shihy2988
shihy2988
> 我在 7b 中遇到了同样的响应问题。但在我将版本更改`torch`为 2.1.2 和`transformers`4.40.0 后。响应显示正确。 > > ``` > Loaded LLaVA model: lmms-lab/llava-onevision-qwen2-7b-ov > Loading vision tower: google/siglip-so400m-patch14-384 > Model Class: LlavaQwenForCausalLM > ['The image shows a radar...
> I change my `transformers` from `4.40.0.dev` to `0 4.40.0`,but the result is still [''].and I have no idea to slove this. sad... i redownload the project,only trans the torch...
hi, maybe you can refer to the following link:mmdetect or https://github.com/longzw1997/Open-GroundingDino