Update app.py

app.py

@@ -18,7 +18,7 @@ print(f"stage ${current_num}")
 
 api = HfApi(token=hf_token)
 # models = f"dad1909/cybersentinal-2.0-{current_num}"
-model_base = "unsloth/Meta-Llama-3.1-70B-Instruct-bnb-4bit"
+model_base = "unsloth/gemma-2-27b-bnb-4bit"
 
 print("Starting model and tokenizer loading...")
 
@@ -28,8 +28,7 @@ model, tokenizer = FastLanguageModel.from_pretrained(
     max_seq_length=max_seq_length,
     dtype=dtype,
     load_in_4bit=load_in_4bit,
-    token=hf_token,
-    load_in_8bit_fp32_cpu_offload=True,  # Enable CPU offloading
+    token=hf_token
 )
 
 print("Model and tokenizer loaded successfully.")