arxyzan's picture
Remove deprecated tokenizer config fields
81f54be verified
raw
history blame contribute delete
426 Bytes
name: bpe_tokenizer
config_type: preprocessor
truncation_side: right
padding_side: right
stride: 0
pad_to_multiple_of: 0
pad_token_type_id: 0
bos_token: <s>
eos_token: </s>
unk_token: <unk>
sep_token: <sep>
pad_token: <pad>
cls_token: <cls>
mask_token: <mask>
continuing_subword_prefix: ''
end_of_word_suffix: ''
fuse_unk: false
vocab_size: 42000
min_frequency: 2
limit_alphabet: 1000
initial_alphabet: []
show_progress: true