Update README.md

README.md

@@ -11,7 +11,9 @@ Please follow the license of the original model.
 
 ## How To Use
 ### INT4 Inference
-Due to kernel issues, potential overflow/underflow has been observed on CUDA. For accuracy, it is recommended to use CPU.
+Potential overflow/underflow issues have been observed on CUDA, primarily due to kernel limitations. 
+For better accuracy, we recommend deploying the model on CPU or using [our INT4 mixed version](https://huggingface.co/Intel/DeepSeek-V3.1-int4-mixed-AutoRound)
+
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import transformers
@@ -121,6 +123,7 @@ Here are the key points about the company:
 *   **Open-Source Contribution:** DeepSeak has made significant contributions to the open-source community. They have released powerful models like **DeepSeek-Coder** (focused on code generation and programming tasks) and the weights for earlier versions of their LLMs, allowing developers and researchers worldwide
 --------------------------------------------------
 """
+```
 
 ### Generate the model
 Mian branch is required if the model is fp8 and the device supports fp8  https://github.com/intel/auto-round