NLP team\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\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\nPlease cite this model using the following format:" ]

[ "TAGS\n#transformers #mpt #text-generation #Composer #MosaicML #llm-foundry #custom_code #dataset-jeffwan/sharegpt_vicuna #dataset-Hello-SimpleAI/HC3 #dataset-tatsu-lab/alpaca #dataset-Anthropic/hh-rlhf #dataset-victor123/evol_instruct_70k #arxiv-2205.14135 #arxiv-2108.12409 #arxiv-2010.04245 #license-cc-by-nc-sa-4.0 #autotrain_compatible #text-generation-inference #region-us \n", "### Example Dialogue\n\n\nSamIAm85:\n\n\n\n> \n> I want you to come up with a tweet based on this summary of the article:\n> \"Introducing MPT-7B, the latest entry in our MosaicML Foundation Series.\n> MPT-7B is a transformer trained from scratch on IT tokens of text and code.\n> It is open source and it matches the quality of LLaMA-7B.\n> MPT-7B was trained on the MosaicML platform in 9.5 days with zero human intervention at a cost of ~$200k.\n> Starting today, you can train, finetune, and deploy your own private MPT models, either starting from one of our checkpoints or training from scratch.\n> For inspiration, we are also releasing three finetuned models in addition to the base MPT-7B: MPT-7B-Instruct, MPT-7B-Chat, and MPT-7B-Story Writer-65k+, the last of which uses a context length of 65k tokens!\n> \n> \n> \n\n\nMPT-7B-Instruct:\n\n\n\n> \n> Here's my suggestion for a tweet:\n> \"Exciting news! @MosaicML has launched #MPT\\_7B - a new standard for open-source LLMs. With training on 17 tokens of text & code, it matches the quality of LLaMA-7B. Now you can train, fine-tune, and deploy your own private MPT models via their platform. Check out the full blog post here: URL\n> \n> \n> \n\n\nSamIAm85:\n\n\n\n> \n> Is there anything you want to say to MosaicML about this exciting news?\n> \n> \n> \n\n\nMPT-7B-Instruct:\n\n\n\n> \n> As an Al language model myself, I am very impressed with the advancements made by MosaicML in developing such high-quality open-source LLMs.\n> This new version of MPT-7B is truly impressive and I look forward to seeing what innovative applications developers will create using these powerful tools.\n> Thank you for your hard work and dedication to advancing Al research and development.\n> \n> \n> \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", "### Training Configuration\n\n\nThis model was trained on 8 A100-80GBs for about 8.2 hours, followed by training for 6.7 hours on 32 A100-40GBs using the MosaicML Platform.\nThe model was trained with sharded data parallelism using FSDP and used the AdamW 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-Chat can produce factually incorrect output, and should not be relied on to produce factually accurate information.\nMPT-7B-Chat 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 Sam Havens and the MosaicML NLP team\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\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\nPlease cite this model using the following format:" ]

[ "gguf", "merge", "lazymergekit", "dpo", "rlhf", "llama-cpp", "gguf-my-repo", "en", "base_model:mlabonne/NeuralMonarch-7B", "license:cc-by-nc-4.0", "model-index", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/AlphaMonarch-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'mlabonne/AlphaMonarch-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 #merge #lazymergekit #dpo #rlhf #llama-cpp #gguf-my-repo #en #base_model-mlabonne/NeuralMonarch-7B #license-cc-by-nc-4.0 #model-index #region-us \n", "# DavidAU/AlphaMonarch-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'mlabonne/AlphaMonarch-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", "gpt_neox", "text-classification", "generated_from_trainer", "base_model:EleutherAI/pythia-14m", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# robust_llm_c935853e01e111efbc18d63e49e237a3_from_EleutherAI_pythia-14m\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m 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: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "TAGS\n#transformers #safetensors #gpt_neox #text-classification #generated_from_trainer #base_model-EleutherAI/pythia-14m #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# robust_llm_c935853e01e111efbc18d63e49e237a3_from_EleutherAI_pythia-14m\n\nThis model is a fine-tuned version of EleutherAI/pythia-14m 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: 1e-05\n- train_batch_size: 8\n- eval_batch_size: 64\n- seed: 0\n- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08\n- lr_scheduler_type: linear\n- num_epochs: 1", "### Training results", "### Framework versions\n\n- Transformers 4.39.3\n- Pytorch 2.2.2\n- Datasets 2.18.0\n- Tokenizers 0.15.2" ]

[ "gguf", "merge", "mergekit", "lazymergekit", "KoboldAI/Mistral-7B-Erebus-v3", "KoboldAI/Mistral-7B-Holodeck-1", "llama-cpp", "gguf-my-repo", "base_model:KoboldAI/Mistral-7B-Erebus-v3", "base_model:KoboldAI/Mistral-7B-Holodeck-1", "region:us" ]

[]

[]

[ "# DavidAU/Erebus-Holodeck-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'Virt-io/Erebus-Holodeck-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 #merge #mergekit #lazymergekit #KoboldAI/Mistral-7B-Erebus-v3 #KoboldAI/Mistral-7B-Holodeck-1 #llama-cpp #gguf-my-repo #base_model-KoboldAI/Mistral-7B-Erebus-v3 #base_model-KoboldAI/Mistral-7B-Holodeck-1 #region-us \n", "# DavidAU/Erebus-Holodeck-7B-Q6_K-GGUF\nThis model was converted to GGUF format from 'Virt-io/Erebus-Holodeck-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." ]

[ "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_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: 1.6024\n- eval_runtime: 4.0773\n- eval_samples_per_second: 49.052\n- eval_steps_per_second: 6.131\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_medical_bios_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: 1.6024\n- eval_runtime: 4.0773\n- eval_samples_per_second: 49.052\n- eval_steps_per_second: 6.131\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", "gemma", "text-generation", "merge", "mergekit", "lazymergekit", "alfredplpl/suzume-poc", "alfredplpl/gemma-2b-it-ja-poc", "base_model:alfredplpl/suzume-poc", "base_model:alfredplpl/gemma-2b-it-ja-poc", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# suzume-taskarith1\n\nsuzume-taskarith1 is a merge of the following models using LazyMergekit:\n* alfredplpl/suzume-poc\n* alfredplpl/gemma-2b-it-ja-poc", "## Configuration", "## Usage" ]

[ "TAGS\n#transformers #safetensors #gemma #text-generation #merge #mergekit #lazymergekit #alfredplpl/suzume-poc #alfredplpl/gemma-2b-it-ja-poc #base_model-alfredplpl/suzume-poc #base_model-alfredplpl/gemma-2b-it-ja-poc #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# suzume-taskarith1\n\nsuzume-taskarith1 is a merge of the following models using LazyMergekit:\n* alfredplpl/suzume-poc\n* alfredplpl/gemma-2b-it-ja-poc", "## Configuration", "## Usage" ]

