Update README.md

README.md

@@ -51,9 +51,59 @@ For more details, see:
 | Think mode (standard requests)    | ≈ 0.6       | 1.0              |
 | Complex reasoning requests        | ≥ 0.8       | 1.0              |
 
+- Hybrid reasoning models need careful tuning of sampling hyperparameters, which vary by domain.   
+- Use lower temperature for straightforward queries and higher temperature for complex 'think-mode' tasks. 
+- A presence_penalty between 0 and 2 can help avoid repetitive outputs.
+
 
 ## 👨‍💻 Examples of usage
 
+
+
+## SGLang Usage
+For better quality and stable performance, we recommend SGLang as your inference framework.
+
+To run an inference server for **T-pro IT 2.0**, start by launching the SGLang server:
+
+```bash
+python -m sglang.launch_server \
+    --model-path t-tech/T-pro-it-2.0 \
+    --reasoning-parser qwen3
+````
+
+Once the server is up and listening on `localhost:30000`, you can send chat-based requests via the OpenAI Python client.
+
+```python
+import openai
+
+client = openai.OpenAI(
+    base_url="http://127.0.0.1:30000/v1",
+    api_key="ANY"  # the server ignores the API key
+)
+
+prompt = (
+    "Пожалуйста, вычисли определённый интеграл ∫_0^1 x² eˣ dx, "
+    "пошагово объясни решение и укажи окончательный результат."
+)
+
+completion = client.chat.completions.create(
+    model="ANY",  # the server ignores the model name
+    messages=[
+        {"role": "system", "content": "Ты T-pro, виртуальный ассистент в Т-Технологии. Твоя задача - быть полезным диалоговым ассистентом."},
+        {"role": "user", "content": prompt}
+    ],
+    # REQUIRED: sampling params from the "Recommended Generation Parameters" table
+    temperature=0.6,
+    presence_penalty=1.0,
+)
+
+# The generated reply is in `completion.choices[0].message.content`
+print(completion.choices[0].message.content)
+```
+
+**Note:** It is **obligatory** to include both `temperature` and `presence_penalty` in every completion call.
+
+
 ### HF Usage
 
 ```python
@@ -242,46 +292,9 @@ generated_text = [output.outputs[0].text for output in outputs]
 print(generated_text)
 ```
 
+## Long Context Usage
+T-pro-it-2.0 natively supports a context length of 32,768 tokens.  
+For conversations where the input significantly exceeds this limit, follow the recommendations from the [Qwen3 model card](https://huggingface.co/Qwen/Qwen3-235B-A22B#processing-long-texts) on processing long texts.
 
-
-## SGLang Usage
-
-To run an inference server for **T-pro IT 2.0**, start by launching the SGLang server:
-
-```bash
-python -m sglang.launch_server \
-    --model-path t-tech/T-pro-it-2.0 \
-    --reasoning-parser qwen3
-````
-
-Once the server is up and listening on `localhost:30000`, you can send chat-based requests via the OpenAI Python client.
-
-```python
-import openai
-
-client = openai.OpenAI(
-    base_url="http://127.0.0.1:30000/v1",
-    api_key="ANY"  # the server ignores the API key
-)
-
-prompt = (
-    "Пожалуйста, вычисли определённый интеграл ∫_0^1 x² eˣ dx, "
-    "пошагово объясни решение и укажи окончательный результат."
-)
-
-completion = client.chat.completions.create(
-    model="ANY",  # the server ignores the model name
-    messages=[
-        {"role": "system", "content": "Ты T-pro, виртуальный ассистент в Т-Технологии. Твоя задача - быть полезным диалоговым ассистентом."},
-        {"role": "user", "content": prompt}
-    ],
-    # REQUIRED: sampling params from the "Recommended Generation Parameters" table
-    temperature=0.6,
-    presence_penalty=1.0,
-)
-
-# The generated reply is in `completion.choices[0].message.content`
-print(completion.choices[0].message.content)
-```
-
-**Note:** It is **obligatory** to include both `temperature` and `presence_penalty` in every completion call.
+For example, in SGLang, you can enable 128K context support with the following command:  
+`llama-server ... --rope-scaling yarn --rope-scale 4 --yarn-orig-ctx 32768`