wenge-research/YAYI2

• highreadme#1

  Reposition the core introduction to the top of the README

  Why:

  CURRENT

  The README currently starts with a div, links, and '## 更新' (Updates) before '## 介绍' (Introduction).

  COPY-PASTE FIX

  Copy

  Move the entire content of the '## 介绍' section to appear immediately after any initial badges or title, and before the '## 更新' section. The content is:
  
  YAYI 2 是中科闻歌研发的**新一代开源大语言模型**，包括 Base 和 Chat 版本，参数规模为 30B。YAYI2-30B 是基于 Transformer 的大语言模型，采用了超过 2 万亿 Tokens 的高质量、多语言语料进行预训练。针对通用和特定领域的应用场景，我们采用了百万级指令进行微调，同时借助人类反馈强化学习方法，以更好地使模型与人类价值观对齐。
  
  本次开源的模型为 YAYI2-30B Base 模型。我们希望通过雅意大模型的开源来促进中文预训练大模型开源社区的发展，并积极为此做出贡献。通过开源，我们与每一位合作伙伴共同构建雅意大模型生态。
  
  更多技术细节，欢迎阅读我们的技术报告🔥YAYI 2: Multilingual Open-Source Large Language Models。

  OpenDoneDismiss
• highhomepage#2

  Add the project homepage URL to the repository metadata

  Why:

  COPY-PASTE FIX

  Copy

  Add the URL that the '[🔗网页端]' link in your README points to, or your primary project page, to the 'Homepage' field in your repository settings.

  OpenDoneDismiss
• mediumtopics#3

  Expand repository topics with more specific keywords

  Why:

  CURRENT

  artificial-intelligence, chat, chinese, gpt, natural-language-generation, pretrained-language-model, yayi

  COPY-PASTE FIX

  Copy

  Add the following topics: multilingual, foundation-model, llm. The full list should be: artificial-intelligence, chat, chinese, gpt, natural-language-generation, pretrained-language-model, yayi, multilingual, foundation-model, llm

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  Looking for an open-source large language model specifically optimized for Chinese text generation.

  you: not recommended
  AI recommended (in order):

  1. Baichuan 2
  2. Qwen
  3. ChatGLM3
  4. Yi
  5. Pangu-Σ

  AI recommended 5 alternatives but never named wenge-research/YAYI2. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  What are powerful open-source foundation models suitable for general-purpose chat applications?

  you: not recommended
  AI recommended (in order):

  1. Llama 3 (facebookresearch/llama)
  2. Mixtral 8x7B (mistralai/mistral-src)
  3. Gemma (google/gemma.cpp)
  4. Mistral 7B Instruct (mistralai/mistral-src)
  5. Falcon 40B Instruct (tiiuae/falcon-40b)

  AI recommended 5 alternatives but never named wenge-research/YAYI2. This is the gap to close.

  Show full AI answer

• Metadata completeness

  warn

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of wenge-research/YAYI2?

  pass
  ✓AI named wenge-research/YAYI2 explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts wenge-research/YAYI2 in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named wenge-research/YAYI2 explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo wenge-research/YAYI2 solve, and who is the primary audience?

  pass
  ✓AI named wenge-research/YAYI2 explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?