AlexWortega
commited on
Commit
•
9ceaf97
1
Parent(s):
abd81e9
Upload tokenizer
Browse files- special_tokens_map.json +28 -3
- tokenizer.json +1 -29
- tokenizer_config.json +3 -1
special_tokens_map.json
CHANGED
@@ -4,7 +4,32 @@
|
|
4 |
"<s>",
|
5 |
"</s>"
|
6 |
],
|
7 |
-
"bos_token":
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
}
|
|
|
4 |
"<s>",
|
5 |
"</s>"
|
6 |
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
}
|
tokenizer.json
CHANGED
@@ -51,12 +51,6 @@
|
|
51 |
"post_processor": {
|
52 |
"type": "TemplateProcessing",
|
53 |
"single": [
|
54 |
-
{
|
55 |
-
"SpecialToken": {
|
56 |
-
"id": "<s>",
|
57 |
-
"type_id": 0
|
58 |
-
}
|
59 |
-
},
|
60 |
{
|
61 |
"Sequence": {
|
62 |
"id": "A",
|
@@ -65,24 +59,12 @@
|
|
65 |
}
|
66 |
],
|
67 |
"pair": [
|
68 |
-
{
|
69 |
-
"SpecialToken": {
|
70 |
-
"id": "<s>",
|
71 |
-
"type_id": 0
|
72 |
-
}
|
73 |
-
},
|
74 |
{
|
75 |
"Sequence": {
|
76 |
"id": "A",
|
77 |
"type_id": 0
|
78 |
}
|
79 |
},
|
80 |
-
{
|
81 |
-
"SpecialToken": {
|
82 |
-
"id": "<s>",
|
83 |
-
"type_id": 1
|
84 |
-
}
|
85 |
-
},
|
86 |
{
|
87 |
"Sequence": {
|
88 |
"id": "B",
|
@@ -90,17 +72,7 @@
|
|
90 |
}
|
91 |
}
|
92 |
],
|
93 |
-
"special_tokens": {
|
94 |
-
"<s>": {
|
95 |
-
"id": "<s>",
|
96 |
-
"ids": [
|
97 |
-
1
|
98 |
-
],
|
99 |
-
"tokens": [
|
100 |
-
"<s>"
|
101 |
-
]
|
102 |
-
}
|
103 |
-
}
|
104 |
},
|
105 |
"decoder": {
|
106 |
"type": "Sequence",
|
|
|
51 |
"post_processor": {
|
52 |
"type": "TemplateProcessing",
|
53 |
"single": [
|
|
|
|
|
|
|
|
|
|
|
|
|
54 |
{
|
55 |
"Sequence": {
|
56 |
"id": "A",
|
|
|
59 |
}
|
60 |
],
|
61 |
"pair": [
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
{
|
63 |
"Sequence": {
|
64 |
"id": "A",
|
65 |
"type_id": 0
|
66 |
}
|
67 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
{
|
69 |
"Sequence": {
|
70 |
"id": "B",
|
|
|
72 |
}
|
73 |
}
|
74 |
],
|
75 |
+
"special_tokens": {}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
},
|
77 |
"decoder": {
|
78 |
"type": "Sequence",
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -35,7 +37,7 @@
|
|
35 |
"eos_token": "</s>",
|
36 |
"legacy": true,
|
37 |
"model_max_length": 1000000000000000019884624838656,
|
38 |
-
"pad_token":
|
39 |
"sp_model_kwargs": {},
|
40 |
"spaces_between_special_tokens": false,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
37 |
"eos_token": "</s>",
|
38 |
"legacy": true,
|
39 |
"model_max_length": 1000000000000000019884624838656,
|
40 |
+
"pad_token": "<unk>",
|
41 |
"sp_model_kwargs": {},
|
42 |
"spaces_between_special_tokens": false,
|
43 |
"tokenizer_class": "LlamaTokenizer",
|