Update app.py

app.py

@@ -1,4 +1,4 @@
-# app.py (with 1024-character limit)
+# app.py (updated with no `max_chars` and using correct model initialization)
 import gradio as gr
 import torch
 from transformers import AutoTokenizer, AutoModelForCausalLM
@@ -131,7 +131,7 @@ Choose a programming language for more tailored responses. Limited to 1024 chara
 iface = gr.Interface(
     fn=code_assistant,
     inputs=[
-        gr.Textbox(lines=5, placeholder="Ask a coding question or paste your code here...", max_chars=1024),
+        gr.Textbox(lines=5, placeholder="Ask a coding question or paste your code here..."),  # Removed `max_chars`
         gr.Dropdown(choices=["Python", "JavaScript", "Java", "C++", "HTML", "CSS", "SQL", "Other"], label="Programming Language")
     ],
     outputs="text",