Upload tokenizer
Browse files- added_tokens.json +103 -0
- special_tokens_map.json +108 -0
- tokenizer.model +3 -0
- tokenizer_config.json +33 -0
added_tokens.json
ADDED
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<end>": 49953,
|
3 |
+
"<unused_token_0>": 49954,
|
4 |
+
"<unused_token_10>": 49964,
|
5 |
+
"<unused_token_11>": 49965,
|
6 |
+
"<unused_token_12>": 49966,
|
7 |
+
"<unused_token_13>": 49967,
|
8 |
+
"<unused_token_14>": 49968,
|
9 |
+
"<unused_token_15>": 49969,
|
10 |
+
"<unused_token_16>": 49970,
|
11 |
+
"<unused_token_17>": 49971,
|
12 |
+
"<unused_token_18>": 49972,
|
13 |
+
"<unused_token_19>": 49973,
|
14 |
+
"<unused_token_1>": 49955,
|
15 |
+
"<unused_token_20>": 49974,
|
16 |
+
"<unused_token_21>": 49975,
|
17 |
+
"<unused_token_22>": 49976,
|
18 |
+
"<unused_token_23>": 49977,
|
19 |
+
"<unused_token_24>": 49978,
|
20 |
+
"<unused_token_25>": 49979,
|
21 |
+
"<unused_token_26>": 49980,
|
22 |
+
"<unused_token_27>": 49981,
|
23 |
+
"<unused_token_28>": 49982,
|
24 |
+
"<unused_token_29>": 49983,
|
25 |
+
"<unused_token_2>": 49956,
|
26 |
+
"<unused_token_30>": 49984,
|
27 |
+
"<unused_token_31>": 49985,
|
28 |
+
"<unused_token_32>": 49986,
|
29 |
+
"<unused_token_33>": 49987,
|
30 |
+
"<unused_token_34>": 49988,
|
31 |
+
"<unused_token_35>": 49989,
|
32 |
+
"<unused_token_36>": 49990,
|
33 |
+
"<unused_token_37>": 49991,
|
34 |
+
"<unused_token_38>": 49992,
|
35 |
+
"<unused_token_39>": 49993,
|
36 |
+
"<unused_token_3>": 49957,
|
37 |
+
"<unused_token_40>": 49994,
|
38 |
+
"<unused_token_41>": 49995,
|
39 |
+
"<unused_token_42>": 49996,
|
40 |
+
"<unused_token_43>": 49997,
|
41 |
+
"<unused_token_44>": 49998,
|
42 |
+
"<unused_token_45>": 49999,
|
43 |
+
"<unused_token_46>": 50000,
|
44 |
+
"<unused_token_47>": 50001,
|
45 |
+
"<unused_token_48>": 50002,
|
46 |
+
"<unused_token_49>": 50003,
|
47 |
+
"<unused_token_4>": 49958,
|
48 |
+
"<unused_token_50>": 50004,
|
49 |
+
"<unused_token_51>": 50005,
|
50 |
+
"<unused_token_52>": 50006,
|
51 |
+
"<unused_token_53>": 50007,
|
52 |
+
"<unused_token_54>": 50008,
|
53 |
+
"<unused_token_55>": 50009,
|
54 |
+
"<unused_token_56>": 50010,
|
55 |
+
"<unused_token_57>": 50011,
|
56 |
+
"<unused_token_58>": 50012,
|
57 |
+
"<unused_token_59>": 50013,
|
58 |
+
"<unused_token_5>": 49959,
|
59 |
+
"<unused_token_60>": 50014,
|
60 |
+
"<unused_token_61>": 50015,
|
61 |
+
"<unused_token_62>": 50016,
|
62 |
+
"<unused_token_63>": 50017,
|
63 |
+
"<unused_token_64>": 50018,
|
64 |
+
"<unused_token_65>": 50019,
|
65 |
+
"<unused_token_66>": 50020,
|
66 |
+
"<unused_token_67>": 50021,
|
67 |
+
"<unused_token_68>": 50022,
|
68 |
+
"<unused_token_69>": 50023,
|
69 |
+
"<unused_token_6>": 49960,
|
70 |
+
"<unused_token_70>": 50024,
|
71 |
+
"<unused_token_71>": 50025,
|
72 |
+
"<unused_token_72>": 50026,
|
73 |
+
"<unused_token_73>": 50027,
|
74 |
+
"<unused_token_74>": 50028,
|
75 |
+
"<unused_token_75>": 50029,
|
76 |
+
"<unused_token_76>": 50030,
|
77 |
+
"<unused_token_77>": 50031,
|
78 |
+
"<unused_token_78>": 50032,
|
79 |
+
"<unused_token_79>": 50033,
|
80 |
+
"<unused_token_7>": 49961,
|
81 |
+
"<unused_token_80>": 50034,
|
82 |
+
"<unused_token_81>": 50035,
|
83 |
+
"<unused_token_82>": 50036,
|
84 |
+
"<unused_token_83>": 50037,
|
85 |
+
"<unused_token_84>": 50038,
|
86 |
+
"<unused_token_85>": 50039,
|
87 |
+
"<unused_token_86>": 50040,
|
88 |
+
"<unused_token_87>": 50041,
|
89 |
+
"<unused_token_88>": 50042,
|
90 |
+
"<unused_token_89>": 50043,
|
91 |
+
"<unused_token_8>": 49962,
|
92 |
+
"<unused_token_90>": 50044,
|
93 |
+
"<unused_token_91>": 50045,
|
94 |
+
"<unused_token_92>": 50046,
|
95 |
+
"<unused_token_93>": 50047,
|
96 |
+
"<unused_token_94>": 50048,
|
97 |
+
"<unused_token_95>": 50049,
|
98 |
+
"<unused_token_96>": 50050,
|
99 |
+
"<unused_token_97>": 50051,
|
100 |
+
"<unused_token_98>": 50052,
|
101 |
+
