TinyLLaVA: A Framework of Small-scale Large Multimodal Models
Baichuan Zhou
bczhou
AI & ML interests
Computer Vision
Organizations
Collections
1
Papers
1
spaces
1
models
8
bczhou/tiny-llava-v1-hf
Updated
•
3.23k
•
42
bczhou/TinyLLaVA-3.1B-Pretrain
Text Generation
•
Updated
•
2
bczhou/TinyLLaVA-1.5B
Image-Text-to-Text
•
Updated
•
4.48k
•
6
bczhou/TinyLLaVA-2.0B
Image-Text-to-Text
•
Updated
•
995
•
5
bczhou/TinyLLaVA-3.1B
Text Generation
•
Updated
•
6.61k
•
21
bczhou/TinyLLaVA-2.0B-SigLIP
Updated
•
64.2k
bczhou/TinyLLaVA-1.5B-SigLIP
Updated
•
4.85k
bczhou/TinyLLaVA-3.1B-SigLIP
Updated
•
36.8k
•
3
datasets
None public yet