| Quantization made by Richard Erkhov. | |
| [Github](https://github.com/RichardErkhov) | |
| [Discord](https://discord.gg/pvy7H8DZMG) | |
| [Request more models](https://github.com/RichardErkhov/quant_request) | |
| zephyr-7b-sft-full-SPIN-iter2 - bnb 4bits | |
| - Model creator: https://huggingface.co/UCLA-AGI/ | |
| - Original model: https://huggingface.co/UCLA-AGI/zephyr-7b-sft-full-SPIN-iter2/ | |
| Original model description: | |
| --- | |
| license: mit | |
| datasets: | |
| - UCLA-AGI/SPIN_iter2 | |
| language: | |
| - en | |
| pipeline_tag: text-generation | |
| --- | |
| Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models (https://arxiv.org/abs/2401.01335) | |
| # zephyr-7b-sft-full-spin-iter2 | |
| This model is a self-play fine-tuned model at iteration 2 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. | |
| ## Model Details | |
| ### Model Description | |
| - Model type: A 7B parameter GPT-like model fine-tuned on synthetic datasets. | |
| - Language(s) (NLP): Primarily English | |
| - License: MIT | |
| - Finetuned from model: alignment-handbook/zephyr-7b-sft-full (based on mistralai/Mistral-7B-v0.1) | |
| ### Training hyperparameters | |
| The following hyperparameters were used during training: | |
| - learning_rate: 1e-07 | |
| - train_batch_size: 8 | |
| - seed: 42 | |
| - distributed_type: multi-GPU | |
| - num_devices: 8 | |
| - total_train_batch_size: 64 | |
| - optimizer: RMSProp | |
| - lr_scheduler_type: linear | |
| - lr_scheduler_warmup_ratio: 0.1 | |
| - num_epochs: 2.0 | |
| ## [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) | |
| Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_UCLA-AGI__test-test) | |
| | Metric | Value | | |
| |-----------------------|---------------------------| | |
| | Avg. | 63.54 | | |
| | ARC (25-shot) | 66.47 | | |
| | HellaSwag (10-shot) | 85.82 | | |
| | MMLU (5-shot) | 61.48 | | |
| | TruthfulQA (0-shot) | 57.75 | | |
| | Winogrande (5-shot) | 76.95 | | |
| | GSM8K (5-shot) | 32.75 | | |
| ## Citation | |
| ``` | |
| @misc{chen2024selfplay, | |
| title={Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models}, | |
| author={Zixiang Chen and Yihe Deng and Huizhuo Yuan and Kaixuan Ji and Quanquan Gu}, | |
| year={2024}, | |
| eprint={2401.01335}, | |
| archivePrefix={arXiv}, | |
| primaryClass={cs.LG} | |
| } | |
| ``` | |