Qwen is an official open-source release of large language models providing pretrained chat models for conversational and general natural language processing tasks. It is available in multiple sizes and quantized versions for accessible deployment.
Project overview
Qwen offers multiple model sizes and quantized versions as an official open-source release, making pretrained chat large language models accessible for deployment across varying hardware configurations.
Project type
Model Runtime
Use cases
Chat Assistants
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers, AI engineers, and researchers seeking an official open-source pretrained chat large language model available in multiple sizes and quantized versions
Key capabilities
Provides pretrained chat large language models in various sizes for conversational and general NLP tasks.
Limitations and risks
This repository is no longer actively maintained due to substantial codebase differences and has been succeeded by Qwen2.
Getting started
Setup instructions are not included in the provided source text; the difficulty of initial setup is unclear.
Evidence and sources
GitHub project description
README: > This repo ([QwenLM/Qwen](https://github.com/QwenLM/Qwen)) is no longer actively maintained, due to substantial codebase differences.