Update app.py

app.py

@@ -75,7 +75,7 @@ def calculate_cache_size(cache):
     
 @st.cache_resource
 def load_model_and_tokenizer(doc_text_count):
-    model_name = "mistralai/Mistral-7B-Instruct-v0.1"  # Configure quantization for 4-bit loading
+    model_name = "google/gemma-3-4b-it"  # Configure quantization for 4-bit loading
     quantization_config = BitsAndBytesConfig(
         load_in_4bit=True,  # Enable 4-bit quantization
         bnb_4bit_compute_dtype=torch.float16,  # Set computation precision