Update README.md

README.md

@@ -132,12 +132,14 @@ export use_triton=False
 
 ### Demonstration of Base Model Inference
 
+**📝Note** Kindly utilize the model employing `bfloat16` instead of `float16`.
+
 ```python
 >>> from transformers import AutoModelForCausalLM, AutoTokenizer
->>> tokenizer = AutoTokenizer.from_pretrained("OpenNLPLab/TransNormerLLM-1B", trust_remote_code=True)
->>> model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-1B", device_map="auto", trust_remote_code=True)
+>>> tokenizer = AutoTokenizer.from_pretrained("OpenNLPLab/TransNormerLLM-7B", trust_remote_code=True)
+>>> model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM-7B", torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True)
 >>> inputs = tokenizer('今天是美好的一天', return_tensors='pt')
->>> pred = model.generate(**inputs, max_new_tokens=2048, repetition_penalty=1.0)
+>>> pred = model.generate(**inputs, max_new_tokens=4096, repetition_penalty=1.0)
 >>> print(tokenizer.decode(pred.cpu()[0], skip_special_tokens=True))
 ```