kabal1000x

For real, guys! When Ovis2? I have tested every single vision model vLLM supports, and none of them is accurate/reliable. Ovis2 is comparable to GPT 4o-mini. Finally something that we...

I tested the batch inference as well, and did not see any performance improvement. It was approx same duration as sequential inference, if not a little slower. I am using...

Have you tried Ovis2-8B? To me, it seems better than 16B. Very similar responses and accuracy, but I prefer 8B because I feel like 16B tends to hallucinate a bit....