tiny-random-LukeForMaskedLM / tokenizer_config.json
hf-transformers-bot's picture
Upload tiny models for LukeForMaskedLM
108a458
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"cls_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"entity_mask2_token": "[MASK2]",
"entity_mask_token": "[MASK]",
"entity_pad_token": "[PAD]",
"entity_token_1": "<ent>",
"entity_token_2": "<ent2>",
"entity_unk_token": "[UNK]",
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"max_entity_length": 32,
"max_mention_length": 30,
"model_max_length": 512,
"pad_token": {
"__type": "AddedToken",
"content": "<pad>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"special_tokens_map_file": "/home/runner/.cache/huggingface/hub/models--studio-ousia--luke-base/snapshots/7438924defd9f3c2018d63c16073bf4bcb6a70aa/special_tokens_map.json",
"task": null,
"tokenizer_class": "LukeTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}