Update README.md

README.md

@@ -32,24 +32,15 @@ Here give some examples of how to use our model.
 #### Chat Model Inference
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("deepseek-coder-33b-instruct", trust_remote_code=True)
-model = AutoModelForCausalLM.from_pretrained("deepseek-coder-33b-instruct", trust_remote_code=True).cuda()
-system_prompt = "You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer.\n"
+tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained("deepseek-ai/deepseek-coder-33b-instruct", trust_remote_code=True).cuda()
 messages=[
     { 'role': 'user', 'content': "write a quick sort algorithm in python."}
 ]
-prompt = system_prompt
-for content in messages:
-    if content['role'] == 'user':
-        prompt += f"### Instruction:\n{content['content']}\n"
-    else:
-        prompt += f"### Response:\n{content['content']}\n"
-        prompt += "<|EOT|>\n"
-prompt += "### Response:\n"
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to(model.device)
 # 32021 is the id of <|EOT|> token
-outputs = model.generate(**inputs, max_new_tokens=256, do_sample=True, top_k=50, top_p=0.95, num_return_sequences=1, eos_token_id=32021)
-print(tokenizer.decode(outputs[0]))
+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=32021)
+print(tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True))
 ```
 
 ### 4. Lincense