BAAI
/

BGE-VL-MLLM-S2

multimodal-retrieval

embedding-model

Model card Files Files and versions Community

Resources

View closed (0)

Can task instruction be changed? And tokenizer bug? what's the difference between q and c embedding?

#3 opened 27 days ago by

Expanding inputs for image tokens in LLaVa-NeXT should be done in processing. Please add `patch_size` and `vision_feature_select_strategy` to the model's processing config

#2 opened about 1 month ago by

可惜没有中文

#1 opened about 1 month ago by