{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "<unk>", "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": { "type": "NFD" }, "pre_tokenizer": { "type": "Whitespace" }, "post_processor": null, "decoder": null, "model": { "type": "BPE", "dropout": null, "unk_token": null, "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "<pad>": 0, "<s>": 1, "</s>": 2, "<unk>": 3, "<mask>": 4 }, "merges": [] } }