Update README.md

README.md

@@ -19,6 +19,8 @@ Qwen3 is the latest generation of large language models in Qwen series, offering
 - Number of Paramaters (Non-Embedding): 29.9B
 - Number of Layers: 48
 - Number of Attention Heads (GQA): 32 for Q and 4 for KV
+- Number of Experts: 128
+- Number of Activated Experts: 8
 - Context Length: 32,768 natively and [131,072 tokens with YaRN](#processing-long-texts). 
 
 For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to our [blog](https://qwenlm.github.io/blog/qwen3/), [GitHub](https://github.com/QwenLM/Qwen3), and [Documentation](https://qwen.readthedocs.io/en/latest/).
@@ -202,7 +204,6 @@ Qwen3 excels in tool calling capabilities. We recommend using [Qwen-Agent](https
 
 To define the available tools, you can use the MCP configuration file, use the integrated tool of Qwen-Agent, or integrate other tools by yourself.
 ```python
-import os
 from qwen_agent.agents import Assistant
 
 # Define LLM
@@ -232,6 +233,10 @@ tools = [
                 'command': 'uvx',
                 'args': ['mcp-server-time', '--local-timezone=Asia/Shanghai']
             },
+            "fetch": {
+                "command": "uvx",
+                "args": ["mcp-server-fetch"]
+            }
         }
     },
   'code_interpreter',  # Built-in tools
@@ -241,7 +246,7 @@ tools = [
 bot = Assistant(llm=llm_cfg, function_list=tools)
 
 # Streaming generation
-messages = [{'role': 'user', 'content': 'What time is it?'}]
+messages = [{'role': 'user', 'content': 'https://qwenlm.github.io/blog/ Introduce the latest developments of Qwen'}]
 for responses in bot.run(messages=messages):
     pass
 print(responses)