CT-LLM-Base / tokenizer_config.json
dododododo's picture
Upload tokenizer_config.json with huggingface_hub
6b46874 verified
{
"auto_map": {
"AutoTokenizer": ["tokenization_baichuan.BaichuanTokenizer", null]
},
"add_bos_token": false,
"add_eos_token": false,
"use_fast": false,
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"model_max_length": 4096,
"sp_model_kwargs": {},
"tokenizer_class": "BaichuanTokenizer",
"pad_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"added_tokens_decoder": {
"125696": {
"content": "<|EOD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"125697": {
"content": "<|MASK|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"125698": {
"content": "<|PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|EOD|>",
"<|MASK|>",
"<|PAD|>"
]
}