Updated model name

app.py

@@ -4,7 +4,7 @@ import subprocess
 from llama_cpp import Llama
 
 # Initialize the model
-model = Llama(model_path="QA_Llama31_Quantized_GGUF")
+model = Llama(model_path="QA_llama31_unsloth.Q4_K_M.gguf")
 
 def generate_response(prompt):
     response = model.create_chat_completion(messages=[{"role": "user", "content": prompt}])
@@ -14,7 +14,7 @@ def generate_response(prompt):
 def predict(text):  
     # Call llama.cpp with the input text  
     result = subprocess.run(  
-        ["./llama.cpp/main", "-m", "QA_Llama31_Quantized_GGUF", "-p", text],  
+        ["./llama.cpp/main", "-m", "QA_llama31_unsloth.Q4_K_M.gguf", "-p", text],  
         capture_output=True,  
         text=True  
     )