tokenizer_config.json

{
    "tokenizer_class": "GPT2TokenizerFast",
    "eos_token": {
        "content": "<EOS>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": false,
        "__type": "AddedToken"
    },
    "unk_token": {
        "content": "<UNK>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": false,
        "__type": "AddedToken"
    },
    "pad_token": {
        "content": "<PAD>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": false,
        "__type": "AddedToken"
    },
    "bos_token": {
        "content": "<EOS>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": false,
        "__type": "AddedToken"
    },
    "sep_token": {
        "content": "<SEP>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": false,
        "__type": "AddedToken"
    },
    "mask_token": {
        "content": "<MASK>",
        "single_word": false,
        "lstrip": false,
        "rstrip": false,
        "normalized": false,
        "__type": "AddedToken"
    },
    "model_max_length": 2048
}