use chat template

app.py

@@ -5,6 +5,7 @@ from threading import Thread
 import torch
 
 MODEL = "m-a-p/OpenCodeInterpreter-DS-33B"
+CHAT_TEMPLATE = "{%- set found_item = false -%}\n{%- for message in messages -%}\n    {%- if message['role'] == 'system' -%}\n        {%- set found_item = true -%}\n    {%- endif -%}\n{%- endfor -%}\n{%- if not found_item -%}\n{{'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'}}\n{%- endif %}\n{%- for message in messages %}\n    {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n    {%- else %}\n        {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n        {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{{'### Response:\\n'}}\n"
 
 system_message = "You are a computer programmer that can translate python code to C++ in order to improve performance"
 
@@ -20,19 +21,6 @@ def messages_for(python):
         {"role": "user", "content": user_prompt_for(python)}
     ]
 
-def apply_chat_template(messages):
-    result = ""
-    for message in messages:
-        if message['role'] == 'system':
-            result += f"{message['content']}\n"
-        elif message['role'] == 'user':
-            result += f"### Instruction:\n{message['content']}\n"
-        else:
-            result += f"### Response:\n{message['content']}\n<|EOT|>\n"
-
-    return result
-
-
 tokenizer = AutoTokenizer.from_pretrained(MODEL)
 model = AutoModelForCausalLM.from_pretrained(MODEL, torch_dtype=torch.bfloat16, device_map="auto")
 model.eval()
@@ -42,7 +30,10 @@ streamer = TextIteratorStreamer(tokenizer, decode_kwargs=decode_kwargs)
 
 cplusplus = None
 def translate(python):
-    inputs = tokenizer(apply_chat_template(messages_for(python)), return_tensors="pt").to(model.device)
+    inputs = tokenizer.apply_chat_template(
+                        messages_for(python),
+                        chat_template=CHAT_TEMPLATE,
+                        return_tensors="pt").to(model.device)
     generation_kwargs = dict(
                             inputs,
                             streamer=streamer,