unsloth

/

llava-v1.6-mistral-7b-hf-bnb-4bit

like 5

Follow

Unsloth AI 3.18k

Adds num_additional_image_tokens so that the model can run with the latest transformers version. Same modification as in https://huggingface.co/unsloth/llava-1.5-7b-hf-bnb-4bit/discussions/1.
Some context for this change can be read in https://github.com/huggingface/transformers/pull/35779