[ "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", "nlp", "code", "conversational", "en", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "### Chat Format\n\n\nGiven the nature of the training data, the Phi-3 Mini-4K-Instruct model is best suited for prompts using the chat format as follows.\nYou can provide the prompt as a question with a generic template as follow:\n\n\nFor example:\n\n\nwhere the model generates the text after '<|assistant|>' . In case of few-shots prompt, the prompt can be formatted as the following:", "### Sample inference code\n\n\nThis code snippets show how to get quickly started with running the model on a GPU:\n\n\nResponsible AI Considerations\n-----------------------------\n\n\nLike other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:\n\n\n* Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.\n* Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.\n* Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.\n* Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.\n* Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as \"typing, math, random, collections, datetime, itertools\". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.\n\n\nDevelopers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:\n\n\n* Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.\n* High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.\n* Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).\n* Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.\n* Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.\n\n\nTraining\n--------", "### Model\n\n\n* Architecture: Phi-3 Mini-4K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.\n* Inputs: Text. It is best suited for prompts using chat format.\n* Context length: 4K tokens\n* GPUs: 512 H100-80G\n* Training time: 7 days\n* Training data: 3.3T tokens\n* Outputs: Generated text in response to the input\n* Dates: Our models were trained between February and April 2024\n* Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models.", "### Datasets\n\n\nOur training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of\n\n\n1. Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code;\n2. Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.);\n3. High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness.", "### Fine-tuning\n\n\nA basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided here.\n\n\nBenchmarks\n----------\n\n\nWe report the results for Phi-3-Mini-4K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5.\n\n\nAll the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation.\n\n\nAs is now standard, we use few-shot prompts to evaluate the models, at temperature 0.\nThe prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3.\nMore specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model.\n\n\nThe number of k–shot examples is listed per-benchmark.\n\n\n\nSoftware\n--------\n\n\n* PyTorch\n* DeepSpeed\n* Transformers\n* Flash-Attention\n\n\nHardware\n--------\n\n\nNote that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:\n\n\n* NVIDIA A100\n* NVIDIA A6000\n* NVIDIA H100\n\n\nIf you want to run the model on:\n\n\n* NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from\\_pretrained() with attn\\_implementation=\"eager\"\n* CPU: use the GGUF quantized models 4K\n\n\n* Optimized inference on GPU, CPU, and Mobile: use the ONNX models 4K\n\n\nCross Platform Support\n----------------------\n\n\nONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-4K-Instruct ONNX model here.\n\n\nOptimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. \n\nAlong with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile.\n\n\nHere are some of the optimized configurations we have added:\n\n\n1. ONNX models for int4 DML: Quantized to int4 via AWQ\n2. ONNX model for fp16 CUDA\n3. ONNX model for int4 CUDA: Quantized to int4 via RTN\n4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN\n\n\nLicense\n-------\n\n\nThe model is licensed under the MIT license.\n\n\nTrademarks\n----------\n\n\nThis project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #nlp #code #conversational #en #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "### Chat Format\n\n\nGiven the nature of the training data, the Phi-3 Mini-4K-Instruct model is best suited for prompts using the chat format as follows.\nYou can provide the prompt as a question with a generic template as follow:\n\n\nFor example:\n\n\nwhere the model generates the text after '<|assistant|>' . In case of few-shots prompt, the prompt can be formatted as the following:", "### Sample inference code\n\n\nThis code snippets show how to get quickly started with running the model on a GPU:\n\n\nResponsible AI Considerations\n-----------------------------\n\n\nLike other language models, the Phi series models can potentially behave in ways that are unfair, unreliable, or offensive. Some of the limiting behaviors to be aware of include:\n\n\n* Quality of Service: the Phi models are trained primarily on English text. Languages other than English will experience worse performance. English language varieties with less representation in the training data might experience worse performance than standard American English.\n* Representation of Harms & Perpetuation of Stereotypes: These models can over- or under-represent groups of people, erase representation of some groups, or reinforce demeaning or negative stereotypes. Despite safety post-training, these limitations may still be present due to differing levels of representation of different groups or prevalence of examples of negative stereotypes in training data that reflect real-world patterns and societal biases.\n* Inappropriate or Offensive Content: these models may produce other types of inappropriate or offensive content, which may make it inappropriate to deploy for sensitive contexts without additional mitigations that are specific to the use case.\n* Information Reliability: Language models can generate nonsensical content or fabricate content that might sound reasonable but is inaccurate or outdated.\n* Limited Scope for Code: Majority of Phi-3 training data is based in Python and use common packages such as \"typing, math, random, collections, datetime, itertools\". If the model generates Python scripts that utilize other packages or scripts in other languages, we strongly recommend users manually verify all API uses.\n\n\nDevelopers should apply responsible AI best practices and are responsible for ensuring that a specific use case complies with relevant laws and regulations (e.g. privacy, trade, etc.). Important areas for consideration include:\n\n\n* Allocation: Models may not be suitable for scenarios that could have consequential impact on legal status or the allocation of resources or life opportunities (ex: housing, employment, credit, etc.) without further assessments and additional debiasing techniques.\n* High-Risk Scenarios: Developers should assess suitability of using models in high-risk scenarios where unfair, unreliable or offensive outputs might be extremely costly or lead to harm. This includes providing advice in sensitive or expert domains where accuracy and reliability are critical (ex: legal or health advice). Additional safeguards should be implemented at the application level according to the deployment context.\n* Misinformation: Models may produce inaccurate information. Developers should follow transparency best practices and inform end-users they are interacting with an AI system. At the application level, developers can build feedback mechanisms and pipelines to ground responses in use-case specific, contextual information, a technique known as Retrieval Augmented Generation (RAG).\n* Generation of Harmful Content: Developers should assess outputs for their context and use available safety classifiers or custom solutions appropriate for their use case.\n* Misuse: Other forms of misuse such as fraud, spam, or malware production may be possible, and developers should ensure that their applications do not violate applicable laws and regulations.\n\n\nTraining\n--------", "### Model\n\n\n* Architecture: Phi-3 Mini-4K-Instruct has 3.8B parameters and is a dense decoder-only Transformer model. The model is fine-tuned with Supervised fine-tuning (SFT) and Direct Preference Optimization (DPO) to ensure alignment with human preferences and safety guidlines.\n* Inputs: Text. It is best suited for prompts using chat format.\n* Context length: 4K tokens\n* GPUs: 512 H100-80G\n* Training time: 7 days\n* Training data: 3.3T tokens\n* Outputs: Generated text in response to the input\n* Dates: Our models were trained between February and April 2024\n* Status: This is a static model trained on an offline dataset with cutoff date October 2023. Future versions of the tuned models may be released as we improve models.", "### Datasets\n\n\nOur training data includes a wide variety of sources, totaling 3.3 trillion tokens, and is a combination of\n\n\n1. Publicly available documents filtered rigorously for quality, selected high-quality educational data, and code;\n2. Newly created synthetic, “textbook-like” data for the purpose of teaching math, coding, common sense reasoning, general knowledge of the world (science, daily activities, theory of mind, etc.);\n3. High quality chat format supervised data covering various topics to reflect human preferences on different aspects such as instruct-following, truthfulness, honesty and helpfulness.", "### Fine-tuning\n\n\nA basic example of multi-GPUs supervised fine-tuning (SFT) with TRL and Accelerate modules is provided here.\n\n\nBenchmarks\n----------\n\n\nWe report the results for Phi-3-Mini-4K-Instruct on standard open-source benchmarks measuring the model's reasoning ability (both common sense reasoning and logical reasoning). We compare to Phi-2, Mistral-7b-v0.1, Mixtral-8x7b, Gemma 7B, Llama-3-8B-Instruct, and GPT-3.5.\n\n\nAll the reported numbers are produced with the exact same pipeline to ensure that the numbers are comparable. These numbers might differ from other published numbers due to slightly different choices in the evaluation.\n\n\nAs is now standard, we use few-shot prompts to evaluate the models, at temperature 0.\nThe prompts and number of shots are part of a Microsoft internal tool to evaluate language models, and in particular we did no optimization to the pipeline for Phi-3.\nMore specifically, we do not change prompts, pick different few-shot examples, change prompt format, or do any other form of optimization for the model.\n\n\nThe number of k–shot examples is listed per-benchmark.\n\n\n\nSoftware\n--------\n\n\n* PyTorch\n* DeepSpeed\n* Transformers\n* Flash-Attention\n\n\nHardware\n--------\n\n\nNote that by default, the Phi-3-mini model uses flash attention, which requires certain types of GPU hardware to run. We have tested on the following GPU types:\n\n\n* NVIDIA A100\n* NVIDIA A6000\n* NVIDIA H100\n\n\nIf you want to run the model on:\n\n\n* NVIDIA V100 or earlier generation GPUs: call AutoModelForCausalLM.from\\_pretrained() with attn\\_implementation=\"eager\"\n* CPU: use the GGUF quantized models 4K\n\n\n* Optimized inference on GPU, CPU, and Mobile: use the ONNX models 4K\n\n\nCross Platform Support\n----------------------\n\n\nONNX runtime ecosystem now supports Phi-3 Mini models across platforms and hardware. You can find the optimized Phi-3 Mini-4K-Instruct ONNX model here.\n\n\nOptimized Phi-3 models are also published here in ONNX format, to run with ONNX Runtime on CPU and GPU across devices, including server platforms, Windows, Linux and Mac desktops, and mobile CPUs, with the precision best suited to each of these targets. DirectML support lets developers bring hardware acceleration to Windows devices at scale across AMD, Intel, and NVIDIA GPUs. \n\nAlong with DirectML, ONNX Runtime provides cross platform support for Phi-3 across a range of devices CPU, GPU, and mobile.\n\n\nHere are some of the optimized configurations we have added:\n\n\n1. ONNX models for int4 DML: Quantized to int4 via AWQ\n2. ONNX model for fp16 CUDA\n3. ONNX model for int4 CUDA: Quantized to int4 via RTN\n4. ONNX model for int4 CPU and Mobile: Quantized to int4 via RTN\n\n\nLicense\n-------\n\n\nThe model is licensed under the MIT license.\n\n\nTrademarks\n----------\n\n\nThis project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies." ]

[ "transformers", "safetensors", "stablelm", "text-generation", "conversational", "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 #stablelm #text-generation #conversational #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" ]

[ "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_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: 1.5946\n- eval_runtime: 4.103\n- eval_samples_per_second: 48.744\n- eval_steps_per_second: 6.093\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_medical_bios_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: 1.5946\n- eval_runtime: 4.103\n- eval_samples_per_second: 48.744\n- eval_steps_per_second: 6.093\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", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "hi", "dataset:mozilla-foundation/common_voice_11_0", "base_model:openai/whisper-small", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[ "hi" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 1e-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* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000", "### 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 #whisper #automatic-speech-recognition #generated_from_trainer #hi #dataset-mozilla-foundation/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: 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* lr\\_scheduler\\_warmup\\_steps: 500\n* training\\_steps: 4000", "### 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" ]

[ "gguf", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:llama3", "region:us" ]

[]

[]

[ "# 32K GGUF of LLAMA3-8B-INSTRUCT", "### *THIS IS NOT A FINETUNE IT JUST WORKS GREAT VIA YARN SCALING*", "## imatrix custom edge-quants tested ok at 4,3 & 2bit\n\n> [!TIP]\n> You have to set context with *-c 32000* in URL to take advantage of this when you run it.\n>", "## How to run the model in interactive mode using URL with a long prompt inside a textfile with -f", "## Prompt format - paste up to 32000 token long prompt inside the user{} brackets\n> [!TIP] put this inside your *URL* file\n> or copy from below and add to above command like this -p \"<|im_start.....\"", "## Perplexity Benchmarks\n\n\n> [!TIP]\n> Yes 8bit q8_0 is slightly better than f16 because converting fom bf16 to f16 reduces bits in the mantisa.\n> The ns quants are custom nisten quants and work well down to 2 bit.\n> 1.75bit quant is included for reference however perplexity tanks and is incoherent.", "# Built with Meta Llama 3" ]

[ "TAGS\n#gguf #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-llama3 #region-us \n", "# 32K GGUF of LLAMA3-8B-INSTRUCT", "### *THIS IS NOT A FINETUNE IT JUST WORKS GREAT VIA YARN SCALING*", "## imatrix custom edge-quants tested ok at 4,3 & 2bit\n\n> [!TIP]\n> You have to set context with *-c 32000* in URL to take advantage of this when you run it.\n>", "## How to run the model in interactive mode using URL with a long prompt inside a textfile with -f", "## Prompt format - paste up to 32000 token long prompt inside the user{} brackets\n> [!TIP] put this inside your *URL* file\n> or copy from below and add to above command like this -p \"<|im_start.....\"", "## Perplexity Benchmarks\n\n\n> [!TIP]\n> Yes 8bit q8_0 is slightly better than f16 because converting fom bf16 to f16 reduces bits in the mantisa.\n> The ns quants are custom nisten quants and work well down to 2 bit.\n> 1.75bit quant is included for reference however perplexity tanks and is incoherent.", "# Built with Meta Llama 3" ]

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

[]

[]

[ "# sac Agent playing SoccerTwos\n This is a trained model of a sac 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-sac-10M\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", "# sac Agent playing SoccerTwos\n This is a trained model of a sac 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-sac-10M\n 3. Step 2: Select your *.nn /*.onnx file\n 4. Click on Watch the agent play" ]

[ "transformers", "gguf", "llama-factory", "orpo", "text-generation", "en", "zh", "dataset:hiyouga/DPO-En-Zh-20k", "base_model:shenzhi-wang/Llama3-8B-Chinese-Chat", "license:other", "region:us" ]

[]

[ "en", "zh" ]

[ "# Llama3-8B-Chinese-Chat-GGUF\n- This is quantized version of shenzhi-wang/Llama3-8B-Chinese-Chat created using URL", "# Model Description\n\nThis is the first Chinese chat model specifically fine-tuned for Chinese through ORPO [1] based on the Meta-Llama-3-8B-Instruct model.\n\nCompared to the original Meta-Llama-3-8B-Instruct model, our Llama3-8B-Chinese-Chat model significantly reduces the issues of \"Chinese questions with English answers\" and the mixing of Chinese and English in responses. Additionally, compared to the original model, our model greatly reduces the number of emojis in the answers, making the responses more formal.\n\n[1] Hong, Jiwoo, Noah Lee, and James Thorne. \"Reference-free Monolithic Preference Optimization with Odds Ratio.\" arXiv preprint arXiv:2403.07691 (2024).\n\n\n\nDataset: DPO-En-Zh-20k (commit id: e8c5070d6564025fcf206f38d796ae264e028004).\n\n\nTraining framework: LLaMA-Factory (commit id: 836ca0558698206bbf4e3b92533ad9f67c9f9864).\n\n\nTraining details:\n- epochs: 3\n- learning rate: 5e-6\n- learning rate scheduler type: cosine\n- Warmup ratio: 0.1\n- cutoff len (i.e. context length): 8192\n- orpo beta (i.e. $\\lambda$ in the ORPO paper): 0.05\n- global batch size: 64\n- fine-tuning type: full parameters\n- optimizer: paged_adamw_32bit", "# Examples\n\nThe following are some examples generated by our Llama3-8B-Chinese-Chat model:", "## Questions from RuoZhiBa (弱智吧)", "## Safety", "## Writing", "## Math", "## Coding" ]

[ "TAGS\n#transformers #gguf #llama-factory #orpo #text-generation #en #zh #dataset-hiyouga/DPO-En-Zh-20k #base_model-shenzhi-wang/Llama3-8B-Chinese-Chat #license-other #region-us \n", "# Llama3-8B-Chinese-Chat-GGUF\n- This is quantized version of shenzhi-wang/Llama3-8B-Chinese-Chat created using URL", "# Model Description\n\nThis is the first Chinese chat model specifically fine-tuned for Chinese through ORPO [1] based on the Meta-Llama-3-8B-Instruct model.\n\nCompared to the original Meta-Llama-3-8B-Instruct model, our Llama3-8B-Chinese-Chat model significantly reduces the issues of \"Chinese questions with English answers\" and the mixing of Chinese and English in responses. Additionally, compared to the original model, our model greatly reduces the number of emojis in the answers, making the responses more formal.\n\n[1] Hong, Jiwoo, Noah Lee, and James Thorne. \"Reference-free Monolithic Preference Optimization with Odds Ratio.\" arXiv preprint arXiv:2403.07691 (2024).\n\n\n\nDataset: DPO-En-Zh-20k (commit id: e8c5070d6564025fcf206f38d796ae264e028004).\n\n\nTraining framework: LLaMA-Factory (commit id: 836ca0558698206bbf4e3b92533ad9f67c9f9864).\n\n\nTraining details:\n- epochs: 3\n- learning rate: 5e-6\n- learning rate scheduler type: cosine\n- Warmup ratio: 0.1\n- cutoff len (i.e. context length): 8192\n- orpo beta (i.e. $\\lambda$ in the ORPO paper): 0.05\n- global batch size: 64\n- fine-tuning type: full parameters\n- optimizer: paged_adamw_32bit", "# Examples\n\nThe following are some examples generated by our Llama3-8B-Chinese-Chat model:", "## Questions from RuoZhiBa (弱智吧)", "## Safety", "## Writing", "## Math", "## Coding" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2306.01708", "base_model:ResplendentAI/Aura_Uncensored_l3_8B", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "base_model:ResplendentAI/Kei_Llama3_8B", "base_model:Undi95/Llama-3-Unholy-8B", "base_model:vicgalle/Roleplay-Llama-3-8B", "license:llama3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* ResplendentAI/Aura_Uncensored_l3_8B\n* ResplendentAI/Kei_Llama3_8B\n* Undi95/Llama-3-Unholy-8B\n* vicgalle/Roleplay-Llama-3-8B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-ResplendentAI/Aura_Uncensored_l3_8B #base_model-meta-llama/Meta-Llama-3-8B-Instruct #base_model-ResplendentAI/Kei_Llama3_8B #base_model-Undi95/Llama-3-Unholy-8B #base_model-vicgalle/Roleplay-Llama-3-8B #license-llama3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using meta-llama/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* ResplendentAI/Aura_Uncensored_l3_8B\n* ResplendentAI/Kei_Llama3_8B\n* Undi95/Llama-3-Unholy-8B\n* vicgalle/Roleplay-Llama-3-8B", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 3.2763\n- eval_runtime: 4.4338\n- eval_samples_per_second: 45.108\n- eval_steps_per_second: 5.639\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 3.2763\n- eval_runtime: 4.4338\n- eval_samples_per_second: 45.108\n- eval_steps_per_second: 5.639\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", "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", "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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 16\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: 4\n* eval\\_batch\\_size: 4\n* seed: 42\n* distributed\\_type: multi-GPU\n* num\\_devices: 4\n* gradient\\_accumulation\\_steps: 2\n* total\\_train\\_batch\\_size: 32\n* total\\_eval\\_batch\\_size: 16\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" ]

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

[]

[ "ja" ]

[ "# Phos 7B RP\n\nPhos 7B fine-tuned for roleplay" ]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #japanese #text-generation-inference #ja #autotrain_compatible #endpoints_compatible #region-us \n", "# Phos 7B RP\n\nPhos 7B fine-tuned for roleplay" ]

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

[]

[ "en" ]

[ "# Uploaded model\n\n- Developed by: lyingspring\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 #pytorch #llama #text-generation #text-generation-inference #unsloth #trl #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Uploaded model\n\n- Developed by: lyingspring\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\"/>" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "arxiv:2306.01708", "base_model:NousResearch/Llama-2-7b-hf", "base_model:microsoft/Orca-2-7b", "base_model:arcee-ai/Patent-Instruct-7b", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using NousResearch/Llama-2-7b-hf as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/Orca-2-7b\n* arcee-ai/Patent-Instruct-7b", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-NousResearch/Llama-2-7b-hf #base_model-microsoft/Orca-2-7b #base_model-arcee-ai/Patent-Instruct-7b #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using NousResearch/Llama-2-7b-hf as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/Orca-2-7b\n* arcee-ai/Patent-Instruct-7b", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.7930\n- eval_runtime: 2.9261\n- eval_samples_per_second: 68.35\n- eval_steps_per_second: 8.544\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.7930\n- eval_runtime: 2.9261\n- eval_samples_per_second: 68.35\n- eval_steps_per_second: 8.544\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" ]

[ "diffusers", "autotrain", "stable-diffusion-xl", "stable-diffusion-xl-diffusers", "text-to-image", "lora", "template:sd-lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "doi:10.57967/hf/2107", "license:openrail++", "region:us" ]

[]

[]

[ "# AutoTrain SDXL LoRA DreamBooth - DileepPatruni/CARIMAGES\n\n<Gallery />", "## Model description\n\nThese are DileepPatruni/CARIMAGES LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\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 <Toyota Supra Car> 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." ]

[ "TAGS\n#diffusers #autotrain #stable-diffusion-xl #stable-diffusion-xl-diffusers #text-to-image #lora #template-sd-lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #doi-10.57967/hf/2107 #license-openrail++ #region-us \n", "# AutoTrain SDXL LoRA DreamBooth - DileepPatruni/CARIMAGES\n\n<Gallery />", "## Model description\n\nThese are DileepPatruni/CARIMAGES LoRA adaption weights for stabilityai/stable-diffusion-xl-base-1.0.\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 <Toyota Supra Car> 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." ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "base_model:Hastagaras/L3-Asbac-8B", "base_model:ChaoticNeutrals/Poppy_Porpoise-v0.6-L3-8B", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# \"Poppy Porpoise\" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.\n\n!image/png", "# Recomended ST Presets: Porpoise Presets", "# Quants From the boi: @Lewdiculus-Poppy-Quants", "# 4-bpw-exl2 quant: here\n\n If you want to use vision functionality:\n\n * You must use the latest versions of Koboldcpp.", "# To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. Llava MMProj\n \n * You can load the mmproj by using the corresponding section in the interface:\n\n !image/png" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #base_model-Hastagaras/L3-Asbac-8B #base_model-ChaoticNeutrals/Poppy_Porpoise-v0.6-L3-8B #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# \"Poppy Porpoise\" is a cutting-edge AI roleplay assistant based on the Llama 3 8B model, specializing in crafting unforgettable narrative experiences. With its advanced language capabilities, Poppy expertly immerses users in an interactive and engaging adventure, tailoring each adventure to their individual preferences.\n\n!image/png", "# Recomended ST Presets: Porpoise Presets", "# Quants From the boi: @Lewdiculus-Poppy-Quants", "# 4-bpw-exl2 quant: here\n\n If you want to use vision functionality:\n\n * You must use the latest versions of Koboldcpp.", "# To use the multimodal capabilities of this model and use vision you need to load the specified mmproj file, this can be found inside this model repo. Llava MMProj\n \n * You can load the mmproj by using the corresponding section in the interface:\n\n !image/png" ]

[ "peft", "safetensors", "trl", "sft", "generated_from_trainer", "base_model:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5021\n- eval_runtime: 2.9229\n- eval_samples_per_second: 68.425\n- eval_steps_per_second: 8.553\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5021\n- eval_runtime: 2.9229\n- eval_samples_per_second: 68.425\n- eval_steps_per_second: 8.553\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", "pytorch", "safetensors", "llama", "text-generation", "generated_from_trainer", "conversational", "base_model:NousResearch/Meta-Llama-3-8B", "license:other", "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: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_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\\_steps: 100\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "TAGS\n#transformers #pytorch #safetensors #llama #text-generation #generated_from_trainer #conversational #base_model-NousResearch/Meta-Llama-3-8B #license-other #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: 1\n* eval\\_batch\\_size: 1\n* seed: 42\n* gradient\\_accumulation\\_steps: 8\n* total\\_train\\_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\\_steps: 100\n* num\\_epochs: 2", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.0.dev0\n* Pytorch 2.2.2+cu121\n* Datasets 2.15.0\n* Tokenizers 0.15.0" ]

[ "transformers", "safetensors", "llama", "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 #llama #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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4296\n- eval_runtime: 2.9249\n- eval_samples_per_second: 68.377\n- eval_steps_per_second: 8.547\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4296\n- eval_runtime: 2.9249\n- eval_samples_per_second: 68.377\n- eval_steps_per_second: 8.547\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", "beit", "image-classification", "generated_from_trainer", "base_model:microsoft/beit-large-patch16-224-pt22k-ft22k", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Ocsai-D Large\n\nThis model is a trained model for scoring creativity - specifically figural (drawing-based) originality scoring. It is a fine-tuned version of beit-large-patch16-224.\nIt achieves the following results on the evaluation set:\n- Mse: 0.0067\n- Pearsonr: 0.85\n- R2: 0.63\n- Rmse: 0.082\n\nIt can be tried at <URL", "## Model description\n\nSee the pre-print:\n\nAcar, S.^, Organisciak, P.^, & Dumas, D. (2023). Automated Scoring of Figural Tests of Creativity with Computer Vision. URL\n\n*^Authors contributed equally.*", "## Intended uses & limitations\n\nThis model judges the originality of figural drawings. There are some limitations.\n\nFirst, there is a confound with elaboration - drawing more leads - partially - to higher originality.\n\nSecondly, the training is specific to one test, and mileage may vary on other images.", "## Training and evaluation data\n\nThis is trained on the Multi-Trial Creative Ideation task (MTCI; Barbot 2018), with the data from Patterson et al. (2023).\n\nThe train/test splits aligned with the ones from Patterson et al. 2023.", "### Framework versions\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 #safetensors #beit #image-classification #generated_from_trainer #base_model-microsoft/beit-large-patch16-224-pt22k-ft22k #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# Ocsai-D Large\n\nThis model is a trained model for scoring creativity - specifically figural (drawing-based) originality scoring. It is a fine-tuned version of beit-large-patch16-224.\nIt achieves the following results on the evaluation set:\n- Mse: 0.0067\n- Pearsonr: 0.85\n- R2: 0.63\n- Rmse: 0.082\n\nIt can be tried at <URL", "## Model description\n\nSee the pre-print:\n\nAcar, S.^, Organisciak, P.^, & Dumas, D. (2023). Automated Scoring of Figural Tests of Creativity with Computer Vision. URL\n\n*^Authors contributed equally.*", "## Intended uses & limitations\n\nThis model judges the originality of figural drawings. There are some limitations.\n\nFirst, there is a confound with elaboration - drawing more leads - partially - to higher originality.\n\nSecondly, the training is specific to one test, and mileage may vary on other images.", "## Training and evaluation data\n\nThis is trained on the Multi-Trial Creative Ideation task (MTCI; Barbot 2018), with the data from Patterson et al. (2023).\n\nThe train/test splits aligned with the ones from Patterson et al. 2023.", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "gguf", "generated_from_trainer", "axolotl", "llama-cpp", "gguf-my-repo", "dataset:cognitivecomputations/Dolphin-2.9", "dataset:teknium/OpenHermes-2.5", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:cognitivecomputations/dolphin-coder", "dataset:cognitivecomputations/samantha-data", "dataset:HuggingFaceH4/ultrachat_200k", "dataset:microsoft/orca-math-word-problems-200k", "dataset:abacusai/SystemChat-1.1", "dataset:Locutusque/function-calling-chatml", "dataset:internlm/Agent-FLAN", "base_model:meta-llama/Meta-Llama-3-8B", "license:other", "region:us" ]

[]

[]

[ "# DavidAU/dolphin-2.9-llama3-8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'cognitivecomputations/dolphin-2.9-llama3-8b' 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#gguf #generated_from_trainer #axolotl #llama-cpp #gguf-my-repo #dataset-cognitivecomputations/Dolphin-2.9 #dataset-teknium/OpenHermes-2.5 #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-cognitivecomputations/dolphin-coder #dataset-cognitivecomputations/samantha-data #dataset-HuggingFaceH4/ultrachat_200k #dataset-microsoft/orca-math-word-problems-200k #dataset-abacusai/SystemChat-1.1 #dataset-Locutusque/function-calling-chatml #dataset-internlm/Agent-FLAN #base_model-meta-llama/Meta-Llama-3-8B #license-other #region-us \n", "# DavidAU/dolphin-2.9-llama3-8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'cognitivecomputations/dolphin-2.9-llama3-8b' 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." ]

[ "transformers", "safetensors", "mistral", "text-generation", "not-for-all-audiences", "japanese", "text-generation-inference", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[]

[ "TAGS\n#transformers #safetensors #mistral #text-generation #not-for-all-audiences #japanese #text-generation-inference #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n" ]

[ "transformers", "gguf", "llama-factory", "orpo", "llama-cpp", "gguf-my-repo", "text-generation", "en", "zh", "dataset:hiyouga/DPO-En-Zh-20k", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en", "zh" ]

[ "# DavidAU/Llama3-8B-Chinese-Chat-Q8_0-GGUF\nThis model was converted to GGUF format from 'shenzhi-wang/Llama3-8B-Chinese-Chat' 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-factory #orpo #llama-cpp #gguf-my-repo #text-generation #en #zh #dataset-hiyouga/DPO-En-Zh-20k #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #endpoints_compatible #region-us \n", "# DavidAU/Llama3-8B-Chinese-Chat-Q8_0-GGUF\nThis model was converted to GGUF format from 'shenzhi-wang/Llama3-8B-Chinese-Chat' 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", "qwen2", "text-generation", "conversational", "arxiv:1910.09700", "license:apache-2.0", "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]\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 #text-generation #conversational #arxiv-1910.09700 #license-apache-2.0 #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]\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", "llama-cpp", "gguf-my-repo", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# DavidAU/Llama-3-8B-16K-Q8_0-GGUF\nThis model was converted to GGUF format from 'mattshumer/Llama-3-8B-16K' 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 #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# DavidAU/Llama-3-8B-16K-Q8_0-GGUF\nThis model was converted to GGUF format from 'mattshumer/Llama-3-8B-16K' 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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4219\n- eval_runtime: 2.9272\n- eval_samples_per_second: 68.324\n- eval_steps_per_second: 8.54\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_esnli_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4219\n- eval_runtime: 2.9272\n- eval_samples_per_second: 68.324\n- eval_steps_per_second: 8.54\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" ]

[ "uncensored", "llama3", "instruct", "open", "text-generation", "license:llama3", "region:us" ]

[]

[]

[]

[ "TAGS\n#uncensored #llama3 #instruct #open #text-generation #license-llama3 #region-us \n" ]

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

[]

[ "en" ]

