data-efficient-training-of-LLMs-v1 / tokenizer_config.json
ChiyuSONG's picture
Upload 23 files
dd2a8ad
raw
history blame contribute delete
954 Bytes
{
"add_bos_token": false,
"add_eos_token": false,
"auto_map": {
"AutoTokenizer": [
"tokenization_baichuan.BaichuanTokenizer",
null
]
},
"bos_token": {
"__type": "AddedToken",
"content": "<s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "</s>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"model_max_length": 4096,
"pad_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
},
"sp_model_kwargs": {},
"tokenizer_class": "BaichuanTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": true
}
}