cryptgpt / tokenizer_config.json
diwank's picture
Training in progress, step 12000
471458c verified
raw
history blame
614 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"auto_map": {
"AutoTokenizer": [
"diwank/cryptgpt--tokenizer_utils.CryptGPTTokenizer",
null
]
},
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"max_length": 1024,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"stride": 0,
"tokenizer_class": "CryptGPTTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first"
}