richarderkhov/gritlm_-_gritlm-7b-kto-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "A **KTO** version of https://huggingface.co/GritLM/GritLM-7B > GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks. | Model | Description | |-------|-------------| | GritLM 7B | Mistral 7B finetuned using GRIT | | GritLM 8x7B | Mixtral 8x7B finetuned using GRIT | # Use The model usage is documented here. # Citation ``bibtex @misc{muennighoff2024generative, title={Generative Representational Instruction Tuning}, author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela}, year={2024}, eprint={2402.09906}, archivePrefix={arXiv}, primaryClass={cs.CL} } ``",
    "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\nGritLM-7B-KTO - GGUF\n- Model creator: https://huggingface.co/GritLM/\n- Original model: https://huggingface.co/GritLM/GritLM-7B-KTO/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [GritLM-7B-KTO.Q2_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q2_K.gguf) | Q2_K | 2.53GB |\n| [GritLM-7B-KTO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [GritLM-7B-KTO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [GritLM-7B-KTO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [GritLM-7B-KTO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [GritLM-7B-KTO.Q3_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q3_K.gguf) | Q3_K | 3.28GB |\n| [GritLM-7B-KTO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [GritLM-7B-KTO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [GritLM-7B-KTO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [GritLM-7B-KTO.Q4_0.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [GritLM-7B-KTO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [GritLM-7B-KTO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [GritLM-7B-KTO.Q4_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q4_K.gguf) | Q4_K | 4.07GB |\n| [GritLM-7B-KTO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [GritLM-7B-KTO.Q4_1.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [GritLM-7B-KTO.Q5_0.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [GritLM-7B-KTO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [GritLM-7B-KTO.Q5_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q5_K.gguf) | Q5_K | 4.78GB |\n| [GritLM-7B-KTO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [GritLM-7B-KTO.Q5_1.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [GritLM-7B-KTO.Q6_K.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q6_K.gguf) | Q6_K | 5.53GB |\n| [GritLM-7B-KTO.Q8_0.gguf](https://huggingface.co/RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf/blob/main/GritLM-7B-KTO.Q8_0.gguf) | Q8_0 | 7.17GB |\n\n\n\n\nOriginal model description:\n---\npipeline_tag: text-generation\ninference: true\nlicense: apache-2.0\ndatasets:\n- GritLM/tulu2\n\n---\n\n# Model Summary\n\nA [**KTO**](https://arxiv.org/abs/2402.01306) version of https://huggingface.co/GritLM/GritLM-7B\n\n> GritLM is a generative representational instruction tuned language model. It unifies text representation (embedding) and text generation into a single model achieving state-of-the-art performance on both types of tasks.\n\n- **Repository:** [ContextualAI/gritlm](https://github.com/ContextualAI/gritlm)\n- **Paper:** https://arxiv.org/abs/2402.09906\n- **Logs:** https://wandb.ai/muennighoff/gritlm/runs/0uui712t/overview\n- **Script:** https://github.com/ContextualAI/gritlm/blob/main/scripts/training/train_gritlm_7b.sh\n\n| Model | Description |\n|-------|-------------|\n| [GritLM 7B](https://hf.co/GritLM/GritLM-7B) | Mistral 7B finetuned using GRIT |\n| [GritLM 8x7B](https://hf.co/GritLM/GritLM-8x7B) | Mixtral 8x7B finetuned using GRIT |\n\n# Use\n\nThe model usage is documented [here](https://github.com/ContextualAI/gritlm?tab=readme-ov-file#inference).\n\n# Citation\n\n```bibtex\n@misc{muennighoff2024generative,\n      title={Generative Representational Instruction Tuning}, \n      author={Niklas Muennighoff and Hongjin Su and Liang Wang and Nan Yang and Furu Wei and Tao Yu and Amanpreet Singh and Douwe Kiela},\n      year={2024},\n      eprint={2402.09906},\n      archivePrefix={arXiv},\n      primaryClass={cs.CL}\n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2402.01306",
    "arxiv:2402.09906",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 109,
  "gated": false,
  "private": false,
  "last_modified": "2024-09-18T23:41:01.000Z",
  "created_at": "2024-09-18T19:47:28.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "66eb2e5062a7994891bbe678",
  "id": "RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf",
  "modelId": "RichardErkhov/GritLM_-_GritLM-7B-KTO-gguf",
  "sha": "d0f1bff916ac5286ea67427fbcc76cfc3f75352e",
  "createdAt": "2024-09-18T19:47:28.000Z",
  "lastModified": "2024-09-18T23:41:01.000Z",
  "author": "RichardErkhov",
  "downloads": 109,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}