qwen vl

We have hosted the application qwen vl in order to run this application in our online workstations with Wine or directly.

Quick description about qwen vl:

Qwen-VL is Alibaba Cloud’s vision-language large model family, designed to integrate visual and linguistic modalities. It accepts image inputs (with optional bounding boxes) and text, and produces text (and sometimes bounding boxes) as output. The model variants (VL-Plus, VL-Max, etc.) have been upgraded for better visual reasoning, text recognition from images, fine-grained understanding, and support for high image resolutions / extreme aspect ratios. Qwen-VL supports multilingual inputs and conversation (e.g. Chinese, English), and is aimed at tasks like image captioning, question answering on images (VQA, DocVQA), grounding (detecting objects or regions from textual queries), etc.

Features:

• Strong performance on many vision-language tasks: image captioning, VQA, DocVQA, grounding, text recognition in images etc.
• Very high resolution image input support (up to millions of pixels), and handling extreme aspect ratios for detailed visual content
• Multilingual: supports Chinese, English, and other languages in image text / conversation tasks
• Variants (VL-Plus, VL-Max) offer increasing capability: VL-Max is more capable in instruction following, visual reasoning, better model of cognition etc.
• Fine-tuning and quantization options (e.g. Int4 modes, Q-LoRA) for lower resource usage
• Supports multi-image interleaved conversations: comparing multiple images, storytelling, multi-image inputs in dialogues

Programming Language: Python.
Categories: