Update README.md

README.md

@@ -74,13 +74,17 @@ The model can also be applied on NLI tasks like so:
 ```python
 import torch
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
 # device = "cuda:0" or "cpu"
 device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
+
 model_name = "mjwong/gte-multilingual-base-xnli"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForSequenceClassification.from_pretrained(model_name, trust_remote_code=True)
+
 premise = "But I thought you'd sworn off coffee."
 hypothesis = "I thought that you vowed to drink more coffee."
+
 input = tokenizer(premise, hypothesis, truncation=True, return_tensors="pt")
 output = model(input["input_ids"].to(device))
 prediction = torch.softmax(output["logits"][0], -1).tolist()