richarderkhov/minillm_-_miniplm-qwen-1.2b-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/2BqT0NgkmIXYlktovw9kG.png",
    "summary": "paper | code **MiniPLM-Qwen-1.2B** is a 1.2B model with Qwen achitecture pre-trained from scratch on the Pile using the MiniPLM knowledge distillation framework with the offcial QWen1.5-1.8B as the teacher model. We also open-source the pre-training corpus refined by Difference Sampling in MiniPLM for reproducibility.",
    "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\nMiniPLM-Qwen-1.2B - GGUF\n- Model creator: https://huggingface.co/MiniLLM/\n- Original model: https://huggingface.co/MiniLLM/MiniPLM-Qwen-1.2B/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [MiniPLM-Qwen-1.2B.Q2_K.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q2_K.gguf) | Q2_K | 0.51GB |\n| [MiniPLM-Qwen-1.2B.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q3_K_S.gguf) | Q3_K_S | 0.57GB |\n| [MiniPLM-Qwen-1.2B.Q3_K.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q3_K.gguf) | Q3_K | 0.61GB |\n| [MiniPLM-Qwen-1.2B.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q3_K_M.gguf) | Q3_K_M | 0.61GB |\n| [MiniPLM-Qwen-1.2B.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q3_K_L.gguf) | Q3_K_L | 0.63GB |\n| [MiniPLM-Qwen-1.2B.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.IQ4_XS.gguf) | IQ4_XS | 0.65GB |\n| [MiniPLM-Qwen-1.2B.Q4_0.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q4_0.gguf) | Q4_0 | 0.67GB |\n| [MiniPLM-Qwen-1.2B.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.IQ4_NL.gguf) | IQ4_NL | 0.67GB |\n| [MiniPLM-Qwen-1.2B.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q4_K_S.gguf) | Q4_K_S | 0.69GB |\n| [MiniPLM-Qwen-1.2B.Q4_K.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q4_K.gguf) | Q4_K | 0.72GB |\n| [MiniPLM-Qwen-1.2B.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q4_K_M.gguf) | Q4_K_M | 0.72GB |\n| [MiniPLM-Qwen-1.2B.Q4_1.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q4_1.gguf) | Q4_1 | 0.72GB |\n| [MiniPLM-Qwen-1.2B.Q5_0.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q5_0.gguf) | Q5_0 | 0.78GB |\n| [MiniPLM-Qwen-1.2B.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q5_K_S.gguf) | Q5_K_S | 0.79GB |\n| [MiniPLM-Qwen-1.2B.Q5_K.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q5_K.gguf) | Q5_K | 0.81GB |\n| [MiniPLM-Qwen-1.2B.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q5_K_M.gguf) | Q5_K_M | 0.81GB |\n| [MiniPLM-Qwen-1.2B.Q5_1.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q5_1.gguf) | Q5_1 | 0.83GB |\n| [MiniPLM-Qwen-1.2B.Q6_K.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q6_K.gguf) | Q6_K | 0.93GB |\n| [MiniPLM-Qwen-1.2B.Q8_0.gguf](https://huggingface.co/RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf/blob/main/MiniPLM-Qwen-1.2B.Q8_0.gguf) | Q8_0 | 1.15GB |\n\n\n\n\nOriginal model description:\n---\nlibrary_name: transformers\nlicense: apache-2.0\ndatasets:\n- monology/pile-uncopyrighted\n- MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5\nlanguage:\n- en\nmetrics:\n- accuracy\npipeline_tag: text-generation\n---\n\n# MinPLM-Qwen-1.2B\n\n[paper](https://arxiv.org/abs/2410.17215) | [code](https://github.com/thu-coai/MiniPLM)\n\n**MiniPLM-Qwen-1.2B** is a 1.2B model with Qwen achitecture pre-trained from scratch on [the Pile](https://huggingface.co/datasets/monology/pile-uncopyrighted) using the MiniPLM knowledge distillation framework with the [offcial QWen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) as the teacher model.\n\nWe also open-source the [pre-training corpus](https://huggingface.co/datasets/MiniLLM/pile-diff_samp-qwen_1.8B-qwen_104M-r0.5) refined by Difference Sampling in MiniPLM for reproducibility.\n\n<p align='left'>\n    <img src=\"https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/2BqT0NgkmIXYlktovw9kG.png\" width=\"1000\">\n</p>\n\n## Evaluation\n\nMiniPLM models achieves better performance given the same computation and scales well across model sizes:\n\n<p align='left'>\n    <img src=\"https://cdn-uploads.huggingface.co/production/uploads/624ac662102fcdff87be51b9/EOYzajQcwQFT5PobqL3j0.png\" width=\"1000\">\n</p>\n\n## Baseline Models\n+ [Conventional Pre-Training](https://huggingface.co/MiniLLM/Pretrain-Qwen-1.2B)\n+ [VanillaKD](https://huggingface.co/MiniLLM/VanillaKD-Pretrain-Qwen-1.2B)\n\n## Citation\n\n```bibtext\n@article{miniplm,\n    title={MiniPLM: Knowledge Distillation for Pre-Training Language Models}, \n    author={Yuxian Gu and Hao Zhou and Fandong Meng and Jie Zhou and Minlie Huang},\n    journal={arXiv preprint arXiv:2410.17215},\n    year={2024}\n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2410.17215",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 758,
  "gated": false,
  "private": false,
  "last_modified": "2024-10-27T16:14:33.000Z",
  "created_at": "2024-10-27T15:56:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "671e62c7de8b8ae4b7439b42",
  "id": "RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf",
  "modelId": "RichardErkhov/MiniLLM_-_MiniPLM-Qwen-1.2B-gguf",
  "sha": "dead74d8455fdf9c541ae00b016d45c6665c057c",
  "createdAt": "2024-10-27T15:56:55.000Z",
  "lastModified": "2024-10-27T16:14:33.000Z",
  "author": "RichardErkhov",
  "downloads": 758,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 21
}