fine-tuning-with-trl

name	fine-tuning-with-trl
description	Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction ...
version	1.0.0
triggers	["fine tuning with trl","fine-tuning-with-trl","微调","RLHF","强化学习微调"]
author	Orchestra Research
license	MIT
dependencies	["trl","transformers","datasets","peft","accelerate","torch"]
metadata	{"hermes":{"tags":["Post-Training","TRL","Reinforcement Learning","Fine-Tuning","SFT","DPO","PPO","GRPO","RLHF","Preference Alignment","HuggingFace"]}}
category	mlops

trl-fine-tuning

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction ...