richarderkhov/ryanyr_-_self-correct_llama-3.2-3b-instruct_metamathqa_dpo_iter2-only2nd-4e-7-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg",
    "summary": "This model is a fine-tuned version of RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2. It has been trained using TRL.",
    "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\nself-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7 - GGUF\n- Model creator: https://huggingface.co/RyanYr/\n- Original model: https://huggingface.co/RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q2_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q2_K.gguf) | Q2_K | 1.39GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K_S.gguf) | Q3_K_S | 1.59GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K.gguf) | Q3_K | 1.73GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K_M.gguf) | Q3_K_M | 1.73GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q3_K_L.gguf) | Q3_K_L | 1.85GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.IQ4_XS.gguf) | IQ4_XS | 1.91GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_0.gguf) | Q4_0 | 1.99GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.IQ4_NL.gguf) | IQ4_NL | 2.0GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_K_S.gguf) | Q4_K_S | 2.0GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_K.gguf) | Q4_K | 2.09GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_K_M.gguf) | Q4_K_M | 2.09GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_1.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q4_1.gguf) | Q4_1 | 2.18GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_0.gguf) | Q5_0 | 2.37GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_K_S.gguf) | Q5_K_S | 2.37GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_K.gguf) | Q5_K | 2.41GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_K_M.gguf) | Q5_K_M | 2.41GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_1.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q5_1.gguf) | Q5_1 | 2.55GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q6_K.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q6_K.gguf) | Q6_K | 2.76GB |\n| [self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q8_0.gguf](https://huggingface.co/RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf/blob/main/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7.Q8_0.gguf) | Q8_0 | 3.58GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2\nlibrary_name: transformers\nmodel_name: self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7\ntags:\n- generated_from_trainer\n- trl\n- dpo\nlicence: license\n---\n\n# Model Card for self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7\n\nThis model is a fine-tuned version of [RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2](https://huggingface.co/RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2).\nIt has been trained using [TRL](https://github.com/huggingface/trl).\n\n## Quick start\n\n```python\nfrom transformers import pipeline\n\nquestion = \"If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?\"\ngenerator = pipeline(\"text-generation\", model=\"RyanYr/self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7\", device=\"cuda\")\noutput = generator([{\"role\": \"user\", \"content\": question}], max_new_tokens=128, return_full_text=False)[0]\nprint(output[\"generated_text\"])\n```\n\n## Training procedure\n\n[<img src=\"https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg\" alt=\"Visualize in Weights & Biases\" width=\"150\" height=\"24\"/>](https://wandb.ai/yyr/huggingface/runs/hmx3gnos)\n\nThis model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).\n\n### Framework versions\n\n- TRL: 0.12.0.dev0\n- Transformers: 4.45.2\n- Pytorch: 2.4.0\n- Datasets: 3.0.1\n- Tokenizers: 0.20.1\n\n## Citations\n\nCite DPO as:\n\n```bibtex\n@inproceedings{rafailov2023direct,\n    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},\n    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},\n    year         = 2023,\n    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},\n    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},\n    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},\n}\n```\n\nCite TRL as:\n    \n```bibtex\n@misc{vonwerra2022trl,\n\ttitle        = {{TRL: Transformer Reinforcement Learning}},\n\tauthor       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},\n\tyear         = 2020,\n\tjournal      = {GitHub repository},\n\tpublisher    = {GitHub},\n\thowpublished = {\\url{https://github.com/huggingface/trl}}\n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2305.18290",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 144,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-26T15:26:16.000Z",
  "created_at": "2024-10-26T14:30:11.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "671cfcf375a642a7c1b44077",
  "id": "RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf",
  "modelId": "RichardErkhov/RyanYr_-_self-correct_Llama-3.2-3B-Instruct_metaMathQA_dpo_iter2-only2nd-4e-7-gguf",
  "sha": "7d4303b8fc98f186b4e80ffbe446f535736a1b8d",
  "createdAt": "2024-10-26T14:30:11.000Z",
  "lastModified": "2024-10-26T15:26:16.000Z",
  "author": "RichardErkhov",
  "downloads": 144,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}