google-research-datasets/conceptual_captions
Viewer • Updated • 5.34M • 15.3k • 106
How to use dhansmair/flamingo-tiny with Transformers:
# Use a pipeline as a high-level helper
# Warning: Pipeline type "image-to-text" is no longer supported in transformers v5.
# You must load the model directly (see below) or downgrade to v4.x with:
# 'pip install "transformers<5.0.0'
from transformers import pipeline
pipe = pipeline("image-to-text", model="dhansmair/flamingo-tiny") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("dhansmair/flamingo-tiny", dtype="auto")Flamingo Model (tiny version) pretrained on Image Captioning on the Conceptual Captions (3M) dataset.
Source Code: https://github.com/dhansmair/flamingo-mini
Demo Space: https://huggingface.co/spaces/dhansmair/flamingo-tiny-cap
Flamingo-mini: https://huggingface.co/spaces/dhansmair/flamingo-mini-cap