Upload tokenizer
Browse files- added_tokens.json +69 -0
- merges.txt +0 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +888 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"AnnAssign": 50274,
|
3 |
+
"Assert": 50278,
|
4 |
+
"Assign": 50272,
|
5 |
+
"AsyncFor": 50275,
|
6 |
+
"AsyncFunctionDef": 50270,
|
7 |
+
"AsyncWith": 50276,
|
8 |
+
"AugAssign": 50273,
|
9 |
+
"AugLoad": 50302,
|
10 |
+
"AugStore": 50303,
|
11 |
+
"Await": 50293,
|
12 |
+
"BinOp": 50284,
|
13 |
+
"BitAnd": 50312,
|
14 |
+
"BitOr": 50310,
|
15 |
+
"BitXor": 50311,
|
16 |
+
"BoolOp": 50282,
|
17 |
+
"ClassDef": 50271,
|
18 |
+
"Constant": 50298,
|
19 |
+
"Dict": 50288,
|
20 |
+
"DictComp": 50291,
|
21 |
+
"Eq": 50317,
|
22 |
+
"ExceptHandler": 50325,
|
23 |
+
"Expr": 50281,
|
24 |
+
"Expression": 50266,
|
25 |
+
"ExtSlice": 50305,
|
26 |
+
"FloorDiv": 50313,
|
27 |
+
"FormattedValue": 50296,
|
28 |
+
"FunctionDef": 50269,
|
29 |
+
"FunctionType": 50267,
|
30 |
+
"GeneratorExp": 50292,
|
31 |
+
"Gt": 50320,
|
32 |
+
"GtE": 50321,
|
33 |
+
"IfExp": 50287,
|
34 |
+
"ImportFrom": 50279,
|
35 |
+
"Interactive": 50265,
|
36 |
+
"Invert": 50314,
|
37 |
+
"IsNot": 50322,
|
38 |
+
"JoinedStr": 50297,
|
39 |
+
"LShift": 50308,
|
40 |
+
"Lambda": 50286,
|
41 |
+
"ListComp": 50289,
|
42 |
+
"LtE": 50319,
|
43 |
+
"MatMult": 50306,
|
44 |
+
"NamedExpr": 50283,
|
45 |
+
"Nonlocal": 50280,
|
46 |
+
"NotEq": 50318,
|
47 |
+
"NotIn": 50323,
|
48 |
+
"Pow": 50307,
|
49 |
+
"RShift": 50309,
|
50 |
+
"Raise": 50277,
|
51 |
+
"Reduce": 50330,
|
52 |
+
"Reduce_primitif": 50331,
|
53 |
+
"SetComp": 50290,
|
54 |
+
"Slice": 50304,
|
55 |
+
"Starred": 50300,
|
56 |
+
"Subscript": 50299,
|
57 |
+
"Suite": 50268,
|
58 |
+
"Tuple": 50301,
|
59 |
+
"TypeIgnore": 50329,
|
60 |
+
"UAdd": 50315,
|
61 |
+
"USub": 50316,
|
62 |
+
"UnaryOp": 50285,
|
63 |
+
"Yield": 50294,
|
64 |
+
"YieldFrom": 50295,
|
65 |
+
"arguments": 50326,
|
66 |
+
"comprehension": 50324,
|
67 |
+
"keyword": 50327,
|
68 |
+
"withitem": 50328
|
69 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,888 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "<pad>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "</s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"1106": {
|
37 |
+
"content": "If",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"1121": {
|
45 |
+
"content": "In",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"2409": {
|
53 |
+
"content": "And",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"2709": {
|
61 |
+
"content": "For",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"3908": {
|
69 |
+
"content": "With",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"5384": {
|
77 |
+
"content": "arg",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"5771": {
|
85 |
+
"content": "While",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"6209": {
|
93 |
+
"content": "Is",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"7199": {
|
101 |
+
"content": "Not",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"11094": {
|
109 |
+
"content": "Or",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"18811": {
|
117 |
+
"content": "Global",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"20340": {
|
125 |
+
"content": "Pass",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"20653": {
|
133 |
+
"content": "Call",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"20763": {
|
141 |
+
"content": "Add",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"21502": {
|
149 |
+
"content": "Del",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"23055": {
|
157 |
+
"content": "Sub",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"28512": {
|
165 |
+
"content": "Set",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"30597": {
|
173 |
+
"content": "Mod",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"31723": {
|
181 |
+
"content": "Name",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"36583": {
|
189 |
+
"content": "List",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"37165": {
|
197 |
+
"content": "Div",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"37172": {
|
205 |
+
"content": "Try",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"39539": {
|
213 |
+
"content": "Break",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"40266": {
|
221 |
+
"content": "Store",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"41929": {
|
229 |
+
"content": "Import",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": true,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"42555": {
|
237 |
+
"content": "Return",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": true,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"45105": {
|
245 |
+
"content": "Lt",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": true,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"45287": {
