\n🤗 Hugging Face • 🤖 ModelScope • 💬 WeChat\n
\n\n\n\n# 更新信息\n- [2023.09.06] 我们发布了新一代开源模型 [Baichuan 2](https://github.com/baichuan-inc/Baichuan2)，包含 7B、13B 尺寸 🔥🔥🔥\n\n# 介绍\n\nBaichuan-7B 是由百川智能开发的一个开源可商用的大规模预训练语言模型。基于 Transformer 结构，在大约 1.2 万亿 tokens 上训练的 70 亿参数模型，支持中英双语，上下文窗口长度为 4096。在标准的中文和英文 benchmark（C-Eval/MMLU）上均取得同尺寸最好的效果。\n\n# 公开benchmark榜单\n\n## 中文评测\n\n### C-Eval\n\n[C-Eval 数据集](https://cevalbenchmark.com/index.html)是一个全面的中文基础模型评测数据集，涵盖了 52 个学科和四个难度的级别。我们使用该数据集的 dev 集作为 few-shot 的来源，在 test 集上进行了 `5-shot` 测试。通过执行执行下面的命令：\n\n```bash\ncd evaluation\npython evaluate_zh.py --model_name_or_path 'your/model/path'\n```\n\n### 结果\n\n| Model 5-shot | Average | Avg(Hard) | STEM | Social Sciences | Humanities | Others |\n| :-------------------------: | :-----: | :-------: | :---: | :-------------: | :--------: | :----: |\n| GPT-4 | 68.7 | 54.9 | 67.1 | 77.6 | 64.5 | 67.8 |\n| ChatGPT | 54.4 | 41.4 | 52.9 | 61.8 | 50.9 | 53.6 |\n| Claude-v1.3 | 54.2 | 39.0 | 51.9 | 61.7 | 52.1 | 53.7 |\n| Claude-instant-v1.0 | 45.9 | 35.5 | 43.1 | 53.8 | 44.2 | 45.4 |\n| BLOOMZ-7B | 35.7 | 25.8 | 31.3 | 43.5 | 36.6 | 35.6 |\n| ChatGLM-6B | 34.5 | 23.1 | 30.4 | 39.6 | 37.4 | 34.5 |\n| Ziya-LLaMA-13B-pretrain | 30.2 | 22.7 | 27.7 | 34.4 | 32.0 | 28.9 |\n| moss-moon-003-base (16B) | 27.4 | 24.5 | 27.0 | 29.1 | 27.2 | 26.9 |\n| LLaMA-7B-hf | 27.1 | 25.9 | 27.1 | 26.8 | 27.9 | 26.3 |\n| Falcon-7B | 25.8 | 24.3 | 25.8 | 26.0 | 25.8 | 25.6 |\n| TigerBot-7B-base | 25.7 | 27.0 | 27.3 | 24.7 | 23.4 | 26.1 |\n| Aquila-7B* | 25.5 | 25.2 | 25.6 | 24.6 | 25.2 | 26.6 |\n| Open-LLaMA-v2-pretrain (7B) | 24.0 | 22.5 | 23.1 | 25.3 | 25.2 | 23.2 |\n| BLOOM-7B | 22.8 | 20.2 | 21.8 | 23.3 | 23.9 | 23.3 |\n| **Baichuan-7B** | 42.8 | 31.5 | 38.2 | 52.0 | 46.2 | 39.3 |\n\n### Gaokao\n\n[Gaokao](https://github.com/OpenLMLab/GAOKAO-Bench) 是一个以中国高考题作为评测大语言模型能力的数据集，用以评估模型的语言能力和逻辑推理能力。\n我们只保留了其中的单项选择题，随机划分后对所有模型进行统一 `5-shot` 测试。\n\n### 结果\n\n以下是测试的结果。\n\n| Model | Average |\n| :---------------------: | :-------: |\n| BLOOMZ-7B | 28.72 |\n| LLaMA-7B | 27.81 |\n| BLOOM-7B | 26.96 |\n| TigerBot-7B-base | 25.94 |\n| Falcon-7B | 23.98 |\n| Ziya-LLaMA-13B-pretrain | 23.17 |\n| ChatGLM-6B | 21.41 |\n| Open-LLaMA-v2-pretrain | 21.41 |\n| Aquila-7B* | 24.39 |\n| **Baichuan-7B** | **36.24** |\n\n### AGIEval\n\n[AGIEval](https://github.com/microsoft/AGIEval) 旨在评估模型的认知和解决问题相关的任务中的一般能力。\n我们只保留了其中的四选一单项选择题，随机划分后对所有模型进行了统一 `5-shot` 测试。\n\n### 结果\n\n| Model | Average |\n| :---------------------: | :-------: |\n| BLOOMZ-7B | 30.27 |\n| LLaMA-7B | 28.17 |\n| Ziya-LLaMA-13B-pretrain | 27.64 |\n| Falcon-7B | 27.18 |\n| BLOOM-7B | 26.55 |\n| Aquila-7B* | 25.58 |","github_created_at":"2023-06-14T10:57:51+00:00","created_at":"2026-07-07T17:34:50.176772+00:00","updated_at":"2026-08-17T12:01:13.507023+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"artificial-intelligence","name":"artificial-intelligence"},{"slug":"ceval","name":"ceval"},{"slug":"chatgpt","name":"chatgpt"},{"slug":"chinese","name":"chinese"},{"slug":"gpt-4","name":"gpt-4"},{"slug":"huggingface","name":"huggingface"},{"slug":"large-language-models","name":"large language models"},{"slug":"llama","name":"llama"}],"trust":{"provenance":{"is_fork":false,"github_id":653595084,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-17T12:01:12.633Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":759,"last_release_at":null,"stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":77,"high_count":0,"last_scan_at":"2026-07-11T11:04:11.761Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-17T12:01:13.145Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-17T12:01:13.145Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-17T12:01:13.145Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["If the project requires strong Chinese language proficiency, as Baichuan-7B has been optimized through extensive training specifically targeting Chinese language tasks.","For applications requiring a large context window size of 4096 tokens, enabling extended dialogue or complex task handling."],"when_not_to_use":["If the application primarily deals with languages other than English and Chinese, as Baichuan-7B's training has been focused on these two languages.","When a model smaller than 7-billion parameters is sufficient for the use case, especially if reducing inference time or resource consumption is more critical."],"source":"enrich:decision_facts","observed_at":"2026-07-14T19:29:08.010Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Baichuan-7B is notable for its performance in Chinese benchmarks and supports both English and Chinese languages."}]}}