minicpm-v

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

vision 8b

42K Pulls Updated 3 days ago

17 Tags

c92bfad01205 • 5.5GB • 3 days ago

c92bfad01205 • 5.5GB • 3 days ago

f3f122c78635 • 16GB • 3 days ago

61cf7cf5edda • 4.1GB • 3 days ago

a62e8056b1f0 • 5.1GB • 3 days ago

b7c14f8aad8c • 4.9GB • 3 days ago

0e5dd84b9d34 • 4.5GB • 3 days ago

c92bfad01205 • 5.5GB • 3 days ago

1e17cbffa666 • 5.9GB • 3 days ago

950a671abea6 • 5.7GB • 3 days ago

eda89b106de0 • 5.5GB • 3 days ago

4b28c460b85e • 6.4GB • 3 days ago

6ac2a6038e89 • 6.8GB • 3 days ago

6dfa70b0f281 • 6.5GB • 3 days ago

b4d3d0c08b9c • 6.4GB • 3 days ago

ac20b8a12390 • 7.3GB • 3 days ago

9e2efdd7b657 • 9.1GB • 3 days ago