feedlight42
commited on
Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +22 -8
tokenizer_config.json
CHANGED
@@ -1,10 +1,24 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"
|
7 |
-
"
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"mask_token": {
|
8 |
+
"__type": "AddedToken",
|
9 |
+
"content": "<mask>",
|
10 |
+
"lstrip": true,
|
11 |
+
"normalized": true,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"model_max_length": 1024,
|
16 |
+
"pad_token": "<pad>",
|
17 |
+
"sep_token": "</s>",
|
18 |
+
"sp_model_kwargs": {},
|
19 |
+
"src_lang": null,
|
20 |
+
"tgt_lang": null,
|
21 |
+
"tokenizer_class": "MBartTokenizer",
|
22 |
+
"tokenizer_file": null,
|
23 |
+
"unk_token": "<unk>"
|
24 |
}
|