You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I know LLAVA has been converted succesfully to GGML, and also I do see the word Llava coming up in the auto_gptq config, yet at the moment loading it gives a key error:
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Would anyone here know how to convert the image recognition model LLava? It's a combination of llama 1 with some layers of clip.
https://huggingface.co/liuhaotian/llava-v1-0719-336px-lora-vicuna-13b-v1.3
I know LLAVA has been converted succesfully to GGML, and also I do see the word Llava coming up in the auto_gptq config, yet at the moment loading it gives a key error:
KeyError: 'llava'
How to approach this?
Thanks!
Beta Was this translation helpful? Give feedback.
All reactions