Fdioa comments

Repositories
Issues
Comments

Results 1 comments of


                                            Fdioa

Is there a way to turn off Qwen3 32B thinking mode and add a thinking budget?

> tokenizer_config.json -> chat_template -> {%- if enable_thinking is not defined or enable_thinking is false %} Will this method work when using vllm_sync for rollout? I couldn't find any implementation...