Update app.py

app.py

@@ -94,13 +94,13 @@ def generate(
         conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
     conversation.append({"role": "user", "content": message})
 
-    input_ids = tokenizer.apply_chat_template(conversation, return_tensors="pt")
+        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)
+
+    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
     generate_kwargs = dict(
         {"input_ids": input_ids},
         streamer=streamer,
@@ -117,10 +117,9 @@ def generate(
 
     outputs = []
     for text in streamer:
-        processed_text = process_text(text)
-        outputs.append(processed_text)
-        output = "".join(outputs)
-        yield output
+        outputs.append(text)
+        yield "".join(outputs)
+
 
     final_story = "".join(outputs)
     try: