Do not stream response, by now

app.py

@@ -5,7 +5,7 @@ from threading import Thread
 import torch
 
 MODEL = "m-a-p/OpenCodeInterpreter-DS-33B"
-CHAT_TEMPLATE = "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}\n{% endfor %}\n{% if add_generation_prompt %}\n{{ '<|im_start|>assistant\n' }}\n{% endif %}"
+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"
 
@@ -34,6 +34,15 @@ def translate(python):
     inputs = tokenizer.apply_chat_template(
                         messages_for(python),
                         return_tensors="pt").to(model.device)
+    outputs = model.generate(
+        inputs, 
+        max_new_tokens=1024,
+        do_sample=False,
+        pad_token_id=tokenizer.eos_token_id,
+        eos_token_id=tokenizer.eos_token_id,
+    )
+    return tokenizer.decode(outputs[0][len(inputs[0]):], skip_special_tokens=True)
+    '''
     generation_kwargs = dict(
                             inputs,
                             streamer=streamer,
@@ -48,6 +57,7 @@ def translate(python):
     for chunk in streamer:
         cplusplus += chunk
         yield cplusplus
+    '''
 
 demo = gr.Interface(fn=translate, inputs="code", outputs="markdown")
 demo.launch()