Upload processor
Browse files- special_tokens_map.json +7 -1
- tokenizer.json +8 -8
- tokenizer_config.json +2 -17
special_tokens_map.json
CHANGED
@@ -1,6 +1,12 @@
|
|
1 |
{
|
2 |
"bos_token": "</s>",
|
3 |
-
"eos_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "[PAD]",
|
5 |
"unk_token": "</s>"
|
6 |
}
|
|
|
1 |
{
|
2 |
"bos_token": "</s>",
|
3 |
+
"eos_token": {
|
4 |
+
"content": "</s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
"pad_token": "[PAD]",
|
11 |
"unk_token": "</s>"
|
12 |
}
|
tokenizer.json
CHANGED
@@ -27,7 +27,7 @@
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
-
"normalized":
|
31 |
"special": true
|
32 |
},
|
33 |
{
|
@@ -62,7 +62,7 @@
|
|
62 |
"single": [
|
63 |
{
|
64 |
"SpecialToken": {
|
65 |
-
"id": "
|
66 |
"type_id": 0
|
67 |
}
|
68 |
},
|
@@ -76,7 +76,7 @@
|
|
76 |
"pair": [
|
77 |
{
|
78 |
"SpecialToken": {
|
79 |
-
"id": "
|
80 |
"type_id": 0
|
81 |
}
|
82 |
},
|
@@ -88,7 +88,7 @@
|
|
88 |
},
|
89 |
{
|
90 |
"SpecialToken": {
|
91 |
-
"id": "
|
92 |
"type_id": 1
|
93 |
}
|
94 |
},
|
@@ -100,13 +100,13 @@
|
|
100 |
}
|
101 |
],
|
102 |
"special_tokens": {
|
103 |
-
"
|
104 |
-
"id": "
|
105 |
"ids": [
|
106 |
-
|
107 |
],
|
108 |
"tokens": [
|
109 |
-
"
|
110 |
]
|
111 |
}
|
112 |
}
|
|
|
27 |
"single_word": false,
|
28 |
"lstrip": false,
|
29 |
"rstrip": false,
|
30 |
+
"normalized": true,
|
31 |
"special": true
|
32 |
},
|
33 |
{
|
|
|
62 |
"single": [
|
63 |
{
|
64 |
"SpecialToken": {
|
65 |
+
"id": "</s>",
|
66 |
"type_id": 0
|
67 |
}
|
68 |
},
|
|
|
76 |
"pair": [
|
77 |
{
|
78 |
"SpecialToken": {
|
79 |
+
"id": "</s>",
|
80 |
"type_id": 0
|
81 |
}
|
82 |
},
|
|
|
88 |
},
|
89 |
{
|
90 |
"SpecialToken": {
|
91 |
+
"id": "</s>",
|
92 |
"type_id": 1
|
93 |
}
|
94 |
},
|
|
|
100 |
}
|
101 |
],
|
102 |
"special_tokens": {
|
103 |
+
"</s>": {
|
104 |
+
"id": "</s>",
|
105 |
"ids": [
|
106 |
+
2
|
107 |
],
|
108 |
"tokens": [
|
109 |
+
"</s>"
|
110 |
]
|
111 |
}
|
112 |
}
|
tokenizer_config.json
CHANGED
@@ -1,12 +1,5 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
"__type": "AddedToken",
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": true,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false
|
9 |
-
},
|
10 |
"clean_up_tokenization_spaces": false,
|
11 |
"eos_token": {
|
12 |
"__type": "AddedToken",
|
@@ -22,13 +15,5 @@
|
|
22 |
"sp_model_kwargs": {},
|
23 |
"tokenizer_class": "LlamaTokenizer",
|
24 |
"truncation_side": "left",
|
25 |
-
"unk_token":
|
26 |
-
"__type": "AddedToken",
|
27 |
-
"content": "<unk>",
|
28 |
-
"lstrip": false,
|
29 |
-
"normalized": true,
|
30 |
-
"rstrip": false,
|
31 |
-
"single_word": false
|
32 |
-
},
|
33 |
-
"use_fast": false
|
34 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "</s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
"clean_up_tokenization_spaces": false,
|
4 |
"eos_token": {
|
5 |
"__type": "AddedToken",
|
|
|
15 |
"sp_model_kwargs": {},
|
16 |
"tokenizer_class": "LlamaTokenizer",
|
17 |
"truncation_side": "left",
|
18 |
+
"unk_token": "</s>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|