baichuan-inc/Baichuan2

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

4084 stars · 294 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

library · maturity maintenance

llm-inference llm-training machine-learning nlp large-language-models artificial-intelligence python cross-platform open-weights chinese-llm huggingface quantization fine-tuning model-weights natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="baichuan-inc/Baichuan2")