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

Use in pipelines?

#40
by harpreetsahota - opened

Hi all!

The model card says one can use in a pipeline, like so:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="HuggingFaceM4/idefics2-8b")

But image-text-to-text is not a valid task for pipeline.

image-to-text is valid and downloads

Sign up or log in to comment