Update app.py

app.py

@@ -5,7 +5,7 @@ import torch
 
 # Device configuration (prioritize GPU if available)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model_id = "phearion/bigbrain-v0.0.1"
+model_id = "phearion/bigbrain-v0.0.2"
 
 bnb_config = BitsAndBytesConfig(
             load_in_4bit=True,
@@ -20,7 +20,7 @@ tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
 model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, quantization_config=bnb_config)
 
 # Load the Lora model
-model = PeftModel.from_pretrained(model, model_id)
+model = PeftModel.from_pretrained(mode, model_id)
 
 def greet(text):
     with torch.no_grad():  # Disable gradient calculation for inference