Hugging Face's logo

TheBloke
/
OpenAssistant-SFT-7-Llama-30B-HF

Text Generation
Transformers
PyTorch
llama
text-generation-inference
Inference Endpoints
Model card Files Community
3
TheBloke commited on
Commit
a7a2306
•
1 Parent(s): 6d0af3d

Try to fix tokenizer

Browse files
Files changed (4) hide show
  1. added_tokens.json +10 -10
  2. special_tokens_map.json +10 -7
  3. tokenizer.json +146 -2
  4. tokenizer_config.json +2 -2
added_tokens.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "<|dummy11|>": 32015,
3
  "<|dummy10|>": 32014,
4
- "<|dummy9|>": 32013,
5
- "<|dummy8|>": 32012,
6
- "<|dummy7|>": 32011,
7
- "<|dummy6|>": 32010,
8
- "<|dummy5|>": 32009,
9
- "<|dummy4|>": 32008,
10
- "<|dummy3|>": 32007,
11
- "<|dummy2|>": 32006,
12
  "<|dummy1|>": 32005,
13
- "<|assistant|>": 32004,
 
 
 
 
 
 
 
14
  "<|prefix_begin|>": 32000,
15
  "<|prefix_end|>": 32003,
16
  "<|prompter|>": 32002,
 
1
  {
2
+ "<|assistant|>": 32004,
3
  "<|dummy10|>": 32014,
4
+ "<|dummy11|>": 32015,
 
 
 
 
 
 
 
5
  "<|dummy1|>": 32005,
6
+ "<|dummy2|>": 32006,
7
+ "<|dummy3|>": 32007,
8
+ "<|dummy4|>": 32008,
9
+ "<|dummy5|>": 32009,
10
+ "<|dummy6|>": 32010,
11
+ "<|dummy7|>": 32011,
12
+ "<|dummy8|>": 32012,
13
+ "<|dummy9|>": 32013,
14
  "<|prefix_begin|>": 32000,
15
  "<|prefix_end|>": 32003,
16
  "<|prompter|>": 32002,
special_tokens_map.json CHANGED
@@ -1,4 +1,11 @@
1
  {
 
 
 
 
 
 
 
2
  "bos_token": {
3
  "content": "",
4
  "lstrip": false,
@@ -6,13 +13,9 @@
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
- "eos_token": {
10
- "content": "",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
  "unk_token": {
17
  "content": "",
18
  "lstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<|prompter|>",
4
+ "<|system|>",
5
+ "<|prefix_begin|>",
6
+ "<|prefix_end|>",
7
+ "<|assistant|>"
8
+ ],
9
  "bos_token": {
10
  "content": "",
11
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "eos_token": "</s>",
17
+ "pad_token": "</s>",
18
+ "sep_token": "<s>",
 
 
 
 
19
  "unk_token": {
20
  "content": "",
21
  "lstrip": false,
tokenizer.json CHANGED
@@ -18,7 +18,7 @@
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
- "normalized": true,
22
  "special": true
23
  },
24
  {
@@ -27,8 +27,152 @@
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
- "normalized": true,
31
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
32
  }
33
  ],
34
  "normalizer": {
 
18
  "single_word": false,
19
  "lstrip": false,
20
  "rstrip": false,
21
+ "normalized": false,
22
  "special": true
23
  },
24
  {
 
27
  "single_word": false,
28
  "lstrip": false,
29
  "rstrip": false,
30
+ "normalized": false,
31
  "special": true
32
+ },
33
+ {
34
+ "id": 32000,
35
+ "content": "<|prefix_begin|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ {
43
+ "id": 32001,
44
+ "content": "<|system|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": false,
49
+ "special": true
50
+ },
51
+ {
52
+ "id": 32002,
53
+ "content": "<|prompter|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": false,
58
+ "special": true
59
+ },
60
+ {
61
+ "id": 32003,
62
+ "content": "<|prefix_end|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": false,
67
+ "special": true
68
+ },
69
+ {
70
+ "id": 32004,
71
+ "content": "<|assistant|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": false,
76
+ "special": true
77
+ },
78
+ {
79
+ "id": 32005,
80
+ "content": "<|dummy1|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 32006,
89
+ "content": "<|dummy2|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 32007,
98
+ "content": "<|dummy3|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 32008,
107
+ "content": "<|dummy4|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 32009,
116
+ "content": "<|dummy5|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 32010,
125
+ "content": "<|dummy6|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 32011,
134
+ "content": "<|dummy7|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 32012,
143
+ "content": "<|dummy8|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 32013,
152
+ "content": "<|dummy9|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": true,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 32014,
161
+ "content": "<|dummy10|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": true,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 32015,
170
+ "content": "<|dummy11|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": true,
175
+ "special": false
176
  }
177
  ],
178
  "normalizer": {
tokenizer_config.json CHANGED
@@ -12,7 +12,7 @@
12
  "clean_up_tokenization_spaces": false,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
- "content": "",
16
  "lstrip": false,
17
  "normalized": true,
18
  "rstrip": false,
@@ -24,7 +24,7 @@
24
  "tokenizer_class": "LlamaTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
27
- "content": "",
28
  "lstrip": false,
29
  "normalized": true,
30
  "rstrip": false,
 
12
  "clean_up_tokenization_spaces": false,
13
  "eos_token": {
14
  "__type": "AddedToken",
15
+ "content": "</s>",
16
  "lstrip": false,
17
  "normalized": true,
18
  "rstrip": false,
 
24
  "tokenizer_class": "LlamaTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
27
+ "content": "</s>",
28
  "lstrip": false,
29
  "normalized": true,
30
  "rstrip": false,