# QwenLM/Qwen

The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.

Repository: https://github.com/QwenLM/Qwen
Canonical: https://ross.abutalabs.com/products/qwen
Language: Python
License: Apache-2.0
License Family: permissive
Topics: chinese, large-language-models, natural-language-processing, flash-attention, llm, pretrained-models
Last push: 2026-03-05T13:55:17+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 70, release rhythm 35, longevity 80
- inputs: {"age_days": 1126, "days_push": 181, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21654, forks 1879 (observed 2026-08-28T04:11:31.917151+00:00)

## What it is
The official repository for Qwen (Tongyi Qianwen), Alibaba Cloud's family of pretrained and chat large language models, with weights on Hugging Face and ModelScope and inference/quantization code. It has been superseded by QwenLM/Qwen2 and is no longer actively maintained.

## Use cases
- run the original Qwen chat model locally
- download Qwen pretrained model weights
- quantize Qwen to int4 or int8 for cheaper inference
- fine-tune Qwen-7B on my own data
- use a bilingual Chinese-English LLM
- deploy Qwen with vLLM or FastChat

## When to choose
- you specifically need the original Qwen1 model weights or reproduce its paper results
- you maintain a legacy pipeline already built on Qwen1

## When to avoid
- you want a maintained codebase - use QwenLM/Qwen2 or newer instead
- you need the latest Qwen capabilities or long-context support
- you are starting a new project with no Qwen1 dependency

## Facets
- artifact type: library
- maturity: abandoned
- function: llm-inference, machine-learning, deep-learning
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: qwen, alibaba-cloud, chat-model, pretrained-models, chinese, flash-attention, hugging-face, quantization, superseded, natural-language-processing, gpu, linux

## Member repositories
- QwenLM/Qwen (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.917151+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:50.710431+00:00, confidence not recorded.
  - readme: https://github.com/QwenLM/Qwen (fetched 2026-08-28T04:11:31.917151+00:00, sha 6ab4be95d925)
- Data as of 2026-08-30T08:39:29.467469+00:00.