Update app.py

app.py

@@ -89,16 +89,16 @@ def generate(
     else:
         model = editing_model
         tokenizer = editing_tokenizer
+        
     for user, assistant in chat_history:
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
-    conversation.append({"role": "user", "content": make_prompt(message)})
-    # enc = tokenizer(make_prompt(message), return_tensors="pt", padding=True, truncation=True)
-    # input_ids = enc.input_ids.to(model.device)
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+    conversation.append({"role": "user", "content": message})
 
+    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
     if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
         input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
         gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
+    input_ids = input_ids.to(model.device)
     
     streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=False)
     generate_kwargs = dict(