TinyLlama-Czech-Poet / tokenizer_config.json
jinymusim's picture
Newer Model
60a5268 verified
raw
history blame contribute delete
No virus
932 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64000": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "[EOS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"eos_token": "[EOS]",
"max_length": 2048,
"model_max_length": 2048,
"pad_to_multiple_of": null,
"pad_token": "[EOS]",
"pad_token_type_id": 0,
"padding_side": "right",
"stride": 0,
"tokenizer_class": "PreTrainedTokenizerFast",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}