Changing Summary Model

[1112321sfdsaf]

Hi, great work!

I’ve been following your project and have a question about the implementation. In your pipeline, an open-source model (“Qwen3-VL-30B-A3B-Instruct”) is used for summarization and as the judge. Would it be feasible to replace it with a GPT model? If so, are there any potential impacts or caveats I should be aware of?

Thanks in advance for your reply.

[Osilly]

Thank you for your interest! You can simply modify the POST request for the summary model in the tool, for example here. Please refer to the OpenAI POST request format and make the corresponding changes. We believe this should be easy to do.