Update README.md

add repetition_penalty to inference code

README.md

@@ -49,7 +49,7 @@ tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remo
 model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True)
 inputs = tokenizer('Hamlet->Shakespeare\nOne Hundred Years of Solitude->', return_tensors='pt')
 inputs = inputs.to('cuda:0')
-pred = model.generate(**inputs, max_new_tokens=64)
+pred = model.generate(**inputs, max_new_tokens=64,repetition_penalty=1.1)
 print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
 ```