Baichuan2

About

What Baichuan2 is

Baichuan 2 百川API支持搜索增强和192K长窗口，新增百川搜索增强知识库、限时免费！<br 🚀 <a href="https://www.baichuan-ai.com/" target="blank"百川大模型在线对话平台</a 已正式向公众开放 🎉 目录/Table of Contents - 📖 模型介绍/Introduction - ⚙️ 快速开始/Quick Start - 📊 Benchmark评估/Benchmark Evaluation - 👥 社区与生态/Community - 📜 声明与协议/Terms and Conditions <span id="Introduction"模型介绍/Introduction</span Baichuan 2 是[百川智能]推出的新一代开源大语言模型，采用 2.6 万亿 Tokens 的高质量语料训练，在权威的中文和英文 benchmark 上均取得同尺寸最好的效果。本次发布包含有 7B、13B 的 Base 和 Chat 版本，并提供了 Chat 版本的 4bits 量化，所有版本不仅对学术研究完全开放，开发者也仅需[邮件申请]并获得官方商用许可后，即可以免费商用。具体发布版本和下载见下表： Baichuan 2 is the new generation of large-scale open-source language models launched by Baichuan Intelligence inc.. It is trained on a high-quality corpus with 2.6 trillion tokens and has achieved the best performance in authoritative Chinese and English benchmarks of the same size. This release includes 7B and 13B versions for both Base and Chat models, along with a 4bits quantized version for the Chat model. All versions are fully open to academic research, and developers can also use them for free in commercial applications after obtaining an official commercial license through email request. The specific release versions and download links are listed in the table below: <span id="Start"快速开始/Quick Start</span 在Baichuan2系列模型中，我们为了加快推理速度使用了Pytorch2.0加入的新功能F.scaleddotproductattention，因此模型需要在Pytorch2.0环境下运行。 In the Baichuan 2 series models, we have utilized the new feature F.scaleddotproductattention introduced in PyTorch 2.0 to accelerate inference speed. Therefore, the model needs to be run in a PyTorch 2.0 environment. <span id="Benchmark"Benchmark 结果/Benchmark Evaluation</span 我们在[通用]、[法律]、[医疗]、[数学]、[代码]和[多语言翻译]六个领域的中英文权威数据集上对模型进行了广泛测试，更多详细测评结果可查看[GitHub]。 We have extensively tested the model on authoritative Chinese-English datasets across six domains: General, Legal, Medical, Mathematics, Code, and Multilingual Translation. For more detailed evaluation results, please refer to GitHub. 7B Model Results 13B Model Results 训练过程模型/Training Dynamics 除了训练了 2.6 万亿 Tokens 的 Baichuan2-7B-Base 模型，我们还提供了在此之前的另外 11 个中间过程的模型（分别对应训练了约 0.2 ~ 2.4 万亿 Tokens）供社区研究使用 （训练过程checkpoint下载）。下图给出了这些 checkpoints 在 C-Eval、MMLU、CMMLU 三个 benchmark 上的效果变化： I

Summarised from the published model card. Read the full card on the HuggingFace links below.

Specifications

What it is

How it works

How language models work

Variants

Sizes & precisions

Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys baichuan2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (baichuan2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"baichuan2","messages":[{"role":"user","content":"Hello"}]}'

Details

Languages, data & research

Licence

Commercial licence needed

Sources

Weights & code

Explore

More language models