richarderkhov/gair-prox_-_math-chunk-refining-lm-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "prox-teaser.png",
    "summary": "ArXiv | Code **Math-chunk-refining-lm** is an adapted 0.3B-ProX model, fine-tuned for doc level refining via program generation, and can be applied over math pre-training corpus such as open-web-math.    ### Citation `` @article{zhou2024programming, title={Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale}, author={Zhou, Fan and Wang, Zengzhi and Liu, Qian and Li, Junlong and Liu, Pengfei}, journal={arXiv preprint arXiv:2409.17115}, year={2024} } ``",
    "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\nmath-chunk-refining-lm - GGUF\n- Model creator: https://huggingface.co/gair-prox/\n- Original model: https://huggingface.co/gair-prox/math-chunk-refining-lm/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [math-chunk-refining-lm.Q2_K.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q2_K.gguf) | Q2_K | 0.14GB |\n| [math-chunk-refining-lm.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.IQ3_XS.gguf) | IQ3_XS | 0.15GB |\n| [math-chunk-refining-lm.IQ3_S.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.IQ3_S.gguf) | IQ3_S | 0.16GB |\n| [math-chunk-refining-lm.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q3_K_S.gguf) | Q3_K_S | 0.16GB |\n| [math-chunk-refining-lm.IQ3_M.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.IQ3_M.gguf) | IQ3_M | 0.16GB |\n| [math-chunk-refining-lm.Q3_K.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q3_K.gguf) | Q3_K | 0.17GB |\n| [math-chunk-refining-lm.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q3_K_M.gguf) | Q3_K_M | 0.17GB |\n| [math-chunk-refining-lm.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q3_K_L.gguf) | Q3_K_L | 0.18GB |\n| [math-chunk-refining-lm.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.IQ4_XS.gguf) | IQ4_XS | 0.19GB |\n| [math-chunk-refining-lm.Q4_0.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q4_0.gguf) | Q4_0 | 0.2GB |\n| [math-chunk-refining-lm.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.IQ4_NL.gguf) | IQ4_NL | 0.2GB |\n| [math-chunk-refining-lm.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q4_K_S.gguf) | Q4_K_S | 0.2GB |\n| [math-chunk-refining-lm.Q4_K.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q4_K.gguf) | Q4_K | 0.2GB |\n| [math-chunk-refining-lm.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q4_K_M.gguf) | Q4_K_M | 0.2GB |\n| [math-chunk-refining-lm.Q4_1.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q4_1.gguf) | Q4_1 | 0.21GB |\n| [math-chunk-refining-lm.Q5_0.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q5_0.gguf) | Q5_0 | 0.23GB |\n| [math-chunk-refining-lm.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q5_K_S.gguf) | Q5_K_S | 0.23GB |\n| [math-chunk-refining-lm.Q5_K.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q5_K.gguf) | Q5_K | 0.24GB |\n| [math-chunk-refining-lm.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q5_K_M.gguf) | Q5_K_M | 0.24GB |\n| [math-chunk-refining-lm.Q5_1.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q5_1.gguf) | Q5_1 | 0.25GB |\n| [math-chunk-refining-lm.Q6_K.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q6_K.gguf) | Q6_K | 0.27GB |\n| [math-chunk-refining-lm.Q8_0.gguf](https://huggingface.co/RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf/blob/main/math-chunk-refining-lm.Q8_0.gguf) | Q8_0 | 0.35GB |\n\n\n\n\nOriginal model description:\n---\nlicense: apache-2.0\ndatasets:\n- gair-prox/RedPajama-pro\nlanguage:\n- en\nbase_model:\n- gair-prox/RedPJ-ProX-0.3B\npipeline_tag: text-generation\nlibrary_name: transformers\ntags:\n- llama\n- code\n---\n\n# Math-chunk-refining-lm\n\n<p align=\"center\">\n  <img src=\"prox-teaser.png\">\n</p>\n\n[ArXiv](http://arxiv.org/abs/2409.17115) | [Code](https://github.com/GAIR-NLP/program-every-example)\n\n**Math-chunk-refining-lm** is an adapted [0.3B-ProX](https://huggingface.co/gair-prox/RedPJ-ProX-0.3B) model, fine-tuned for doc level refining via program generation, and can be applied over math pre-training corpus such as open-web-math.\n\n<p align=\"center\">\n  <img src=\"func_design.png\">\n</p>\n\n### Citation\n```\n@article{zhou2024programming,\n  title={Programming Every Example: Lifting Pre-training Data Quality like Experts at Scale},\n  author={Zhou, Fan and Wang, Zengzhi and Liu, Qian and Li, Junlong and Liu, Pengfei},\n  journal={arXiv preprint arXiv:2409.17115},\n  year={2024}\n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2409.17115",
    "endpoints_compatible",
    "region:us"
  ],
  "likes": 0,
  "downloads": 1003,
  "gated": false,
  "private": false,
  "last_modified": "2025-03-14T05:12:11.000Z",
  "created_at": "2025-03-14T05:06:21.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "67d3b94ddc79f6e3c6a47de7",
  "id": "RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf",
  "modelId": "RichardErkhov/gair-prox_-_math-chunk-refining-lm-gguf",
  "sha": "d96f6011b84327fafeb995cd9f7054b0a8843edd",
  "createdAt": "2025-03-14T05:06:21.000Z",
  "lastModified": "2025-03-14T05:12:11.000Z",
  "author": "RichardErkhov",
  "downloads": 1003,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}