LongVILA - a Efficient-Large-Model Collection

Efficient-Large-Model 's Collections

VILA: On Pre-training for Visual Language Models

VILA-1.5-checkpoints-intermediate

LongVILA

updated Aug 21

A series of VILA models that specialize for **long-context** abilities

Efficient-Large-Model/Llama-3-LongVILA-8B-128Frames

Text Generation • Updated Aug 26 • 3.07k • 6
Efficient-Large-Model/Llama-3-LongVILA-8B-256Frames

Text Generation • Updated Aug 20 • 563 • 1
Efficient-Large-Model/Llama-3-LongVILA-8B-512Frames

Text Generation • Updated Aug 20 • 30 • 2
Efficient-Large-Model/Llama-3-LongVILA-8B-1024Frames

Text Generation • Updated Aug 21 • 83