Official Tempo-6B collection: A query-aware framework solving the mismatch between massive video streams and bounded LLM context windows.
visioncairgroup
Vision-CAIR
AI & ML interests
None yet
Recent Activity
liked a Space about 9 hours ago
Vision-CAIR/Tempo updated a model about 11 hours ago
Vision-CAIR/Tempo-6B new activity about 11 hours ago
Vision-CAIR/Tempo-6B:Improve model card with detailed architecture, installation and inference instructionsOrganizations
spaces 6
Running on Zero
3
Tempo
🏃
Smart Compressors for Long Video Understanding
Runtime error
Featured
886
MiniGPT-4
🚀
Runtime error
113
MiniGPT-v2
🚀
Running on Zero
88
LongVU
🌖
Generate responses to video or image inputs
Configuration error
1
MiniGPT-Med
🚀
Configuration error
46
MiniGPT4 Video
🎞
Answer questions about videos using text
models 17
Vision-CAIR/Tempo-6B
Video-Text-to-Text • Updated • 74
Vision-CAIR/BFPO-Mistral-7b-v0.1
Text Generation • 7B • Updated • 10 • 1
Vision-CAIR/LongVU_Llama3_2_1B
Video-Text-to-Text • Updated • 29 • 12
Vision-CAIR/LongVU_Llama3_2_3B_img
Updated • 2 • 6
Vision-CAIR/LongVU_Qwen2_7B_img
Updated • 6 • 5
Vision-CAIR/LongVU_Llama3_2_3B
Video-Text-to-Text • Updated • 24 • 8
Vision-CAIR/LongVU_Qwen2_7B
Video-Text-to-Text • 8B • Updated • 176 • 76
Vision-CAIR/BFPO-redteaming-Zephyr-7b-beta
Text Generation • 7B • Updated • 1
Vision-CAIR/LongVU_Llama3_2_1B_img
Updated
Vision-CAIR/llama_3_2_output
Updated • 5