G-Transformer / tokenizer.json
Syamsuddin's picture
Upload 14 files
a0d6ae6 verified
{
"version": "1.0",
"truncation": {
"max_length": 65536,
"strategy": "longest_first",
"direction": "right"
},
"padding": {
"strategy": "right",
"pad_id": 0,
"pad_token": "<pad>"
},
"added_tokens": [
{"id": 0, "content": "<pad>", "single_word": false, "special": true},
{"id": 1, "content": "<bos>", "single_word": false, "special": true},
{"id": 2, "content": "<eos>", "single_word": false, "special": true}
],
"normalizer": {
"type": "NFKC"
},
"pre_tokenizer": {
"type": "Whitespace"
},
"post_processor": {
"type": "TemplateProcessing",
"single": "<bos> $A <eos>",
"pair": "<bos> $A <eos> $B <eos>",
"special_tokens": {
"<bos>": 1,
"<eos>": 2
}
},
"decoder": {
"type": "WordPiece",
"prefix": "##"
},
"model": {
"type": "BPE",
"vocab": {
"<pad>": 0,
"<bos>": 1,
"<eos>": 2,
"the": 3,
"of": 4,
"to": 5,
"and": 6,
"I": 7,
"you": 8
},
"merges": [
"t h",
"th e",
"a n",
"a nd",
"i n",
"i ng"
]
}
}