kanon-tokenizer / special_tokens_map.json
umarbutler's picture
initial commit
a7568ea verified
{
"bos_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"cls_token": {
"content": "<|startoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "<|hiddenword|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|nothingword|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<|magicword|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}