Tran Hoai Chau
commited on
Commit
•
4c8e586
1
Parent(s):
f9de2a2
add tokenizer
Browse files- added_tokens.json +5 -1
- merges.txt +0 -0
- special_tokens_map.json +3 -2
- tokenizer.json +0 -0
- tokenizer_config.json +7 -109
- vocab.json +0 -0
added_tokens.json
CHANGED
@@ -1 +1,5 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"[end]": 50258,
|
3 |
+
"[jest]": 50259,
|
4 |
+
"[react]": 50257
|
5 |
+
}
|
merges.txt
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -4,7 +4,8 @@
|
|
4 |
"[end]",
|
5 |
"[jest]"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
|
|
9 |
"unk_token": "<unk>"
|
10 |
}
|
|
|
4 |
"[end]",
|
5 |
"[jest]"
|
6 |
],
|
7 |
+
"bos_token": "<bos>",
|
8 |
+
"eos_token": "<|endoftext|>",
|
9 |
+
"pad_token": "<eos>",
|
10 |
"unk_token": "<unk>"
|
11 |
}
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -1,112 +1,10 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
"<extra_id_4>",
|
8 |
-
"<extra_id_5>",
|
9 |
-
"<extra_id_6>",
|
10 |
-
"<extra_id_7>",
|
11 |
-
"<extra_id_8>",
|
12 |
-
"<extra_id_9>",
|
13 |
-
"<extra_id_10>",
|
14 |
-
"<extra_id_11>",
|
15 |
-
"<extra_id_12>",
|
16 |
-
"<extra_id_13>",
|
17 |
-
"<extra_id_14>",
|
18 |
-
"<extra_id_15>",
|
19 |
-
"<extra_id_16>",
|
20 |
-
"<extra_id_17>",
|
21 |
-
"<extra_id_18>",
|
22 |
-
"<extra_id_19>",
|
23 |
-
"<extra_id_20>",
|
24 |
-
"<extra_id_21>",
|
25 |
-
"<extra_id_22>",
|
26 |
-
"<extra_id_23>",
|
27 |
-
"<extra_id_24>",
|
28 |
-
"<extra_id_25>",
|
29 |
-
"<extra_id_26>",
|
30 |
-
"<extra_id_27>",
|
31 |
-
"<extra_id_28>",
|
32 |
-
"<extra_id_29>",
|
33 |
-
"<extra_id_30>",
|
34 |
-
"<extra_id_31>",
|
35 |
-
"<extra_id_32>",
|
36 |
-
"<extra_id_33>",
|
37 |
-
"<extra_id_34>",
|
38 |
-
"<extra_id_35>",
|
39 |
-
"<extra_id_36>",
|
40 |
-
"<extra_id_37>",
|
41 |
-
"<extra_id_38>",
|
42 |
-
"<extra_id_39>",
|
43 |
-
"<extra_id_40>",
|
44 |
-
"<extra_id_41>",
|
45 |
-
"<extra_id_42>",
|
46 |
-
"<extra_id_43>",
|
47 |
-
"<extra_id_44>",
|
48 |
-
"<extra_id_45>",
|
49 |
-
"<extra_id_46>",
|
50 |
-
"<extra_id_47>",
|
51 |
-
"<extra_id_48>",
|
52 |
-
"<extra_id_49>",
|
53 |
-
"<extra_id_50>",
|
54 |
-
"<extra_id_51>",
|
55 |
-
"<extra_id_52>",
|
56 |
-
"<extra_id_53>",
|
57 |
-
"<extra_id_54>",
|
58 |
-
"<extra_id_55>",
|
59 |
-
"<extra_id_56>",
|
60 |
-
"<extra_id_57>",
|
61 |
-
"<extra_id_58>",
|
62 |
-
"<extra_id_59>",
|
63 |
-
"<extra_id_60>",
|
64 |
-
"<extra_id_61>",
|
65 |
-
"<extra_id_62>",
|
66 |
-
"<extra_id_63>",
|
67 |
-
"<extra_id_64>",
|
68 |
-
"<extra_id_65>",
|
69 |
-
"<extra_id_66>",
|
70 |
-
"<extra_id_67>",
|
71 |
-
"<extra_id_68>",
|
72 |
-
"<extra_id_69>",
|
73 |
-
"<extra_id_70>",
|
74 |
-
"<extra_id_71>",
|
75 |
-
"<extra_id_72>",
|
76 |
-
"<extra_id_73>",
|
77 |
-
"<extra_id_74>",
|
78 |
-
"<extra_id_75>",
|
79 |
-
"<extra_id_76>",
|
80 |
-
"<extra_id_77>",
|
81 |
-
"<extra_id_78>",
|
82 |
-
"<extra_id_79>",
|
83 |
-
"<extra_id_80>",
|
84 |
-
"<extra_id_81>",
|
85 |
-
"<extra_id_82>",
|
86 |
-
"<extra_id_83>",
|
87 |
-
"<extra_id_84>",
|
88 |
-
"<extra_id_85>",
|
89 |
-
"<extra_id_86>",
|
90 |
-
"<extra_id_87>",
|
91 |
-
"<extra_id_88>",
|
92 |
-
"<extra_id_89>",
|
93 |
-
"<extra_id_90>",
|
94 |
-
"<extra_id_91>",
|
95 |
-
"<extra_id_92>",
|
96 |
-
"<extra_id_93>",
|
97 |
-
"<extra_id_94>",
|
98 |
-
"<extra_id_95>",
|
99 |
-
"<extra_id_96>",
|
100 |
-
"<extra_id_97>",
|
101 |
-
"<extra_id_98>",
|
102 |
-
"<extra_id_99>"
|
103 |
-
],
|
104 |
-
"eos_token": "</s>",
|
105 |
-
"extra_ids": 100,
|
106 |
-
"model_max_length": 512,
|
107 |
-
"name_or_path": "t5-base",
|
108 |
-
"pad_token": "<pad>",
|
109 |
"special_tokens_map_file": null,
|
110 |
-
"tokenizer_class": "
|
111 |
-
"unk_token": "
|
112 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"model_max_length": 1024,
|
6 |
+
"name_or_path": "gpt2",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"special_tokens_map_file": null,
|
8 |
+
"tokenizer_class": "GPT2Tokenizer",
|
9 |
+
"unk_token": "<|endoftext|>"
|
10 |
}
|
vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|