Update main.py

main.py

@@ -9,10 +9,11 @@ max_new_tokens = 1096,
 threads = 3,
 )
 
-llm = AutoModelForCausalLM.from_pretrained("TheBloke/CodeLlama-7B-Instruct-GGUF", 
-model_file="codellama-7b-instruct.q4_K_M.gguf",                                            
-model_type="codellama", 
-gpu_layers=0)
+llm = AutoModelForCausalLM.from_pretrained("codellama-7b-instruct.q4_K_M.gguf",                                            
+model_type="llama", 
+max_new_tokens = 1096,
+threads = 3,
+)