Aleksey Dorkin
commited on
Commit
•
cf42ab7
1
Parent(s):
be8cb29
add model
Browse files- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
sentencepiece.bpe.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef009ae2ede7beded780cfa82e11d2d977473cb6ddf9c3b5bdce3c367497fc01
|
| 3 |
+
size 943862
|
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": true}}
|
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"}, "sp_model_kwargs": {}, "special_tokens_map_file": "/root/.cache/huggingface/transformers/6ea33bfad55f516eeb1e52bb6e3f5c198c976c6ebfaa7e1fb9f56b33b2ddc8a9.f6ac38e94db1fb749ad0f52af2f7cd5b7863b9b30f1aa680a1b0d22ec09b717d", "name_or_path": "DeepPavlov/xlm-roberta-large-en-ru", "tokenizer_class": "XLMRobertaTokenizer"}
|