Home/LLM Frameworks/Awesome-Chinese-LLM
Awesome-Chinese-LLM logo

Awesome-Chinese-LLM

AiHubCN/Awesome-Chinese-LLM

整理开源的中文大语言模型

GraphCanon updated 3d · GitHub synced 3d

23k stars2.1k forksLast push 3mo

Decision brief

Awesome-Chinese-LLM is a curated list focusing on smaller, less computationally expensive Chinese language models suitable for private deployment.

Good fit when

  • If you are looking to implement low-cost and efficient Chinese NLP solutions that can be deployed privately.
  • When your project requires access to both foundational and specific domain-tuned models along with supporting data sets and tutorials.

Avoid when

  • Avoid if your project necessitates large-scale, highly advanced computational capabilities or you are working with languages other than Chinese.
  • If your deployment scenario is limited to public cloud services only without the option for private deployment.

Observed Jul 11, 2026 · Source: enrich:decision_facts

Verify the decision

Maintenance and security

Full trust report
Maintenance
Slowing (98d since push)
As of 3d
Provenance
Not a fork · Personal account
As of 3d
Security (OSV)
No lockfile
As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/AiHubCN/Awesome-Chinese-LLM

How it fits your stack(16)

Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.

Integrates

Related

Relationship graph

Optional deeper exploration of typed edges and category neighbours.

Similar tools

Same-category neighbours not already linked as typed edges.

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

汇集了规模较小、适合私有化部署和低成本训练的中文大语言模型,包括基础模型、垂直领域的微调应用、相关数据集与教程。

Capability facts

No sourced capability facts yet. Facts appear after ingest scans repo manifests (Dockerfile, package.json, MCP configs).

Categories

Graph entities

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

LangChain integrationLangChain

Source: README excerpt (regex_v1, Aug 17, 2026)

- [2.2 LangChain应用](#22-langchain应用)
Source link
Works with ChatGPTChatGPT

Source: README excerpt (regex_v1, Aug 17, 2026)

自ChatGPT为代表的大语言模型(Large Language Model, LLM)出现以后,由于其惊人的类通用人工智能(AGI)的能力,掀起了新一轮自然语言处理领域的研究
Source link

Tags

README

Awesome Chinese LLM

Badge image

An Awesome Collection for LLM in Chinese

收集和梳理中文LLM相关

GitHub stars GitHub issues GitHub forks

自ChatGPT为代表的大语言模型(Large Language Model, LLM)出现以后,由于其惊人的类通用人工智能(AGI)的能力,掀起了新一轮自然语言处理领域的研究和应用的浪潮。尤其是以ChatGLM、LLaMA等平民玩家都能跑起来的较小规模的LLM开源之后,业界涌现了非常多基于LLM的二次微调或应用的案例。本项目旨在收集和梳理中文LLM相关的开源模型、应用、数据集及教程等资料,目前收录的资源已达100+个!

如果本项目能给您带来一点点帮助,麻烦点个⭐️吧~

同时也欢迎大家贡献本项目未收录的开源模型、应用、数据集等。提供新的仓库信息请发起PR,并按照本项目的格式提供仓库链接、star数,简介等相关信息,感谢~

常见底座模型细节概览:

底座包含模型模型参数大小训练token数训练最大长度是否可商用
ChatGLMChatGLM/2/3/4 Base&Chat6B1T/1.42K/32K可商用
LLaMALLaMA/2/3 Base&Chat7B/8B/13B/33B/70B1T/2T2k/4k部分可商用
BaichuanBaichuan/2 Base&Chat7B/13B1.2T/1.4T4k可商用
QwenQwen/1.5/2/2.5 Base&Chat&VL7B/14B/32B/72B/110B2.2T/3T/18T8k/32k可商用
BLOOMBLOOM1B/7B/176B-MT1.5T2k可商用
AquilaAquila/2 Base/Chat7B/34B-2k可商用
InternLMInternLM/2/2.5 Base/Chat/VL7B/20B-200k可商用
MixtralBase&Chat8x7B-32k可商用
YiBase&Chat6B/9B/34B3T200k可商用
DeepSeekBase&Chat1.3B/7B/33B/67B-4k可商用
XVERSEBase&Chat7B/13B/65B/A4.2B2.6T/3.2T8k/16k/256k可商用
MiniMaxMiniMax-Text-01/VL-01456B(45.9B activated)-1M/4M可商用

目录

  • 目录
    • 1. 模型
      • 1.1 文本LLM模型
      • 1.2 多模态LLM模型
    • 2. 应用
      • 2.1 垂直领域微调
        • 医疗
        • 法律
        • 金融
        • 教育
        • 科技
        • 电商
        • 网络安全
        • 农业
      • 2.2 LangChain应用
      • 2.3 其他应用
    • 3. 数据集
      • 预训练数据集
      • SFT数据集
      • 偏好数据集
    • 4. LLM训练微调框架
    • 5. LLM推理部署框架
    • 6. LLM评测
    • 7. LLM教程
      • LLM基础知识
      • 提示工程教程
      • LLM应用教程
      • LLM实战教程
    • 8. 相关仓库
  • Star History

1. 模型

1.1 文本LLM模型

  • ChatGLM:
    • 地址:https://github.com/THUDM/ChatGLM-6B

    • 简介:中文领域效果最好的开源底座模型之一,针对中文问答和对话进行了优化。经过约 1T 标识符的中英双语训练,辅以监督微调、反馈自助、人类反馈强化学习等技术的加持

  • ChatGLM2-6B
    • 地址:https://github.com/THUDM/ChatGLM2-6B

    • 简介:基于开源中英双语对话模型 ChatGLM-6B 的第二代版本,在保留了初代模型对话流畅、部署门槛较低等众多优秀特性的基础之上,引入了GLM 的混合目标函数,经过了 1.4T 中英标识符的预训练与人类偏好对齐训练;基座模型的上下文长度扩展到了 32K,并在对话阶段使用 8K 的上下文长度训练;基于 Multi-Query Attention 技术实现更高效的推理速度和更低的显存占用;允许商业使用。

  • ChatGLM3-6B

For agents

This page has a .md twin and JSON over the API.

Was this helpful?

Anonymous feedback helps us improve pages and translations.