Upload tokenizer
0729d94
verified
|
|
{ |
|
|
"version": "1.0", |
|
|
"truncation": null, |
|
|
"padding": null, |
|
|
"added_tokens": [ |
|
|
{ |
|
|
"id": 2, |
|
|
"content": "<pad>", |
|
|
"single_word": false, |
|
|
"lstrip": false, |
|
|
"rstrip": false, |
|
|
"normalized": false, |
|
|
"special": true |
|
|
} |
|
|
], |
|
|
"normalizer": null, |
|
|
"pre_tokenizer": { |
|
|
"type": "Whitespace" |
|
|
}, |
|
|
"post_processor": null, |
|
|
"decoder": null, |
|
|
"model": { |
|
|
"type": "WordLevel", |
|
|
"vocab": { |
|
|
"<unk>": 0, |
|
|
"<bos>": 1, |
|
|
"<pad>": 2, |
|
|
":": 3, |
|
|
"S": 4, |
|
|
"P": 5, |
|
|
"C": 6, |
|
|
"A": 7, |
|
|
"I": 8, |
|
|
"0": 9, |
|
|
"1": 10, |
|
|
"2": 11, |
|
|
"3": 12, |
|
|
"4": 13, |
|
|
"5": 14, |
|
|
"6": 15, |
|
|
"7": 16, |
|
|
"8": 17, |
|
|
"9": 18, |
|
|
"10": 19, |
|
|
"11": 20, |
|
|
"12": 21, |
|
|
"13": 22, |
|
|
"14": 23, |
|
|
"15": 24, |
|
|
"16": 25, |
|
|
"17": 26, |
|
|
"18": 27, |
|
|
"19": 28, |
|
|
"20": 29, |
|
|
"21": 30, |
|
|
"22": 31, |
|
|
"23": 32, |
|
|
"24": 33, |
|
|
"25": 34, |
|
|
"26": 35, |
|
|
"27": 36, |
|
|
"28": 37, |
|
|
"29": 38 |
|
|
}, |
|
|
"unk_token": "<unk>" |
|
|
} |
|
|
} |
