hiyouga/LLaMA-Efficient-Tuning

This is stars and forks stats for /hiyouga/LLaMA-Efficient-Tuning repository. As of 28 Apr, 2024 this repository has 4808 stars and 946 forks.

LLaMA Efficient Tuning 👋 Join our WeChat. [ English | 中文 ] Changelog [23/09/27] We supported $S^2$-Attn proposed by LongLoRA for the LLaMA models. Try --shift_attn argument to enable shift short attention. [23/09/23] We integrated MMLU, C-Eval and CMMLU benchmarks in this repo. See this example to evaluate your models. [23/09/10] We supported using FlashAttention-2 for the LLaMA models. Try --flash_attn argument to enable FlashAttention-2 if you are using RTX4090, A100 or H100 GPUs. [23/08/18] We...