Update README.md

README.md

@@ -10,14 +10,16 @@ This model is an int4 model with group_size 128 and and symmetric quantization o
 
 **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
+Due to limited GPU resources, we have only tested a few prompts on a CPU backend using QBits. If you found this modelnot perform well, **you can explore a quantized model in AWQ format with different hyperparameters generated via AutoRound** which will be uploaded soon
+
+Please follow the license of the original model.
 
 ## How To Use
 
 ### INT4 Inference
 
 ````python
-from transformers import AutoModelForCausalLM, AutoTokenizer,GenerationConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-gptq-inc-preview"
 
@@ -53,7 +55,7 @@ response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
 print(response)
 
 
-## The following result is infercenced on CPU with qbits backend
+## The following result is inferred on CPU with qbits backend
 prompt = "9.11和9.8哪个数字大"  
 
 ##INT4