Upload tokenizer
Browse files- added_tokens.json +13 -0
- merges.txt +0 -0
- special_tokens_map.json +102 -0
- tokenizer.json +0 -0
- tokenizer_config.json +120 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<INPUT_END>": 50265,
|
3 |
+
"<INPUT_START>": 50264,
|
4 |
+
"<INSTR_END>": 50261,
|
5 |
+
"<INSTR_START>": 50259,
|
6 |
+
"<NEXT_INPUT>": 50266,
|
7 |
+
"<NEXT_INSTR>": 50260,
|
8 |
+
"<RECIPE_END>": 50263,
|
9 |
+
"<RECIPE_START>": 50262,
|
10 |
+
"<TITLE_END>": 50258,
|
11 |
+
"<TITLE_START>": 50257,
|
12 |
+
"<pad>": 50267
|
13 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<TITLE_START>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<TITLE_END>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<INSTR_START>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "<NEXT_INSTR>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<INSTR_END>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": false,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "<RECIPE_START>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<RECIPE_END>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "<INPUT_START>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"content": "<INPUT_END>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"content": "<NEXT_INPUT>",
|
68 |
+
"lstrip": false,
|
69 |
+
"normalized": false,
|
70 |
+
"rstrip": false,
|
71 |
+
"single_word": false
|
72 |
+
}
|
73 |
+
],
|
74 |
+
"bos_token": {
|
75 |
+
"content": "<|endoftext|>",
|
76 |
+
"lstrip": false,
|
77 |
+
"normalized": false,
|
78 |
+
"rstrip": false,
|
79 |
+
"single_word": false
|
80 |
+
},
|
81 |
+
"eos_token": {
|
82 |
+
"content": "<|endoftext|>",
|
83 |
+
"lstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"rstrip": false,
|
86 |
+
"single_word": false
|
87 |
+
},
|
88 |
+
"pad_token": {
|
89 |
+
"content": "<pad>",
|
90 |
+
"lstrip": false,
|
91 |
+
"normalized": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"single_word": false
|
94 |
+
},
|
95 |
+
"unk_token": {
|
96 |
+
"content": "<|endoftext|>",
|
97 |
+
"lstrip": false,
|
98 |
+
"normalized": false,
|
99 |
+
"rstrip": false,
|
100 |
+
"single_word": false
|
101 |
+
}
|
102 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": "<TITLE_START>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"50258": {
|
21 |
+
"content": "<TITLE_END>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"50259": {
|
29 |
+
"content": "<INSTR_START>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"50260": {
|
37 |
+
"content": "<NEXT_INSTR>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"50261": {
|
45 |
+
"content": "<INSTR_END>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"50262": {
|
53 |
+
"content": "<RECIPE_START>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"50263": {
|
61 |
+
"content": "<RECIPE_END>",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"50264": {
|
69 |
+
"content": "<INPUT_START>",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"50265": {
|
77 |
+
"content": "<INPUT_END>",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"50266": {
|
85 |
+
"content": "<NEXT_INPUT>",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"50267": {
|
93 |
+
"content": "<pad>",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
}
|
100 |
+
},
|
101 |
+
"additional_special_tokens": [
|
102 |
+
"<TITLE_START>",
|
103 |
+
"<TITLE_END>",
|
104 |
+
"<INSTR_START>",
|
105 |
+
"<NEXT_INSTR>",
|
106 |
+
"<INSTR_END>",
|
107 |
+
"<RECIPE_START>",
|
108 |
+
"<RECIPE_END>",
|
109 |
+
"<INPUT_START>",
|
110 |
+
"<INPUT_END>",
|
111 |
+
"<NEXT_INPUT>"
|
112 |
+
],
|
113 |
+
"bos_token": "<|endoftext|>",
|
114 |
+
"clean_up_tokenization_spaces": true,
|
115 |
+
"eos_token": "<|endoftext|>",
|
116 |
+
"model_max_length": 1024,
|
117 |
+
"pad_token": "<pad>",
|
118 |
+
"tokenizer_class": "GPT2Tokenizer",
|
119 |
+
"unk_token": "<|endoftext|>"
|
120 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|