# LinkSoul-AI/Chinese-Llama-2-7b

开源社区第一个能下载、能运行的中文 LLaMA2 模型！

Repository: https://github.com/LinkSoul-AI/Chinese-Llama-2-7b
Canonical: https://ross.abutalabs.com/products/chinese-llama-2-7b
Language: Python
License: Apache-2.0
License Family: permissive
Topics: deep-learning, llama2, llama2-docker, llm, pytorch
Last push: 2023-10-26T01:37:18+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 81
- inputs: {"age_days": 1140, "days_push": 1043, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2203, forks 196 (observed 2026-08-28T04:06:25.789252+00:00)

## What it is
An open-source, commercially usable Chinese-adapted LLaMA 2 7B chat model with a bilingual Chinese-English SFT dataset, following the llama-2-chat input format. The repo provides model weights (including 4-bit and GGML quantized versions), training/inference code, Docker one-click deployment, and Colab demos.

## Use cases
- run a chinese llama2 chat model locally
- fine-tune llama2 on chinese instruction data
- deploy a self-hosted chinese chatbot with docker
- download quantized 4bit or ggml llama2 weights
- chat with an open-source bilingual chinese-english llm
- build a chinese assistant compatible with llama-2-chat optimizations

## When to choose
- you need a downloadable, commercially usable Chinese LLaMA2 chat model
- you want SFT training data and code for Chinese-English instruction tuning
- you want Docker one-click deployment or Colab demos
- you need quantized (4-bit/GGML) versions for lower-resource inference

## When to avoid
- you need a state-of-the-art Chinese LLM with stronger benchmarks (newer models exist)
- you need a multilingual model beyond Chinese/English
- you want an actively developed project rather than a released model snapshot
- you cannot run a 7B parameter model locally or on GPU

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: llm-inference, llm-training, chatbot, machine-learning
- domain: large-language-models, artificial-intelligence, machine-learning
- platform: python, cross-platform
- tags: llama2, chinese-llm, sft-dataset, quantization, ggml, 4bit, huggingface, self-hosted-llm, natural-language-processing, docker, gpu

## Member repositories
- LinkSoul-AI/Chinese-Llama-2-7b (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:25.789252+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 2026-08-30T02:46:45.284908+00:00, confidence not recorded.
  - readme: https://github.com/LinkSoul-AI/Chinese-Llama-2-7b (fetched 2026-08-28T04:06:25.789252+00:00, sha bb0286b9531d)
- Data as of 2026-08-30T08:39:29.467469+00:00.