# ymcui/Chinese-LLaMA-Alpaca

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Repository: https://github.com/ymcui/Chinese-LLaMA-Alpaca
Canonical: https://ross.abutalabs.com/products/chinese-llama-alpaca
Homepage: https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki
Language: Python
License: Apache-2.0
License Family: permissive
Topics: llm, plm, pre-trained-language-models, alpaca, llama, nlp, quantization, large-language-models, lora, alpaca-2, llama-2
Last push: 2026-04-19T00:58:05+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 78, release rhythm 8, longevity 90
- inputs: {"age_days": 1267, "days_push": 137, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 18931, forks 1840 (observed 2026-08-28T04:11:27.229241+00:00)

## What it is
A project releasing Chinese-adapted LLaMA and instruction-tuned Alpaca large language models with extended Chinese vocabulary, plus pre-training and fine-tuning scripts. It supports local CPU/GPU quantized deployment via llama.cpp, transformers, and other ecosystem tools.

## Use cases
- run a chinese large language model locally on cpu
- fine-tune llama on chinese instruction data
- quantize an llm for laptop deployment
- chinese text generation with open-source models
- continue pretraining llama with chinese corpus
- deploy a local chatbot without cloud apis

## When to choose
- you need open-source Chinese-capable LLaMA/Alpaca models with training scripts
- you want to run quantized LLMs locally on consumer hardware
- you need LoRA-based instruction fine-tuning recipes for Chinese

## When to avoid
- you need the newest Llama-3-based models (use Chinese-LLaMA-Alpaca-3 instead)
- you need a production-grade managed LLM service
- your use case is non-Chinese multilingual generation

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, llm-training, nlp, machine-learning
- domain: large-language-models, machine-learning
- platform: python, cross-platform, cli
- tags: chinese-llm, llama, alpaca, lora, quantization, pretrained-models, local-deployment, huggingface, natural-language-processing

## Member repositories
- ymcui/Chinese-LLaMA-Alpaca (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:27.229241+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 2026-08-29T17:01:15.947807+00:00, confidence not recorded.
  - readme: https://github.com/ymcui/Chinese-LLaMA-Alpaca (fetched 2026-08-28T04:11:27.229241+00:00, sha d103da6d661a)
  - homepage: https://github.com/ymcui/Chinese-LLaMA-Alpaca/wiki (fetched 2026-08-29T07:59:04.915638+00:00, sha 334853a8f196)
- Data as of 2026-08-30T08:39:29.467469+00:00.