Update app.py

app.py

@@ -2,10 +2,13 @@ import gradio as gr
 from ctransformers import AutoModelForCausalLM
 import time
 
-# Load the quantized GGUF model (optimized for CPU)
+# 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-13B-GGUF",  # You can change to CodeLlama, Phind, etc.
-    model_file="wizardcoder-python-13b.Q4_K_M.gguf",  # Use Q4_K_M for 16GB RAM
+    "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
     model_type="llama",
     config={
         "max_new_tokens": 512,