Image-Text-to-Text
Transformers
Safetensors
English
idefics2
pretraining
multimodal
vision
Inference Endpoints
5 papers

colour and direction detection and ICL

#5
by karambos - opened

idefic2 model works for any specific object color or direction detection and in the code they mention something in-context learning(ICL) something, Is it ICL possible through this model?

HuggingFaceM4 org

Is it ICL possible through this model?
Yes, icl is possible. you can refer to the doc to see how to concantenate multiple images/texts to create your few shot examples

VictorSanh changed discussion status to closed

Sign up or log in to comment