Update app.py

app.py

@@ -52,14 +52,15 @@ def load_model_in_background():
     global MODEL, TOKENIZER, PIPE, MODEL_LOADING, MODEL_LOADED
     try:
         MODEL_LOADING = True
+        print("Starting model loading...")
         
         # Model identifier
         model_id = "mistralai/Mistral-7B-Instruct-v0.3"
         
-        # Load tokenizer
+        print("Loading tokenizer...")
         TOKENIZER = AutoTokenizer.from_pretrained(model_id)
         
-        # Configure model loading (with lower precision for efficiency)
+        print("Loading model (this may take several minutes)...")
         MODEL = AutoModelForCausalLM.from_pretrained(
             model_id,
             torch_dtype=torch.float16,
@@ -67,7 +68,7 @@ def load_model_in_background():
             low_cpu_mem_usage=True
         )
         
-        # Create text generation pipeline
+        print("Creating pipeline...")
         PIPE = pipeline(
             "text-generation",
             model=MODEL,
@@ -77,9 +78,11 @@ def load_model_in_background():
         
         MODEL_LOADING = False
         MODEL_LOADED = True
+        print("Model loaded successfully!")
         return "Model loaded successfully!"
     except Exception as e:
         MODEL_LOADING = False
+        print(f"Error loading model: {str(e)}")
         return f"Error loading model: {str(e)}"
 
 # Function to generate response using the model