Upload 3 files
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +1 -117
- vocab.json +0 -0
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,117 +1 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"50256": {
|
5 |
-
"content": "<|endoftext|>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": true,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"50257": {
|
13 |
-
"content": "<bos>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"50258": {
|
21 |
-
"content": "<eos>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"50259": {
|
29 |
-
"content": "<pad>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"50260": {
|
37 |
-
"content": "<unk>",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
},
|
44 |
-
"50261": {
|
45 |
-
"content": "<sep>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": true
|
51 |
-
},
|
52 |
-
"50262": {
|
53 |
-
"content": "<cls>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
"50263": {
|
61 |
-
"content": "<mask>",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": false,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": true
|
67 |
-
},
|
68 |
-
"50264": {
|
69 |
-
"content": "<greeting>",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": false,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": true
|
75 |
-
},
|
76 |
-
"50265": {
|
77 |
-
"content": "<farewell>",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": false,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": true
|
83 |
-
},
|
84 |
-
"50266": {
|
85 |
-
"content": "<thank>",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": false,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": true
|
91 |
-
},
|
92 |
-
"50267": {
|
93 |
-
"content": "<apology>",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": false,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": true
|
99 |
-
}
|
100 |
-
},
|
101 |
-
"additional_special_tokens": [
|
102 |
-
"<greeting>",
|
103 |
-
"<farewell>",
|
104 |
-
"<thank>",
|
105 |
-
"<apology>"
|
106 |
-
],
|
107 |
-
"bos_token": "<bos>",
|
108 |
-
"clean_up_tokenization_spaces": true,
|
109 |
-
"cls_token": "<cls>",
|
110 |
-
"eos_token": "<eos>",
|
111 |
-
"mask_token": "<mask>",
|
112 |
-
"model_max_length": 1024,
|
113 |
-
"pad_token": "<eos>",
|
114 |
-
"sep_token": "<sep>",
|
115 |
-
"tokenizer_class": "GPT2Tokenizer",
|
116 |
-
"unk_token": "<unk>"
|
117 |
-
}
|
|
|
1 |
+
{"model_max_length": 1024}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|