Upload folder using huggingface_hub
Browse files- added_tokens.json +3 -0
- config.json +0 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +54 -0
- tokenizer.json +0 -0
- tokenizer_config.json +67 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"$START": 50265
|
3 |
+
}
|
config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b98b190d31517c4bd8aae7040ac70abed4d862628958b5c859fa1a80debffe29
|
3 |
+
size 1641333743
|
special_tokens_map.json
ADDED
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"$START"
|
4 |
+
],
|
5 |
+
"bos_token": {
|
6 |
+
"content": "[CLS]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"cls_token": {
|
13 |
+
"content": "[CLS]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": true,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false
|
25 |
+
},
|
26 |
+
"mask_token": {
|
27 |
+
"content": "[MASK]",
|
28 |
+
"lstrip": true,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
},
|
33 |
+
"pad_token": {
|
34 |
+
"content": "[PAD]",
|
35 |
+
"lstrip": false,
|
36 |
+
"normalized": true,
|
37 |
+
"rstrip": false,
|
38 |
+
"single_word": false
|
39 |
+
},
|
40 |
+
"sep_token": {
|
41 |
+
"content": "[SEP]",
|
42 |
+
"lstrip": false,
|
43 |
+
"normalized": true,
|
44 |
+
"rstrip": false,
|
45 |
+
"single_word": false
|
46 |
+
},
|
47 |
+
"unk_token": {
|
48 |
+
"content": "[UNK]",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
}
|
54 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": true,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "[CLS]",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "[CLS]",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"do_lower_case": false,
|
21 |
+
"eos_token": {
|
22 |
+
"__type": "AddedToken",
|
23 |
+
"content": "[SEP]",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"errors": "replace",
|
30 |
+
"mask_token": {
|
31 |
+
"__type": "AddedToken",
|
32 |
+
"content": "[MASK]",
|
33 |
+
"lstrip": true,
|
34 |
+
"normalized": true,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
"model_max_length": 512,
|
39 |
+
"name_or_path": "models/stage2/deberta-large/5k/seed12/best",
|
40 |
+
"pad_token": {
|
41 |
+
"__type": "AddedToken",
|
42 |
+
"content": "[PAD]",
|
43 |
+
"lstrip": false,
|
44 |
+
"normalized": true,
|
45 |
+
"rstrip": false,
|
46 |
+
"single_word": false
|
47 |
+
},
|
48 |
+
"sep_token": {
|
49 |
+
"__type": "AddedToken",
|
50 |
+
"content": "[SEP]",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": true,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
},
|
56 |
+
"special_tokens_map_file": null,
|
57 |
+
"tokenizer_class": "DebertaTokenizer",
|
58 |
+
"unk_token": {
|
59 |
+
"__type": "AddedToken",
|
60 |
+
"content": "[UNK]",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": true,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
"vocab_type": "gpt2"
|
67 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|