Avalon comments

Repositories
Issues
Comments

Results 2 comments of


                                            Avalon

[Question] The results of the local model are inconsistent with the web ui in the demo

I suffered the issue here. The web demo version ran this "llava-v1.6-34b" version of llava. Given the "34b-v1.6" version of model in Ollama, the results of queries into these two...

Support for structured output like OpenAI's response format or tools from Claude

Even if I can cache it, the inference time will still be increased given the necessary example prompt, right?