Commit
•
b669239
1
Parent(s):
64b3de2
Upload tokenizer
Browse files- added_tokens.json +5 -1
- tokenizer.json +36 -0
- tokenizer_config.json +32 -0
added_tokens.json
CHANGED
@@ -1,7 +1,11 @@
|
|
1 |
{
|
2 |
"<|assistant|>": 32003,
|
3 |
"<|end_of_turn|>": 32000,
|
|
|
|
|
4 |
"<|pad_0|>": 32001,
|
|
|
5 |
"<|system|>": 32004,
|
6 |
-
"<|user|>": 32002
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
"<|assistant|>": 32003,
|
3 |
"<|end_of_turn|>": 32000,
|
4 |
+
"<|im_end|>": 32006,
|
5 |
+
"<|im_start|>": 32007,
|
6 |
"<|pad_0|>": 32001,
|
7 |
+
"<|prompter|>": 32005,
|
8 |
"<|system|>": 32004,
|
9 |
+
"<|user|>": 32002,
|
10 |
+
"[PAD]": 32008
|
11 |
}
|
tokenizer.json
CHANGED
@@ -74,6 +74,42 @@
|
|
74 |
"rstrip": false,
|
75 |
"normalized": false,
|
76 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
}
|
78 |
],
|
79 |
"normalizer": {
|
|
|
74 |
"rstrip": false,
|
75 |
"normalized": false,
|
76 |
"special": true
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"id": 32005,
|
80 |
+
"content": "<|prompter|>",
|
81 |
+
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": false,
|
84 |
+
"normalized": false,
|
85 |
+
"special": true
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"id": 32006,
|
89 |
+
"content": "<|im_end|>",
|
90 |
+
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": false,
|
93 |
+
"normalized": false,
|
94 |
+
"special": true
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"id": 32007,
|
98 |
+
"content": "<|im_start|>",
|
99 |
+
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"special": true
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"id": 32008,
|
107 |
+
"content": "[PAD]",
|
108 |
+
"single_word": false,
|
109 |
+
"lstrip": false,
|
110 |
+
"rstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"special": true
|
113 |
}
|
114 |
],
|
115 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -63,6 +63,38 @@
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false,
|
65 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
},
|
68 |
"additional_special_tokens": [
|
|
|
63 |
"rstrip": false,
|
64 |
"single_word": false,
|
65 |
"special": true
|
66 |
+
},
|
67 |
+
"32005": {
|
68 |
+
"content": "<|prompter|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"32006": {
|
76 |
+
"content": "<|im_end|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"32007": {
|
84 |
+
"content": "<|im_start|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"32008": {
|
92 |
+
"content": "[PAD]",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
}
|
99 |
},
|
100 |
"additional_special_tokens": [
|