Instructions to use kkatiz/THAI-BLIP-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kkatiz/THAI-BLIP-2 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="kkatiz/THAI-BLIP-2")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("kkatiz/THAI-BLIP-2") model = AutoModelForMultimodalLM.from_pretrained("kkatiz/THAI-BLIP-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 54311065df79cc9056b76be43103358b0137f327bc811ff55e1a242593a2226e
- Size of remote file:
- 4.76 GB
- SHA256:
- ccd6b9198e46abb01da610621dd54bb45c7c9de2258065e71b4c93b3e61e7e55
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.