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
879 stars 55 forks source link

How's the DownSampleBlock performance compare with CAbstractor? #55

Open lucasjinreal opened 1 month ago

lucasjinreal commented 1 month ago

How's the DownSampleBlock performance compare with CAbstractor?

Efficient-Large-Language-Model commented 1 month ago

Could you give a reference to CAbstractor

lucasjinreal commented 1 month ago

Oh, it's HoneybeeChat

Efficient-Large-Language-Model commented 1 month ago

Could you send a link?