Update README.md

README.md

@@ -6,11 +6,15 @@ base_model:
 ---
 ## Model Details
 
-This model is an int4 model with group_size 128 and and symmetric quantization of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. **Please note that loading the model in Transformers can be quite slow. Consider using an alternative serving framework for better performance.** Due to limited GPU resources,  we have only tested a few prompts on a CPU backend using QBits . If you found this model not perform well, **you can explore a quantized model in AWQ format with different hyperparameters generated via AutoRound** which will be uploaded soon
+This model is an int4 model with group_size 128 and and symmetric quantization of [deepseek-ai/DeepSeek-V3](https://huggingface.co/deepseek-ai/DeepSeek-V3) generated by [intel/auto-round](https://github.com/intel/auto-round) algorithm. 
+
+**Please note that loading the model in Transformers can be quite slow. Consider using an alternative serving framework for better performance.**
+
+Due to limited GPU resources,  we have only tested a few prompts on a CPU backend using QBits . If you found this model not perform well, **you can explore a quantized model in AWQ format with different hyperparameters generated via AutoRound** which will be uploaded soon
 
 ## How To Use
 
-### INT4 Inference(CPU/CUDA)
+### INT4 Inference
 
 ````python
 from transformers import AutoModelForCausalLM, AutoTokenizer,GenerationConfig
@@ -107,7 +111,7 @@ prompt = "strawberry中有几个r?"
 8. r - 是r
 """
 
-prompt = "strawberry中有几个r?"
+prompt = "How many r in strawberry."
 ##INT4 
 """The word "strawberry" contains **3 "r"s.
 """