QA_FineTuned_ArabianGPT-03B / tokenizer_config.json
Amr-khaled's picture
Training in progress, step 50
c14cc68 verified
raw
history blame
735 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64000": {
"content": "<EOS>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"64001": {
"content": "<PAD>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": true,
"eos_token": "<EOS>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<EOS>",
"tokenizer_class": "PreTrainedTokenizerFast"
}