minicpm-v

A series of multimodal LLMs (MLLMs) designed for vision-language understanding.

Vision 7B

12.2K Pulls Updated 9 days ago

17 Tags

1862d7d5fee5 • 5.5GB • Updated 9 days ago

latest

1862d7d5fee5 • 5.5GB • Updated 9 days ago

fc17efece003 • 16GB • Updated 9 days ago

f7c948f4e191 • 4.1GB • Updated 9 days ago

51f5ec69cd3e • 4.5GB • Updated 9 days ago

e0e987b0879d • 4.9GB • Updated 9 days ago

6cb4e4f13e67 • 5.1GB • Updated 9 days ago

1862d7d5fee5 • 5.5GB • Updated 9 days ago

2bae48df3302 • 5.9GB • Updated 9 days ago

e00472e4cde9 • 5.5GB • Updated 9 days ago

620f0e7c1641 • 5.7GB • Updated 9 days ago

4e957cb7ad06 • 6.4GB • Updated 9 days ago

0e0425984b12 • 6.8GB • Updated 9 days ago

5948b495378d • 6.4GB • Updated 9 days ago

04ffe07a994a • 6.5GB • Updated 9 days ago

4f12fa84e598 • 7.3GB • Updated 9 days ago

50e40737b5af • 9.1GB • Updated 9 days ago