Update main.py

main.py

@@ -6,7 +6,7 @@ from llama_cpp import Llama
 
 # Model loading with specified path and configuration
 llm = Llama(
-    model_path="Meta-Llama-3-8B-Instruct.Q4_K_M.gguf",  # Update the path as necessary
+    model_path="Llama-3.2-3B-Instruct-Q8_0.gguf",  # Update the path as necessary
     n_ctx=4096,       # Maximum number of tokens for context (input + output)
     n_threads=2,      # Number of CPU cores used
 )