LegendLeoChen / llm-finetune Public

Notifications You must be signed in to change notification settings
Fork 1
Star 6

使用trl、peft、transformers等库，实现对huggingface上模型的微调。

6 stars 1 fork Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
chat.py		chat.py
convert.py		convert.py
download_data.py		download_data.py
main_GRPO.py		main_GRPO.py
main_lora.py		main_lora.py
main_prefix.py		main_prefix.py

Repository files navigation

概述

使用trl、peft、transformers等库，实现对huggingface上模型的微调。
blog

文件

datasets：数据集
models：大模型
results：微调后的模型
chat.py：仅聊天
convert.py：获取数据集并转为json文件保存
download_data.py：仅下载原数据集
main_GRPO.py：RLHF微调模型，使用GRPO算法
main_lora.py：SFT微调模型，lora方法
main_prefix.py：SFT微调模型，prefix方法

About

使用trl、peft、transformers等库，实现对huggingface上模型的微调。

reinforcement-learning transformers rl lora peft sft huggingface trl llm rlhf qwen grpo

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%