tokenizer_config.json

{
    "add_bos_token": false,
    "add_eos_token": false,
    "additional_special_tokens": [
        "<role>",
        "</role>",
        "<|arithmetic_start|>",
        "<|arithmetic_end|>",
        "<|number_start|>",
        "<|number_end|>"
    ],
    "bos_token": "<|startoftext|>",
    "chat_template": "{% for message in messages %}{% set role = message['role'] | lower %}{% if role == 'user' %}{% set role = 'HUMAN' %}{% endif %}{% set role = role | upper %}{{ '<role>' + role + '</role>' + message['content'].split('</think>')[-1].lstrip('\\n') }}{% endfor %}{% if add_generation_prompt %}{{ '<role>ASSISTANT</role><think>' }}{% endif %}",
	"clean_up_tokenization_spaces": false,
    "cls_token": "[CLS]",
    "eos_token": "<|endoftext|>",
    "gmask_token": "[gMASK]",
    "merges_file": null,
    "model_max_length": 1000000000000000019884624838656,
    "pad_token": "<|endoftext|>",
    "tokenizer_class": "PreTrainedTokenizerFast",
    "trust_remote_code": true,
    "vocab_file": null,
    "fast_tokenizer": true
}