Update app.py

app.py

@@ -5,8 +5,8 @@ from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStr
 from threading import Thread
 
 # Loading the tokenizer and model from Hugging Face's model hub.
-tokenizer = AutoTokenizer.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
-model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.1")
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1")
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')