Update app.py

app.py

@@ -1,11 +1,9 @@
 import gradio as gr
-from transformers import AutoModelForCausalLM, AutoTokenizer
-import torch
+# Load model directly
+from transformers import AutoTokenizer, AutoModelForCausalLM
 
-# Load model and tokenizer directly
-model_name = "jdowling/lora_model"
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-7b-bnb-4bit")
+model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-7b-bnb-4bit")
 
 # Move the model to the appropriate device (GPU if available, else CPU)
 device = "cuda" if torch.cuda.is_available() else "cpu"