wsd_myriade_synth_data_gpt4turbov5 / tokenizer_config.json
gguichard's picture
Training in progress, epoch 1
87a7bba verified
raw
history blame
544 Bytes
{
"additional_special_tokens": [
"<s>NOTUSED",
"</s>NOTUSED"
],
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": "</s>",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sep_token": "</s>",
"sp_model_kwargs": {},
"tokenizer_class": "CamembertTokenizer",
"unk_token": "<unk>"
}