add tokenizer
Browse files- sentencepiece.bpe.model +2 -2
- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
sentencepiece.bpe.model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
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:
|
3 |
-
size
|
|
|
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"}, "
|
|
|
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"}
|