Update app.py

app.py

@@ -12,8 +12,7 @@ else:
     print("GPU is not available, using CPU.")
 
 # Load the model and config when the script starts
-peft_model_id =
- "phearion/bigbrain-v0.0.1"
+peft_model_id = "phearion/bigbrain-v0.0.1"
 config = PeftConfig.from_pretrained(peft_model_id)
 model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path, return_dict=True)
 tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
@@ -26,7 +25,8 @@ def greet(text):
     batch = tokenizer(f"\"{text}\" ->: ", return_tensors='pt')
     
     # Use torch.no_grad to disable gradient calculation
-    with torch.no_grad():
+    with torch
+.no_grad():
         output_tokens = model.generate(**batch, do_sample=True, max_new_tokens=15
 )