"<unused_token_99>": 50053,
|
102 |
+
"<unused_token_9>": 49963
|
103 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,108 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<end>",
|
4 |
+
"<unused_token_0>",
|
5 |
+
"<unused_token_1>",
|
6 |
+
"<unused_token_2>",
|
7 |
+
"<unused_token_3>",
|
8 |
+
"<unused_token_4>",
|
9 |
+
"<unused_token_5>",
|
10 |
+
"<unused_token_6>",
|
11 |
+
"<unused_token_7>",
|
12 |
+
"<unused_token_8>",
|
13 |
+
"<unused_token_9>",
|
14 |
+
"<unused_token_10>",
|
15 |
+
"<unused_token_11>",
|
16 |
+
"<unused_token_12>",
|
17 |
+
"<unused_token_13>",
|
18 |
+
"<unused_token_14>",
|
19 |
+
"<unused_token_15>",
|
20 |
+
"<unused_token_16>",
|
21 |
+
"<unused_token_17>",
|
22 |
+
"<unused_token_18>",
|
23 |
+
"<unused_token_19>",
|
24 |
+
"<unused_token_20>",
|
25 |
+
"<unused_token_21>",
|
26 |
+
"<unused_token_22>",
|
27 |
+
"<unused_token_23>",
|
28 |
+
"<unused_token_24>",
|
29 |
+
"<unused_token_25>",
|
30 |
+
"<unused_token_26>",
|
31 |
+
"<unused_token_27>",
|
32 |
+
"<unused_token_28>",
|
33 |
+
"<unused_token_29>",
|
34 |
+
"<unused_token_30>",
|
35 |
+
"<unused_token_31>",
|
36 |
+
"<unused_token_32>",
|
37 |
+
"<unused_token_33>",
|
38 |
+
"<unused_token_34>",
|
39 |
+
"<unused_token_35>",
|
40 |
+
"<unused_token_36>",
|
41 |
+
"<unused_token_37>",
|
42 |
+
"<unused_token_38>",
|
43 |
+
"<unused_token_39>",
|
44 |
+
"<unused_token_40>",
|
45 |
+
"<unused_token_41>",
|
46 |
+
"<unused_token_42>",
|
47 |
+
"<unused_token_43>",
|
48 |
+
"<unused_token_44>",
|
49 |
+
"<unused_token_45>",
|
50 |
+
"<unused_token_46>",
|
51 |
+
"<unused_token_47>",
|
52 |
+
"<unused_token_48>",
|
53 |
+
"<unused_token_49>",
|
54 |
+
"<unused_token_50>",
|
55 |
+
"<unused_token_51>",
|
56 |
+
"<unused_token_52>",
|
57 |
+
"<unused_token_53>",
|
58 |
+
"<unused_token_54>",
|
59 |
+
"<unused_token_55>",
|
60 |
+
"<unused_token_56>",
|
61 |
+
"<unused_token_57>",
|
62 |
+
"<unused_token_58>",
|
63 |
+
"<unused_token_59>",
|
64 |
+
"<unused_token_60>",
|
65 |
+
"<unused_token_61>",
|
66 |
+
"<unused_token_62>",
|
67 |
+
"<unused_token_63>",
|
68 |
+
"<unused_token_64>",
|
69 |
+
"<unused_token_65>",
|
70 |
+
"<unused_token_66>",
|
71 |
+
"<unused_token_67>",
|
72 |
+
"<unused_token_68>",
|
73 |
+
"<unused_token_69>",
|
74 |
+
"<unused_token_70>",
|
75 |
+
"<unused_token_71>",
|
76 |
+
"<unused_token_72>",
|
77 |
+
"<unused_token_73>",
|
78 |
+
"<unused_token_74>",
|
79 |
+
"<unused_token_75>",
|
80 |
+
"<unused_token_76>",
|
81 |
+
"<unused_token_77>",
|
82 |
+
"<unused_token_78>",
|
83 |
+
"<unused_token_79>",
|
84 |
+
"<unused_token_80>",
|
85 |
+
"<unused_token_81>",
|
86 |
+
"<unused_token_82>",
|
87 |
+
"<unused_token_83>",
|
88 |
+
"<unused_token_84>",
|
89 |
+
"<unused_token_85>",
|
90 |
+
"<unused_token_86>",
|
91 |
+
"<unused_token_87>",
|
92 |
+
"<unused_token_88>",
|
93 |
+
"<unused_token_89>",
|
94 |
+
"<unused_token_90>",
|
95 |
+
"<unused_token_91>",
|
96 |
+
"<unused_token_92>",
|
97 |
+
"<unused_token_93>",
|
98 |
+
"<unused_token_94>",
|
99 |
+
"<unused_token_95>",
|
100 |
+
"<unused_token_96>",
|
101 |
+
"<unused_token_97>",
|
102 |
+
"<unused_token_98>",
|
103 |
+
"<unused_token_99>"
|
104 |
+
],
|
105 |
+
"bos_token": "<s>",
|
106 |
+
"eos_token": "</s>",
|
107 |
+
"unk_token": "<unk>"
|
108 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2676d4ca29ca1750f6ff203328d73b189321dc5776ceede037cbd36541d70c0
|
3 |
+
size 757958
|
tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<s>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": false,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"model_max_length": 1000000000000000019884624838656,
|
22 |
+
"pad_token": null,
|
23 |
+
"sp_model_kwargs": {},
|
24 |
+
"tokenizer_class": "LlamaTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<unk>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|