Safetensors
dododododo's picture
Upload Chinese_tiny_llm-en_105k/tokenizer_config.json with huggingface_hub
2ba9cca verified
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true,
"special": true
},
"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|>"
],
"auto_map": {
"AutoTokenizer": [
"tokenization_baichuan.BaichuanTokenizer",
null
]
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 4096,
"pad_token": "<unk>",
"padding_side": "right",
"sp_model_kwargs": {},
"split_special_tokens": false,
"tokenizer_class": "BaichuanTokenizer",
"unk_token": "<unk>",
"use_fast": false
}