Upload tokenizer
Browse files- special_tokens_map.json +12 -0
- tokenizer.json +57 -8
- tokenizer_config.json +15 -4
special_tokens_map.json
CHANGED
@@ -1,4 +1,9 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
@@ -13,6 +18,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
"bos_token": {
|
8 |
"content": "<s>",
|
9 |
"lstrip": false,
|
|
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
"unk_token": {
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,7 +1,19 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
@@ -31,13 +43,23 @@
|
|
31 |
"special": true
|
32 |
}
|
33 |
],
|
34 |
-
"normalizer":
|
35 |
-
|
36 |
-
"
|
37 |
-
|
38 |
-
|
39 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
40 |
},
|
|
|
41 |
"post_processor": {
|
42 |
"type": "TemplateProcessing",
|
43 |
"single": [
|
@@ -52,6 +74,12 @@
|
|
52 |
"id": "A",
|
53 |
"type_id": 0
|
54 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"pair": [
|
@@ -67,6 +95,12 @@
|
|
67 |
"type_id": 0
|
68 |
}
|
69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
{
|
71 |
"SpecialToken": {
|
72 |
"id": "<s>",
|
@@ -78,9 +112,24 @@
|
|
78 |
"id": "B",
|
79 |
"type_id": 1
|
80 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
81 |
}
|
82 |
],
|
83 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
"<s>": {
|
85 |
"id": "<s>",
|
86 |
"ids": [
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
+
"padding": {
|
10 |
+
"strategy": "BatchLongest",
|
11 |
+
"direction": "Right",
|
12 |
+
"pad_to_multiple_of": null,
|
13 |
+
"pad_id": 2,
|
14 |
+
"pad_type_id": 0,
|
15 |
+
"pad_token": "</s>"
|
16 |
+
},
|
17 |
"added_tokens": [
|
18 |
{
|
19 |
"id": 0,
|
|
|
43 |
"special": true
|
44 |
}
|
45 |
],
|
46 |
+
"normalizer": {
|
47 |
+
"type": "Sequence",
|
48 |
+
"normalizers": [
|
49 |
+
{
|
50 |
+
"type": "Prepend",
|
51 |
+
"prepend": "▁"
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"type": "Replace",
|
55 |
+
"pattern": {
|
56 |
+
"String": " "
|
57 |
+
},
|
58 |
+
"content": "▁"
|
59 |
+
}
|
60 |
+
]
|
61 |
},
|
62 |
+
"pre_tokenizer": null,
|
63 |
"post_processor": {
|
64 |
"type": "TemplateProcessing",
|
65 |
"single": [
|
|
|
74 |
"id": "A",
|
75 |
"type_id": 0
|
76 |
}
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"SpecialToken": {
|
80 |
+
"id": "</s>",
|
81 |
+
"type_id": 0
|
82 |
+
}
|
83 |
}
|
84 |
],
|
85 |
"pair": [
|
|
|
95 |
"type_id": 0
|
96 |
}
|
97 |
},
|
98 |
+
{
|
99 |
+
"SpecialToken": {
|
100 |
+
"id": "</s>",
|
101 |
+
"type_id": 0
|
102 |
+
}
|
103 |
+
},
|
104 |
{
|
105 |
"SpecialToken": {
|
106 |
"id": "<s>",
|
|
|
112 |
"id": "B",
|
113 |
"type_id": 1
|
114 |
}
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"SpecialToken": {
|
118 |
+
"id": "</s>",
|
119 |
+
"type_id": 1
|
120 |
+
}
|
121 |
}
|
122 |
],
|
123 |
"special_tokens": {
|
124 |
+
"</s>": {
|
125 |
+
"id": "</s>",
|
126 |
+
"ids": [
|
127 |
+
2
|
128 |
+
],
|
129 |
+
"tokens": [
|
130 |
+
"</s>"
|
131 |
+
]
|
132 |
+
},
|
133 |
"<s>": {
|
134 |
"id": "<s>",
|
135 |
"ids": [
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
@@ -28,16 +28,27 @@
|
|
28 |
"special": true
|
29 |
}
|
30 |
},
|
31 |
-
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
32 |
"bos_token": "<s>",
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
-
"legacy":
|
|
|
36 |
"model_max_length": 1000000000000000019884624838656,
|
37 |
-
"
|
|
|
|
|
|
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
|
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
41 |
"unk_token": "<unk>",
|
42 |
"use_default_system_prompt": false
|
43 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": true,
|
4 |
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
|
|
28 |
"special": true
|
29 |
}
|
30 |
},
|
31 |
+
"additional_special_tokens": [
|
32 |
+
"<unk>",
|
33 |
+
"<s>",
|
34 |
+
"</s>"
|
35 |
+
],
|
36 |
"bos_token": "<s>",
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"max_length": 512,
|
41 |
"model_max_length": 1000000000000000019884624838656,
|
42 |
+
"pad_to_multiple_of": null,
|
43 |
+
"pad_token": "</s>",
|
44 |
+
"pad_token_type_id": 0,
|
45 |
+
"padding_side": "right",
|
46 |
"sp_model_kwargs": {},
|
47 |
"spaces_between_special_tokens": false,
|
48 |
+
"stride": 0,
|
49 |
"tokenizer_class": "LlamaTokenizer",
|
50 |
+
"truncation_side": "right",
|
51 |
+
"truncation_strategy": "longest_first",
|
52 |
"unk_token": "<unk>",
|
53 |
"use_default_system_prompt": false
|
54 |
}
|