Updated the sample code to avoid warning

README.md

@@ -38,6 +38,7 @@ deepseek-coder-33b-instruct is a 33B parameter model initialized from deepseek-c
 Here give some examples of how to use our model.
 #### Chat Model Inference
 ```python
+import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
 tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-6.7b-instruct", trust_remote_code=True, torch_dtype=torch.bfloat16).cuda()
@@ -46,7 +47,7 @@ messages=[
 ]
 inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
 # tokenizer.eos_token_id is the id of <|EOT|> token
-outputs = model.generate(inputs, max_new_tokens=512, do_sample=False, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
+outputs = model.generate(inputs, max_new_tokens=512, do_sample=True, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=tokenizer.eos_token_id)
 print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
 ```