update readme

README.md

@@ -53,7 +53,7 @@ from transformers import AutoTokenizer, AutoModelForCausalLM
 
 # Load the model and tokenizer
 tokenizer = AutoTokenizer.from_pretrained("premai-io/prem-1B-chat")
-model = AutoModelForCausalLM.from_pretrained('premai-io/prem-1B-chat')
+model = AutoModelForCausalLM.from_pretrained('premai-io/prem-1B-chat', torch_dtype=torch.bfloat16)
 model = model.to('cuda')
 
 # Setup terminators