richarderkhov/1bitllm_-_bitnet_b1_58-xl-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "Quantization made by Richard Erkhov. Github Discord Request more models bitnet_b1_58-xl - GGUF | Name | Quant method | Size | | ---- | ---- | ---- | | bitnet_b1_58-xl.Q2_K.gguf | Q2_K | 0.05GB | | bitnet_b1_58-xl.IQ3_XS.gguf | IQ3_XS | 0.05GB | | bitnet_b1_58-xl.IQ3_S.gguf | IQ3_S | 0.05GB | | bitnet_b1_58-xl.Q3_K_S.gguf | Q3_K_S | 0.05GB | | bitnet_b1_58-xl.IQ3_M.gguf | IQ3_M | 0.05GB | | bitnet_b1_58-xl.Q3_K.gguf | Q3_K | 0.05GB | | bitnet_b1_58-xl.Q3_K_M.gguf | Q3_K_M | 0.05GB | | bitnet_b1_58-xl.Q3_K_L.gguf | Q3_K_L | 0.05GB | | bitnet_b1_58-xl.IQ4_XS.gguf | IQ4_XS | 0.05GB | | bitnet_b1_58-xl.Q4_0.gguf | Q4_0 | 0.05GB | | bitnet_b1_58-xl.IQ4_NL.gguf | IQ4_NL | 0.05GB | | bitnet_b1_58-xl.Q4_K_S.gguf | Q4_K_S | 0.05GB | | bitnet_b1_58-xl.Q4_K.gguf | Q4_K | 0.05GB | | bitnet_b1_58-xl.Q4_K_M.gguf | Q4_K_M | 0.05GB | | bitnet_b1_58-xl.Q4_1.gguf | Q4_1 | 0.05GB | | bitnet_b1_58-xl.Q5_0.gguf | Q5_0 | 0.05GB | | bitnet_b1_58-xl.Q5_K_S.gguf | Q5_K_S | 0.05GB | | bitnet_b1_58-xl.Q5_K.gguf | Q5_K | 0.05GB | | bitnet_b1_58-xl.Q5_K_M.gguf | Q5_K_M | 0.05GB | | bitnet_b1_58-xl.Q5_1.gguf | Q5_1 | 0.05GB | | bitnet_b1_58-xl.Q6_K.gguf | Q6_K | 0.05GB | | bitnet_b1_58-xl.Q8_0.gguf | Q8_0 | 0.07GB | Original model description: --- license: mit --- This is a reproduction of the  BitNet b1.58 paper. The models are trained with RedPajama dataset for 100B tokens. The hypers, as well as two-stage LR and weight decay, are implemented as suggested in their following paper. All models are open-source in the repo. We will train larger models and/or more tokens when resource is available.",
    "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\nbitnet_b1_58-xl - GGUF\n- Model creator: https://huggingface.co/1bitLLM/\n- Original model: https://huggingface.co/1bitLLM/bitnet_b1_58-xl/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [bitnet_b1_58-xl.Q2_K.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q2_K.gguf) | Q2_K | 0.05GB |\n| [bitnet_b1_58-xl.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.IQ3_XS.gguf) | IQ3_XS | 0.05GB |\n| [bitnet_b1_58-xl.IQ3_S.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.IQ3_S.gguf) | IQ3_S | 0.05GB |\n| [bitnet_b1_58-xl.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q3_K_S.gguf) | Q3_K_S | 0.05GB |\n| [bitnet_b1_58-xl.IQ3_M.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.IQ3_M.gguf) | IQ3_M | 0.05GB |\n| [bitnet_b1_58-xl.Q3_K.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q3_K.gguf) | Q3_K | 0.05GB |\n| [bitnet_b1_58-xl.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q3_K_M.gguf) | Q3_K_M | 0.05GB |\n| [bitnet_b1_58-xl.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q3_K_L.gguf) | Q3_K_L | 0.05GB |\n| [bitnet_b1_58-xl.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.IQ4_XS.gguf) | IQ4_XS | 0.05GB |\n| [bitnet_b1_58-xl.Q4_0.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q4_0.gguf) | Q4_0 | 0.05GB |\n| [bitnet_b1_58-xl.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.IQ4_NL.gguf) | IQ4_NL | 0.05GB |\n| [bitnet_b1_58-xl.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q4_K_S.gguf) | Q4_K_S | 0.05GB |\n| [bitnet_b1_58-xl.Q4_K.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q4_K.gguf) | Q4_K | 0.05GB |\n| [bitnet_b1_58-xl.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q4_K_M.gguf) | Q4_K_M | 0.05GB |\n| [bitnet_b1_58-xl.Q4_1.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q4_1.gguf) | Q4_1 | 0.05GB |\n| [bitnet_b1_58-xl.Q5_0.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q5_0.gguf) | Q5_0 | 0.05GB |\n| [bitnet_b1_58-xl.