Rui Zhong
Results
2
comments of
Rui Zhong
Add `model.config.use_cache = False` before pruner. The same problem [here](https://github.com/horseee/LLM-Pruner/issues/93) and [here](https://github.com/VainF/Torch-Pruning/issues/461)
> Right, so this one is a bit of a rabbit hole... > > I. Reverting the Qwen2.5 config files to: > > ` "processor_class": "Qwen2VLProcessor"` > > and >...