gaoqie/DeepSeekVL-1.3B-Chat-fire
Visual Question Answering • 2B • Updated • 123
Flash-Cascade
Using Multimodal Large Language Models (MLLMs) for false alarm reduction in image-based fire detection.Doi:https://doi.org/10.21203/rs.3.rs-8847038/v1
-
-
gaoqie/Qwen2VL-2B-Instruct-fire
Visual Question Answering • 2B • Updated • 50 -
gaoqie/DeepSeekVL2-Tiny-fire
Visual Question Answering • 3B • Updated • 46 -
gaoqie/Qwen2.5VL-3B-Instruct-fire
Visual Question Answering • 4B • Updated • 42 • 1 -
gaoqie/Glm-Edge-V-5B-fire
Visual Question Answering • 5B • Updated • 36 -
gaoqie/Qwen2.5VL-7B-Instruct-fire
Visual Question Answering • 8B • Updated • 55 • 1 -
gaoqie/DeepSeekVL-7B-Chat-fire
Visual Question Answering • 7B • Updated • 41 -
gaoqie/InternVl2-8B-fire
Visual Question Answering • 8B • Updated • 37 -
gaoqie/qwen2-vl-7b-instruct-fire
Visual Question Answering • 8B • Updated • 38 -
gaoqie/Fire-CoT
Updated • 9