gpt-czech-poet-unicode / tokenizer_config.json
jinymusim's picture
Upload 6 files
3bf0e27 verified
raw
history blame contribute delete
736 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<|EOS|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|PAD|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<|UNK|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"eos_token": "<|EOS|>",
"model_max_length": 1024,
"pad_token": "<|PAD|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "<|UNK|>"
}