ROOK-CLF-9m / tokenizer.json
jrahn's picture
Upload TextClassificationPipeline
05d5902 verified
raw
history blame contribute delete
No virus
1.63 kB
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 32,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 33,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 34,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 35,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": null,
"post_processor": null,
"decoder": null,
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"byte_fallback": false,
"ignore_merges": false,
"vocab": {
"-": 0,
".": 1,
"0": 2,
"1": 3,
"2": 4,
"3": 5,
"4": 6,
"5": 7,
"6": 8,
"7": 9,
"8": 10,
"9": 11,
"B": 12,
"K": 13,
"N": 14,
"P": 15,
"Q": 16,
"R": 17,
"a": 18,
"b": 19,
"c": 20,
"d": 21,
"e": 22,
"f": 23,
"g": 24,
"h": 25,
"k": 26,
"n": 27,
"p": 28,
"q": 29,
"r": 30,
"w": 31
},
"merges": []
}
}