rmihaylov commited on
Commit
7a8c1ad
1 Parent(s): 015365f

add tokenizer

Browse files
sentencepiece.bpe.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
- size 5069051
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:35a6b08670ea154bc7d246fea7832e7ccce758a91f1f765dbac1d3ff49ec1f6e
3
+ size 1766104
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b44a9d7b51c3c62626640cda0e2c2f70fdacdc25bbbd68038369d14ebdf4c39
3
- size 17082730
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f2ac344124dcca7d127410b59f4dcb3a59d81d55c1582720e0093395978ca6b
3
+ size 6069612
tokenizer_config.json CHANGED
@@ -1 +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"}, "model_max_length": 512, "special_tokens_map_file": "/content/drive/MyDrive/ColabModels/XROBERTA_USE_QA/pytorch_model/special_tokens_map.json", "name_or_path": "/content/tokenizer/", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}
 
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, "special_tokens_map_file": "/content/drive/MyDrive/ColabModels/XROBERTA_USE_QA_THESEUS/pytorch_model/special_tokens_map.json", "name_or_path": "/content/drive/MyDrive/ColabModels/XROBERTA_USE_QA_THESEUS/pytorch_model/", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}