| { |
| "added_tokens_decoder": { |
| "0": { |
| "content": "<s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "1": { |
| "content": "<pad>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "2": { |
| "content": "</s>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "250001": { |
| "content": "<mask>", |
| "lstrip": true, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| }, |
| "3": { |
| "content": "<unk>", |
| "lstrip": false, |
| "normalized": false, |
| "rstrip": false, |
| "single_word": false, |
| "special": true |
| } |
| }, |
| "bos_token": "<s>", |
| "clean_up_tokenization_spaces": true, |
| "cls_token": "<s>", |
| "do_lower_case": true, |
| "eos_token": "</s>", |
| "mask_token": "<mask>", |
| "model_max_length": 512, |
| "name_or_path": "./data/dense/mult-miracl/train/contrast/", |
| "pad_token": "<pad>", |
| "sep_token": "</s>", |
| "special_tokens_map_file": "/content/output/model-distillation-2024-05-16_05-50-35/special_tokens_map.json", |
| "strip_accents": null, |
| "tokenize_chinese_chars": true, |
| "tokenizer_class": "BertTokenizer", |
| "unk_token": "<unk>" |
| } |
|
|
