Load tokenizer from the repo now that it ships with one

README.md

@@ -91,7 +91,7 @@ from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
 
 name = "Flaglab/ESNLIR-XLM-RoBERTa-premise-only"
-tok = AutoTokenizer.from_pretrained("FacebookAI/xlm-roberta-base")
+tok = AutoTokenizer.from_pretrained(name)
 model = AutoModelForSequenceClassification.from_pretrained(name)
 
 # premise only, by design
@@ -104,8 +104,9 @@ with torch.no_grad():
 print(model.config.id2label[int(logits.argmax(-1))])
 ```
 
-> The tokenizer is not stored in this repository — load it from the base model
-> `FacebookAI/xlm-roberta-base`, as shown above.
+> The tokenizer bundled here is an unmodified copy of the one from
+> [`FacebookAI/xlm-roberta-base`](https://huggingface.co/FacebookAI/xlm-roberta-base); vocabulary size matches this model's
+> embedding table exactly.
 
 ## Citation