Update main.py

main.py

@@ -30,6 +30,7 @@ def generater(message, history, temperature, top_p, top_k):
         prompt += model.config["promptTemplate"].format(user_message)
         prompt += assistant_message + "</s>"
     prompt += model.config["promptTemplate"].format(message)
+    print("[prompt]",prompt)
     outputs = []    
     for token in model.generate(prompt=prompt, temp=temperature, top_k = top_k, top_p = top_p, max_tokens = max_new_tokens, streaming=True):
         outputs.append(token)
@@ -58,6 +59,7 @@ def generate_text(
     temperature = body.get("temperature", 0.5)
     top_p = body.get("top_p", 0.95)
     top_k = body.get("top_k", 40)
+    print("[request details]",message, temperature, top_p, top_k)
     # max_new_tokens = body.get("max_new_tokens",512)
     # repetition_penalty = body.get("repetition_penalty", 1.0)
     history = []  # You might need to handle this based on your actual usage