progen2-oas / tokenizer.json
hugohrban's picture
Create tokenizer.json
cdc9d7a verified
{
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"special": true,
"content": "<|pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 1,
"special": true,
"content": "<|bos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 2,
"special": true,
"content": "<|eos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"<|pad|>": 0,
"<|bos|>": 1,
"<|eos|>": 2,
"1": 3,
"2": 4,
"A": 5,
"B": 6,
"C": 7,
"D": 8,
"E": 9,
"F": 10,
"G": 11,
"H": 12,
"I": 13,
"K": 14,
"L": 15,
"M": 16,
"N": 17,
"O": 18,
"P": 19,
"Q": 20,
"R": 21,
"S": 22,
"T": 23,
"U": 24,
"V": 25,
"W": 26,
"X": 27,
"Y": 28,
"Z": 29
},
"merges": []
}
}