diff --git a/tokenizer/special_tokens_map.json b/tokenizer/special_tokens_map.json index d073e26..2c2130b 100644 --- a/tokenizer/special_tokens_map.json +++ b/tokenizer/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": "<|endoftext|>", - "unk_token": "<|endoftext|>" + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } }