modernlogbert-wce / tokenizer_config.json
hazemkhaled-94's picture
Upload folder using huggingface_hub
13f5bf5 verified
Raw
History Blame Contribute Delete
826 Bytes
{
"backend": "tokenizers",
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"extra_special_tokens": [
"</mnt/sdcard/sandbox/AnyOfficeSDK/sdk/cffb628ad277b3e98d6e9ae9dceca2a7_AnyOfficeSDKMDMResult>",
"</mnt/sdcard/sandbox/AnyOfficeSDK/sdk/e7ace0c2dd803111ba7ffcc997aec59f_AnyOfficeSDKMDMResult>",
"<CLASS_NAME>",
"<COMPOSITE_ID>",
"<ERROR>",
"<HAL>",
"<HEX>",
"<INFO>",
"<IP>",
"<MASKED_INFO>",
"<MCI>",
"<NA>",
"<NUM>",
"<SENSOR>",
"<UUID>",
"<init>"
],
"is_local": false,
"local_files_only": false,
"mask_token": "[MASK]",
"model_input_names": [
"input_ids",
"attention_mask"
],
"model_max_length": 8192,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"tokenizer_class": "TokenizersBackend",
"unk_token": "[UNK]"
}