Instructions to use Maverick17/idefics3-llama-gui-dense-descriptions with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Maverick17/idefics3-llama-gui-dense-descriptions with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Using truncation in idefics3 processor
#1
by jainarchit76 - opened
Is it possible to use truncation with processor(text=texts, images=images, return_tensors="pt", padding=True, truncation=True, max_length=512).
When using max_length of 512, it raises an error:
RuntimeError: shape mismatch: value tensor of shape [2197, 4096] cannot be broadcast to indexing result of shape [485, 4096]
So? What is the point of actually using the max_length truncation parameter?
jainarchit76 changed discussion status to closed