Ram20307/qwen3vl-2b-ag-lora
Image-Text-to-Text • Updated • 31
sanjaya
Qwen3-VL-2B fine-tuned on Action Genome to describe a person's relations to nearby objects (LoRA adapter and merged model).
-
-
Ram20307/qwen3vl-2b-ag-merged
Image-Text-to-Text • 2B • Updated • 50 -
Ram20307/qwen3vl-2b-ag-GGUF
Image-Text-to-Text • 2B • Updated • 111 -
Ram20307/qwen3vl-2b-ag-hico-lora
Image-Text-to-Text • Updated • 22 -
Ram20307/qwen3vl-2b-hico-lora
Image-Text-to-Text • Updated • 26 • 1 -
Ram20307/qwen3vl-2b-ag-hico-merged
Image-Text-to-Text • 2B • Updated • 41 -
Ram20307/qwen3vl-2b-ag-hico-GGUF
Image-Text-to-Text • 2B • Updated • 109 -
Ram20307/qwen3vl-2b-hico-merged
Image-Text-to-Text • 2B • Updated • 38 -
Ram20307/qwen3vl-2b-hico-GGUF
Image-Text-to-Text • 2B • Updated • 109 -
Ram20307/qwen3-vl-2b-action-genome-scene-graph-lora
Updated • 13 -
Ram20307/qwen3-vl-2b-action-genome-scene-graph
Image-Text-to-Text • 2B • Updated • 21 -
Ram20307/qwen3-vl-2b-action-genome-scene-graph-GGUF
2B • Updated • 70