Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +1 -33
- tokenizer_config.json +2 -4
special_tokens_map.json
CHANGED
@@ -13,7 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 1024,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
@@ -76,12 +71,6 @@
|
|
76 |
"id": "A",
|
77 |
"type_id": 0
|
78 |
}
|
79 |
-
},
|
80 |
-
{
|
81 |
-
"SpecialToken": {
|
82 |
-
"id": "</s>",
|
83 |
-
"type_id": 0
|
84 |
-
}
|
85 |
}
|
86 |
],
|
87 |
"pair": [
|
@@ -97,12 +86,6 @@
|
|
97 |
"type_id": 0
|
98 |
}
|
99 |
},
|
100 |
-
{
|
101 |
-
"SpecialToken": {
|
102 |
-
"id": "</s>",
|
103 |
-
"type_id": 0
|
104 |
-
}
|
105 |
-
},
|
106 |
{
|
107 |
"SpecialToken": {
|
108 |
"id": "<s>",
|
@@ -114,24 +97,9 @@
|
|
114 |
"id": "B",
|
115 |
"type_id": 1
|
116 |
}
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"SpecialToken": {
|
120 |
-
"id": "</s>",
|
121 |
-
"type_id": 1
|
122 |
-
}
|
123 |
}
|
124 |
],
|
125 |
"special_tokens": {
|
126 |
-
"</s>": {
|
127 |
-
"id": "</s>",
|
128 |
-
"ids": [
|
129 |
-
2
|
130 |
-
],
|
131 |
-
"tokens": [
|
132 |
-
"</s>"
|
133 |
-
]
|
134 |
-
},
|
135 |
"<s>": {
|
136 |
"id": "<s>",
|
137 |
"ids": [
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
71 |
"id": "A",
|
72 |
"type_id": 0
|
73 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
74 |
}
|
75 |
],
|
76 |
"pair": [
|
|
|
86 |
"type_id": 0
|
87 |
}
|
88 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
{
|
90 |
"SpecialToken": {
|
91 |
"id": "<s>",
|
|
|
97 |
"id": "B",
|
98 |
"type_id": 1
|
99 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
}
|
101 |
],
|
102 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
103 |
"<s>": {
|
104 |
"id": "<s>",
|
105 |
"ids": [
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": true,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -40,9 +38,9 @@
|
|
40 |
"eos_token": "</s>",
|
41 |
"legacy": false,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
-
"pad_token": "
|
44 |
"sp_model_kwargs": {},
|
45 |
"tokenizer_class": "LlamaTokenizer",
|
46 |
"unk_token": "<unk>",
|
47 |
-
"use_default_system_prompt":
|
48 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
38 |
"eos_token": "</s>",
|
39 |
"legacy": false,
|
40 |
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "<unk>",
|
42 |
"sp_model_kwargs": {},
|
43 |
"tokenizer_class": "LlamaTokenizer",
|
44 |
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": true
|
46 |
}
|