Update README.md

README.md

@@ -12,7 +12,7 @@ base_model:
 
 This model is an int4 model with group_size 128 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. 
 
-**Loading the model in Transformers can be quite slow, especially with CUDA devices(30m-1hours). Consider using an alternative serving framework.** However, we have not tested it on other frameworks due to limited cuda resources.
+**Loading the model in Transformers can be quite slow, especially with CUDA devices(30m-1hours). Consider using an alternative serving framework (some frameworks have overflow issues).** However, we have not tested it on other frameworks due to limited cuda resources.
 
 Please follow the license of the original model.
 
@@ -20,7 +20,9 @@ Please follow the license of the original model.
 
 **INT4 Inference on CUDA**(**at least 7*80G**)
 
-On CUDA devices, the computation dtype is typically FP16 for int4 , which may lead to overflow for this model. While we have added a workaround to address this issue, we cannot guarantee reliable performance for all prompts. **For better stability, using CPU version is recommended. Please refer to the following section for details.**
+On CUDA devices, the computation dtype is typically FP16 for int4 , which may lead to overflow for this model. 
+While we have added a workaround to address this issue, we cannot guarantee reliable performance for all prompts. 
+**For better stability, using CPU version is recommended. Please refer to the following section for details.**
 
 ~~~python
 from transformers import AutoModelForCausalLM, AutoTokenizer