omnitab-large / tokenizer_config.json
Zhengbao Jiang
set add_prefix_space to false
b00b0ca
raw
history blame
1.63 kB
{
"do_lower_case": false,
"errors": "replace",
"bos_token": {
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"eos_token": {
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"unk_token": {
"content": "<unk>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"sep_token": {
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"cls_token": {
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"pad_token": {
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"mask_token": {
"content": "<mask>",
"single_word": false,
"lstrip": true,
"rstrip": false,
"normalized": true,
"__type": "AddedToken"
},
"add_prefix_space": false,
"max_cell_length": 15,
"model_max_length": 1024,
"special_tokens_map_file": null,
"name_or_path": "neulab/omnitab-large",
"use_fast": true,
"tokenizer_class": "TapexTokenizer"
}