tsinghua-ee/video-SALMONN-2_plus_72B
Updated • 27 • 2
video-SALMONN 2
video-SALMONN 2 is a powerful audio-visual large language model (LLM) that generates high-quality audio-visual video captions.
-
-
tsinghua-ee/video_SALMONN2plus_72B_audioAlign
Updated • 71 -
tsinghua-ee/video-SALMONN2_plus_7B_full
9B • Updated • 431 -
tsinghua-ee/video-SALMONN-2_plus_7B
Updated • 669 • 6 -
tsinghua-ee/video_SALMONN2plus_7B_audioAlign
9B • Updated • 136 -
tsinghua-ee/video-SALMONN2_plus_3B_full
5B • Updated • 299 -
tsinghua-ee/video-SALMONN-2_plus_3B
Updated • 458 • 3 -
tsinghua-ee/video_SALMONN2plus_3B_audioAlign
5B • Updated • 5 -
tsinghua-ee/video-SALMONN-2
Video-Text-to-Text • 9B • Updated • 67 • 3 -
tsinghua-ee/video_SALMONN2_7B_audioAlign
Updated • 2 -
tsinghua-ee/video-SALMONN_2_testset
Preview • Updated • 293