Update app.py

app.py

@@ -2,8 +2,8 @@ import gradio as gr
 # Load model directly
 from transformers import AutoTokenizer, AutoModelForCausalLM
 
-tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-7b-bnb-4bit")
-model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-7b-bnb-4bit")
+tokenizer = AutoTokenizer.from_pretrained("unsloth/Llama-3.2-1B")
+model = AutoModelForCausalLM.from_pretrained("unsloth/Llama-3.2-1B")
 
 # Move the model to the appropriate device (GPU if available, else CPU)
 device = "cuda" if torch.cuda.is_available() else "cpu"