From ca32832c44abf0e1b6c5247b6a07a69d9b1037bc Mon Sep 17 00:00:00 2001 From: Jonathan Tow Date: Fri, 19 Jan 2024 22:52:04 +0000 Subject: [PATCH] fix: add default special tokens --- tokenizer_config.json | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tokenizer_config.json b/tokenizer_config.json index e0422ac..9f65345 100644 --- a/tokenizer_config.json +++ b/tokenizer_config.json @@ -5,5 +5,8 @@ "tokenization_arcade100k.Arcade100kTokenizer", null ] - } + }, + "bos_token": "<|endoftext|>", + "eos_token": "<|endoftext|>", + "pad_token": "<|endoftext|>" } \ No newline at end of file