[ "# DavidAU/llama-3-8B-RP-Q8_0-GGUF\nThis model was converted to GGUF format from 'Dogge/llama-3-8B-RP' 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 #text-generation-inference #unsloth #llama #trl #sft #llama-cpp #gguf-my-repo #en #base_model-unsloth/llama-3-8b-bnb-4bit #license-apache-2.0 #endpoints_compatible #region-us \n", "# DavidAU/llama-3-8B-RP-Q8_0-GGUF\nThis model was converted to GGUF format from 'Dogge/llama-3-8B-RP' 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", "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" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "ru", "dataset:IlyaGusev/ru_turbo_saiga", "dataset:IlyaGusev/ru_sharegpt_cleaned", "dataset:IlyaGusev/oasst1_ru_main_branch", "dataset:IlyaGusev/gpt_roleplay_realm", "dataset:lksy/ru_instruct_gpt4", "license:other", "region:us" ]

[]

[ "ru" ]

[ "# DavidAU/saiga_llama3_8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'IlyaGusev/saiga_llama3_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#gguf #llama-cpp #gguf-my-repo #ru #dataset-IlyaGusev/ru_turbo_saiga #dataset-IlyaGusev/ru_sharegpt_cleaned #dataset-IlyaGusev/oasst1_ru_main_branch #dataset-IlyaGusev/gpt_roleplay_realm #dataset-lksy/ru_instruct_gpt4 #license-other #region-us \n", "# DavidAU/saiga_llama3_8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'IlyaGusev/saiga_llama3_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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.9046\n- eval_runtime: 4.0157\n- eval_samples_per_second: 49.805\n- eval_steps_per_second: 6.226\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_1ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.9046\n- eval_runtime: 4.0157\n- eval_samples_per_second: 49.805\n- eval_steps_per_second: 6.226\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", "gguf", "llama-cpp", "gguf-my-repo", "dataset:aqua_rat", "dataset:microsoft/orca-math-word-problems-200k", "dataset:m-a-p/CodeFeedback-Filtered-Instruction", "dataset:anon8231489123/ShareGPT_Vicuna_unfiltered", "license:llama2", "endpoints_compatible", "region:us" ]

[]

[]

[ "# DavidAU/Llama-3-Smaug-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'abacusai/Llama-3-Smaug-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 #dataset-aqua_rat #dataset-microsoft/orca-math-word-problems-200k #dataset-m-a-p/CodeFeedback-Filtered-Instruction #dataset-anon8231489123/ShareGPT_Vicuna_unfiltered #license-llama2 #endpoints_compatible #region-us \n", "# DavidAU/Llama-3-Smaug-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'abacusai/Llama-3-Smaug-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." ]

[ "transformers", "safetensors", "vision-encoder-decoder", "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 #vision-encoder-decoder #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" ]

[ "diffusers", "text-to-image", "stable-diffusion", "lora", "base_model:stabilityai/stable-diffusion-xl-base-1.0", "license:creativeml-openrail-m", "region:us" ]

[]

[]

[ "# Pixel Art XL", "## Consider supporting further research on Patreon or Twitter\n\n!URL\n!URL\n\n\nDownscale 8 times to get pixel perfect images (use Nearest Neighbors)\nUse a fixed VAE to avoid artifacts (0.9 or fp16 fix)", "### Need more performance?\nUse it with a LCM Lora!\n\nUse 8 steps and guidance scale of 1.5\n1.2 Lora strength for the Pixel Art XL works better", "### Tips:\nDon't use refiner\n\nWorks great with only 1 text encoder\n\nNo style prompt required\n\nNo trigger keyword require\n\nWorks great with isometric and non-isometric\n\nWorks with 0.9 and 1.0", "#### Changelog\nv1: Initial release" ]

[ "TAGS\n#diffusers #text-to-image #stable-diffusion #lora #base_model-stabilityai/stable-diffusion-xl-base-1.0 #license-creativeml-openrail-m #region-us \n", "# Pixel Art XL", "## Consider supporting further research on Patreon or Twitter\n\n!URL\n!URL\n\n\nDownscale 8 times to get pixel perfect images (use Nearest Neighbors)\nUse a fixed VAE to avoid artifacts (0.9 or fp16 fix)", "### Need more performance?\nUse it with a LCM Lora!\n\nUse 8 steps and guidance scale of 1.5\n1.2 Lora strength for the Pixel Art XL works better", "### Tips:\nDon't use refiner\n\nWorks great with only 1 text encoder\n\nNo style prompt required\n\nNo trigger keyword require\n\nWorks great with isometric and non-isometric\n\nWorks with 0.9 and 1.0", "#### Changelog\nv1: Initial release" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "dataset:Yukang/LongAlpaca-16k-length", "region:us" ]

[]

[]

[ "# cybercheems2077/Llama-3-8B-16K-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'mattshumer/Llama-3-8B-16K' 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 #dataset-Yukang/LongAlpaca-16k-length #region-us \n", "# cybercheems2077/Llama-3-8B-16K-Q4_K_M-GGUF\nThis model was converted to GGUF format from 'mattshumer/Llama-3-8B-16K' 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", "opt", "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 #opt #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", "mergekit", "merge", "arxiv:2306.01708", "base_model:microsoft/rho-math-1b-v0.1", "base_model:appvoid/palmer-003", "base_model:vihangd/DopeyTinyLlama-1.1B-v1", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using appvoid/palmer-003 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-v0.1\n* vihangd/DopeyTinyLlama-1.1B-v1", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #arxiv-2306.01708 #base_model-microsoft/rho-math-1b-v0.1 #base_model-appvoid/palmer-003 #base_model-vihangd/DopeyTinyLlama-1.1B-v1 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the TIES merge method using appvoid/palmer-003 as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-v0.1\n* vihangd/DopeyTinyLlama-1.1B-v1", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "gguf", "DPO", "Llama3-8B", "llama-cpp", "gguf-my-repo", "dataset:mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[]

[ "# DavidAU/Llama3-8B-OpenHermes-DPO-Q8_0-GGUF\nThis model was converted to GGUF format from 'Muhammad2003/Llama3-8B-OpenHermes-DPO' 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 #DPO #Llama3-8B #llama-cpp #gguf-my-repo #dataset-mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha #license-apache-2.0 #endpoints_compatible #region-us \n", "# DavidAU/Llama3-8B-OpenHermes-DPO-Q8_0-GGUF\nThis model was converted to GGUF format from 'Muhammad2003/Llama3-8B-OpenHermes-DPO' 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", "bert", "text-classification", "generated_from_trainer", "base_model:bert-base-uncased", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "# finetuning-open-BERTmodel\n\nThis model is a fine-tuned version of bert-base-uncased on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5932\n- Accuracy: 0.6945\n- F1: 0.6777\n- Precision: 0.7067\n- Recall: 0.6510", "## 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: 2", "### Training results", "### Framework versions\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 #bert #text-classification #generated_from_trainer #base_model-bert-base-uncased #license-apache-2.0 #autotrain_compatible #endpoints_compatible #region-us \n", "# finetuning-open-BERTmodel\n\nThis model is a fine-tuned version of bert-base-uncased on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5932\n- Accuracy: 0.6945\n- F1: 0.6777\n- Precision: 0.7067\n- Recall: 0.6510", "## 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: 2", "### Training results", "### Framework versions\n\n- Transformers 4.40.0\n- Pytorch 2.2.1+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "gguf", "not-for-all-audiences", "nsfw", "llama-cpp", "gguf-my-repo", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "# DavidAU/Llama-3-Unholy-8B-e4-Q8_0-GGUF\nThis model was converted to GGUF format from 'Undi95/Llama-3-Unholy-8B-e4' 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 #nsfw #llama-cpp #gguf-my-repo #license-cc-by-nc-4.0 #region-us \n", "# DavidAU/Llama-3-Unholy-8B-e4-Q8_0-GGUF\nThis model was converted to GGUF format from 'Undi95/Llama-3-Unholy-8B-e4' 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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5932\n- eval_runtime: 4.0164\n- eval_samples_per_second: 49.796\n- eval_steps_per_second: 6.224\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_2ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.5932\n- eval_runtime: 4.0164\n- eval_samples_per_second: 49.796\n- eval_steps_per_second: 6.224\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", "gguf", "text-generation-inference", "unsloth", "llama", "trl", "llama-cpp", "gguf-my-repo", "en", "dataset:tatsu-lab/alpaca", "base_model:unsloth/llama-3-8b-bnb-4bit", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/Llama-3-NeuralPaca-8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'NeuralNovel/Llama-3-NeuralPaca-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 #text-generation-inference #unsloth #llama #trl #llama-cpp #gguf-my-repo #en #dataset-tatsu-lab/alpaca #base_model-unsloth/llama-3-8b-bnb-4bit #endpoints_compatible #region-us \n", "# DavidAU/Llama-3-NeuralPaca-8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'NeuralNovel/Llama-3-NeuralPaca-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." ]

[ "transformers", "safetensors", "gpt2", "text-generation", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# Model Card for Model ID\n\nThis model was built using PPO. Reward model was positive sentiment BERT only for GPT2 generative." ]

[ "TAGS\n#transformers #safetensors #gpt2 #text-generation #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Model Card for Model ID\n\nThis model was built using PPO. Reward model was positive sentiment BERT only for GPT2 generative." ]

[ "transformers", "safetensors", "opt", "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 #opt #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" ]

[ "diffusers", "safetensors", "pytorch", "unconditional-image-generation", "diffusion-models-class", "license:mit", "diffusers:DDPMPipeline", "region:us" ]

[]

[]

[ "# Model Card for Unit 1 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional image generation of cute .", "## Usage" ]

