Image-to-Text
Transformers
PyTorch
Safetensors
English
blip-2
visual-question-answering
vision
image-captioning
8-bit precision
Instructions to use Mediocreatmybest/blip2-opt-6.7b_8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Mediocreatmybest/blip2-opt-6.7b_8bit 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="Mediocreatmybest/blip2-opt-6.7b_8bit")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Mediocreatmybest/blip2-opt-6.7b_8bit") model = AutoModelForMultimodalLM.from_pretrained("Mediocreatmybest/blip2-opt-6.7b_8bit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 5f305b2fd708300752143381346bf4767ff883754d75c4cdc7d0bdf12e37823c
- Size of remote file:
- 9.97 GB
- SHA256:
- b65a82eb4cc9868ba3b1072661ad48639405981ffb8cd705b9e5dfdcc8c833b9
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.