Instructions to use unalignment/Pixtral-12B-Captioner-Relaxed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use unalignment/Pixtral-12B-Captioner-Relaxed 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="unalignment/Pixtral-12B-Captioner-Relaxed")# Load model directly from transformers import AutoProcessor, AutoModelForImageTextToText processor = AutoProcessor.from_pretrained("unalignment/Pixtral-12B-Captioner-Relaxed") model = AutoModelForImageTextToText.from_pretrained("unalignment/Pixtral-12B-Captioner-Relaxed") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7184af1f78ddc57de40b9afa54fbc23622d3a8b6e6ef4da606681f3ac041f8a4
- Size of remote file:
- 17.1 MB
- SHA256:
- fcdf3e6b96371b9a5c8673bdf2f1bc838b994b73a6fa995dca62196346aaddb5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.