Video-language models that read V-JEPA dynamics (1B-8B, Qwen3 and Llama). Technical report and code: github.com/kkt94/Llama-V-JEPA-LM
-
kkt94/Llama-V-JEPA-LM-Qwen3-1.7B
Video-Text-to-Text • 2B • Updated • 191 • 9 -
kkt94/Llama-V-JEPA-LM-Qwen3-4B
Video-Text-to-Text • 5B • Updated • 186 • 8 -
kkt94/Llama-V-JEPA-LM-Qwen3-8B
Video-Text-to-Text • 9B • Updated • 197 • 10 -
kkt94/Llama-V-JEPA-LM-Llama3.2-1B
Video-Text-to-Text • 2B • Updated • 416 • 9