Efficient-Large-Model / VILA

VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
Apache License 2.0
878 stars 55 forks source link

What is the LLM used for VILA 1.5 40B? #63

Closed javier-m closed 1 month ago

javier-m commented 1 month ago

I understand that Llama 2 models were used for VILA, but only 7B, 13B and 70B models were released. As for Llama 3, only the 7B and the 70B models were released. However the licence only list the Llama licence, and there is nothing in the model card.

Which LLM was used as a foundation of VILA 40B?

Efficient-Large-Language-Model commented 1 month ago

https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B