large_LLMMDLFIND_11_09_2023_0 / tokenizer_config.json
nagupv's picture
Upload tokenizer
fdbf51d
raw
history blame contribute delete
412 Bytes
{
"bos_token": "<s>",
"clean_text": true,
"clean_up_tokenization_spaces": true,
"cls_token": "<cls>",
"do_lower_case": true,
"eos_token": "</s>",
"mask_token": "<mask>",
"model_max_length": 512,
"pad_token": "<pad>",
"sep_token": "<sep>",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "FunnelTokenizer",
"unk_token": "<unk>",
"wordpieces_prefix": "##"
}