debugging / tokenizer_config.json
bowphs's picture
Training in progress, epoch 1
11ebb06 verified
raw
history blame
748 Bytes
{
"add_bos_token": false,
"add_eos_token": false,
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|padding|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"tokenizer_class": "GPTNeoXTokenizer",
"unk_token": "<|endoftext|>"
}