diffugpt-s / tokenizer_config.json
Sansa's picture
End of training
ef4bd0c verified
raw
history blame contribute delete
536 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"mask_token": "------------",
"model_max_length": 1024,
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}