Image-to-Text
Transformers
PyTorch
English
blip-2
text-generation
vision
video-to-text
image-captioning
video-captioning
visual-question-answering
Instructions to use kpyu/video-blip-opt-2.7b-ego4d with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kpyu/video-blip-opt-2.7b-ego4d 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="kpyu/video-blip-opt-2.7b-ego4d")# Load model directly from transformers import AutoProcessor, AutoModelForSeq2SeqLM processor = AutoProcessor.from_pretrained("kpyu/video-blip-opt-2.7b-ego4d") model = AutoModelForSeq2SeqLM.from_pretrained("kpyu/video-blip-opt-2.7b-ego4d") - Notebooks
- Google Colab
- Kaggle
Ctrl+K