# baichuan-inc/Baichuan2

A series of large language models developed by Baichuan Intelligent Technology

Repository: https://github.com/baichuan-inc/Baichuan2
Canonical: https://ross.abutalabs.com/products/baichuan2
Homepage: https://huggingface.co/baichuan-inc
Language: Python
License: Apache-2.0
License Family: permissive
Topics: artificial-intelligence, benchmark, ceval, chatgpt, chinese, gpt, gpt-4, huggingface, large-language-models, llama2, mmlu, natural-language-processing
Last push: 2024-11-08T08:31:29+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 78
- inputs: {"age_days": 1098, "days_push": 663, "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 4084, forks 294 (observed 2026-08-28T04:08:34.472979+00:00)

## What it is
Baichuan 2 is a family of open large language models (7B and 13B, Base and Chat variants with 4-bit quantized versions) trained by Baichuan Intelligent Technology on 2.6 trillion tokens, with strong Chinese and multilingual performance. The repository provides model weights, inference and deployment code, and fine-tuning tooling.

## Use cases
- run a chinese open-source llm locally
- fine-tune a 7b or 13b language model
- deploy a chat model with 4-bit quantization
- benchmark llms on ceval and mmlu
- self-host an alternative to chatgpt
- commercially use an open llm with a license

## When to choose
- you need strong Chinese-language understanding or generation
- you want open weights you can fine-tune and deploy yourself
- you need a mid-size (7B/13B) model that fits modest GPU budgets

## When to avoid
- you need the newest frontier-level reasoning or long-context capabilities
- you want a maintained tool rather than model weights - the repo is largely a model release
- your workload is primarily English-only and you prefer models with larger ecosystems

## Facets
- artifact type: library
- maturity: maintenance
- function: llm-inference, llm-training, machine-learning, nlp
- domain: large-language-models, artificial-intelligence
- platform: python, cross-platform
- tags: open-weights, chinese-llm, huggingface, quantization, fine-tuning, model-weights, natural-language-processing, gpu, linux

## Member repositories
- baichuan-inc/Baichuan2 (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:34.472979+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 2026-08-29T18:23:24.238984+00:00, confidence not recorded.
  - readme: https://github.com/baichuan-inc/Baichuan2 (fetched 2026-08-28T04:08:34.472979+00:00, sha bffabbb806e0)
  - homepage: https://huggingface.co/baichuan-inc (fetched 2026-08-29T09:15:19.200663+00:00, sha 299eb66a5b19)
  - site_page: https://huggingface.co/docs (fetched 2026-08-29T09:15:19.209762+00:00, sha bdec26667b98)
  - site_page: https://huggingface.co/pricing (fetched 2026-08-29T09:15:19.211558+00:00, sha de6b7a178be5)
  - site_page: https://huggingface.co/huggingface (fetched 2026-08-29T09:15:19.213743+00:00, sha fd2b8729a7a0)
- Data as of 2026-08-30T08:39:29.467469+00:00.