Update app.py

app.py

@@ -47,9 +47,9 @@ def generate(
     conversation.append({"role": "user", "content": message})
 
     input_ids = tokenizer.apply_chat_template(conversation, add_generation_prompt=True, 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.")
+    if input_ids.shape[1] > 4096:
+        input_ids = input_ids[:, -4096:]
+        gr.Warning(f"Trimmed input from conversation as it was longer than {4096} tokens.")
     input_ids = input_ids.to(model.device)
 
     streamer = TextIteratorStreamer(tokenizer, timeout=20.0, skip_prompt=True, skip_special_tokens=True)