InternLM / InternLM/lmdeploy

[Bug] MLP.inter_size (Qwen-14B-Chat) read from config not Applicable.

Open
#3,054 0 comments 0 reactions 1 assignee Claimed by @lvhan028 View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

Description

### Checklist

- [x] 1. I have searched related issues but cannot get the expected help.
- [x] 2. The bug has not been fixed in the latest version.
- [ ] 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.

### Describe the bug

1.The current inter_size is read from the config. json file.
2.Qwen-14B-Chat config.intermediate_size = 27392,https://www.modelscope.cn/models/Qwen/Qwen-14B-Chat/file/view/master?fileName=config.json&status=1
3.but,real intermediate_size is 13696.

![Image](https://github.com/user-attachments/assets/6ffd9334-8cec-4c27-878e-bc0d0005c181)

### Reproduction

None

### Environment

```Shell
None
```

### Error traceback

```Shell
None
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.