add python codes to code blocks

README.md

@@ -173,39 +173,41 @@ This configuration:
 
 **Extracting reasoning content from the API response:**
 
-    from openai import OpenAI
-
-    client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")
-
-    response = client.chat.completions.create(
-        model="arcee-ai/Trinity-Large-Thinking",
-        messages=[
-            {"role": "user", "content": "What's the weather like in Paris?"}
-        ],
-        tools=[ # your tool definitions here
-            {
-                "type": "function",
-                "function": {
-                    "name": "get_weather",
-                    "description": "Get current weather for a location",
-                    "parameters": {
-                        "type": "object",
-                        "properties": {
-                            "location": {"type": "string"}
-                        },
-                        "required": ["location"]
-                    }
+```python
+from openai import OpenAI
+
+client = OpenAI(api_key="EMPTY", base_url="http://localhost:8000/v1")
+
+response = client.chat.completions.create(
+    model="arcee-ai/Trinity-Large-Thinking",
+    messages=[
+        {"role": "user", "content": "What's the weather like in Paris?"}
+    ],
+    tools=[ # your tool definitions here
+        {
+            "type": "function",
+            "function": {
+                "name": "get_weather",
+                "description": "Get current weather for a location",
+                "parameters": {
+                    "type": "object",
+                    "properties": {
+                        "location": {"type": "string"}
+                    },
+                    "required": ["location"]
                 }
             }
-        ],
-    )
+        }
+    ],
+)
 
-    # Access reasoning (thinking) content
-    reasoning = response.choices[0].message.reasoning_content
+# Access reasoning (thinking) content
+reasoning = response.choices[0].message.reasoning_content
 
-    # Access final response or tool calls
-    content = response.choices[0].message.content
-    tool_calls = response.choices[0].message.tool_calls
+# Access final response or tool calls
+content = response.choices[0].message.content
+tool_calls = response.choices[0].message.tool_calls
+```
 
 **Note on thinking-in-context with vLLM**: When building multi-turn agentic loops, include both `reasoning_content` and `content` in the conversation history you send back to the model. The reasoning content should be re-wrapped in `<think>...</think>` tags within the assistant message.
 
@@ -213,40 +215,41 @@ This configuration:
 
 Use the `main` transformers branch or pass `trust_remote_code=True` with a released version.
 
-    from transformers import AutoTokenizer, AutoModelForCausalLM
-    import torch
-
-    model_id = "arcee-ai/Trinity-Large-Thinking"
-    tokenizer = AutoTokenizer.from_pretrained(model_id)
-    model = AutoModelForCausalLM.from_pretrained(
-        model_id,
-        torch_dtype=torch.bfloat16,
-        device_map="auto",
-        trust_remote_code=True
-    )
-
-    messages = [
-        {"role": "user", "content": "Who are you?"},
-    ]
-
-    input_ids = tokenizer.apply_chat_template(
-        messages,
-        add_generation_prompt=True,
-        return_tensors="pt"
-    ).to(model.device)
-
-    outputs = model.generate(
-        input_ids,
-        max_new_tokens=4096,
-        do_sample=True,
-        temperature=0.6,
-        top_k=50,
-        top_p=0.95
-    )
-
-    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-    print(response)
-
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "arcee-ai/Trinity-Large-Thinking"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True
+)
+
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=4096,
+    do_sample=True,
+    temperature=0.6,
+    top_k=50,
+    top_p=0.95
+)
+
+response = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(response)
+```
 
 ### API