cmp-nct's picture
Update README.md
7f6b800
|
raw
history blame
238 Bytes
metadata
license: llama2

The original model is here: https://huggingface.co/Lin-Chen/ShareGPT4V-7B
This is the K-type quantized variant (for inference with llama.cpp llava-cli)

In my tests this is currently the best open vision model