About Qwen
Alibaba Cloud provides Tongyi Qianwen (Qwen) model series to the open-source community, including Qwen, the large language model (LLM), Qwen-VL, the large language vision model, and Qwen-Audio, the large language audio model. Qwen models are pre-trained on multilingual data covering various industries and domains, with Qwen-72B being trained on an astounding 3 trillion tokens of data. These models offer a wide range of capabilities, including multimodal understanding and generation, state-of-the-art image processing, and fully managed APIs to support your innovation in generative AI.
Qwen has been upgraded to version 1.5 (the Beta version of Qwen 2). Qwen 1.5 includes 6 model sizes: 0.5B, 1.8B, 4B, 7B, and 72B, all of which support the context length of 32768 tokens, with significant quality improvements and enhanced multilingual capabilities. A comprehensive evaluation was conducted to test Qwen 1.5's performance in language understanding, coding, reasoning, multilingual capabilities, human preference, agent, retrieval-augmented generation (RAG), etc. See more details in this article.
-
Leading Performance in Multiple Dimensions
Qwen outperforms other open-source baseline models of similar sizes on a series of benchmark datasets that evaluate natural language understanding, mathematical problem-solving, coding, etc.
-
Easy and Low-Cost Customization
You can deploy Qwen models with a few clicks in PAI-EAS, and fine-tune them with your data stored on Alibaba Cloud, or external sources, to perform industry or enterprise-specific tasks.
-
Applications for Generative AI Era
You can leverage Qwen APIs to build generative AI applications for a broad range of scenarios such as writing, image generation, audio analysis, etc. to improve work efficiency in your organization and transform customer experience.
Qwen Model Family
Qwen models have been pre-trained with data from a wide range of domains and languages, supporting the context length of 32768 tokens. These models can create content, summarize and translate text, write and interpret code, solve math problems, use tools, and act as agents.
Learn More on GitHub >
Qwen-VL is the large vision language model of the Qwen series. It generates content based on images, text, and bounding boxes as input. With leading performance verified by multiple evaluation benchmarks, Qwen-VL can perform fine-grained text recognition in both Chinese and English, compare and analyze these images, then create stories, solve math problems, or answer questions.
Learn More on GitHub >
Qwen-Audio is the large audio language model of the Qwen series. Qwen-Audio accepts text and diverse audio files (human speech, natural sound, music, and songs) as inputs, and provides text-based output. Qwen-Audio achieves impressive performance without any task-specific fine-tuning on the test set of Aishell1, cochlscene, ClothoAQA, and VocalSound.
Learn More on GitHub >
Qwen Success Stories
Chatbot based on Qwen, Qwen-Audio, and Qwen-VL answering questions containing multimodal data
Use Tools
Qwen-Agent helps you summarize content, and integrates Code Interpreter to read code and process data. It can provide results of analysis in rich text, graphs, and code.
Qwen-Agent analyzing data and providing visualized results
Generate Images
Based on text prompts and input images, Qwen-VL can produce high-quality images in various styles and genres for different industry-specific scenarios.
Qwen-VL producing a cartoon-style human portrait based on prompts
Analyze Images
Qwen-VL learns and analyzes objects and texts in images, and creates new content based on its learning.
Qwen-VL recognizing the objects (the woman and the dog) in the image and their gestures (high five)
Understand and Analyze Audio
Qwen-Audio can accept diverse types of audio (such as human speech, natural sounds, instrumental music, and songs) and text as inputs, understand the audio content, and summarize information such as music genres and emotions of the speaker. It can also use tools to edit the audio files.
Qwen-Audio analyzing the identity and emotions of the speaker and recommending replies
Qwen-Agent: Developing AI Agents and Applications in Simple Steps
Qwen-Agent is a framework for developing LLM applications based on the instruction following, tool usage, planning, and memory capabilities of Qwen models. It provides various components for LLMs, prompts, and agents. Follow this tutorial and learn to use the Assistant component to add customized tools and quickly develop an agent that uses these tools.
Download Qwen models and try Qwen demos on Hugging Face.
Qwen on Hugging Face >
Download Qwen models and try Qwen demos on ModelScope.
Qwen on ModelScope >
Download Qwen models and read tutorials on GitHub.
Qwen on GitHub >
