From 4a2cc60b9440d245141e9317c35a0ac4c687dbdb Mon Sep 17 00:00:00 2001 From: hiyouga Date: Fri, 8 Mar 2024 03:06:21 +0800 Subject: [PATCH] update readme --- README.md | 2 +- README_zh.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 9d1e425f..4232da90 100644 --- a/README.md +++ b/README.md @@ -49,7 +49,7 @@ Choose your path: - **Integrated methods**: (Continuous) pre-training, supervised fine-tuning, reward modeling, PPO and DPO. - **Scalable resources**: 32-bit full-tuning, 16-bit freeze-tuning, 16-bit LoRA and 2/4/8-bit QLoRA via AQLM/AWQ/GPTQ/LLM.int8. - **Advanced algorithms**: DoRA, LongLoRA, LLaMA Pro, LoftQ and Agent tuning. -- **Practical tricks**: FlashAttention-2, Unsloth, RoPE scaling, NEFTune and rsLoRA. +- **Practical tricks**: FlashAttention-2, Unsloth, RoPE scaling, NEFTune, rsLoRA and GaLore. - **Experiment monitors**: LlamaBoard, TensorBoard, Wandb, MLflow, etc. - **Faster inference**: OpenAI-style API, Gradio UI and CLI with vLLM worker. diff --git a/README_zh.md b/README_zh.md index 86f7a5fe..66d86d30 100644 --- a/README_zh.md +++ b/README_zh.md @@ -49,7 +49,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd - **集成方法**：（增量）预训练、指令监督微调、奖励模型训练、PPO 训练和 DPO 训练。 - **多种精度**：32 比特全参数微调、16 比特冻结微调、16 比特 LoRA 微调和基于 AQLM/AWQ/GPTQ/LLM.int8 的 2/4/8 比特 QLoRA 微调。 - **先进算法**：DoRA、LongLoRA、LLaMA Pro、LoftQ 和 Agent 微调。 -- **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune 和 rsLoRA。 +- **实用技巧**：FlashAttention-2、Unsloth、RoPE scaling、NEFTune、rsLoRA 和 GaLore。 - **实验监控**：LlamaBoard、TensorBoard、Wandb、MLflow 等等。 - **极速推理**：基于 vLLM 的 OpenAI 风格 API、浏览器界面和命令行接口。