richarderkhov/qgallouedec_-_qwen2-0.5b-nashmd-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 Qwen/Qwen2-0.5B-Instruct. 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\nQwen2-0.5B-NashMD - GGUF\n- Model creator: https://huggingface.co/qgallouedec/\n- Original model: https://huggingface.co/qgallouedec/Qwen2-0.5B-NashMD/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Qwen2-0.5B-NashMD.Q2_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q2_K.gguf) | Q2_K | 0.32GB |\n| [Qwen2-0.5B-NashMD.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.IQ3_XS.gguf) | IQ3_XS | 0.32GB |\n| [Qwen2-0.5B-NashMD.IQ3_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.IQ3_S.gguf) | IQ3_S | 0.32GB |\n| [Qwen2-0.5B-NashMD.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q3_K_S.gguf) | Q3_K_S | 0.32GB |\n| [Qwen2-0.5B-NashMD.IQ3_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.IQ3_M.gguf) | IQ3_M | 0.32GB |\n| [Qwen2-0.5B-NashMD.Q3_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q3_K.gguf) | Q3_K | 0.33GB |\n| [Qwen2-0.5B-NashMD.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q3_K_M.gguf) | Q3_K_M | 0.33GB |\n| [Qwen2-0.5B-NashMD.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q3_K_L.gguf) | Q3_K_L | 0.34GB |\n| [Qwen2-0.5B-NashMD.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.IQ4_XS.gguf) | IQ4_XS | 0.33GB |\n| [Qwen2-0.5B-NashMD.Q4_0.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q4_0.gguf) | Q4_0 | 0.33GB |\n| [Qwen2-0.5B-NashMD.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.IQ4_NL.gguf) | IQ4_NL | 0.33GB |\n| [Qwen2-0.5B-NashMD.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q4_K_S.gguf) | Q4_K_S | 0.36GB |\n| [Qwen2-0.5B-NashMD.Q4_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q4_K.gguf) | Q4_K | 0.37GB |\n| [Qwen2-0.5B-NashMD.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q4_K_M.gguf) | Q4_K_M | 0.37GB |\n| [Qwen2-0.5B-NashMD.Q4_1.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q4_1.gguf) | Q4_1 | 0.35GB |\n| [Qwen2-0.5B-NashMD.Q5_0.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q5_0.gguf) | Q5_0 | 0.37GB |\n| [Qwen2-0.5B-NashMD.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q5_K_S.gguf) | Q5_K_S | 0.38GB |\n| [Qwen2-0.5B-NashMD.Q5_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q5_K.gguf) | Q5_K | 0.39GB |\n| [Qwen2-0.5B-NashMD.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q5_K_M.gguf) | Q5_K_M | 0.39GB |\n| [Qwen2-0.5B-NashMD.Q5_1.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q5_1.gguf) | Q5_1 | 0.39GB |\n| [Qwen2-0.5B-NashMD.Q6_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q6_K.gguf) | Q6_K | 0.47GB |\n| [Qwen2-0.5B-NashMD.Q8_0.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf/blob/main/Qwen2-0.5B-NashMD.Q8_0.gguf) | Q8_0 | 0.49GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: Qwen/Qwen2-0.5B-Instruct\nlibrary_name: transformers\nmodel_name: Qwen2-0.5B-NashMD\ntags:\n- generated_from_trainer\n- trl\n- nash-md\nlicence: license\n---\n\n# Model Card for Qwen2-0.5B-NashMD\n\nThis model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct).\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=\"qgallouedec/Qwen2-0.5B-NashMD\", 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/huggingface/trl/runs/5r7w3wt4)\n\nThis model was trained with Nash-MD, a method introduced in [Nash Learning from Human Feedback](https://huggingface.co/papers/2312.00886).\n\n### Framework versions\n\n- TRL: 0.12.0.dev0\n- Transformers: 4.46.0.dev0\n- Pytorch: 2.4.1\n- Datasets: 3.0.2\n- Tokenizers: 0.20.0\n\n## Citations\n\nCite Nash-MD as:\n\n```bibtex\n@inproceedings{munos2024nash,\n    title        = {Nash Learning from Human Feedback},\n    author       = {R{'{e}}mi Munos and Michal Valko and Daniele Calandriello and Mohammad Gheshlaghi Azar and Mark Rowland and Zhaohan Daniel Guo and Yunhao Tang and Matthieu Geist and Thomas Mesnard and C{\\^{o}}me Fiegel and Andrea Michi and Marco Selvi and Sertan Girgin and Nikola Momchev and Olivier Bachem and Daniel J. Mankowitz and Doina Precup and Bilal Piot},\n    year         = 2024,\n    booktitle    = {Forty-first International Conference on Machine Learning, {ICML} 2024, Vienna, Austria, July 21-27, 2024},\n    publisher    = {OpenReview.net},\n    url          = {https://openreview.net/forum?id=Y5AmNYiyCQ}\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:2312.00886",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 734,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-15T00:58:31.000Z",
  "created_at": "2025-03-15T00:50:02.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67d4ceba53fce758344ff7a4",
  "id": "RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf",
  "modelId": "RichardErkhov/qgallouedec_-_Qwen2-0.5B-NashMD-gguf",
  "sha": "4bb18ef9e6ced7eb3c853543c282a20396160d16",
  "createdAt": "2025-03-15T00:50:02.000Z",
  "lastModified": "2025-03-15T00:58:31.000Z",
  "author": "RichardErkhov",
  "downloads": 734,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}