search

hiyouga / LLaMA-Factory

Unified Efficient Fine-Tuning of 100+ LLMs (ACL 2024)
https://arxiv.org/abs/2403.13372
Apache License 2.0
34.17k stars 4.2k forks source link

请问基于llama2微调自己的模型流程。 #1236

Closed yinjiaoyuan closed 1 year ago

yinjiaoyuan commented 1 year ago

请问基于llama2微调自己的模型流程也是把下面五个步骤都先后做一遍吗？我只是在llama2基础上增加我自己的训练数据微调，不需要全量训练。谢谢。 Pre-Training Supervised Fine-Tuning Reward Modeling PPO Training DPO Training

hiyouga commented 1 year ago

问 ChatGPT