mm2024-debertav3-M-20240303T203254 / tokenizer_config.json
zach-lamberty's picture
Training in progress, step 15000
0644eb8 verified
raw
history blame
953 Bytes
{
"added_tokens_decoder": {
"764": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"765": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"766": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"767": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"mask_token": "[MASK]",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}