How did you get this?
#1
by
lastrosade
- opened
Using the normal llava surgery method doesn't work for me, and I'd like to get better quants.
The failure comes when running convert-image-encoder-to-gguf.py
v_hparams = config["vision_config"]
KeyError: 'vision_config'
I can't figure out how you did it from the PR alone
Yes me too. I would like a 6_k with an importance matrix.