model_save_subgen / tokenizer_config.json
SilentLearner's picture
Upload 7 files
c9d6ffe
Raw History Blame Contribute Delete
1.1 kB
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": {
"__type": "AddedToken",
"content": "<|startoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"clean_up_tokenization_spaces": true,
"cls_token": "<s>",
"eos_token": {
"__type": "AddedToken",
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"errors": "replace",
"mask_token": {
"__type": "AddedToken",
"content": "<mask>",
"lstrip": true,
"normalized": false,
"rstrip": false,
"single_word": false
},
"model_max_length": 1024,
"pad_token": {
"__type": "AddedToken",
"content": "<|pad|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
},
"sep_token": "</s>",
"tokenizer_class": "GPT2Tokenizer",
"trim_offsets": true,
"unk_token": {
"__type": "AddedToken",
"content": "<unk>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false
}
}