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

VILA Context-length #73

Closed oroojlooy closed 1 week ago

oroojlooy commented 2 weeks ago

Question Is there any table/page with the context-len of each model?

yaolug commented 1 week ago

4K

oroojlooy commented 1 week ago

Thanks!