Upload 7 files
Browse files- added_tokens.json +7 -0
- config.json +0 -1
- pytorch_model.bin +2 -2
- special_tokens_map.json +1 -7
- tokenizer_config.json +44 -8
added_tokens.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<mask>": 64001,
|
4 |
+
"<pad>": 1,
|
5 |
+
"<s>": 0,
|
6 |
+
"<unk>": 3
|
7 |
+
}
|
config.json
CHANGED
@@ -6,7 +6,6 @@
|
|
6 |
],
|
7 |
"attention_dropout": 0.0,
|
8 |
"deepnorm": false,
|
9 |
-
"drop_path_rate": 0.1,
|
10 |
"dropout": 0.0,
|
11 |
"embed_dim": 768,
|
12 |
"encoder_normalize_before": true,
|
|
|
6 |
],
|
7 |
"attention_dropout": 0.0,
|
8 |
"deepnorm": false,
|
|
|
9 |
"dropout": 0.0,
|
10 |
"embed_dim": 768,
|
11 |
"encoder_normalize_before": true,
|
pytorch_model.bin
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 sha256:73eb95e8a5f4c30a014db6fdd33b47d154c5e665ff245dac6853ad57f2309d37
|
3 |
+
size 903044889
|
special_tokens_map.json
CHANGED
@@ -2,13 +2,7 @@
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
5 |
-
"mask_token":
|
6 |
-
"content": "<mask>",
|
7 |
-
"lstrip": true,
|
8 |
-
"normalized": true,
|
9 |
-
"rstrip": false,
|
10 |
-
"single_word": false
|
11 |
-
},
|
12 |
"pad_token": "<pad>",
|
13 |
"sep_token": "</s>",
|
14 |
"unk_token": "<unk>"
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"cls_token": "<s>",
|
4 |
"eos_token": "</s>",
|
5 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
"pad_token": "<pad>",
|
7 |
"sep_token": "</s>",
|
8 |
"unk_token": "<unk>"
|
tokenizer_config.json
CHANGED
@@ -1,16 +1,52 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": "<s>",
|
3 |
"clean_up_tokenization_spaces": true,
|
4 |
"cls_token": "<s>",
|
5 |
"eos_token": "</s>",
|
6 |
-
"mask_token":
|
7 |
-
"__type": "AddedToken",
|
8 |
-
"content": "<mask>",
|
9 |
-
"lstrip": true,
|
10 |
-
"normalized": true,
|
11 |
-
"rstrip": false,
|
12 |
-
"single_word": false
|
13 |
-
},
|
14 |
"model_max_length": 1000000000000000019884624838656,
|
15 |
"pad_token": "<pad>",
|
16 |
"sep_token": "</s>",
|
|
|
1 |
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"64001": {
|
36 |
+
"content": "<mask>",
|
37 |
+
"lstrip": true,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [],
|
45 |
"bos_token": "<s>",
|
46 |
"clean_up_tokenization_spaces": true,
|
47 |
"cls_token": "<s>",
|
48 |
"eos_token": "</s>",
|
49 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
"model_max_length": 1000000000000000019884624838656,
|
51 |
"pad_token": "<pad>",
|
52 |
"sep_token": "</s>",
|