EngineX-Hygon/sglang
5
0
Fork 0
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity

[Model] Support Qwen2ForSequenceClassification (#4609)

Browse Source 
Co-authored-by: ximing.wxm <ximing.wxm@antgroup.com>
This commit is contained in:
Ximingwang-09
2025-03-25 10:13:44 +08:00
committed by GitHub
parent 4c584fc632
commit 22c3702e1e
4 changed files with 87 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/references/supported_models.md
View File

@@ -54,6 +54,8 @@
- `python -m sglang.launch_server --model-path internlm/internlm2-7b-reward --is-embedding --trust-remote-code`
- Qwen2ForRewardModel
- `python -m sglang.launch_server --model-path Qwen/Qwen2.5-Math-RM-72B --is-embedding --trust-remote-code --tp-size=4`
- Qwen2ForSequenceClassification
- `python -m sglang.launch_server --model-path jason9693/Qwen2.5-1.5B-apeach --is-embedding --trust-remote-code`
## How to Support a New Language Model
To support a new model in SGLang, you only need to add a single file under [SGLang Models Directory](https://github.com/sgl-project/sglang/tree/main/python/sglang/srt/models).