hzhang57 comments

Repositories
Issues
Comments

Results 3 comments of


                                            hzhang57

Pre-trained weights?

Hi, I trained a model with the provided codes on ImageNet-1k only with 4x2080ti (batch100), finally reach 82.0 around. I upload this temporal alternative in google drive to facilate other's...

Pre-trained weights?

yes, I trained the visformer small with 224: visformer_small

Does the GRPO Trainer support multi-image input for Qwen3-VL?

I tried Qwen3-VL-4B-Instruct. it can be GRPO tuned with vllm version 0.11.2