Update app.py

app.py

@@ -11,7 +11,8 @@ bnb_config = BitsAndBytesConfig(
             load_in_4bit=True,
             bnb_4bit_use_double_quant=True,
             bnb_4bit_quant_type="nf4",
-            bnb_4bit_compute_dtype=torch.bfloat16
+            bnb_4bit_compute_dtype=torch
+.bfloat16
         )
 
 # Load models and tokenizer efficiently
@@ -19,9 +20,6 @@ config = PeftConfig.from_pretrained("phearion/bigbrain-v0.0.1")
 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)
-
 def greet(text):
     with torch.no_grad():  # Disable gradient calculation for inference
         batch = tokenizer(f'"{text}" ->:', return_tensors='pt')  # Move tensors to device