richarderkhov/xinlai_-_qwen2-7b-sft-step-dpo-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "🖥️Code | 🤗Data | 📄Paper This repo contains the **Qwen2-7B-SFT-Step-DPO** model. It is obtained by performing **Step-DPO** on **Qwen2-7B-SFT**. **Step-DPO** is a simple, effective, and data-efficient method for boosting the mathematical reasoning ability of LLMs. Notably, Step-DPO, when applied to Qwen2-72B-Instruct, achieves scores of **70.8%** and **94.0%** on the test sets of **MATH** and **GSM8K** without bells and wistles, respectively, surpassing a series of closed-source models, including GPT-4-1106, Claude-3-Opus, and Gemini-1.5-Pro.",
    "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\nQwen2-7B-SFT-Step-DPO - GGUF\n- Model creator: https://huggingface.co/xinlai/\n- Original model: https://huggingface.co/xinlai/Qwen2-7B-SFT-Step-DPO/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [Qwen2-7B-SFT-Step-DPO.Q2_K.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q2_K.gguf) | Q2_K | 2.81GB |\n| [Qwen2-7B-SFT-Step-DPO.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.IQ3_XS.gguf) | IQ3_XS | 3.12GB |\n| [Qwen2-7B-SFT-Step-DPO.IQ3_S.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.IQ3_S.gguf) | IQ3_S | 3.26GB |\n| [Qwen2-7B-SFT-Step-DPO.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q3_K_S.gguf) | Q3_K_S | 3.25GB |\n| [Qwen2-7B-SFT-Step-DPO.IQ3_M.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.IQ3_M.gguf) | IQ3_M | 3.33GB |\n| [Qwen2-7B-SFT-Step-DPO.Q3_K.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q3_K.gguf) | Q3_K | 3.55GB |\n| [Qwen2-7B-SFT-Step-DPO.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q3_K_M.gguf) | Q3_K_M | 3.55GB |\n| [Qwen2-7B-SFT-Step-DPO.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q3_K_L.gguf) | Q3_K_L | 3.81GB |\n| [Qwen2-7B-SFT-Step-DPO.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.IQ4_XS.gguf) | IQ4_XS | 3.96GB |\n| [Qwen2-7B-SFT-Step-DPO.Q4_0.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q4_0.gguf) | Q4_0 | 4.13GB |\n| [Qwen2-7B-SFT-Step-DPO.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.IQ4_NL.gguf) | IQ4_NL | 4.16GB |\n| [Qwen2-7B-SFT-Step-DPO.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q4_K_S.gguf) | Q4_K_S | 4.15GB |\n| [Qwen2-7B-SFT-Step-DPO.Q4_K.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q4_K.gguf) | Q4_K | 4.36GB |\n| [Qwen2-7B-SFT-Step-DPO.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q4_K_M.gguf) | Q4_K_M | 4.36GB |\n| [Qwen2-7B-SFT-Step-DPO.Q4_1.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q4_1.gguf) | Q4_1 | 4.54GB |\n| [Qwen2-7B-SFT-Step-DPO.Q5_0.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q5_0.gguf) | Q5_0 | 4.95GB |\n| [Qwen2-7B-SFT-Step-DPO.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q5_K_S.gguf) | Q5_K_S | 4.95GB |\n| [Qwen2-7B-SFT-Step-DPO.Q5_K.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q5_K.gguf) | Q5_K | 5.07GB |\n| [Qwen2-7B-SFT-Step-DPO.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q5_K_M.gguf) | Q5_K_M | 5.07GB |\n| [Qwen2-7B-SFT-Step-DPO.Q5_1.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q5_1.gguf) | Q5_1 | 5.36GB |\n| [Qwen2-7B-SFT-Step-DPO.Q6_K.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q6_K.gguf) | Q6_K | 5.82GB |\n| [Qwen2-7B-SFT-Step-DPO.Q8_0.gguf](https://huggingface.co/RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf/blob/main/Qwen2-7B-SFT-Step-DPO.Q8_0.gguf) | Q8_0 | 7.54GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\n---\n# Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs\n\n🖥️[Code](https://github.com/dvlab-research/Step-DPO) | 🤗[Data](https://huggingface.co/datasets/xinlai/Math-Step-DPO-10K) | 📄[Paper](https://arxiv.org/pdf/2406.18629)\n\nThis repo contains the **Qwen2-7B-SFT-Step-DPO** model. It is obtained by performing **Step-DPO** on [**Qwen2-7B-SFT**](https://huggingface.co/xinlai/Qwen2-7B-SFT).\n\n**Step-DPO** is a simple, effective, and data-efficient method for boosting the mathematical reasoning ability of LLMs. Notably, Step-DPO, when applied to Qwen2-72B-Instruct, achieves scores of **70.8%** and **94.0%** on the test sets of **MATH** and **GSM8K** without bells and wistles, respectively, surpassing a series of closed-source models, including GPT-4-1106, Claude-3-Opus, and Gemini-1.5-Pro.\n\n## Contact\n\nPlease submit an issue [here](https://github.com/dvlab-research/Step-DPO) or send me an email [here](mailto:xinlai@cse.cuhk.edu.hk).\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2406.18629",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 1804,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-09T03:45:38.000Z",
  "created_at": "2024-10-09T00:18:50.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6705cbea3c3d62c443a001a5",
  "id": "RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf",
  "modelId": "RichardErkhov/xinlai_-_Qwen2-7B-SFT-Step-DPO-gguf",
  "sha": "d59f3612072e01c1a9113782df3b252a7136aad0",
  "createdAt": "2024-10-09T00:18:50.000Z",
  "lastModified": "2024-10-09T03:45:38.000Z",
  "author": "RichardErkhov",
  "downloads": 1804,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}