string-ops-tokenizer / tokenizer.json
ardauzunoglu's picture
Upload string operations tokenizer
f9fb8ba verified
Raw
History Blame Contribute Delete
1.66 kB
{
"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,
"a": 4,
"b": 5,
"c": 6,
"d": 7,
"e": 8,
"f": 9,
"g": 10,
"h": 11,
"i": 12,
"j": 13,
"k": 14,
"EQUALS": 15,
"END": 16,
"l": 17,
"OP_IDENTITY": 18,
"OP_REVERSE": 19,
"OP_ROTATE_LEFT_1": 20,
"OP_ROTATE_RIGHT_1": 21,
"OP_ROTATE_LEFT_2": 22,
"OP_ROTATE_RIGHT_2": 23,
"OP_SWAP_HALVES": 24,
"OP_REVERSE_FIRST_HALF": 25,
"OP_REVERSE_SECOND_HALF": 26,
"OP_REVERSE_EACH_2BLOCK": 27,
"OP_REVERSE_EACH_4BLOCK": 28,
"OP_INTERLEAVE_HALVES": 29
},
"unk_token": "<unk>"
}
}