Update README.md

README.md

@@ -23,9 +23,11 @@ license: apache-2.0
 
 # Intro
 
-Yi-Coder series models are trained for coding tasks with two sizes available, 1.5B and 9B, supporting 52 major coding languages. Notably, the Yi-Coder-9B outperforms other models under 10 billion parameters such as CodeQwen1.5 7B and CodeGeex4 9B, and even achieves performance on par with DeepSeek-Coder 33B.
+Yi-Coder is a series of open-source code language models that delivers state-of-the-art coding performance with fewer than 10 billion parameters. 
 
-Yi-Coder excels in long-context understanding, handling up to 128K tokens for project-level code comprehension and generation. Despite its relatively small size, Yi-coder is versatile in tasks like programming, code editing, debugging, completion, and mathematical reasoning. 
+Key features:
+- Excelling in long-context understanding with a maximum context length of 128K tokens.
+- Supporting 52 major programming languages, including popular ones such as Java, Python, JavaScript, and C++.
 
 For model details and benchmarks, see [Yi-Coder blog](https://01-ai.github.io/) and [Yi-Coder README](https://github.com/01-ai/Yi-Coder).