Hugging Face's logo

numind
/
NuExtract

Text Generation
Transformers
Safetensors
English
phi3
conversational
custom_code
Inference Endpoints
Model card Files Community
9
Alexandre-Numind commited on
Commit
7c67b1e
•
1 Parent(s): acf7388

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +138 -138
tokenizer_config.json CHANGED
@@ -1,138 +1,138 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "added_tokens_decoder": {
5
- "0": {
6
- "content": "<unk>",
7
- "lstrip": false,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false,
11
- "special": true
12
- },
13
- "1": {
14
- "content": "<s>",
15
- "lstrip": false,
16
- "normalized": false,
17
- "rstrip": false,
18
- "single_word": false,
19
- "special": true
20
- },
21
- "2": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": true,
26
- "single_word": false,
27
- "special": false
28
- },
29
- "32000": {
30
- "content": "<|endoftext|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32001": {
38
- "content": "<|assistant|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": true,
42
- "single_word": false,
43
- "special": true
44
- },
45
- "32002": {
46
- "content": "<|placeholder1|>",
47
- "lstrip": false,
48
- "normalized": false,
49
- "rstrip": true,
50
- "single_word": false,
51
- "special": true
52
- },
53
- "32003": {
54
- "content": "<|placeholder2|>",
55
- "lstrip": false,
56
- "normalized": false,
57
- "rstrip": true,
58
- "single_word": false,
59
- "special": true
60
- },
61
- "32004": {
62
- "content": "<|placeholder3|>",
63
- "lstrip": false,
64
- "normalized": false,
65
- "rstrip": true,
66
- "single_word": false,
67
- "special": true
68
- },
69
- "32005": {
70
- "content": "<|placeholder4|>",
71
- "lstrip": false,
72
- "normalized": false,
73
- "rstrip": true,
74
- "single_word": false,
75
- "special": true
76
- },
77
- "32006": {
78
- "content": "<|system|>",
79
- "lstrip": false,
80
- "normalized": false,
81
- "rstrip": true,
82
- "single_word": false,
83
- "special": true
84
- },
85
- "32007": {
86
- "content": "<|end|>",
87
- "lstrip": false,
88
- "normalized": false,
89
- "rstrip": true,
90
- "single_word": false,
91
- "special": true
92
- },
93
- "32008": {
94
- "content": "<|placeholder5|>",
95
- "lstrip": false,
96
- "normalized": false,
97
- "rstrip": true,
98
- "single_word": false,
99
- "special": true
100
- },
101
- "32009": {
102
- "content": "<|placeholder6|>",
103
- "lstrip": false,
104
- "normalized": false,
105
- "rstrip": true,
106
- "single_word": false,
107
- "special": true
108
- },
109
- "32010": {
110
- "content": "<|user|>",
111
- "lstrip": false,
112
- "normalized": false,
113
- "rstrip": true,
114
- "single_word": false,
115
- "special": true
116
- },
117
- "32011": {
118
- "content": "<|end-output|>",
119
- "lstrip": false,
120
- "normalized": true,
121
- "rstrip": false,
122
- "single_word": false,
123
- "special": false
124
- }
125
- },
126
- "bos_token": "<s>",
127
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
128
- "clean_up_tokenization_spaces": false,
129
- "eos_token": "<|endoftext|>",
130
- "legacy": false,
131
- "model_max_length": 4096,
132
- "pad_token": "<|endoftext|>",
133
- "padding_side": "left",
134
- "sp_model_kwargs": {},
135
- "tokenizer_class": "LlamaTokenizer",
136
- "unk_token": "<unk>",
137
- "use_default_system_prompt": false
138
- }
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|placeholder1|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|placeholder2|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|placeholder3|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|placeholder4|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|placeholder5|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|placeholder6|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|end-output|>",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ }
125
+ },
126
+ "bos_token": "<s>",
127
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') %}{{'<|user|>' + '\n' + message['content'] + '<|end|>' + '\n' + '<|assistant|>' + '\n'}}{% elif (message['role'] == 'assistant') %}{{message['content'] + '<|end|>' + '\n'}}{% endif %}{% endfor %}",
128
+ "clean_up_tokenization_spaces": false,
129
+ "eos_token": "<|endoftext|>",
130
+ "legacy": false,
131
+ "model_max_length": 4096,
132
+ "pad_token": "<|end-output|>",
133
+ "padding_side": "left",
134
+ "sp_model_kwargs": {},
135
+ "tokenizer_class": "LlamaTokenizer",
136
+ "unk_token": "<unk>",
137
+ "use_default_system_prompt": false
138
+ }