ci-base / tokenizer_config.json
ghosthets's picture
Upload folder using huggingface_hub
ce3668f verified
Raw
History Blame Contribute Delete
845 Bytes
{
"bos_token": "<s>",
"eos_token": "</s>",
"unk_token": "<unk>",
"pad_token": "<pad>",
"cls_token": "<s>",
"sep_token": "</s>",
"mask_token": "<unk>",
"model_max_length": 512,
"tokenizer_class": "PreTrainedTokenizerFast",
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"rstrip": false,
"single_word": false,
"normalized": false
},
"1": {
"content": "<s>",
"lstrip": false,
"rstrip": false,
"single_word": false,
"normalized": false
},
"2": {
"content": "</s>",
"lstrip": false,
"rstrip": false,
"single_word": false,
"normalized": false
},
"3": {
"content": "<unk>",
"lstrip": false,
"rstrip": false,
"single_word": false,
"normalized": false
}
}
}