Replies: 3 comments 3 replies
-
我也是第二条遇到了问题,如果采用python inference.py |
Beta Was this translation helpful? Give feedback.
0 replies
-
大佬,请问这个问题你解决了? |
Beta Was this translation helpful? Give feedback.
3 replies
-
move to #253 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
第一:为什么训练出来的模型是问答式的,是因为数据量太少吗,格式和官方给的测试数据集格式一样都是类型#描述类型#描述,训练使用的是./scripts/finetune_pt.sh 参数只改了sourse和target还有step三个数值。
第二:为什么训练完的模型,使用“cd ../composite_demo
MODEL_PATH="THUDM/chatglm3-6b" PT_PATH="path to p-tuning checkpoint" streamlit run main.py”启动UI界面,使用API启动,最终运行的还是原来的chatglm3-6b,不是微调后的模型
第三:数据集的格式“类型#描述类型#描述”,后面只描述一个或多个描述词或者类型词,可以得到回复吗,是经过ChatGLM3-6B思考后的回复还是数据集的内容完全一模一样的回复还是会参考数据集答案的格式来回复。。。。
Beta Was this translation helpful? Give feedback.
All reactions