richarderkhov/ucla-agi_-_zephyr-7b-sft-full-spin-iter0-gguf overview

{
  "metadata": {},
  "card_data": {
    "frontmatter": {},
    "hero_image_url": "",
    "summary": "This model is a self-play fine-tuned model at iteration 0 from alignment-handbook/zephyr-7b-sft-full using synthetic data based on on the HuggingFaceH4/ultrachat_200k dataset.",
    "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\nzephyr-7b-sft-full-SPIN-iter0 - GGUF\n- Model creator: https://huggingface.co/UCLA-AGI/\n- Original model: https://huggingface.co/UCLA-AGI/zephyr-7b-sft-full-SPIN-iter0/\n\n\n| Name | Quant method | Size |\n| ---- | ---- | ---- |\n| [zephyr-7b-sft-full-SPIN-iter0.Q2_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q2_K.gguf) | Q2_K | 2.53GB |\n| [zephyr-7b-sft-full-SPIN-iter0.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.IQ3_XS.gguf) | IQ3_XS | 2.81GB |\n| [zephyr-7b-sft-full-SPIN-iter0.IQ3_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.IQ3_S.gguf) | IQ3_S | 2.96GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q3_K_S.gguf) | Q3_K_S | 2.95GB |\n| [zephyr-7b-sft-full-SPIN-iter0.IQ3_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.IQ3_M.gguf) | IQ3_M | 3.06GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q3_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q3_K.gguf) | Q3_K | 3.28GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q3_K_M.gguf) | Q3_K_M | 3.28GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q3_K_L.gguf) | Q3_K_L | 3.56GB |\n| [zephyr-7b-sft-full-SPIN-iter0.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.IQ4_XS.gguf) | IQ4_XS | 3.67GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q4_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q4_0.gguf) | Q4_0 | 3.83GB |\n| [zephyr-7b-sft-full-SPIN-iter0.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.IQ4_NL.gguf) | IQ4_NL | 3.87GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q4_K_S.gguf) | Q4_K_S | 3.86GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q4_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q4_K.gguf) | Q4_K | 4.07GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q4_K_M.gguf) | Q4_K_M | 4.07GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q4_1.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q4_1.gguf) | Q4_1 | 4.24GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q5_0.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q5_0.gguf) | Q5_0 | 4.65GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q5_K_S.gguf) | Q5_K_S | 4.65GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q5_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q5_K.gguf) | Q5_K | 4.78GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q5_K_M.gguf) | Q5_K_M | 4.78GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q5_1.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q5_1.gguf) | Q5_1 | 5.07GB |\n| [zephyr-7b-sft-full-SPIN-iter0.Q6_K.gguf](https://huggingface.co/RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf/blob/main/zephyr-7b-sft-full-SPIN-iter0.Q6_K.gguf) | Q6_K | 5.53GB |\n\n\n\n\nOriginal model description:\n---\nlicense: mit\ndatasets:\n- UCLA-AGI/SPIN_iter0\nlanguage:\n- en\npipeline_tag: text-generation\n---\nSelf-Play Fine-Tuning Converts Weak Language Models to Strong Language Models (https://arxiv.org/abs/2401.01335)\n\n# zephyr-7b-sft-full-spin-iter0\n\nThis model is a self-play fine-tuned model at iteration 0 from [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) using synthetic data based on on the [HuggingFaceH4/ultrachat_200k](https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k) dataset.\n\n## Model Details\n\n### Model Description\n\n- Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets.\n- Language(s) (NLP): Primarily English\n- License: MIT\n- Finetuned from model: alignment-handbook/zephyr-7b-sft-full (based on mistralai/Mistral-7B-v0.1)\n\n### Training hyperparameters\nThe following hyperparameters were used during training:\n\n- learning_rate: 5e-07\n- train_batch_size: 8\n- seed: 42\n- distributed_type: multi-GPU\n- num_devices: 8\n- total_train_batch_size: 64\n- optimizer: RMSProp \n- lr_scheduler_type: linear \n- lr_scheduler_warmup_ratio: 0.1\n- num_epochs: 2.0\n\n## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)\nDetailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_UCLA-AGI__test0)\n| Metric                | Value                     |\n|-----------------------|---------------------------|\n| Avg.                  | 62.37   |\n| ARC (25-shot)         | 63.65          |\n| HellaSwag (10-shot)   | 84.44    |\n| MMLU (5-shot)         | 61.01         |\n| TruthfulQA (0-shot)   | 50.48   |\n| Winogrande (5-shot)   | 77.98   |\n| GSM8K (5-shot)        | 36.69        |\n  \n## Citation\n```\n@misc{chen2024selfplay,\n      title={Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models}, \n      author={Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu},\n      year={2024},\n      eprint={2401.01335},\n      archivePrefix={arXiv},\n      primaryClass={cs.LG}\n}\n```\n\n",
    "related_quantizations": []
  },
  "tags": [
    "gguf",
    "arxiv:2401.01335",
    "endpoints_compatible",
    "region:us",
    "conversational"
  ],
  "likes": 0,
  "downloads": 277,
  "gated": false,
  "private": false,
  "last_modified": "2024-05-12T03:24:51.000Z",
  "created_at": "2024-05-12T01:22:50.000Z",
  "pipeline_tag": "",
  "library_name": ""
}

{
  "_id": "664019ea69597de25613d75a",
  "id": "RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf",
  "modelId": "RichardErkhov/UCLA-AGI_-_zephyr-7b-sft-full-SPIN-iter0-gguf",
  "sha": "d68d474362c71003a26e6295da4f31941cf9bbd8",
  "createdAt": "2024-05-12T01:22:50.000Z",
  "lastModified": "2024-05-12T03:24:51.000Z",
  "author": "RichardErkhov",
  "downloads": 277,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "",
  "library_name": "",
  "siblings_count": 23
}