richarderkhov/huggingfaceh4_-_mistral-7b-grok-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 that has been aligned via Constitutional AI to mimic the style of xAI's Grok assistant. It achieves the following results on the evaluation set:",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "Quantization made by Richard Erkhov.\n\n[Github](https://github.com/RichardErkhov)\n\n[Discord](https://discord.gg/pvy7H8DZMG)\n\n[Request more models](https://github.com/RichardErkhov/quant_request)\n\n\nmistral-7b-grok - GGUF\n- Model creator: https://huggingface.co/HuggingFaceH4/\n- Original model: https://huggingface.co/HuggingFaceH4/mistral-7b-grok/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [mistral-7b-grok.Q2_K.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q2_K.gguf) | Q2_K | 2.53GB |\n| [mistral-7b-grok.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [mistral-7b-grok.IQ3_S.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [mistral-7b-grok.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [mistral-7b-grok.IQ3_M.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [mistral-7b-grok.Q3_K.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q3_K.gguf) | Q3_K | 3.28GB |\n| [mistral-7b-grok.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [mistral-7b-grok.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [mistral-7b-grok.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [mistral-7b-grok.Q4_0.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [mistral-7b-grok.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [mistral-7b-grok.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [mistral-7b-grok.Q4_K.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q4_K.gguf) | Q4_K | 4.07GB |\n| [mistral-7b-grok.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [mistral-7b-grok.Q4_1.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [mistral-7b-grok.Q5_0.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [mistral-7b-grok.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [mistral-7b-grok.Q5_K.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q5_K.gguf) | Q5_K | 4.78GB |\n| [mistral-7b-grok.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [mistral-7b-grok.Q5_1.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [mistral-7b-grok.Q6_K.gguf](https://huggingface.co/RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf/blob/main/mistral-7b-grok.Q6_K.gguf) | Q6_K | 5.53GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\nbase_model: mistralai/Mistral-7B-v0.1\ntags:\n- alignment-handbook\n- generated_from_trainer\ndatasets:\n- HuggingFaceH4/grok-conversation-harmless\n- HuggingFaceH4/ultrachat_200k\nmodel-index:\n- name: mistral-7b-grok\n  results: []\n---\n\n<!-- This model card has been generated automatically according to the information the Trainer had access to. You\nshould probably proofread and complete it, then remove this comment. -->\n\n# Mistral 7B Grok\n\nThis model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) that has been aligned via Constitutional AI to mimic the style of [xAI's Grok assistant](https://grok.x.ai/).\n\nIt achieves the following results on the evaluation set:\n- Loss: 0.9348\n\n## Model description\n\nMore information needed\n\n## Intended uses & limitations\n\nMore information needed\n\n## Training and evaluation data\n\nMore information needed\n\n## Training procedure\n\n### Training hyperparameters\n\nThe following hyperparameters were used during training:\n- learning_rate: 2e-05\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\n\n### Training results\n\n| Training Loss | Epoch | Step | Validation Loss |\n|:-------------:|:-----:|:----:|:---------------:|\n| 0.9326        | 1.0   | 545  | 0.9348          |\n\n\n### Framework versions\n\n- Transformers 4.36.2\n- Pytorch 2.1.2+cu121\n- Datasets 2.16.1\n- Tokenizers 0.15.0\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 1,
  "downloads": 276,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-01T05:32:20.000Z",
  "created_at": "2024-05-01T03:46:06.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6631bafed858660eab67cd0b",
  "id": "RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf",
  "modelId": "RichardErkhov/HuggingFaceH4_-_mistral-7b-grok-gguf",
  "sha": "60f26fb41336dc1f421bdf2ae8b56b74392a2a09",
  "createdAt": "2024-05-01T03:46:06.000Z",
  "lastModified": "2024-05-01T05:32:20.000Z",
  "author": "RichardErkhov",
  "downloads": 276,
  "likes": 1,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 23
}