nlptown commited on
Commit
196af2a
1 Parent(s): 0ffd9e0

add tokenizer

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +1 -0
  3. tokenizer_config.json +1 -0
  4. vocab.json +0 -0
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": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"]}
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "</s>", "mask_token": "<special1>", "additional_special_tokens": ["<special0>", "<special1>", "<special2>", "<special3>", "<special4>", "<special5>", "<special6>", "<special7>", "<special8>", "<special9>"], "lang2id": null, "id2lang": null, "do_lowercase_and_remove_accent": true, "do_lowercase": false, "do_lower_case": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "flaubert/flaubert_small_cased", "tokenizer_class": "FlaubertTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff