BactoTiny-Beta / tokenizer.json
EphAsad's picture
Training in progress, step 500
8bd6d8f verified
{
"version": "1.0",
"truncation": {
"direction": "Right",
"max_length": 16,
"strategy": "LongestFirst",
"stride": 0
},
"padding": {
"strategy": {
"Fixed": 16
},
"direction": "Right",
"pad_to_multiple_of": null,
"pad_id": 0,
"pad_type_id": 0,
"pad_token": "[PAD]"
},
"added_tokens": [
{
"id": 0,
"content": "[PAD]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 1,
"content": "[UNK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 2,
"content": "[CLS]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 3,
"content": "[SEP]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
},
{
"id": 4,
"content": "[MASK]",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false,
"special": true
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "Split",
"pattern": {
"String": ""
},
"behavior": "Isolated",
"invert": false
},
"post_processor": {
"type": "TemplateProcessing",
"single": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
}
],
"pair": [
{
"Sequence": {
"id": "A",
"type_id": 0
}
},
{
"Sequence": {
"id": "B",
"type_id": 1
}
}
],
"special_tokens": {}
},
"decoder": null,
"model": {
"type": "WordLevel",
"vocab": {
"[PAD]": 0,
"[UNK]": 1,
"[CLS]": 2,
"[SEP]": 3,
"[MASK]": 4,
"A": 5,
"T": 6,
"G": 7,
"C": 8,
"N": 9
},
"unk_token": "[UNK]"
}
}