Update app.py

app.py

@@ -3,12 +3,13 @@ import torch
 from peft import PeftModel
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
+
 # Load tokenizer
-tokenizer = AutoTokenizer.from_pretrained("google/gemma-3-1b-pt")
+tokenizer = AutoTokenizer.from_pretrained("hackergeek98/gemma-finetuned")
 
 # Load base model on CPU with optimizations
 base_model = AutoModelForCausalLM.from_pretrained(
-    "google/gemma-3-1b-pt",
+    "hackergeek98/gemma-finetuned",
     torch_dtype=torch.bfloat16,  # Efficient memory usage
     low_cpu_mem_usage=True
 )