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("CohereForAI/c4ai-command-r-v01")
-model = AutoModelForCausalLM.from_pretrained("CohereForAI/c4ai-command-r-v01")
+tokenizer = AutoTokenizer.from_pretrained("CohereForAI/c4ai-command-r-v01-4bit")
+model = AutoModelForCausalLM.from_pretrained("CohereForAI/c4ai-command-r-v01-4bit")
 
 # using CUDA for an optimal experience
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')