HuatuoGPT2-34B-8bits / tokenizer_config.json
jymcc's picture
init
d0edc11
{
"add_bos_token": false,
"add_eos_token": false,
"auto_map": {
"AutoTokenizer": [
"tokenization_yi.YiTokenizer",
null
]
},
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": false,
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"model_max_length": 4096,
"pad_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"padding_side": "left",
"sp_model_kwargs": {},
"tokenizer_class": "YiTokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}