update cn doc

README.md

@@ -36,13 +36,15 @@
 
 ## Introduction
 
-- **200K Context window**: Both base and chat models can work with more than 200K context after being sufficiently trained on 32K-context data. Try it with [LMDeploy](./inference/) for 200K-context inference.
+InternLM2 series are released with the following features:
 
-- **Outstanding comprehensive performance**: Significantly better than the last generation in all dimensions including reasoning, code, chat experience, instruction following, and creative writing.
+- **200K Context window**: Nearly perfect at finding needles in the haystack with 200K-long context, with leading performance on long-context tasks like LongBench and L-Eval. Try it with [LMDeploy](./inference/) for 200K-context inference.
 
-- **Code interpreter & Data analysis**: New state-of-the-art results in using code interpreter for math problems, also good at data analysis.
+- **Outstanding comprehensive performance**: Significantly better than the last generation in all dimensions, especially in reasoning, math, code, chat experience, instruction following, and creative writing, with leading performance among open-source models in similar sizes. In some evaluations, InternLM2-Chat-20B may match or even surpass ChatGPT (GPT-3.5).
 
-- **Stronger tool use**: Excellent zero-shot and multi-step tool calling capabilities, better with [streaming](docs/chat_format.md##streaming-style) and also works with [ReAct](docs/chat_format.md##react-style) format. Try it with [Lagent](./agent/).
+- **Code interpreter & Data analysis**: With code interpreter, InternLM2-Chat-20B obtains compatible performance with GPT-4 on GSM8K and MATH. InternLM2-Chat also provides data analysis capability.
+
+- **Stronger tool use**: Based on better tool utilization-related capabilities in instruction following, tool selection and reflection, InternLM2 can support more kinds of agents and multi-step tool calling for complex tasks. See [examples](./agent/).
 
 ## News
 

README_zh-CN.md

@@ -37,9 +37,12 @@
 
 ## 简介
 
-InternLM 是一个开源的轻量级训练框架，旨在支持大模型训练而无需大量的依赖。通过单一的代码库，它支持在拥有数千个 GPU 的大型集群上进行预训练，并在单个 GPU 上进行微调，同时实现了卓越的性能优化。在1024个 GPU 上训练时，InternLM 可以实现近90%的加速效率。
+InternLM2 系列模型在本仓库正式发布，具有如下特性：
 
-基于InternLM训练框架，我们已经发布了两个开源的预训练模型：InternLM-7B 和 InternLM-20B。
+- 有效支持20万字超长上下文：模型在20万字长输入中几乎完美地实现长文“大海捞针”，而且在 LongBench 和 L-Eval 等长文任务中的表现也达到开源模型中的领先水平。 可以通过 [LMDeploy](./inference/) 尝试20万字超长上下文推理。
+- 综合性能全面提升：各能力维度相比上一代模型全面进步，在推理、数学、代码、对话体验、指令遵循和创意写作等方面的能力提升尤为显著，综合性能达到同量级开源模型的领先水平，在重点能力评测上 InternLM2-Chat-20B 能比肩甚至超越 ChatGPT （GPT-3.5）。
+- 代码解释器与数据分析：在配合代码解释器（code-interpreter）的条件下，InternLM2-Chat-20B 在 GSM8K 和 MATH 上可以达到和 GPT-4 相仿的水平。基于在数理和工具方面强大的基础能力，InternLM2-Chat 提供了实用的数据分析能力。
+- 工具调用能力整体升级：基于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](./agent/)。
 
 ## 更新