Any-to-Any
Transformers
Safetensors
English
mathematics
reasoning
multi-modal
image-text-interleave
visual-chain-of-thought
vcot
mathcanvas
Instructions to use shiwk24/BAGEL-Canvas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use shiwk24/BAGEL-Canvas with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("shiwk24/BAGEL-Canvas", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Add pipeline_tag and library_name to model card
#1
by nielsr HF Staff - opened
This PR updates the model card to include the pipeline_tag: any-to-any, reflecting its multimodal reasoning capabilities involving both text and visual outputs. It also adds library_name: transformers as the model's configuration files (e.g., Qwen2 and Siglip components) suggest compatibility with the π€ Transformers library, enabling the automated "how to use" widget on the Hub.
shiwk24 changed pull request status to merged