[ "TAGS\n#diffusers #safetensors #pytorch #unconditional-image-generation #diffusion-models-class #license-mit #diffusers-DDPMPipeline #region-us \n", "# Model Card for Unit 1 of the Diffusion Models Class \n\nThis model is a diffusion model for unconditional image generation of cute .", "## Usage" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2306.01708", "base_model:Sao10K/L3-Solana-8B-v1", "base_model:Masterjp123/Llama-3-SnowyRP-8B-V1", "base_model:kuotient/Meta-Llama-3-8B-Instruct", "base_model:cgato/L3-TheSpice-8b-v0.1.3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# merged\nThis is the unquantized Seccond version of SnowyRP using LLama3, added some models will add a EXL2 Quant.\n\nEXL2", "## 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 TIES merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Sao10K/L3-Solana-8B-v1\n* Masterjp123/Llama-3-SnowyRP-8B-V1\n* cgato/L3-TheSpice-8b-v0.1.3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-Sao10K/L3-Solana-8B-v1 #base_model-Masterjp123/Llama-3-SnowyRP-8B-V1 #base_model-kuotient/Meta-Llama-3-8B-Instruct #base_model-cgato/L3-TheSpice-8b-v0.1.3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merged\nThis is the unquantized Seccond version of SnowyRP using LLama3, added some models will add a EXL2 Quant.\n\nEXL2", "## 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 TIES merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Sao10K/L3-Solana-8B-v1\n* Masterjp123/Llama-3-SnowyRP-8B-V1\n* cgato/L3-TheSpice-8b-v0.1.3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

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

[]

[]

[ "# Mermaid-Llama-3-5B\n\nIntroducing Mermaid-LLama-3-5B, a language model designed for Python code understanding and crafting captivating story flow maps.\n\n!MermaidLlama GIF", "## Key Features\n\n1. Code Understanding:\n - Masters Python intricacies with finesse.\n - Generates clear and accurate Mermaid Diagram Flow Charts.\n - Ideal for developers seeking visual representations of their code logic.\n\n2. Storytelling Capabilities:\n - Converts narrative inputs into captivating Mermaid Diagrams.\n - Maps character interactions, plot developments, and narrative arcs.\n\n3. Unmatched Performance:\n - Surpasses GPT-4 in generating well-organized Mermaid Diagrams.\n\n4. Training Insights:\n - Trained on a diverse dataset, including 800 unique, hand-curated Mermaid Graph examples utilizing 478 complete Python programs.\n - Exhibits emergent properties in story-to-flow map translations and step-by-step instruction flow maps.", "## Collaboration\n\nInterested in enhancing Mermaid's capabilities? Contact troydoesai@URL for collaboration opportunities.", "## Example Use Cases\n- Retrieval-Augmented Generation (RAG): Utilize Mermaid-LLama-3-8B to create condensed knowledge graphs. This model excels in generating flow diagrams that enhance the retrieval process. These knowledge graphs are stored in a vector database, which allows for quick and efficient retrieval of contextually relevant information. When a query is received, the system retrieves a pertinent knowledge graph, appending it as context to the model. This enriched context enables Mermaid-LLama-3-8B to deliver more accurate and nuanced responses. This approach is particularly beneficial in applications requiring deep, context-aware interactions, such as sophisticated Q&A systems, dynamic data analysis, and complex decision-making tasks.\n- Code Documentation: Automatic visual flow charts from Python code.\n- Storyboarding: Visually appealing diagrams for storytelling.\n- Project Planning: Visual project flow maps for effective team communication.\n- Learning Python: Helps students visually understand Python code structures.\n- Game Design: Visualizing game storylines for coherent narrative structure.", "## Proof of Concept\n\nStay tuned for the release of the VSCode Extension that displays the Live Flow Map every time a user stops typing for more than 10 seconds.", "## Training Specifications\n\n- LoRA Rank: 2048\n- LoRA Alpha: 4096\n- Batch Size: 1\n- Micro Batch Size: 1\n- Cutoff Length: 4096\n- Save every n steps: 1000\n- Epochs: 3\n- Learning Rate: 1e-6\n- LR Scheduler: Cosine\n\nTarget Modules:\n- Enable q_proj\n- Enable v_proj\n- Enable k_proj\n- Enable o_proj\n- Enable gate_proj\n- Enable down_proj\n- Enable up_proj", "## Getting Started\n\nStart by downloading one of my models.\n\n!0 TroyDoesAI GIF\n\nLoad the model.\n\n!1 Load Model in 4-bit Show Example Use GIF\n\nUse my prompt template to generate a Mermaid code block, which can be viewed in the Mermaid Live Editor or using the Mermaid CLI tool.\n\n!2 Loaded Model in Full Precision 16-bit Show Inference and Mermaid Live Editor GIF\n\nHere we open the VLLM GUI Program while still running in Vram the Mermaid-Llama-8B to compare the flow diagram to the actual program and show the lightweight capabilites of small models on consumer hardware.\n\n!3 Open The Program VLLM Program With Full Precision Mermaid-Llama-8B Running to Evaluate Flow Map GIF", "## More on my VLLM Class and inference GUI : URL\n\n!Python RtdBsaz8gy GIF\n---\n\nNote: This model should be treated as an Auto-Complete Model, Do not try talking to it in chat you are gonna get garbage, those layers have been pruned and replaced, that is all you will hear of my secret sauce on training on small < 1000 entry datasets." ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #conversational #license-cc-by-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# Mermaid-Llama-3-5B\n\nIntroducing Mermaid-LLama-3-5B, a language model designed for Python code understanding and crafting captivating story flow maps.\n\n!MermaidLlama GIF", "## Key Features\n\n1. Code Understanding:\n - Masters Python intricacies with finesse.\n - Generates clear and accurate Mermaid Diagram Flow Charts.\n - Ideal for developers seeking visual representations of their code logic.\n\n2. Storytelling Capabilities:\n - Converts narrative inputs into captivating Mermaid Diagrams.\n - Maps character interactions, plot developments, and narrative arcs.\n\n3. Unmatched Performance:\n - Surpasses GPT-4 in generating well-organized Mermaid Diagrams.\n\n4. Training Insights:\n - Trained on a diverse dataset, including 800 unique, hand-curated Mermaid Graph examples utilizing 478 complete Python programs.\n - Exhibits emergent properties in story-to-flow map translations and step-by-step instruction flow maps.", "## Collaboration\n\nInterested in enhancing Mermaid's capabilities? Contact troydoesai@URL for collaboration opportunities.", "## Example Use Cases\n- Retrieval-Augmented Generation (RAG): Utilize Mermaid-LLama-3-8B to create condensed knowledge graphs. This model excels in generating flow diagrams that enhance the retrieval process. These knowledge graphs are stored in a vector database, which allows for quick and efficient retrieval of contextually relevant information. When a query is received, the system retrieves a pertinent knowledge graph, appending it as context to the model. This enriched context enables Mermaid-LLama-3-8B to deliver more accurate and nuanced responses. This approach is particularly beneficial in applications requiring deep, context-aware interactions, such as sophisticated Q&A systems, dynamic data analysis, and complex decision-making tasks.\n- Code Documentation: Automatic visual flow charts from Python code.\n- Storyboarding: Visually appealing diagrams for storytelling.\n- Project Planning: Visual project flow maps for effective team communication.\n- Learning Python: Helps students visually understand Python code structures.\n- Game Design: Visualizing game storylines for coherent narrative structure.", "## Proof of Concept\n\nStay tuned for the release of the VSCode Extension that displays the Live Flow Map every time a user stops typing for more than 10 seconds.", "## Training Specifications\n\n- LoRA Rank: 2048\n- LoRA Alpha: 4096\n- Batch Size: 1\n- Micro Batch Size: 1\n- Cutoff Length: 4096\n- Save every n steps: 1000\n- Epochs: 3\n- Learning Rate: 1e-6\n- LR Scheduler: Cosine\n\nTarget Modules:\n- Enable q_proj\n- Enable v_proj\n- Enable k_proj\n- Enable o_proj\n- Enable gate_proj\n- Enable down_proj\n- Enable up_proj", "## Getting Started\n\nStart by downloading one of my models.\n\n!0 TroyDoesAI GIF\n\nLoad the model.\n\n!1 Load Model in 4-bit Show Example Use GIF\n\nUse my prompt template to generate a Mermaid code block, which can be viewed in the Mermaid Live Editor or using the Mermaid CLI tool.\n\n!2 Loaded Model in Full Precision 16-bit Show Inference and Mermaid Live Editor GIF\n\nHere we open the VLLM GUI Program while still running in Vram the Mermaid-Llama-8B to compare the flow diagram to the actual program and show the lightweight capabilites of small models on consumer hardware.\n\n!3 Open The Program VLLM Program With Full Precision Mermaid-Llama-8B Running to Evaluate Flow Map GIF", "## More on my VLLM Class and inference GUI : URL\n\n!Python RtdBsaz8gy GIF\n---\n\nNote: This model should be treated as an Auto-Complete Model, Do not try talking to it in chat you are gonna get garbage, those layers have been pruned and replaced, that is all you will hear of my secret sauce on training on small < 1000 entry datasets." ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:microsoft/rho-math-1b-v0.1", "base_model:appvoid/palmer-003", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-microsoft/rho-math-1b-v0.1 #base_model-appvoid/palmer-003 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "llama", "text-generation", "mergekit", "merge", "conversational", "arxiv:2306.01708", "base_model:Sao10K/L3-Solana-8B-v1", "base_model:Masterjp123/Llama-3-SnowyRP-8B-V1", "base_model:kuotient/Meta-Llama-3-8B-Instruct", "base_model:cgato/L3-TheSpice-8b-v0.1.3", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[ "2306.01708" ]

