Update app.py

app.py

@@ -1,8 +1,7 @@
 import gradio as gr
 from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
-import
- torch
+import torch
 
 # Device configuration (prioritize GPU if available)
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
@@ -10,10 +9,14 @@ device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 # Load models and tokenizer efficiently
 config = PeftConfig.from_pretrained("phearion/bigbrain-v0.0.1")
 tokenizer = AutoTokenizer.from_pretrained(config.base_model_name_or_path)
-model = PeftModel.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(config.base_model_name_or_path)
+
+# Load the Lora model
+model = PeftModel.from_pretrained(model, peft_model_id)
 model.to(device)
 
-def greet(text):
+def greet(text
+):
     with torch.no_grad():  # Disable gradient calculation for inference
         batch = tokenizer(text, return_tensors='pt').to(device)  # Move tensors to device
         with torch.cuda.amp.autocast():  # Enable mixed-precision if available