top200mystery / tokenizer_config.json
NekoMikoReimu's picture
Training in progress, epoch 0
8c75eac
raw
history blame
1.37 kB
{
"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
},
"65000": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65001": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65002": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"65003": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "[PAD]",
"tokenizer_class": "GPTNeoXTokenizer",
"trust_remote_code": false,
"unk_token": "<unk>",
"use_fast": true
}