From f3db68b382ab6079b9969aad113beb33729094da Mon Sep 17 00:00:00 2001
From: Ankur Goyal <ankur@impira.com>
Date: Thu, 8 Sep 2022 15:12:32 -0700
Subject: [PATCH] Update tokenizer to add_prefix_space by default

---
 tokenizer_config.json | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tokenizer_config.json b/tokenizer_config.json
index 9959cea..da08db1 100644
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -1 +1 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base"}
\ No newline at end of file
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "add_prefix_space": true}