search

NVlabs / 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
973 stars 68 forks source link

VILA Context-length #73

Closed oroojlooy closed 3 weeks ago

oroojlooy commented 3 weeks ago

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

yaolug commented 3 weeks ago

4K

oroojlooy commented 3 weeks ago

Thanks!