{
    "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": "<|im_start|>",
            "single_word": false,
            "lstrip": false,
            "rstrip": false,
            "normalized": false,
            "special": true
        },
        {
            "id": 3,
            "content": "<|im_sep|>",
            "single_word": false,
            "lstrip": false,
            "rstrip": false,
            "normalized": false,
            "special": true
        },
        {
            "id": 4,
            "content": "<|im_end|>",
            "single_word": false,
            "lstrip": false,
            "rstrip": false,
            "normalized": false,
            "special": true
        }
    ],
    "normalizer": null,
    "pre_tokenizer": {
        "type": "ByteLevel",
        "add_prefix_space": true,
        "trim_offsets": true,
        "use_regex": true
    },
    "post_processor": null,
    "decoder": null,
    "model": {
        "type": "BPE",
        "dropout": null,
        "unk_token": "<|unk|>",
        "continuing_subword_prefix": null,
        "end_of_word_suffix": null,
        "fuse_unk": false,
        "byte_fallback": false,
        "ignore_merges": false,
                "vocab": {
            "<|unk|>": 0,
            " ": 1,
            "<|im_start|>": 2,
            "<|im_sep|>": 3,
            "<|im_end|>": 4,
            "!": 5,
            "'": 6,
            ",": 7,
            "I": 8,
            "T": 9,
            "d": 10,
            "e": 11,
            "g": 12,
            "h": 13,
            "i": 14,
            "m": 15,
            "n": 16,
            "o": 17,
            "r": 18,
            "s": 19,
            "t": 20,
            "u": 21,
            "y": 22,
            "Ċ": 23,
            "Ġ": 24,
            "hi": 25,
            "ng": 26,
            "re": 27,
            "Ġs": 28
            },
        "merges": [
            [
                "h",
                "i"
            ]
        ]
    }
}