codeparrot-ds / tokenizer.json
DancingIguana's picture
End of training
d898fce
raw
history blame
No virus
2.05 kB
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 128,
"strategy": "LongestFirst",
"stride": 0
},
"padding": null,
"added_tokens": [
{
"id": 0,
"content": "<|endoftext|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true,
"use_regex": true
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": false,
"use_regex": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true,
"use_regex": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"<|endoftext|>": 0,
"#": 1,
"-": 2,
".": 3,
"/": 4,
"0": 5,
"1": 6,
"2": 7,
"3": 8,
"4": 9,
"5": 10,
"6": 11,
"7": 12,
"8": 13,
"9": 14,
"A": 15,
"B": 16,
"C": 17,
"D": 18,
"E": 19,
"F": 20,
"G": 21,
"_": 22,
"c": 23,
"n": 24,
"r": 25,
"Ġ": 26,
"25": 27,
"Ġn": 28,
"Ġc": 29,
"Ġr": 30,
"75": 31,
"12": 32,
"11": 33,
"13": 34,
"17": 35,
"23": 36,
"19": 37,
"24": 38,
"10": 39,
"29": 40,
"35": 41,
"37": 42,
"125": 43,
"375": 44,
"20": 45,
"41": 46,
"53": 47,
"49": 48
},
"merges": [
"2 5",
"Ġ n",
"Ġ c",
"Ġ r",
"7 5",
"1 2",
"1 1",
"1 3",
"1 7",
"2 3",
"1 9",
"2 4",
"1 0",
"2 9",
"3 5",
"3 7",
"1 25",
"3 75",
"2 0",
"4 1",
"5 3",
"4 9"
]
}
}