Update app.py

app.py

@@ -5,18 +5,27 @@ import torch
 MODEL_NAME = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 
 # Load tokenizer and model
+print("Loading tokenizer...")
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+print("Tokenizer loaded.")
+
 if tokenizer.pad_token is None:
     tokenizer.pad_token = tokenizer.eos_token
 
+print("Loading model...")
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32
 )
+print("Model loaded.")
+
 if torch.cuda.is_available():
+    print("Moving model to GPU...")
     model.to("cuda")
 model.eval()
 
+print("Model ready.")
+
 def generate_text(prompt, max_new_tokens=100, temperature=0.7, top_k=50):
     if not prompt:
         return "Please enter a prompt."