canine-s-wordseg-pl / tokenizer_config.json
Carbon225
init
5d2ee02
{
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"cls_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"mask_token": {
"__type": "AddedToken",
"content": "",
"lstrip": true,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 2048,
"name_or_path": "google/canine-s",
"pad_token": {
"__type": "AddedToken",
"content": "\u0000",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": {
"__type": "AddedToken",
"content": "",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"special_tokens_map_file": "/home/carbon/.cache/huggingface/hub/models--google--canine-s/snapshots/731b77c59a31a88fa2ed1812e88ca214ec2877b8/special_tokens_map.json",
"tokenizer_class": "CanineTokenizer"
}