llm-jp-13b-v2.0 / tokenizer_config.json
hkiyomaru's picture
add tokenizer_config.json
79413dd
raw
history blame contribute delete
529 Bytes
{
"unk_token": "<unk|LLM-jp>",
"bos_token": "<s|LLM-jp>",
"eos_token": "<EOD|LLM-jp>",
"pad_token": "<pad|LLM-jp>",
"cls_token": "<CLS|LLM-jp>",
"sep_token": "<SEP|LLM-jp>",
"eod_token": "<EOD|LLM-jp>",
"mask_token": "<mask|LLM-jp>",
"extra_ids": 0,
"additional_special_tokens": [
"</s|LLM-jp>"
],
"sp_model_kwargs": {},
"model_max_length": 1000000000000000019884624838656,
"clean_up_tokenization_spaces": false,
"special_tokens_map_file": null,
"tokenizer_class": "PreTrainedTokenizerFast"
}