Update README.md

update inference case

README.md

@@ -35,9 +35,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True)
-inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->\n', return_tensors='pt')
+inputs = tokenizer('登鹳雀楼->王之涣\n夜雨寄北->', return_tensors='pt')
 inputs = inputs.to('cuda:0')
-pred = model.generate(**inputs, max_new_tokens=512, do_sample=True)
+pred = model.generate(**inputs, max_new_tokens=64)
 print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
 ```
 
@@ -47,9 +47,9 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 
 tokenizer = AutoTokenizer.from_pretrained("baichuan-inc/baichuan-7B", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("baichuan-inc/baichuan-7B", device_map="auto", trust_remote_code=True)
-inputs = tokenizer('Hamlet->Shakespeare\nOne Hundred Years of Solitude->\n', return_tensors='pt')
+inputs = tokenizer('Hamlet->Shakespeare\nOne Hundred Years of Solitude->', return_tensors='pt')
 inputs = inputs.to('cuda:0')
-pred = model.generate(**inputs, max_new_tokens=512, do_sample=True)
+pred = model.generate(**inputs, max_new_tokens=64)
 print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
 ```