Explicitly set lang adapter bias to False

#7
Mistral AI_ org

Thanks for spotting this @ArthurZ

Mistral AI_ org
This comment has been hidden
Mistral AI_ org
vllm serve mistralai/Pixtral-Large-Instruct-2411 --tokenizer_mode mistral --limit_mm_per_prompt 'image=10' --tensor-parallel-size 8 --tool-call-parser mistral --enable-auto-tool-choice --config-format mistral --load-format mistral --revision refs/pr/7
Mistral AI_ org
Mistral AI_ org

This should be fully compatible actually with current vllm version so it can be safely merged.

patrickvonplaten changed pull request status to merged

Sign up or log in to comment