upload readme

README.md

@@ -32,15 +32,28 @@ license: other
 
 ## Introduction
 
-TODO
+InternLM2.5 has open-sourced a 1.8 billion parameter base model and a chat model tailored for practical scenarios. The model has the following characteristics:
+
+- **Outstanding reasoning capability**: State-of-the-art performance on Math reasoning, surpassing models like MiniCPM-2 and Qwen2-1.5B.
+
+- **Stronger tool use**: InternLM2.5 supports gathering information from more than 100 web pages, corresponding implementation has be released in [MindSearch](https://github.com/InternLM/MindSearch). InternLM2.5 has better tool utilization-related capabilities in instruction following, tool selection and reflection. See [examples](https://github.com/InternLM/InternLM/blob/main/agent/lagent.md).
 
 ## InternLM2.5-1.8B-Chat
 
 ### Performance Evaluation
 
-TODO
+We conducted a comprehensive evaluation of InternLM using the open-source evaluation tool [OpenCompass](https://github.com/internLM/OpenCompass/). The evaluation covered five dimensions of capabilities: disciplinary competence, language competence, knowledge competence, inference competence, and comprehension competence. Here are some of the evaluation results, and you can visit the [OpenCompass leaderboard](https://rank.opencompass.org.cn) for more evaluation results.
 
-- The evaluation results were obtained from [OpenCompass](https://github.com/internLM/OpenCompass/) (some data marked with *, which means come from the original papers), and evaluation configuration can be found in the configuration files provided by [OpenCompass](https://github.com/internLM/OpenCompass/). 
+| Benchmark          | InternLM2.5-1.8B-Chat | MiniCPM-2 | Qwen2-1.5B-Instruct |
+| ------------------ | --------------------- | --------- | ------------------- |
+| MMLU (5-shot)      | 50.7                  | 54.2      | 55.7                |
+| CMMLU (5-shot)     | 62.2                  | 50.6      | 65.2                |
+| BBH (3-shot CoT)   | **41.9**              | 41.5      | 36.5                |
+| MATH (0-shot CoT)  | **40.2**              | 15.5      | 21.4                |
+| HumanEval          | 43.3                  | 50.0      | 47.6                |
+| GPQA (0-shot)      | **27.8**              | 23.7      | 27.3                |
+
+- The evaluation results were obtained from [OpenCompass](https://github.com/internLM/OpenCompass/), and evaluation configuration can be found in the configuration files provided by [OpenCompass](https://github.com/internLM/OpenCompass/). 
 - The evaluation data may have numerical differences due to the version iteration of [OpenCompass](https://github.com/internLM/OpenCompass/), so please refer to the latest evaluation results of [OpenCompass](https://github.com/internLM/OpenCompass/).
 
 
@@ -169,7 +182,10 @@ The code is licensed under Apache-2.0, while model weights are fully open for ac
 
 ## 简介
 
-TODO
+InternLM2.5 ，即书生·浦语大模型第 2.5 代，开源了面向实用场景的 18 亿参数基础模型与对话模型 （InternLM2.5-20B-Chat）。模型具有以下特点：
+
+- 卓越的推理性能：在数学推理方面取得了同量级模型最优精度，超越了 MiniCPM-2 和 Qwen2-1.5B。
+- 工具调用能力整体升级：InternLM2.5 支持从上百个网页搜集有效信息进行分析推理，相关实现已开源到 [MindSearch](https://github.com/InternLM/MindSearch)。InternLM2.5 具有更强和更具有泛化性的指令理解、工具筛选与结果反思等能力，新版模型可以更可靠地支持复杂智能体的搭建，支持对工具进行有效的多轮调用，完成较复杂的任务。可以查看更多[样例](https://github.com/InternLM/InternLM/blob/main/agent/lagent.md)。
 
 ## InternLM2.5-1.8B-Chat
 
@@ -177,9 +193,16 @@ TODO
 
 我们使用开源评测工具 [OpenCompass](https://github.com/internLM/OpenCompass/) 从学科综合能力、语言能力、知识能力、推理能力、理解能力五大能力维度对InternLM开展全面评测，部分评测结果如下表所示，欢迎访问[ OpenCompass 榜单 ](https://rank.opencompass.org.cn)获取更多的评测结果。
 
-TODO
+| Benchmark          | InternLM2.5-1.8B-Chat | MiniCPM-2 | Qwen2-1.5B-Instruct |
+| ------------------ | --------------------- | --------- | ------------------- |
+| MMLU (5-shot)      | 50.7                  | 54.2      | 55.7                |
+| CMMLU (5-shot)     | 62.2                  | 50.6      | 65.2                |
+| BBH (3-shot CoT)   | **41.9**              | 41.5      | 36.5                |
+| MATH (0-shot CoT)  | **40.2**              | 15.5      | 21.4                |
+| HumanEval          | 43.3                  | 50.0      | 47.6                |
+| GPQA (0-shot)      | **27.8**              | 23.7      | 27.3                |
 
-- 以上评测结果基于 [OpenCompass](https://github.com/internLM/OpenCompass/) 获得（部分数据标注`*`代表数据来自原始论文），具体测试细节可参见 [OpenCompass](https://github.com/internLM/OpenCompass/) 中提供的配置文件。
+- 以上评测结果基于 [OpenCompass](https://github.com/internLM/OpenCompass/) 获得，具体测试细节可参见 [OpenCompass](https://github.com/internLM/OpenCompass/) 中提供的配置文件。
 - 评测数据会因 [OpenCompass](https://github.com/internLM/OpenCompass/) 的版本迭代而存在数值差异，请以 [OpenCompass](https://github.com/internLM/OpenCompass/) 最新版的评测结果为主。
 
 **局限性：** 尽管在训练过程中我们非常注重模型的安全性，尽力促使模型输出符合伦理和法律要求的文本，但受限于模型大小以及概率生成范式，模型可能会产生各种不符合预期的输出，例如回复内容包含偏见、歧视等有害内容，请勿传播这些内容。由于传播不良信息导致的任何后果，本项目不承担责任。