Update README.md

README.md

@@ -45,7 +45,7 @@ The paper is coming soon.
 </div>
 
 
-## Recommend system prompt
+## **Recommend system prompt**
 
 More controllable | less reasoning capability
 ```
@@ -60,7 +60,7 @@ Highest reasoning capability | least controllable
 # No system prompt
 ```
 
-## Usage Example
+## **Usage Example**
 
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -103,7 +103,7 @@ response = outputs[0][input_ids.shape[-1]:]
 print(tokenizer.decode(response, skip_special_tokens=True)) # <think> Okay, .... </think> ดังนั้น จำนวนเต็มบวกที่น้อยที่สุดที่เป็นผลคูณของ 30 และเขียนได้ด้วยตัวเลข 0 และ 2 เท่านั้นคือ 2220 boxed{2220}
 ```
 
-## Inference Server Hosting Example
+## **Inference Server Hosting Example**
 ```bash
 pip install vllm
 vllm serve scb10x/llama3.1-typhoon2-deepseek-r1-70b --tensor-parallel-size 2 --gpu-memory-utilization 0.95 --max-model-len 16384 --enforce-eager
@@ -112,6 +112,9 @@ vllm serve scb10x/llama3.1-typhoon2-deepseek-r1-70b --tensor-parallel-size 2 --g
 # see more information at https://docs.vllm.ai/
 ```
 
+## **Tool use**
+We don't recommend using tool use on this model.
+
 ## **Intended Uses & Limitations**
 
 This model is an reasoning instructional model. However, it’s still undergoing development. It incorporates some level of guardrails, but it still may produce answers that are inaccurate, biased, or otherwise objectionable in response to user prompts. We recommend that developers assess these risks in the context of their use case.