运行run.sh训练后，加载新的模型，对话异常
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 12.3k
- Forks
- 1.1k
- PR merge metrics
- No merged PRs in 30d
Description
1.运行run.sh，生成moss-moon-003-sft-int4下面的文件，包含：
- 1
- latest
- zero_to_fp32.py
2.运行zero_to_fp32.py 生成新文件到output_file路径下面（新模型）
3.加载新模型demo，正常。
4.对话输出，任何问题的答案都变成了感叹号，：
“!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!”
这是什么原因，有哪位大佬帮助解决一下，谢谢。
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the sequence using run.sh, zero_to_fp32.py, the output_file checkpoint, and the demo described in the report. First inspect whether the converted model is loaded correctly, then compare its generated output with the original model. Done means the new model produces normal conversational responses instead of repeated exclamation marks.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, shell
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100