from transformers import AutoTokenizer, XLMRobertaXLForMaskedLM
import torch

tokenizer = AutoTokenizer.from_pretrained("xlm-roberta-xlarge")
model = XLMRobertaXLForMaskedLM.from_pretrained("xlm-roberta-xlarge")

inputs = tokenizer("The capital of France is <mask>.", return_tensors="pt")

with torch.no_grad():
    logits = model(**inputs).logits

# retrieve index of <mask>
mask_token_index = (inputs.input_ids == tokenizer.mask_token_id)[0].nonzero(
    as_tuple=True
)[0]

predicted_token_id = logits[0, mask_token_index].argmax(axis=-1)

labels = tokenizer("The capital of France is Paris.", return_tensors="pt")["input_ids"]
# mask labels of non-<mask> tokens
labels = torch.where(inputs.input_ids == tokenizer.mask_token_id, labels, -100)

outputs = model(**inputs, labels=labels)

OSError: xlm-roberta-xlarge is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'
If this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`