metadata
language:
- en
library_name: transformers
This is the LLaVa model in Huggingface format which was derived from actuaryzhang/product-taxonomy-llava-v1.6-13b
A modified version of the https://github.com/huggingface/transformers/blob/0f67ba1d741d65b07d549daf4ee157609ce4f9c1/src/transformers/models/llava/convert_llava_weights_to_hf.py#L1 for the OSS to Huggingface format was used to create this model.
Note that though this model is marked as v1.6 (LLaVa-NeXT), it doesn't completely inherit the improvements on of LLaVa-NeXT. In particular, it does not leverage LLaVa-NeXT's improvements on image processing, and the image_newline tensor is missing