Update app.py

app.py

@@ -8,7 +8,8 @@ from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
 tokenizer = AutoTokenizer.from_pretrained("soketlabs/pragna-1b", token=os.environ.get('HF_TOKEN'))
-model = AutoModelForCausalLM.from_pretrained("soketlabs/pragna-1b-it-v0.1", token=os.environ.get('HF_TOKEN'))
+model = AutoModelForCausalLM.from_pretrained("soketlabs/pragna-1b", token=os.environ.get('HF_TOKEN'))
+model.load_adapter('soketlabs/pragna-1b-it-v0.1', token=os.environ.get('HF_TOKEN'))
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')