Upload tokenizer
Browse files- added_tokens.json +12 -1
- special_tokens_map.json +79 -0
- tokenizer.json +99 -0
- tokenizer_config.json +101 -0
added_tokens.json
CHANGED
@@ -1,3 +1,14 @@
|
|
1 |
{
|
2 |
-
"<|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
}
|
|
|
1 |
{
|
2 |
+
"<|assistant|>": 32001,
|
3 |
+
"<|continue|>": 32009,
|
4 |
+
"<|endoftext|>": 32000,
|
5 |
+
"<|end|>": 32007,
|
6 |
+
"<|function_call|>": 32005,
|
7 |
+
"<|function_list|>": 32011,
|
8 |
+
"<|function_output|>": 32003,
|
9 |
+
"<|raw|>": 32008,
|
10 |
+
"<|step|>": 32002,
|
11 |
+
"<|system|>": 32006,
|
12 |
+
"<|tag|>": 32004,
|
13 |
+
"<|user|>": 32010
|
14 |
}
|
special_tokens_map.json
CHANGED
@@ -1,4 +1,83 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
|
|
1 |
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
{
|
4 |
+
"content": "<|assistant|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": true,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
{
|
11 |
+
"content": "<|step|>",
|
12 |
+
"lstrip": false,
|
13 |
+
"normalized": false,
|
14 |
+
"rstrip": true,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"content": "<|function_output|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": true,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"content": "<|tag|>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": false,
|
28 |
+
"rstrip": true,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"content": "<|function_call|>",
|
33 |
+
"lstrip": false,
|
34 |
+
"normalized": false,
|
35 |
+
"rstrip": true,
|
36 |
+
"single_word": false
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"content": "<|system|>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": true,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<|end|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": true,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"content": "<|raw|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": true,
|
57 |
+
"single_word": false
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"content": "<|continue|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": true,
|
64 |
+
"single_word": false
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"content": "<|user|>",
|
68 |
+
"lstrip": false,
|
69 |
+
"normalized": false,
|
70 |
+
"rstrip": true,
|
71 |
+
"single_word": false
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"content": "<|function_list|>",
|
75 |
+
"lstrip": false,
|
76 |
+
"normalized": false,
|
77 |
+
"rstrip": true,
|
78 |
+
"single_word": false
|
79 |
+
}
|
80 |
+
],
|
81 |
"bos_token": {
|
82 |
"content": "<s>",
|
83 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -38,6 +38,105 @@
|
|
38 |
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"normalizer": {
|
|
|
38 |
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 32001,
|
44 |
+
"content": "<|assistant|>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": true,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
{
|
52 |
+
"id": 32002,
|
53 |
+
"content": "<|step|>",
|
54 |
+
"single_word": false,
|
55 |
+
"lstrip": false,
|
56 |
+
"rstrip": true,
|
57 |
+
"normalized": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"id": 32003,
|
62 |
+
"content": "<|function_output|>",
|
63 |
+
"single_word": false,
|
64 |
+
"lstrip": false,
|
65 |
+
"rstrip": true,
|
66 |
+
"normalized": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"id": 32004,
|
71 |
+
"content": "<|tag|>",
|
72 |
+
"single_word": false,
|
73 |
+
"lstrip": false,
|
74 |
+
"rstrip": true,
|
75 |
+
"normalized": false,
|
76 |
+
"special": true
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"id": 32005,
|
80 |
+
"content": "<|function_call|>",
|
81 |
+
"single_word": false,
|
82 |
+
"lstrip": false,
|
83 |
+
"rstrip": true,
|
84 |
+
"normalized": false,
|
85 |
+
"special": true
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"id": 32006,
|
89 |
+
"content": "<|system|>",
|
90 |
+
"single_word": false,
|
91 |
+
"lstrip": false,
|
92 |
+
"rstrip": true,
|
93 |
+
"normalized": false,
|
94 |
+
"special": true
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"id": 32007,
|
98 |
+
"content": "<|end|>",
|
99 |
+
"single_word": false,
|
100 |
+
"lstrip": false,
|
101 |
+
"rstrip": true,
|
102 |
+
"normalized": false,
|
103 |
+
"special": true
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"id": 32008,
|
107 |
+
"content": "<|raw|>",
|
108 |
+
"single_word": false,
|
109 |
+
"lstrip": false,
|
110 |
+
"rstrip": true,
|
111 |
+
"normalized": false,
|
112 |
+
"special": true
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"id": 32009,
|
116 |
+
"content": "<|continue|>",
|
117 |
+
"single_word": false,
|
118 |
+
"lstrip": false,
|
119 |
+
"rstrip": true,
|
120 |
+
"normalized": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"id": 32010,
|
125 |
+
"content": "<|user|>",
|
126 |
+
"single_word": false,
|
127 |
+
"lstrip": false,
|
128 |
+
"rstrip": true,
|
129 |
+
"normalized": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"id": 32011,
|
134 |
+
"content": "<|function_list|>",
|
135 |
+
"single_word": false,
|
136 |
+
"lstrip": false,
|
137 |
+
"rstrip": true,
|
138 |
+
"normalized": false,
|
139 |
+
"special": true
|
140 |
}
|
141 |
],
|
142 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -31,8 +31,109 @@
|
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
34 |
}
|
35 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
36 |
"bos_token": "<s>",
|
37 |
"clean_up_tokenization_spaces": false,
|
38 |
"eos_token": "<|endoftext|>",
|
|
|
31 |
"rstrip": false,
|
32 |
"single_word": false,
|
33 |
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "<|assistant|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": true,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"32002": {
|
44 |
+
"content": "<|step|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": true,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"32003": {
|
52 |
+
"content": "<|function_output|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": true,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"32004": {
|
60 |
+
"content": "<|tag|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": true,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"32005": {
|
68 |
+
"content": "<|function_call|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": true,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"32006": {
|
76 |
+
"content": "<|system|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": true,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"32007": {
|
84 |
+
"content": "<|end|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": true,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"32008": {
|
92 |
+
"content": "<|raw|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": true,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"32009": {
|
100 |
+
"content": "<|continue|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": true,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"32010": {
|
108 |
+
"content": "<|user|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": true,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"32011": {
|
116 |
+
"content": "<|function_list|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": true,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
}
|
123 |
},
|
124 |
+
"additional_special_tokens": [
|
125 |
+
"<|assistant|>",
|
126 |
+
"<|step|>",
|
127 |
+
"<|function_output|>",
|
128 |
+
"<|tag|>",
|
129 |
+
"<|function_call|>",
|
130 |
+
"<|system|>",
|
131 |
+
"<|end|>",
|
132 |
+
"<|raw|>",
|
133 |
+
"<|continue|>",
|
134 |
+
"<|user|>",
|
135 |
+
"<|function_list|>"
|
136 |
+
],
|
137 |
"bos_token": "<s>",
|
138 |
"clean_up_tokenization_spaces": false,
|
139 |
"eos_token": "<|endoftext|>",
|