Qwen Vision-Language Models

6 repos

Fine-tuned and specialized variants of Qwen2.5-VL and related vision-language models, optimized for multimodal reasoning tasks. The cluster centers on model implementations using PyTorch and safetensors format, with particular focus on reasoning-enhanced architectures (like LLaVA-Critic variants) and task-specific adaptations. These repositories represent the ecosystem around deploying and customizing open-source vision-language models for computer vision and reasoning applications.

Related clusters