Qwen-VL
QwenLM/Qwen-VL
Qwen-VL is a large vision-language model from Alibaba Cloud with various versions optimized for different applications.
Overview
Repository for Qwen-VL (通义千问-VL), a large vision-language model developed by Alibaba Cloud. It includes multiple versions like Qwen-VL-Plus and Qwen-VL-Max, each offering enhanced capabilities in visual language understanding. Available via Hugging Face, ModelScope, Web interfaces, mobile apps, APIs, Discord, and a research paper.
Categories
Tags
Similar tools
ollama
ollama/ollama
Local inference runtime and CLI for open-weight large language models
transformers
huggingface/transformers
huggingface/transformers
JavaGuide
Snailclimb/JavaGuide
Java guide for backend interviews & AI application development covering system design, LLMs, Agents, and RAG.
langflow
langflow-ai/langflow
Metadata derived from provided repository information.
langchain
langchain-ai/langchain
The agent engineering platform.
LLMs-from-scratch
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch
Install
pip install Qwen-VLREADME
中文 ｜ English ｜ 日本語 ｜ 한국어
Qwen-VL
🤗
🤖 ｜
Qwen-VL-Chat
🤗
🤖
(Int4:
🤗
🤖 ) ｜
Qwen-VL-Plus
🤗
🤖 ｜
Qwen-VL-Max
🤗
🤖
Web |
APP |
API |
WeChat |
Discord |
Paper |
Tutorial
Qwen-VL-Plus & Qwen-VL-Max
Qwen-Vl-Plus and Qwen-VL-Max are the upgraded and latest versions of the Qwen-VL model family, currently supporting access for free through 🤗, 🤖, Web pages, APP and APIs.
| Model name | Model description |
|---|---|
| Qwen-VL-Plus | Qwen's Enhanced Large Visual Language Model. Significantly upgraded for detailed recognition capabilities and text recognition abilities, supporting ultra-high pixel resolutions up to millions of pixels and extreme aspect ratios for image input. It delivers significant performance across a broad range of visual tasks. |
| Qwen-VL-Max | Qwen's Most Capable Large Visual Language Model. Compared to the enhanced version, further improvements have been made to visual reasoning and instruction-following capabilities, offering a higher level of visual perception and cognitive understanding. It delivers optimal performance on an even broader range of complex tasks. |
The key technical advancements in these versions include:
- Substantially boost in image-related reasoning capabilities;
- Considerable enhancement in recognizing, extracting, and analyzing details of images, especially for text-oriented tasks;
- Support for high-definition images with resolutions above one million pixels and extreme aspect ratios;
These two models not only significantly surpass all previous best results from open-source LVLM models, but also perform on par with Gemini Ultra and GPT-4V in multiple text-image multimodal tasks.
Notably, Qwen-VL-Max outperforms both GPT-4V from OpenAI and Gemini from Google in tasks on Chinese question answering and Chinese text comprehension. This breakthrough underscores the model’s advanced capabilities and its potential to set new standards in the field of multimodal AI research and application.
| Model | DocVQA | ChartQA | AI2D | TextVQA |
|---|