Update app.py

app.py

@@ -2,20 +2,14 @@ import gradio as gr
 from ctransformers import AutoModelForCausalLM
 import time
 
-# Note: If this is a private or gated repo, you need to authenticate with your HF token.
-# You can do this by setting the environment variable HF_HOME or passing token to from_pretrained.
-# For public repos, no extra auth needed.
-
 llm = AutoModelForCausalLM.from_pretrained(
-    "TheBloke/WizardCoder-Python-7B-V1.0-GGUF",  # Updated model name
-    model_file="wizardcoder-python-7b-v1.0.Q4_K_M.gguf",  # Adjust the filename accordingly
+    "TheBloke/WizardCoder-Python-7B-V1.0-GGUF",
+    model_file="wizardcoder-python-7b-v1.0.Q4_K_M.gguf",
     model_type="llama",
-    config={
-        "max_new_tokens": 512,
-        "temperature": 0.7,
-        "top_p": 0.9,
-        "stream": True
-    }
+    max_new_tokens=512,
+    temperature=0.7,
+    top_p=0.9,
+    stream=True
 )
 
 def generate_response(message, history):
@@ -32,7 +26,6 @@ def generate_response(message, history):
         time.sleep(0.01)
         yield history
 
-# Gradio UI
 with gr.Blocks() as demo:
     chatbot = gr.Chatbot()
     msg = gr.Textbox(placeholder="Ask coding questions...", label="Your Message")