InternLM / InternLM/Tutorial

微调训练后,直接提问数据集问题,没有得到预期回答

Open
#377 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
2k
Forks
1.5k
PR merge metrics
No merged PRs in 30d

Description

按文档训练后,直接提问数据集问题,没有得到预期回答

![WechatIMG299](https://github.com/InternLM/tutorial/assets/20661962/c316461c-3b7d-4f0b-a322-87008431b773)
![WechatIMG300](https://github.com/InternLM/tutorial/assets/20661962/b36fc12b-8842-437b-a2e9-f9bc8458bdad)
![WechatIMG301](https://github.com/InternLM/tutorial/assets/20661962/c5d1a6f7-cc35-4b6a-81e1-8e547a89cb8b)
![WechatIMG307](https://github.com/InternLM/tutorial/assets/20661962/aef26a98-e414-4444-81ce-ef359e479829)
![WechatIMG309](https://github.com/InternLM/tutorial/assets/20661962/d4edcbbe-769e-4774-b99f-7c8081e059c1)
之前训练还加了参数deepspeed,也是一样对话结果,还以为是使用了这个参数影响,后面重新来了一遍跟文档一样的配置操作,仅仅区别只做了一轮训练

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.