Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer.json +6 -28
- tokenizer_config.json +6 -4
special_tokens_map.json
CHANGED
@@ -14,7 +14,7 @@
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
"rstrip": false,
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
@@ -62,12 +67,6 @@
|
|
62 |
"id": "A",
|
63 |
"type_id": 0
|
64 |
}
|
65 |
-
},
|
66 |
-
{
|
67 |
-
"SpecialToken": {
|
68 |
-
"id": "</s>",
|
69 |
-
"type_id": 0
|
70 |
-
}
|
71 |
}
|
72 |
],
|
73 |
"pair": [
|
@@ -83,12 +82,6 @@
|
|
83 |
"type_id": 0
|
84 |
}
|
85 |
},
|
86 |
-
{
|
87 |
-
"SpecialToken": {
|
88 |
-
"id": "</s>",
|
89 |
-
"type_id": 0
|
90 |
-
}
|
91 |
-
},
|
92 |
{
|
93 |
"SpecialToken": {
|
94 |
"id": "<s>",
|
@@ -100,24 +93,9 @@
|
|
100 |
"id": "B",
|
101 |
"type_id": 1
|
102 |
}
|
103 |
-
},
|
104 |
-
{
|
105 |
-
"SpecialToken": {
|
106 |
-
"id": "</s>",
|
107 |
-
"type_id": 1
|
108 |
-
}
|
109 |
}
|
110 |
],
|
111 |
"special_tokens": {
|
112 |
-
"</s>": {
|
113 |
-
"id": "</s>",
|
114 |
-
"ids": [
|
115 |
-
2
|
116 |
-
],
|
117 |
-
"tokens": [
|
118 |
-
"</s>"
|
119 |
-
]
|
120 |
-
},
|
121 |
"<s>": {
|
122 |
"id": "<s>",
|
123 |
"ids": [
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 250,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
67 |
"id": "A",
|
68 |
"type_id": 0
|
69 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
71 |
],
|
72 |
"pair": [
|
|
|
82 |
"type_id": 0
|
83 |
}
|
84 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
{
|
86 |
"SpecialToken": {
|
87 |
"id": "<s>",
|
|
|
93 |
"id": "B",
|
94 |
"type_id": 1
|
95 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
}
|
97 |
],
|
98 |
"special_tokens": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
99 |
"<s>": {
|
100 |
"id": "<s>",
|
101 |
"ids": [
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
4 |
-
"add_prefix_space": true,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -33,12 +32,15 @@
|
|
33 |
"clean_up_tokenization_spaces": false,
|
34 |
"eos_token": "</s>",
|
35 |
"legacy": false,
|
|
|
36 |
"model_max_length": 2048,
|
37 |
-
"pad_token": "
|
38 |
"padding_side": "right",
|
39 |
"sp_model_kwargs": {},
|
40 |
-
"
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
42 |
"unk_token": "<unk>",
|
43 |
"use_default_system_prompt": false
|
44 |
}
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
|
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
34 |
"legacy": false,
|
35 |
+
"max_length": 250,
|
36 |
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
"padding_side": "right",
|
39 |
"sp_model_kwargs": {},
|
40 |
+
"stride": 0,
|
41 |
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"truncation_side": "right",
|
43 |
+
"truncation_strategy": "longest_first",
|
44 |
"unk_token": "<unk>",
|
45 |
"use_default_system_prompt": false
|
46 |
}
|