Jo Kristian Bergum commited on
Commit
85b42e5
1 Parent(s): 4936a42

clean up tokenizer and add [unused0] and [unused1] as special tokens

Browse files
special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
 
 
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "name_or_path": "minilm", "special_tokens_map_file": "/Users/bergum/.cache/huggingface/transformers/3295d833faab1b0a5258c61d5d6ba3db7c2414aca8614a8503c6deb89fc00611.dd8bd9bfd3664b530ea4e645105f557769387b3da9f79bdb55ed556bdd80611d", "tokenizer_file": null}