|
253 |
+
"content": "Mult",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"45448": {
|
261 |
+
"content": "Compare",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": true,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"45673": {
|
269 |
+
"content": "Index",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"46006": {
|
277 |
+
"content": "Delete",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"46982": {
|
285 |
+
"content": "Continue",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"47167": {
|
293 |
+
"content": "Load",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"47910": {
|
301 |
+
"content": "alias",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"48348": {
|
309 |
+
"content": "Param",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"48720": {
|
317 |
+
"content": "Module",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": true,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": false
|
323 |
+
},
|
324 |
+
"49385": {
|
325 |
+
"content": "Attribute",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": true,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": false
|
331 |
+
},
|
332 |
+
"50264": {
|
333 |
+
"content": "<mask>",
|
334 |
+
"lstrip": true,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"50265": {
|
341 |
+
"content": "Interactive",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": true,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": false
|
347 |
+
},
|
348 |
+
"50266": {
|
349 |
+
"content": "Expression",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": true,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": false
|
355 |
+
},
|
356 |
+
"50267": {
|
357 |
+
"content": "FunctionType",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": true,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": false
|
363 |
+
},
|
364 |
+
"50268": {
|
365 |
+
"content": "Suite",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": true,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": false
|
371 |
+
},
|
372 |
+
"50269": {
|
373 |
+
"content": "FunctionDef",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": true,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": false
|
379 |
+
},
|
380 |
+
"50270": {
|
381 |
+
"content": "AsyncFunctionDef",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": true,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": false
|
387 |
+
},
|
388 |
+
"50271": {
|
389 |
+
"content": "ClassDef",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": true,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": false
|
395 |
+
},
|
396 |
+
"50272": {
|
397 |
+
"content": "Assign",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": true,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": false
|
403 |
+
},
|
404 |
+
"50273": {
|
405 |
+
"content": "AugAssign",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": true,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": false
|
411 |
+
},
|
412 |
+
"50274": {
|
413 |
+
"content": "AnnAssign",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": true,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": false
|
419 |
+
},
|
420 |
+
"50275": {
|
421 |
+
"content": "AsyncFor",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": true,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": false
|
427 |
+
},
|
428 |
+
"50276": {
|
429 |
+
"content": "AsyncWith",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": true,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": false
|
435 |
+
},
|
436 |
+
"50277": {
|
437 |
+
"content": "Raise",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": true,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": false
|
443 |
+
},
|
444 |
+
"50278": {
|
445 |
+
"content": "Assert",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": true,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": false
|
451 |
+
},
|
452 |
+
"50279": {
|
453 |
+
"content": "ImportFrom",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": true,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": false
|
459 |
+
},
|
460 |
+
"50280": {
|
461 |
+
"content": "Nonlocal",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": true,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": false
|
467 |
+
},
|
468 |
+
"50281": {
|
469 |
+
"content": "Expr",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": true,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": false
|
475 |
+
},
|
476 |
+
"50282": {
|
477 |
+
"content": "BoolOp",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": true,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": false
|
483 |
+
},
|
484 |
+
"50283": {
|
485 |
+
"content": "NamedExpr",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": true,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": false
|
491 |
+
},
|
492 |
+
"50284": {
|
493 |
+
"content": "BinOp",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": true,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": false
|
499 |
+
},
|
500 |
+
"50285": {
|
501 |
+
"content": "UnaryOp",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": true,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": false
|
507 |
+
},
|
508 |
+
"50286": {
|
509 |
+
"content": "Lambda",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": true,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": false
|
515 |
+
},
|
516 |
+
"50287": {
|
517 |
+
"content": "IfExp",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": true,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": false
|
523 |
+
},
|
524 |
+
"50288": {
|
525 |
+
"content": "Dict",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": true,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": false
|
531 |
+
},
|
532 |
+
"50289": {
|
533 |
+
"content": "ListComp",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": true,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": false
|
539 |
+
},
|
540 |
+
"50290": {
|
541 |
+
"content": "SetComp",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": true,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": false
|
547 |
+
},
|
548 |
+
"50291": {
|
549 |
+
"content": "DictComp",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": true,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": false
|
555 |
+
},
|
556 |
+
"50292": {
|
557 |
+
"content": "GeneratorExp",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": true,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": false
|
563 |
+
},
|
564 |
+
"50293": {
|
565 |
+
"content": "Await",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": true,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": false
|
571 |
+
},
|
572 |
+
"50294": {
|
573 |
+
"content": "Yield",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": true,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": false
|
579 |
+
},
|
580 |
+
"50295": {
|
581 |
+
"content": "YieldFrom",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": true,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": false
|
587 |
+
},
|
588 |
+
"50296": {
|
589 |
+
"content": "FormattedValue",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": true,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": false
|
595 |
+
},
|
596 |
+
"50297": {
|
597 |
+
"content": "JoinedStr",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": true,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": false
|
603 |
+
},
|
604 |
+
"50298": {
|
605 |
+
"content": "Constant",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": true,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": false
|
611 |
+
},
|
612 |
+
"50299": {
|
613 |
+
"content": "Subscript",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": true,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": false
|
619 |
+
},
|
620 |
+
"50300": {
|
621 |
+
"content": "Starred",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": true,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": false
|
627 |
+
},
|
628 |
+
"50301": {
|
629 |
+
"content": "Tuple",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": true,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": false
|
635 |
+
},
|
636 |
+
"50302": {
|
637 |
+
"content": "AugLoad",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": true,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": false
|
643 |
+
},
|
644 |
+
"50303": {
|
645 |
+
"content": "AugStore",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": true,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": false
|
651 |
+
},
|
652 |
+
"50304": {
|
653 |
+
"content": "Slice",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": true,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": false
|
659 |
+
},
|
660 |
+
"50305": {
|
661 |
+
"content": "ExtSlice",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": true,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": false
|
667 |
+
},
|
668 |
+
"50306": {
|
669 |
+
"content": "MatMult",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": true,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": false
|
675 |
+
},
|
676 |
+
"50307": {
|
677 |
+
"content": "Pow",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": true,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": false
|
683 |
+
},
|
684 |
+
"50308": {
|
685 |
+
"content": "LShift",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": true,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": false
|
691 |
+
},
|
692 |
+
"50309": {
|
693 |
+
