kogpt-j-base / tokenizer_config.json
heegyu's picture
gpt-j로 config 생성, 51.2k tokenizer 학습해서 추가
8ec9cce
raw
history blame
736 Bytes
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"name_or_path": "models/tokenizer-51k",
"pad_token": null,
"special_tokens_map_file": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}