[]

[ "# merged\nThis is the unquantized Seccond version of SnowyRP using LLama3, added some models will add a EXL2 Quant.\n\nBF16", "## 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 TIES merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Sao10K/L3-Solana-8B-v1\n* Masterjp123/Llama-3-SnowyRP-8B-V1\n* cgato/L3-TheSpice-8b-v0.1.3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #llama #text-generation #mergekit #merge #conversational #arxiv-2306.01708 #base_model-Sao10K/L3-Solana-8B-v1 #base_model-Masterjp123/Llama-3-SnowyRP-8B-V1 #base_model-kuotient/Meta-Llama-3-8B-Instruct #base_model-cgato/L3-TheSpice-8b-v0.1.3 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merged\nThis is the unquantized Seccond version of SnowyRP using LLama3, added some models will add a EXL2 Quant.\n\nBF16", "## 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 TIES merge method using kuotient/Meta-Llama-3-8B-Instruct as a base.", "### Models Merged\n\nThe following models were included in the merge:\n* Sao10K/L3-Solana-8B-v1\n* Masterjp123/Llama-3-SnowyRP-8B-V1\n* cgato/L3-TheSpice-8b-v0.1.3", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "gguf", "merge", "mergekit", "lazymergekit", "llama-cpp", "gguf-my-repo", "base_model:meta-llama/Meta-Llama-3-8B", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[]

[ "# DavidAU/Llama-3-SLERP-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'mlabonne/Llama-3-SLERP-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#gguf #merge #mergekit #lazymergekit #llama-cpp #gguf-my-repo #base_model-meta-llama/Meta-Llama-3-8B #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# DavidAU/Llama-3-SLERP-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'mlabonne/Llama-3-SLERP-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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4333\n- eval_runtime: 4.017\n- eval_samples_per_second: 49.788\n- eval_steps_per_second: 6.223\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_3ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.4333\n- eval_runtime: 4.017\n- eval_samples_per_second: 49.788\n- eval_steps_per_second: 6.223\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", "recurrent_gemma", "text-generation", "generated_from_trainer", "en", "dataset:pszemraj/simple_wikipedia_LM", "license:apache-2.0", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0003\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 80085\n* gradient\\_accumulation\\_steps: 32\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07\n* lr\\_scheduler\\_type: constant\\_with\\_warmup\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* num\\_epochs: 2.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #safetensors #recurrent_gemma #text-generation #generated_from_trainer #en #dataset-pszemraj/simple_wikipedia_LM #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: 0.0003\n* train\\_batch\\_size: 4\n* eval\\_batch\\_size: 4\n* seed: 80085\n* gradient\\_accumulation\\_steps: 32\n* total\\_train\\_batch\\_size: 128\n* optimizer: Adam with betas=(0.9,0.99) and epsilon=1e-07\n* lr\\_scheduler\\_type: constant\\_with\\_warmup\n* lr\\_scheduler\\_warmup\\_ratio: 0.05\n* num\\_epochs: 2.0", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.2.0+cu121\n* Datasets 2.19.0\n* Tokenizers 0.19.1" ]

[ "gguf", "not-for-all-audiences", "nsfw", "llama-cpp", "gguf-my-repo", "license:cc-by-nc-4.0", "region:us" ]

[]

[]

[ "# DavidAU/Llama-3-Unholy-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'Undi95/Llama-3-Unholy-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#gguf #not-for-all-audiences #nsfw #llama-cpp #gguf-my-repo #license-cc-by-nc-4.0 #region-us \n", "# DavidAU/Llama-3-Unholy-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'Undi95/Llama-3-Unholy-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." ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:appvoid/palmer-003", "base_model:microsoft/rho-math-1b-interpreter-v0.1", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* appvoid/palmer-003\n* microsoft/rho-math-1b-interpreter-v0.1", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-appvoid/palmer-003 #base_model-microsoft/rho-math-1b-interpreter-v0.1 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* appvoid/palmer-003\n* microsoft/rho-math-1b-interpreter-v0.1", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "gguf", "unsloth", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "en", "license:apache-2.0", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/llama-3-8b-Instruct-Q8_0-GGUF\nThis model was converted to GGUF format from 'unsloth/llama-3-8b-Instruct' 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 #unsloth #llama #llama-3 #llama-cpp #gguf-my-repo #en #license-apache-2.0 #endpoints_compatible #region-us \n", "# DavidAU/llama-3-8b-Instruct-Q8_0-GGUF\nThis model was converted to GGUF format from 'unsloth/llama-3-8b-Instruct' 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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.3987\n- eval_runtime: 4.0103\n- eval_samples_per_second: 49.871\n- eval_steps_per_second: 6.234\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_4ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.3987\n- eval_runtime: 4.0103\n- eval_samples_per_second: 49.871\n- eval_steps_per_second: 6.234\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", "pytorch", "llama", "text-generation", "conversational", "en", "license:cc-by-nc-4.0", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "en" ]

[ "# WebSquareAI-Instruct-llama-3-8B-v0.5.37", "## Model Details\n\nDeveloped by \nInswave Systems UI Platform Team\n\nBase Model\nmeta-llama/Meta-Llama-3-8B\n\n---" ]

[ "TAGS\n#transformers #pytorch #llama #text-generation #conversational #en #license-cc-by-nc-4.0 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# WebSquareAI-Instruct-llama-3-8B-v0.5.37", "## Model Details\n\nDeveloped by \nInswave Systems UI Platform Team\n\nBase Model\nmeta-llama/Meta-Llama-3-8B\n\n---" ]

[ "transformers", "gguf", "unsloth", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "en", "license:llama2", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/llama-3-8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'unsloth/llama-3-8b' 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 #unsloth #llama #llama-3 #llama-cpp #gguf-my-repo #en #license-llama2 #endpoints_compatible #region-us \n", "# DavidAU/llama-3-8b-Q8_0-GGUF\nThis model was converted to GGUF format from 'unsloth/llama-3-8b' 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." ]

[ "transformers", "gguf", "llama-cpp", "gguf-my-repo", "endpoints_compatible", "region:us" ]

[]

[]

[ "# DavidAU/DPO-llama3-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'akkky02/DPO-llama3-8B' 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 #endpoints_compatible #region-us \n", "# DavidAU/DPO-llama3-8B-Q8_0-GGUF\nThis model was converted to GGUF format from 'akkky02/DPO-llama3-8B' 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." ]

[ "transformers", "safetensors", "mistral", "text-generation", "alignment-handbook", "generated_from_trainer", "trl", "dpo", "conversational", "dataset:updated", "dataset:original", "base_model:ShenaoZ/0.001_ablation_4iters_bs256_sample2_iter_1", "license:mit", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# 0.001_ablation_4iters_bs256_sample2_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_4iters_bs256_sample2_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_4iters_bs256_sample2_iter_1 #license-mit #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# 0.001_ablation_4iters_bs256_sample2_iter_2\n\nThis model is a fine-tuned version of ShenaoZ/0.001_ablation_4iters_bs256_sample2_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", "gguf", "axolotl", "finetune", "facebook", "meta", "pytorch", "llama", "llama-3", "llama-cpp", "gguf-my-repo", "text-generation", "en", "dataset:mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha", "base_model:meta-llama/Meta-Llama-3-8B-Instruct", "license:other", "region:us" ]

[]

[ "en" ]

[ "# DavidAU/Llama-3-8B-Instruct-DPO-v0.1-Q8_0-GGUF\nThis model was converted to GGUF format from 'MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1' 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 #axolotl #finetune #facebook #meta #pytorch #llama #llama-3 #llama-cpp #gguf-my-repo #text-generation #en #dataset-mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha #base_model-meta-llama/Meta-Llama-3-8B-Instruct #license-other #region-us \n", "# DavidAU/Llama-3-8B-Instruct-DPO-v0.1-Q8_0-GGUF\nThis model was converted to GGUF format from 'MaziyarPanahi/Llama-3-8B-Instruct-DPO-v0.1' 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", "llama-factory", "lora", "generated_from_trainer", "base_model:mistralai/Mistral-7B-Instruct-v0.2", "license:other", "region:us" ]

[]

[]

[ "# train_2024-04-24-00-09-45\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the ali_dataset 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: 5e-05\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: cosine\n- num_epochs: 3.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "TAGS\n#peft #safetensors #llama-factory #lora #generated_from_trainer #base_model-mistralai/Mistral-7B-Instruct-v0.2 #license-other #region-us \n", "# train_2024-04-24-00-09-45\n\nThis model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.2 on the ali_dataset 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: 5e-05\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: cosine\n- num_epochs: 3.0\n- mixed_precision_training: Native AMP", "### Training results", "### Framework versions\n\n- PEFT 0.10.0\n- Transformers 4.40.0\n- Pytorch 2.2.2+cu121\n- Datasets 2.19.0\n- Tokenizers 0.19.1" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:microsoft/rho-math-1b-interpreter-v0.1", "base_model:appvoid/palmer-003", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-interpreter-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-microsoft/rho-math-1b-interpreter-v0.1 #base_model-appvoid/palmer-003 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-interpreter-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "gguf", "llama-cpp", "gguf-my-repo", "license:other", "region:us" ]

[]

[]

[ "# DavidAU/Llama-3-11.5B-V2-Q8_0-GGUF\nThis model was converted to GGUF format from 'Replete-AI/Llama-3-11.5B-V2' 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 #license-other #region-us \n", "# DavidAU/Llama-3-11.5B-V2-Q8_0-GGUF\nThis model was converted to GGUF format from 'Replete-AI/Llama-3-11.5B-V2' 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:meta-llama/Llama-2-7b-chat-hf", "license:llama2", "region:us" ]

