dkleczek commited on
Commit
b1fca3e
1 Parent(s): 034362e

add tokenizer

Browse files
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>"}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "sep_token": "</s>", "do_lowercase_and_remove_accent": false, "bos_token": "<s>", "additional_special_tokens": [], "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/7e8fe8852a1ff7e03195cb41fac16af837f8c14a34a61850b02a7395eb294f00.b8e113717eb1828d09e47de853cf49c8fad05ebdce24df2614cd942dc23e2a77", "name_or_path": "allegro/herbert-large-cased", "lang2id": null, "id2lang": null, "tokenizer_file": null, "tokenizer_class": "HerbertTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff