From e762ad4cc9ae3e6e8e7db5df20c085712b2b3cac Mon Sep 17 00:00:00 2001 From: Yatharth Gupta Date: Sat, 21 Oct 2023 15:31:49 +0000 Subject: [PATCH] Update tokenizer_2/special_tokens_map.json --- tokenizer_2/special_tokens_map.json | 24 +++++++++++++++++++++--- 1 file changed, 21 insertions(+), 3 deletions(-) diff --git a/tokenizer_2/special_tokens_map.json b/tokenizer_2/special_tokens_map.json index 39808ac..ae0c5be 100644 --- a/tokenizer_2/special_tokens_map.json +++ b/tokenizer_2/special_tokens_map.json @@ -1,6 +1,24 @@ { - "bos_token": "<|startoftext|>", - "eos_token": "<|endoftext|>", + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, "pad_token": "!", - "unk_token": "<|endoftext|>" + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } }