{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "[MASK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[SOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 4, "content": "[EOS]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true } ], "normalizer": { "type": "NFKC" }, "pre_tokenizer": { "type": "Metaspace", "replacement": "▁", "prepend_scheme": "always", "split": true }, "post_processor": null, "decoder": { "type": "Metaspace", "replacement": "▁", "prepend_scheme": "always", "split": true }, "model": { "type": "BPE", "dropout": null, "unk_token": "", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "[UNK]": 0, "[PAD]": 1, "[MASK]": 2, "[SOS]": 3, "[EOS]": 4, "!": 5, "I": 6, "a": 7, "c": 8, "d": 9, "e": 10, "g": 11, "h": 12, "l": 13, "m": 14, "n": 15, "o": 16, "r": 17, "v": 18, "w": 19, "▁": 20 }, "merges": [] } }