Upload tokenizer
Browse files- tokenizer.json +2 -29
- tokenizer_config.json +2 -3
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",
|
@@ -134,6 +106,7 @@
|
|
134 |
"end_of_word_suffix": null,
|
135 |
"fuse_unk": true,
|
136 |
"byte_fallback": true,
|
|
|
137 |
"vocab": {
|
138 |
"<unk>": 0,
|
139 |
"<s>": 1,
|
|
|
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",
|
|
|
106 |
"end_of_word_suffix": null,
|
107 |
"fuse_unk": true,
|
108 |
"byte_fallback": true,
|
109 |
+
"ignore_merges": false,
|
110 |
"vocab": {
|
111 |
"<unk>": 0,
|
112 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"add_bos_token":
|
3 |
"add_eos_token": false,
|
4 |
-
"add_prefix_space":
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
@@ -39,7 +39,6 @@
|
|
39 |
"padding_side": "left",
|
40 |
"sep_token": "</s>",
|
41 |
"sp_model_kwargs": {},
|
42 |
-
"spaces_between_special_tokens": false,
|
43 |
"tokenizer_class": "LlamaTokenizer",
|
44 |
"unk_token": "<unk>",
|
45 |
"use_default_system_prompt": false
|
|
|
1 |
{
|
2 |
+
"add_bos_token": false,
|
3 |
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
"added_tokens_decoder": {
|
6 |
"0": {
|
7 |
"content": "<unk>",
|
|
|
39 |
"padding_side": "left",
|
40 |
"sep_token": "</s>",
|
41 |
"sp_model_kwargs": {},
|
|
|
42 |
"tokenizer_class": "LlamaTokenizer",
|
43 |
"unk_token": "<unk>",
|
44 |
"use_default_system_prompt": false
|