PersianLlamaTokenizerFast / tokenizer_config.json
mshojaei77's picture
Upload tokenizer
8781d8e verified
raw
history blame contribute delete
888 Bytes
{
"added_tokens_decoder": {
"128000": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128004": {
"content": "<|finetune_right_pad_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"128009": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|begin_of_text|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|eot_id|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|finetune_right_pad_id|>",
"tokenizer_class": "PreTrainedTokenizer",
"unk_token": null
}