GPT-Neo-75m / tokenizer_config.json
nikitastheo's picture
submit
af8e6bd verified
raw
history blame contribute delete
612 Bytes
{
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 512,
"pad_token": "<|endoftext|>",
"tokenizer_class": "PreTrainedTokenizerFast",
"unk_token": "[UNK]"
}