# wenge-research/YAYI

雅意大模型：为客户打造安全可靠的专属大模型，基于大规模中英文多领域指令数据训练的 LlaMA 2 & BLOOM 系列模型，由中科闻歌算法团队研发。(Repo for YaYi Chinese LLMs based on LlaMA2 & BLOOM)

Repository: https://github.com/wenge-research/YAYI
Canonical: https://ross.abutalabs.com/products/yayi
Homepage: https://www.wenge.com/yayi/index.html
Language: Python
License: Apache-2.0
License Family: permissive
Topics: bloom, chinese, llama, llama2, llm, yayi, chat, lora
Archived: true
Last push: 2024-01-17T07:37:16+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 85
- inputs: {"age_days": 1197, "days_push": 959, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2527, forks 45 (observed 2026-08-28T04:06:58.629886+00:00)

## What it is
YAYI is a family of open-source Chinese-optimized large language models (7B/13B) instruction-tuned from LLaMA 2 and BLOOM base models by Wenge Technology. The repo provides inference code, prompt formatting, and links to Hugging Face model weights for multi-domain Chinese NLP tasks.

## Use cases
- run a chinese chat llm locally
- deploy a chinese instruction-tuned llama2 model
- fine-tune or use a chinese domain llm for finance or public safety tasks
- chat with a bilingual chinese-english assistant model
- download yayi 7b 13b weights from huggingface

## When to choose
- you need a Chinese-focused open LLM based on LLaMA 2 or BLOOM
- you want self-hosted model weights with permissive Apache-2.0 code licensing
- your tasks span media, public opinion, finance, or public-safety domains

## When to avoid
- you need state-of-the-art general LLM performance from actively maintained models
- you require commercial model licensing freedom (model weights use a custom YAYI license and data is CC BY-NC)
- you need a managed API rather than self-hosted GPU inference

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, machine-learning, chatbot
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: chinese-llm, llama2, bloom, instruction-tuning, open-weights, chat-model, natural-language-processing, gpu, linux

## Member repositories
- wenge-research/YAYI (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:58.629886+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 2026-08-30T02:25:25.304350+00:00, confidence not recorded.
  - readme: https://github.com/wenge-research/YAYI (fetched 2026-08-28T04:06:58.629886+00:00, sha def12dc026f8)
  - homepage: https://www.wenge.com/yayi/index.html (fetched 2026-08-29T10:08:20.135869+00:00, sha 6ff07e06c401)
  - site_page: https://www.wenge.com/site/about (fetched 2026-08-29T10:08:20.160097+00:00, sha 8ddbe9ae9d59)
- Data as of 2026-08-30T08:39:29.467469+00:00.