mft-random / tokenizer_config.json
alibayram's picture
Add new SentenceTransformer model
58b9c3b verified
raw
history blame contribute delete
918 Bytes
{
"added_tokens_decoder": {
"1": {
"content": "<unknown>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": null,
"auto_map": {
"AutoTokenizer": [
"tokenization_turkish_mft.TurkishMFTTokenizerHF",
null
]
},
"backend": "custom",
"eos_token": "<eos>",
"extra_special_tokens": [],
"is_local": false,
"model_max_length": 2048,
"pad_token": "<pad>",
"tokenizer_class": "TurkishMFTTokenizerHF",
"unk_token": "<unknown>"
}