patrickvonplaten
commited on
Commit
•
a933ea9
1
Parent(s):
49bb9f1
up
Browse files- config.json +2 -1
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
config.json
CHANGED
@@ -22,5 +22,6 @@
|
|
22 |
"transformers_version": "4.11.0.dev0",
|
23 |
"type_vocab_size": 1,
|
24 |
"use_cache": true,
|
25 |
-
"vocab_size": 250880
|
|
|
26 |
}
|
|
|
22 |
"transformers_version": "4.11.0.dev0",
|
23 |
"type_vocab_size": 1,
|
24 |
"use_cache": true,
|
25 |
+
"vocab_size": 250880,
|
26 |
+
"tokenizer_class": "XLMRobertaTokenizer"
|
27 |
}
|
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": "./special_tokens_map.json", "name_or_path": "./", "tokenizer_class": "XLMRobertaTokenizer"}
|