"content": "RShift",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": true,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": false
|
699 |
+
},
|
700 |
+
"50310": {
|
701 |
+
"content": "BitOr",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": true,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": false
|
707 |
+
},
|
708 |
+
"50311": {
|
709 |
+
"content": "BitXor",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": true,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": false
|
715 |
+
},
|
716 |
+
"50312": {
|
717 |
+
"content": "BitAnd",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": true,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": false
|
723 |
+
},
|
724 |
+
"50313": {
|
725 |
+
"content": "FloorDiv",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": true,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": false
|
731 |
+
},
|
732 |
+
"50314": {
|
733 |
+
"content": "Invert",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": true,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": false
|
739 |
+
},
|
740 |
+
"50315": {
|
741 |
+
"content": "UAdd",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": true,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": false
|
747 |
+
},
|
748 |
+
"50316": {
|
749 |
+
"content": "USub",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": true,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": false
|
755 |
+
},
|
756 |
+
"50317": {
|
757 |
+
"content": "Eq",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": true,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": false
|
763 |
+
},
|
764 |
+
"50318": {
|
765 |
+
"content": "NotEq",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": true,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": false
|
771 |
+
},
|
772 |
+
"50319": {
|
773 |
+
"content": "LtE",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": true,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": false
|
779 |
+
},
|
780 |
+
"50320": {
|
781 |
+
"content": "Gt",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": true,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": false
|
787 |
+
},
|
788 |
+
"50321": {
|
789 |
+
"content": "GtE",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": true,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": false
|
795 |
+
},
|
796 |
+
"50322": {
|
797 |
+
"content": "IsNot",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": true,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": false
|
803 |
+
},
|
804 |
+
"50323": {
|
805 |
+
"content": "NotIn",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": true,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": false
|
811 |
+
},
|
812 |
+
"50324": {
|
813 |
+
"content": "comprehension",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": true,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": false
|
819 |
+
},
|
820 |
+
"50325": {
|
821 |
+
"content": "ExceptHandler",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": true,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": false
|
827 |
+
},
|
828 |
+
"50326": {
|
829 |
+
"content": "arguments",
|
830 |
+
"lstrip": false,
|
831 |
+
"normalized": true,
|
832 |
+
"rstrip": false,
|
833 |
+
"single_word": false,
|
834 |
+
"special": false
|
835 |
+
},
|
836 |
+
"50327": {
|
837 |
+
"content": "keyword",
|
838 |
+
"lstrip": false,
|
839 |
+
"normalized": true,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false,
|
842 |
+
"special": false
|
843 |
+
},
|
844 |
+
"50328": {
|
845 |
+
"content": "withitem",
|
846 |
+
"lstrip": false,
|
847 |
+
"normalized": true,
|
848 |
+
"rstrip": false,
|
849 |
+
"single_word": false,
|
850 |
+
"special": false
|
851 |
+
},
|
852 |
+
"50329": {
|
853 |
+
"content": "TypeIgnore",
|
854 |
+
"lstrip": false,
|
855 |
+
"normalized": true,
|
856 |
+
"rstrip": false,
|
857 |
+
"single_word": false,
|
858 |
+
"special": false
|
859 |
+
},
|
860 |
+
"50330": {
|
861 |
+
"content": "Reduce",
|
862 |
+
"lstrip": false,
|
863 |
+
"normalized": true,
|
864 |
+
"rstrip": false,
|
865 |
+
"single_word": false,
|
866 |
+
"special": false
|
867 |
+
},
|
868 |
+
"50331": {
|
869 |
+
"content": "Reduce_primitif",
|
870 |
+
"lstrip": false,
|
871 |
+
"normalized": true,
|
872 |
+
"rstrip": false,
|
873 |
+
"single_word": false,
|
874 |
+
"special": false
|
875 |
+
}
|
876 |
+
},
|
877 |
+
"bos_token": "<s>",
|
878 |
+
"clean_up_tokenization_spaces": true,
|
879 |
+
"cls_token": "<s>",
|
880 |
+
"eos_token": "</s>",
|
881 |
+
"errors": "replace",
|
882 |
+
"mask_token": "<mask>",
|
883 |
+
"model_max_length": 512,
|
884 |
+
"pad_token": "<pad>",
|
885 |
+
"sep_token": "</s>",
|
886 |
+
"tokenizer_class": "RobertaTokenizer",
|
887 |
+
"unk_token": "<unk>"
|
888 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|