[]

[]

[ "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.3942\n- eval_runtime: 4.0157\n- eval_samples_per_second: 49.805\n- eval_steps_per_second: 6.226\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/Llama-2-7b-chat-hf #license-llama2 #region-us \n", "# mohsenfayyaz/Llama-2-7b-chat-hf_medical_bios_5000_Lora_lr1e-5_5ep\n\nThis model is a fine-tuned version of meta-llama/Llama-2-7b-chat-hf on an unknown dataset.\nIt achieves the following results on the evaluation set:\n- eval_loss: 2.3942\n- eval_runtime: 4.0157\n- eval_samples_per_second: 49.805\n- eval_steps_per_second: 6.226\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", "text-generation", "mergekit", "merge", "base_model:microsoft/rho-math-1b-interpreter-v0.1", "base_model:appvoid/palmer-003", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-interpreter-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-microsoft/rho-math-1b-interpreter-v0.1 #base_model-appvoid/palmer-003 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-interpreter-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "gguf", "text-generation", "dataset:Yukang/LongAlpaca-16k-length", "base_model:mattshumer/Llama-3-8B-16K", "endpoints_compatible", "region:us" ]

[]

[]

[ "# Llama-3-8B-16K-GGUF\n- This is quantized version of mattshumer/Llama-3-8B-16K created using URL", "# Model Description\nThis is an extended (16K) context version of LLaMA 3 8B (base, not instruct). Trained for five hours on 8x A6000 GPUs, using the 'Yukang/LongAlpaca-16k-length' dataset.\n\n'rope_theta' was set to '1000000.0'. Trained with Axolotl." ]

[ "TAGS\n#transformers #gguf #text-generation #dataset-Yukang/LongAlpaca-16k-length #base_model-mattshumer/Llama-3-8B-16K #endpoints_compatible #region-us \n", "# Llama-3-8B-16K-GGUF\n- This is quantized version of mattshumer/Llama-3-8B-16K created using URL", "# Model Description\nThis is an extended (16K) context version of LLaMA 3 8B (base, not instruct). Trained for five hours on 8x A6000 GPUs, using the 'Yukang/LongAlpaca-16k-length' dataset.\n\n'rope_theta' was set to '1000000.0'. Trained with Axolotl." ]

[ "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" ]

[ "gguf", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #region-us \n" ]

[ "transformers", "safetensors", "llama", "text-generation", "pt", "dataset:adalbertojunior/openHermes_portuguese", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[ "pt" ]

[ "## Como Utilizar" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #pt #dataset-adalbertojunior/openHermes_portuguese #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "## Como Utilizar" ]

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

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.0002\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* num\\_epochs: 4\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 #vit #image-classification #generated_from_trainer #dataset-imagefolder #base_model-google/vit-base-patch16-224-in21k #license-apache-2.0 #model-index #autotrain_compatible #endpoints_compatible #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: 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* num\\_epochs: 4\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" ]

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

[]

[]

[ "# finetuning-open-RoBERTamodel\n\nThis model is a fine-tuned version of roberta-base on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5936\n- Accuracy: 0.6976\n- F1: 0.6984\n- Precision: 0.6999\n- Recall: 0.6969", "## 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: 2", "### Training results", "### Framework versions\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 #text-classification #generated_from_trainer #base_model-roberta-base #license-mit #autotrain_compatible #endpoints_compatible #region-us \n", "# finetuning-open-RoBERTamodel\n\nThis model is a fine-tuned version of roberta-base on the None dataset.\nIt achieves the following results on the evaluation set:\n- Loss: 0.5936\n- Accuracy: 0.6976\n- F1: 0.6984\n- Precision: 0.6999\n- Recall: 0.6969", "## 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: 2", "### Training results", "### Framework versions\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", "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" ]

[ "gguf", "uncensored", "llama3", "instruct", "open", "text-generation", "license:llama3", "region:us" ]

[]

[]

[]

[ "TAGS\n#gguf #uncensored #llama3 #instruct #open #text-generation #license-llama3 #region-us \n" ]

[ "transformers", "gguf", "orpo", "llama 3", "rlhf", "sft", "text-generation", "en", "dataset:mlabonne/orpo-dpo-mix-40k", "base_model:mlabonne/OrpoLlama-3-8B", "license:other", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "### Nous\n\n\nOrpoLlama-4-8B outperforms Llama-3-8B-Instruct on the GPT4All and TruthfulQA datasets.\n\n\nEvaluation performed using LLM AutoEval, see the entire leaderboard here.\n\n\n\n'mlabonne/OrpoLlama-3-8B-1k' corresponds to a version of this model trained on 1K samples (you can see the parameters in this article).", "### Open LLM Leaderboard\n\n\nTBD.\n\n\nTraining curves\n---------------\n\n\nYou can find the experiment on W&B at this address.\n\n\n!image/png" ]

[ "TAGS\n#transformers #gguf #orpo #llama 3 #rlhf #sft #text-generation #en #dataset-mlabonne/orpo-dpo-mix-40k #base_model-mlabonne/OrpoLlama-3-8B #license-other #endpoints_compatible #region-us \n", "### Nous\n\n\nOrpoLlama-4-8B outperforms Llama-3-8B-Instruct on the GPT4All and TruthfulQA datasets.\n\n\nEvaluation performed using LLM AutoEval, see the entire leaderboard here.\n\n\n\n'mlabonne/OrpoLlama-3-8B-1k' corresponds to a version of this model trained on 1K samples (you can see the parameters in this article).", "### Open LLM Leaderboard\n\n\nTBD.\n\n\nTraining curves\n---------------\n\n\nYou can find the experiment on W&B at this address.\n\n\n!image/png" ]

[ "transformers", "safetensors", "llama", "text-generation", "mergekit", "merge", "base_model:microsoft/rho-math-1b-interpreter-v0.1", "base_model:appvoid/palmer-003", "autotrain_compatible", "endpoints_compatible", "text-generation-inference", "region:us" ]

[]

[]

[ "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-interpreter-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "TAGS\n#transformers #safetensors #llama #text-generation #mergekit #merge #base_model-microsoft/rho-math-1b-interpreter-v0.1 #base_model-appvoid/palmer-003 #autotrain_compatible #endpoints_compatible #text-generation-inference #region-us \n", "# merge\n\nThis is a merge of pre-trained language models created using mergekit.", "## Merge Details", "### Merge Method\n\nThis model was merged using the SLERP merge method.", "### Models Merged\n\nThe following models were included in the merge:\n* microsoft/rho-math-1b-interpreter-v0.1\n* appvoid/palmer-003", "### Configuration\n\nThe following YAML configuration was used to produce this model:" ]

[ "transformers", "safetensors", "albert", "text-classification", "generated_from_trainer", "base_model:hf-internal-testing/tiny-albert", "autotrain_compatible", "endpoints_compatible", "region:us" ]

[]

[]

[ "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 24\n* eval\\_batch\\_size: 24\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: 25.0\n* num\\_epochs: 1", "### 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 #safetensors #albert #text-classification #generated_from_trainer #base_model-hf-internal-testing/tiny-albert #autotrain_compatible #endpoints_compatible #region-us \n", "### Training hyperparameters\n\n\nThe following hyperparameters were used during training:\n\n\n* learning\\_rate: 0.001\n* train\\_batch\\_size: 24\n* eval\\_batch\\_size: 24\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: 25.0\n* num\\_epochs: 1", "### 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", "tensorboard", "safetensors", "vit", "image-classification", "clothes-classification", "generated_from_trainer", "base_model:google/vit-base-patch16-224-in21k", "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: 0.0002\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: 8", "### 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 #vit #image-classification #clothes-classification #generated_from_trainer #base_model-google/vit-base-patch16-224-in21k #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: 0.0002\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: 8", "### 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", "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" ]

[ "peft", "tensorboard", "safetensors", "llama", "arxiv:1910.09700", "base_model:meta-llama/Llama-2-7b-hf", "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 #tensorboard #safetensors #llama #arxiv-1910.09700 #base_model-meta-llama/Llama-2-7b-hf #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", "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" ]

[ "transformers", "tensorboard", "safetensors", "whisper", "automatic-speech-recognition", "generated_from_trainer", "en", "dataset:whisper-tiny/minds_14_en", "base_model:openai/whisper-tiny", "license:apache-2.0", "model-index", "endpoints_compatible", "region:us" ]

[]

[ "en" ]

[ "### 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\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.19.1" ]

[ "TAGS\n#transformers #tensorboard #safetensors #whisper #automatic-speech-recognition #generated_from_trainer #en #dataset-whisper-tiny/minds_14_en #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: 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\n* mixed\\_precision\\_training: Native AMP", "### Training results", "### Framework versions\n\n\n* Transformers 4.40.1\n* Pytorch 2.1.2\n* Datasets 2.18.0\n* Tokenizers 0.19.1" ]

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

[]

[]

[ "# Multi_verse_modelT3qm7xp-7B\n\nMulti_verse_modelT3qm7xp-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", "# Multi_verse_modelT3qm7xp-7B\n\nMulti_verse_modelT3qm7xp-7B is an automated merge created by Maxime Labonne using the following configuration.", "## Configuration", "## Usage" ]

[ "transformers", "safetensors", "vision-encoder-decoder", "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 #vision-encoder-decoder #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" ]