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q5_K_S.gguf) | Q5_K_S | 0.05GB |\n| [bitnet_b1_58-xl.Q5_K.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q5_K.gguf) | Q5_K | 0.05GB |\n| [bitnet_b1_58-xl.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q5_K_M.gguf) | Q5_K_M | 0.05GB |\n| [bitnet_b1_58-xl.Q5_1.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q5_1.gguf) | Q5_1 | 0.05GB |\n| [bitnet_b1_58-xl.Q6_K.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q6_K.gguf) | Q6_K | 0.05GB |\n| [bitnet_b1_58-xl.Q8_0.gguf](https://huggingface.co/RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf/blob/main/bitnet_b1_58-xl.Q8_0.gguf) | Q8_0 | 0.07GB |\n\n\n\n\nOriginal model description:\n---\nlicense: mit\n---\n\nThis is a reproduction of the <a href=\"https://arxiv.org/abs/2402.17764\"> BitNet b1.58</a> paper. The models are trained with <a href=\"https://github.com/togethercomputer/RedPajama-Data\">RedPajama dataset</a> for 100B tokens. The hypers, as well as two-stage LR and weight decay, are implemented as suggested in their following <a href=\"https://github.com/microsoft/unilm/blob/master/bitnet/The-Era-of-1-bit-LLMs__Training_Tips_Code_FAQ.pdf\">paper</a>. All models are open-source in the <a href=\"https://huggingface.co/1bitLLM\">repo</a>. We will train larger models and/or more tokens when resource is available.\n\n## Results\nPPL and zero-shot accuracy:\n| Models | PPL| ARCe| ARCc| HS | BQ | OQ | PQ | WGe | Avg\n|-------|-------|-------|-------|-------|-------|-------|-------|-------|-------|\n| FP16 700M (reported) | 12.33 | 54.7 | 23.0 | 37.0 | 60.0 | 20.2 | 68.9 | 54.8 | 45.5 |\n| BitNet b1.58 700M (reported) | 12.87 | 51.8 | 21.4 | 35.1 | 58.2 | 20.0 | 68.1 | 55.2 | 44.3 |\n| BitNet b1.58 700M (reproduced) | 12.78 | 51.4 | 21.8 | 35.0 | 59.6 | 20.6 | 67.5 | 55.4 | 44.5 |\n| FP16 1.3B (reported)    | 11.25  | 56.9 | 23.5 | 38.5 | 59.1 | 21.6 | 70.0 | 53.9 | 46.2\n| BitNet b1.58 1.3B (reported)    | 11.29  | 54.9 | 24.2 | 37.7 | 56.7 | 19.6 | 68.8 | 55.8 | 45.4 |\n| BitNet b1.58 1.3B (reproduced)    | 11.19 | 55.8 | 23.7 | 37.6 | 59.0 | 20.2 | 69.2 | 56.0 | 45.9\n| FP16 3B (reported)    | 10.04   | 62.1 | 25.6 | 43.3 | 61.8 | 24.6 | 72.1 | 58.2 | 49.7\n| BitNet b1.58 3B (reported)    | 9.91   | 61.4 | 28.3 | 42.9 | 61.5 | 26.6 | 71.5 | 59.3 | 50.2\n| BitNet b1.58 3B (reproduced)    | 9.88 | 60.9 | 28.0 | 42.3 | 58.3 | 26.0 | 71.4 | 60.3 | 49.6 |\n\nThe differences between the reported numbers and the reproduced results are possibly variances from the training data processing, seeds, or other random factors.\n\n## Evaluation\nThe evaluation pipelines are from the paper authors. Here is the commands to run the evaluation:\n```\npip install lm-eval==0.3.0\n```\n```\npython eval_ppl.py --hf_path 1bitLLM/bitnet_b1_58-3B --seqlen 2048\n```\n```\npython eval_task.py --hf_path 1bitLLM/bitnet_b1_58-3B \\\n    --batch_size 1 \\\n    --tasks \\\n    --output_path result.json \\\n    --num_fewshot 0 \\\n    --ctx_size 2048\n```\n\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2402.17764",
    "region:us"
  ],
  "likes": 0,
  "downloads": 94,
  "gated": false,
  "private": false,
  "last_modified": "2024-07-13T19:19:51.000Z",
  "created_at": "2024-07-13T19:18:55.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "6692d31f5a10e25ee3108d1d",
  "id": "RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf",
  "modelId": "RichardErkhov/1bitLLM_-_bitnet_b1_58-xl-gguf",
  "sha": "346f3f8f44b4aa9a9ff286615208063daa5c10f0",
  "createdAt": "2024-07-13T19:18:55.000Z",
  "lastModified": "2024-07-13T19:19:51.000Z",
  "author": "RichardErkhov",
  "downloads": 94,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 24
}