GraphCanon
Home/LLM Frameworks/Chinese-LLaMA-Alpaca
Chinese-LLaMA-Alpaca logo

Chinese-LLaMA-Alpaca

ymcui/Chinese-LLaMA-Alpaca

Chinese LLaMA & Alpaca Large Language Models for Local CPU/GPU Training and Deployment

GitHub Website

GraphCanon updated 3d · GitHub synced 3d

19k stars1.8k forksLast push 4mo Python Apache-2.0

Decision brief

`Chinese-LLaMA-Alpaca` is a repository that includes Chinese versions of the LLaMA and Alpaca large language models, specifically designed with extended Chinese vocabulary and fine-tuned on Chinese instruction data for a

Good fit when

  • You should consider using `Chinese-LLaMA-Alpaca` if your project involves local deployment and training using CPUs or GPUs, particularly if the focus is on Chinese language texts. These models are pre
  • If you need advanced command comprehension and execution in Mandarin, where traditional models may fall short.

Avoid when

  • `Chinese-LLaMA-Alpaca` might not be the best fit if your project requires extensive multi-language support beyond Chinese.
  • If you are exclusively targeting markets where English is the primary language, and fine-tuning or additional pre-training on Chinese data does not add value to your application.
Pricing:
freemium - Access to `Chinese-LLaMA-Alpaca` models and documentation is free, but commercial usage should adhere to open-source licensing requirements.

Observed Jul 11, 2026 · Source: enrich:decision_facts

Chinese-LLaMA-Alpaca alternativesTrust report
Chinese-LLaMA-Alpaca vs Chinese-LLaMA-Alpaca-2Chinese-LLaMA-Alpaca vs LlamaFactoryChinese-LLaMA-Alpaca vs Video-LLaMA

Verify the decision

Maintenance and security

Full trust report
Maintenance
Slowing (119d since push)
As of 3d
Provenance
Not a fork · Personal account
As of 3d
Security (OSV)
73 low (73 low)
As of 1mo

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

Install

pip install Chinese-LLaMA-Alpaca
PyPI

How it fits your stack(11)

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

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

A repository that includes Chinese versions of the LLaMA and Alpaca large language models, designed with additional Chinese vocabulary and fine-tuned on Chinese instruction data for better comprehension and execution. The repository provides scripts for pre-training and instruction tuning.

Capability facts

Languages
python

Source: github.language · Aug 17, 2026

Categories

LLM FrameworksModel Training

Graph entities

LangChainframeworkSmolagentsframework

Compatibility

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

LangChain integrationLangChain

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

ext-generation-webui), [LlamaChat](https://github.com/alexrozanski/LlamaChat), [LangChain](https://github.com/hwchase17/langchain), [privateGPT](https://github.com/imart
Source link

Tags

alpacalarge language modelsllamanlppre-trained-language-models

README

Chinese-LLaMA-Alpaca-3项目启动！

🇨🇳中文 | 🌐English | 📖文档/Docs | ❓提问/Issues | 💬讨论/Discussions | ⚔️竞技场/Arena



GitHub GitHub release (latest by date) GitHub top language GitHub last commit Badge image

本项目开源了中文LLaMA模型和指令精调的Alpaca大模型，以进一步促进大模型在中文NLP社区的开放研究。这些模型在原版LLaMA的基础上扩充了中文词表并使用了中文数据进行二次预训练，进一步提升了中文基础语义理解能力。同时，中文Alpaca模型进一步使用了中文指令数据进行精调，显著提升了模型对指令的理解和执行能力。

技术报告（V2）：[Cui, Yang, and Yao] Efficient and Effective Text Encoding for Chinese LLaMA and Alpaca

本项目主要内容：

  • 🚀 针对原版LLaMA模型扩充了中文词表，提升了中文编解码效率
  • 🚀 开源了使用中文文本数据预训练的中文LLaMA以及经过指令精调的中文Alpaca
  • 🚀 开源了预训练脚本、指令精调脚本，用户可根据需要进一步训练模型
  • 🚀 快速使用笔记本电脑（个人PC）的CPU/GPU本地量化和部署体验大模型
  • 🚀 支持🤗transformers, llama.cpp, text-generation-webui, LlamaChat, LangChain, privateGPT等生态
  • 目前已开源的模型版本：7B（基础版、Plus版、Pro版）、13B（基础版、Plus版、Pro版）、33B（基础版、Plus版、Pro版）

💡 下图是中文Alpaca-Plus-7B模型在本地CPU量化部署后的实际体验速度和效果。

中文LLaMA-2&Alpaca-2大模型 | 多模态中文LLaMA&Alpaca大模型 | 多模态VLE | 中文MiniRBT | 中文LERT | 中英文PERT | 中文MacBERT | 中文ELECTRA | 中文XLNet | 中文BERT | 知识蒸馏工具TextBrewer | 模型裁剪工具TextPruner

新闻

[2024/04/30] Chinese-LLaMA-Alpaca-3 已正式发布，开源基于Llama-3的Llama-3-Chinese-8B和Llama-3-Chinese-8B-Instruct，推荐所有一期、二期项目用户升级至三代模型，请参阅：https://github.com/ymcui/Chinese-LLaMA-Alpaca-3

[2024/03/27] 本项目已入驻机器之心SOTA!模型平台，欢迎关注：https://sota.jiqizhixin.com/project/chinese-llama-alpaca

[2023/08/14] Chinese-LLaMA-Alpaca-2 v2.0版本已正式发布，开源Chinese-LLaMA-2-13B和Chinese-Alpaca-2-13B，推荐所有一期用户升级至二代模型，请参阅：https://github.com/ymcui/Chinese-LLaMA-Alpaca-2

[2023/07/31] Chinese-LLaMA-Alpaca-2 v1.0版本已正式发布，请参阅：https://github.com/ymcui/Chinese-LLaMA-Alpaca-2

[2023/07/19] v5.0版本: 发布Alpaca-Pro系列模型，显著提升回复长度和质量；同时发布Plus-33B系列模型。

[2023/07/19] 🚀启动中文LLaMA-2、Alpaca-2开源大模型项目，欢迎关注了解最新信息。

[2023/07/10] Beta测试预览，提前了解即将到来的更新：详见讨论区

[2023/07/07] Chinese-LLaMA-Alpaca家族再添新成员，推出面向视觉问答与对话的多模态中文LLaMA&Alpaca大模型，发布了7B测试版本。

[2023/06/30] llama.cpp下8K context支持（无需对模型做出修改），相关方法

For agents

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

/tools/ymcui-chinese-llama-alpaca.mdGET /api/graphcanon/tools/ymcui-chinese-llama-alpacaGET /api/graphcanon/graph?tool=ymcui-chinese-llama-alpaca

Was this helpful?

Anonymous feedback helps us improve pages and translations.