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
2.04k stars 164 forks source link

Issue: The size of tensor a (2) must match the size of tensor b (8) at non-singleton dimension 0 #151

Open apfsds3bm9 opened 1 week ago

apfsds3bm9 commented 1 week ago

image

apfsds3bm9 commented 1 week ago

image The error occurs when I add the line of code --conv-mode llama_3.