lmms-lab/LLaVA-Video-7B-Qwen2 download history
lmms-lab/LLaVA-Video-7B-Qwen2 is an 8.0B-parameter video text to text model by lmms-lab. In the last 30 days it was downloaded 11,849 times (2,710 in the last 7 days), and 1,362,091 times in total.
It ranks #7,506 on the Hub by monthly downloads and #4 among video text to text models.
It has 127 likes.
It is a fine-tune of lmms-lab/llava-onevision-qwen2-7b-si.
17 models build on LLaVA-Video-7B-Qwen2: 0 quantized, 16 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 12,218 times in the last 30 days. See the LLaVA-Video-7B-Qwen2 galaxy.
Most downloaded derivatives
- MLAdaptiveIntelligence/LLaVAction-7B (finetune), 91 downloads in 30 days
- Eku127/streamvln-satnav-scratch-1ep-f32h8s4-lr2e-5 (finetune), 42 downloads in 30 days
- nkkbr/ViCA (finetune), 38 downloads in 30 days
- TidalYang/SNav-7B (finetune), 33 downloads in 30 days
- nkkbr/ViCA-base (finetune), 21 downloads in 30 days
- nkkbr/ViCA-ARKitScenes (finetune), 20 downloads in 30 days
- nkkbr/ViCA-ScanNet (finetune), 19 downloads in 30 days
- nkkbr/ViCA-thinking (finetune), 17 downloads in 30 days
- Fujitsu/QViC-MF-7B (adapter), 13 downloads in 30 days
- pritamqu/LLaVA-Video-7B-Qwen2-RRPO-16f (finetune), 12 downloads in 30 days
- goxq/q-geomem-llava-qwen2-vsi (finetune), 11 downloads in 30 days
- qgeomem/q-geomem-llava-qwen2-vsi (finetune), 11 downloads in 30 days