Update main.py

main.py

@@ -18,20 +18,14 @@ class Item(BaseModel):
     repetition_penalty: float = 1.0
 
 def format_prompt(message, history):
-    prompt = "<s>"
-    for user_prompt, bot_response in history:
-        prompt += f"[INST] {user_prompt} [/INST]"
-        prompt += f" {bot_response}</s> "
-    prompt += f"[INST] {message} [/INST]"
+    prompt = message
     return prompt
 
 def generate(item: Item):
-    print('Sto partendo con la funzione')
     temperature = float(item.temperature)
     if temperature < 1e-2:
         temperature = 1e-2
     top_p = float(item.top_p)
-    print('kwargs')
     generate_kwargs = dict(
         temperature=temperature,
         max_new_tokens=item.max_new_tokens,
@@ -40,15 +34,12 @@ def generate(item: Item):
         do_sample=True,
         seed=42,
     )
-    print('Formatto il prompt')
     formatted_prompt = format_prompt(f"{item.system_prompt}, {item.prompt}", item.history)
     stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
-    print('Parte lo stream')
     output = ""
 
     for response in stream:
         output += response.token.text
-    print('HO QUASI FINITO')
     return output
 
 @app.post("/generate/")