Update app.py

app.py

@@ -60,35 +60,39 @@ def stream_chat(
     message: str, 
     history: list,
 ):
-    system_prompt = "You are a Kamala Harris chatbot. You only answer like Harris in style and tone."
-    temperature = 0.8
-    max_new_tokens = 1024
-    top_p = 1.0
-    top_k = 20
-    penalty = 1.2
-
+    system_prompt = "You are a Kamala Harris chatbot. You only answer like Harris in style and tone. Provide concise and key responses."
+    temperature = 1.0
+    max_new_tokens = 150
+    top_p = 0.9
+    top_k = 50
+    repetition_penalty = 1.5
+    frequency_penalty = 0.8
+    presence_penalty = 0.8
+    
     conversation = [
         {"role": "system", "content": system_prompt}
     ]
     for prompt, answer in history:
         conversation.extend([
-            {"role": "user", "content": prompt}, 
+            {"role": "user", "content": prompt},
             {"role": "assistant", "content": answer},
         ])
-
     conversation.append({"role": "user", "content": message})
-
+    
     input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
     
     generate_kwargs = dict(
-        input_ids=input_ids, 
+        input_ids=input_ids,
         max_new_tokens=max_new_tokens,
         do_sample=True,
         top_p=top_p,
         top_k=top_k,
         temperature=temperature,
+        repetition_penalty=repetition_penalty,
+        frequency_penalty=frequency_penalty,
+        presence_penalty=presence_penalty,
         eos_token_id=[128001,128008,128009],
         streamer=streamer,
     )