Add Blip2 model in VQA pipeline (#25532)

Commit

2 years ago

Add Blip2 model in VQA pipeline (#25532) * Add Blip2 model in VQA pipeline * use require_torch_gpu for test_large_model_pt_blip2 * use can_generate in vqa pipeline * test Blip2ForConditionalGeneration using float16 * remove custom can_generate from Blip2ForConditionalGeneration

References

#62 - Add initial DEIMv2 model implementation

#58 - Add EoMT DINOv3 model

#59 - Fix attention mask handling in EoMT-DINOv3 converter

#27720 - Add common processor tests

#32831 - [Docs] Update resources

#29969 - [SigLIP] Add fast tokenizer

#41212 - Add EoMT with DINOv3 backbone

#39821 - Support MetaCLIP 2

#33111 - [Backbone] Remove out_features everywhere

#33174 - [Zero-shot image classification pipeline] Remove tokenizer_kwargs

#25532 - Add Blip2 model in VQA pipeline

Author

jpizarrom

Parents

62399d6f

transformers 09dc9951 - Add Blip2 model in VQA pipeline (#25532)

transformers
09dc9951 - Add Blip2 model in VQA pipeline (#25532)