utf8-lm-tiny / tokenizer_config.json
AmitMY's picture
Upload folder using huggingface_hub
fb6b7fa verified
raw
history blame contribute delete
841 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "\u0000",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "\u0002",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "\u0003",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "\u0002",
"bos_token_id": 2,
"clean_up_tokenization_spaces": false,
"eos_token": "\u0003",
"eos_token_id": 3,
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "\u0000",
"pad_token_id": 0,
"tokenizer_class": "UTF8Tokenizer"
}