rmihaylov commited on
Commit
1a64033
1 Parent(s): 73108aa

add tokenizer

Browse files
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a6b08670ea154bc7d246fea7832e7ccce758a91f1f765dbac1d3ff49ec1f6e
3
+ size 1766104
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": "<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
+ {"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": true, "__type": "AddedToken"}, "max_len": 512, "do_lower_case": true, "special_tokens_map_file": "/content/drive/MyDrive/ColabModels/XROBERTA_SST2_SMALL/pytorch_model/special_tokens_map.json", "name_or_path": "/content/drive/MyDrive/ColabModels/XROBERTA_SST2_SMALL/pytorch_model/", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}