Text Generation
Transformers
PyTorch
English
llava_stablelm_epoch
Multimodal
StableLM
Inference Endpoints

How does this compare to LLama 13b models for "visual smarts"

#2
by clevnumb - opened

I'm just curious if anyone has compared them both yet. Thanks.

well llama 13b doesnt have visual smarts but llava 13b is better then obsidian since its just much bigger. However obsidian is still very good for its size so yeah.

Sign up or log in to comment