unary_bitwise_tokenizer / tokenizer.json
ardauzunoglu's picture
Upload tokenizer
946d53f verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<pad>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "<s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "</s>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "<unk>",
"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": {
"<pad>": 0,
"<s>": 1,
"</s>": 2,
"<unk>": 3,
"0": 4,
"1": 5,
"OP_IDENTITY": 6,
"OP_NOT": 7,
"OP_REVERSE": 8,
"OP_REVERSE_NOT": 9,
"OP_POPCOUNT": 10,
"OP_PARITY": 11,
"OP_LEADING_ZEROS": 12,
"OP_TRAILING_ZEROS": 13,
"OP_MSB": 14,
"EQUALS": 15,
"END": 16,
"OP_LSB": 17,
"OP_UPPER_HALF": 18,
"OP_LOWER_HALF": 19
},
"unk_token": "<unk>"
}
}