richarderkhov/qgallouedec_-_online-dpo-qwen2-4-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 on the trl-lib/ultrafeedback-prompt dataset. 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\nonline-dpo-qwen2-4 - GGUF\n- Model creator: https://huggingface.co/qgallouedec/\n- Original model: https://huggingface.co/qgallouedec/online-dpo-qwen2-4/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [online-dpo-qwen2-4.Q2_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q2_K.gguf) | Q2_K | 0.32GB |\n| [online-dpo-qwen2-4.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.IQ3_XS.gguf) | IQ3_XS | 0.32GB |\n| [online-dpo-qwen2-4.IQ3_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.IQ3_S.gguf) | IQ3_S | 0.32GB |\n| [online-dpo-qwen2-4.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q3_K_S.gguf) | Q3_K_S | 0.32GB |\n| [online-dpo-qwen2-4.IQ3_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.IQ3_M.gguf) | IQ3_M | 0.32GB |\n| [online-dpo-qwen2-4.Q3_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q3_K.gguf) | Q3_K | 0.33GB |\n| [online-dpo-qwen2-4.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q3_K_M.gguf) | Q3_K_M | 0.33GB |\n| [online-dpo-qwen2-4.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q3_K_L.gguf) | Q3_K_L | 0.34GB |\n| [online-dpo-qwen2-4.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.IQ4_XS.gguf) | IQ4_XS | 0.33GB |\n| [online-dpo-qwen2-4.Q4_0.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q4_0.gguf) | Q4_0 | 0.33GB |\n| [online-dpo-qwen2-4.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.IQ4_NL.gguf) | IQ4_NL | 0.33GB |\n| [online-dpo-qwen2-4.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q4_K_S.gguf) | Q4_K_S | 0.36GB |\n| [online-dpo-qwen2-4.Q4_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q4_K.gguf) | Q4_K | 0.37GB |\n| [online-dpo-qwen2-4.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q4_K_M.gguf) | Q4_K_M | 0.37GB |\n| [online-dpo-qwen2-4.Q4_1.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q4_1.gguf) | Q4_1 | 0.35GB |\n| [online-dpo-qwen2-4.Q5_0.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q5_0.gguf) | Q5_0 | 0.37GB |\n| [online-dpo-qwen2-4.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q5_K_S.gguf) | Q5_K_S | 0.38GB |\n| [online-dpo-qwen2-4.Q5_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q5_K.gguf) | Q5_K | 0.39GB |\n| [online-dpo-qwen2-4.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q5_K_M.gguf) | Q5_K_M | 0.39GB |\n| [online-dpo-qwen2-4.Q5_1.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q5_1.gguf) | Q5_1 | 0.39GB |\n| [online-dpo-qwen2-4.Q6_K.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q6_K.gguf) | Q6_K | 0.47GB |\n| [online-dpo-qwen2-4.Q8_0.gguf](https://huggingface.co/RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf/blob/main/online-dpo-qwen2-4.Q8_0.gguf) | Q8_0 | 0.49GB |\n\n\n\n\nOriginal model description:\n---\nbase_model: Qwen/Qwen2-0.5B-Instruct\ndatasets: trl-lib/ultrafeedback-prompt\nlibrary_name: transformers\nmodel_name: online-dpo-qwen2-4\ntags:\n- trl\n- generated_from_trainer\n- online-dpo\nlicence: license\n---\n\n# Model Card for online-dpo-qwen2-4\n\nThis model is a fine-tuned version of [Qwen/Qwen2-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2-0.5B-Instruct) on the [trl-lib/ultrafeedback-prompt](https://huggingface.co/datasets/trl-lib/ultrafeedback-prompt) dataset.\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/online-dpo-qwen2-4\", device=\"cuda\")\noutput = generator([{\"role\": \"user\", \"content\": question}], max_new_tokens=500)[0]\nprint(output[\"generated_text\"][1][\"content\"])\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/huggingface/runs/8q6fzgyf)\n\nThis model was trained with Online DPO, a method introduced in [Direct Language Model Alignment from Online AI Feedback](https://huggingface.co/papers/2402.04792).\n\n### Framework versions\n\n- TRL: 0.12.0.dev0\n- Transformers: 4.45.0.dev0\n- Pytorch: 2.4.1\n- Datasets: 3.0.0\n- Tokenizers: 0.19.1\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2402.04792",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 159,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-18T18:09:17.000Z",
  "created_at": "2024-10-18T17:56:17.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6712a141c057189305bd9c02",
  "id": "RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf",
  "modelId": "RichardErkhov/qgallouedec_-_online-dpo-qwen2-4-gguf",
  "sha": "f1d2eebf1eb8c28c5fb5e71da46302e7dc60f776",
  "createdAt": "2024-10-18T17:56:17.000Z",
  "lastModified": "2024-10-18T18:09:17.000Z",
  "author": "RichardErkhov",
  "downloads": 159,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}