Update app.py

app.py

@@ -64,29 +64,25 @@ def stream_chat(
     print(f'message: {message}')
     print(f'history: {history}')
 
-    conversation = [
-        {"role": "system", "content": system_prompt}
-    ]
+    conversation = [system_prompt]
     for prompt, answer in history:
-        conversation.extend([
-            {"role": "user", "content": prompt}, 
-            {"role": "assistant", "content": answer},
-        ])
+        conversation.append(prompt)
+        conversation.append(answer)
 
-    conversation.append({"role": "user", "content": message})
+    conversation.append(message)
 
-    input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, return_tensors="pt").to(model.device)
+    input_ids = tokenizer(conversation, return_tensors="pt").input_ids.to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=60.0, skip_prompt=True, skip_special_tokens=True)
     
     generate_kwargs = dict(
         input_ids=input_ids, 
-        max_new_tokens = max_new_tokens,
-        do_sample = False if temperature == 0 else True,
-        top_p = top_p,
-        top_k = top_k,
-        temperature = temperature,
-        eos_token_id=[128001,128008,128009],
+        max_new_tokens=max_new_tokens,
+        do_sample=False if temperature == 0 else True,
+        top_p=top_p,
+        top_k=top_k,
+        temperature=temperature,
+        eos_token_id=[128001, 128008, 128009],
         streamer=streamer,
     )