bczhou/TinyLLaVA-3.1B
Text Generation • 3B • Updated • 228 • 27
TinyLLaVA
TinyLLaVA: A Framework of Small-scale Large Multimodal Models
-
-
bczhou/TinyLLaVA-2.0B
Image-Text-to-Text • 2B • Updated • 79 • 6 -
bczhou/TinyLLaVA-1.5B
Image-Text-to-Text • 2B • Updated • 47 • 19 -
bczhou/tiny-llava-v1-hf
Image-Text-to-Text • 1B • Updated • 1.5k • 57 -
bczhou/TinyLLaVA-3.1B-SigLIP
0.4B • Updated • 182 • 4 -
bczhou/TinyLLaVA-1.5B-SigLIP
0.4B • Updated • 48 • 1 -
bczhou/TinyLLaVA-2.0B-SigLIP
0.4B • Updated • 69 • 1