imamnurby commited on
Commit
1936ed6
1 Parent(s): 3740009

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>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "add_prefix_space": false, "trim_offsets": true, "model_max_length": 512, "special_tokens_map_file": "/root/.cache/huggingface/transformers/4da22fec5578ecec5fbe32b80d5a43c6fb66b0f6ad5e359979463f0722ac3b5f.0dc5b1041f62041ebbd23b1297f2f573769d5c97d8b7c28180ec86b8f6185aa8", "name_or_path": "microsoft/codebert-base", "tokenizer_class": "RobertaTokenizer"}
vocab.json ADDED
The diff for this file is too large to render. See raw diff