tokenizer_config.json

{
    "added_tokens_decoder": {
        "0": {
            "content": "<pad>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "3": {
            "content": "<unk>",
            "lstrip": false,
            "normalized": true,
            "rstrip": false,
            "single_word": false,
            "special": true
        },
        "5": {
            "content": "<end>",
            "lstrip": false,
            "normalized": false,
            "rstrip": false,
            "single_word": false,
            "special": true
        }
    },
    "bos_token": null,
    "clean_up_tokenization_spaces": false,
    "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<System> ' + system_message + '<end>' }}{% endif %}{% for message in messages %}{% if message['role'] == 'user' %}{{ '<User> ' + message['content'] + '<end><Bot> ' }}{% elif message['role'] == 'assistant' %}{{  message['content'] + '<end>' }}{% endif %}{% endfor %}",
    "do_lower_case": false,
    "eos_token": "<end>",
    "model_max_length": 32768,
    "pad_token": "<pad>",
    "sp_model_kwargs": {},
    "split_by_punct": false,
    "unk_token": "<unk>",
    "auto_map": {
        "AutoTokenizer": [
            "tokenization_spark.SparkTokenizer",
            null
        ]
    }
}