tokenizer-test-gn / tokenizer_config.json
loubnabnl's picture
loubnabnl HF Staff
Duplicate from HuggingFaceTB/tokenizer-opengenome2-fwedu
a1d5b43 verified
raw
history blame contribute delete
580 Bytes
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<|endoftext|>"
],
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>",
"vocab_size": 32000
}