Hugging Face's logo

ehristoforu
/
ruphi-4b

Text Generation
Transformers
Safetensors
English
phi3
text-generation-inference
unsloth
llama
trl
sft
conversational
custom_code
Inference Endpoints
Model card Files Community
ehristoforu commited on
Commit
c151730
·
verified ·
1 Parent(s): d1317ce

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +127 -129
tokenizer_config.json CHANGED
@@ -1,132 +1,130 @@
1
  {
2
- "add_bos_token": false,
3
- "add_eos_token": false,
4
- "add_prefix_space": null,
5
- "added_tokens_decoder": {
6
- "0": {
7
- "content": "<unk>",
8
- "lstrip": false,
9
- "normalized": false,
10
- "rstrip": false,
11
- "single_word": false,
12
- "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  },
14
- "1": {
15
- "content": "<s>",
16
- "lstrip": false,
17
- "normalized": false,
18
- "rstrip": false,
19
- "single_word": false,
20
- "special": true
21
- },
22
- "2": {
23
- "content": "</s>",
24
- "lstrip": false,
25
- "normalized": false,
26
- "rstrip": true,
27
- "single_word": false,
28
- "special": false
29
- },
30
- "32000": {
31
- "content": "<|endoftext|>",
32
- "lstrip": false,
33
- "normalized": false,
34
- "rstrip": false,
35
- "single_word": false,
36
- "special": true
37
- },
38
- "32001": {
39
- "content": "<|assistant|>",
40
- "lstrip": false,
41
- "normalized": false,
42
- "rstrip": true,
43
- "single_word": false,
44
- "special": true
45
- },
46
- "32002": {
47
- "content": "<|placeholder1|>",
48
- "lstrip": false,
49
- "normalized": false,
50
- "rstrip": true,
51
- "single_word": false,
52
- "special": true
53
- },
54
- "32003": {
55
- "content": "<|placeholder2|>",
56
- "lstrip": false,
57
- "normalized": false,
58
- "rstrip": true,
59
- "single_word": false,
60
- "special": true
61
- },
62
- "32004": {
63
- "content": "<|placeholder3|>",
64
- "lstrip": false,
65
- "normalized": false,
66
- "rstrip": true,
67
- "single_word": false,
68
- "special": true
69
- },
70
- "32005": {
71
- "content": "<|placeholder4|>",
72
- "lstrip": false,
73
- "normalized": false,
74
- "rstrip": true,
75
- "single_word": false,
76
- "special": true
77
- },
78
- "32006": {
79
- "content": "<|system|>",
80
- "lstrip": false,
81
- "normalized": false,
82
- "rstrip": true,
83
- "single_word": false,
84
- "special": true
85
- },
86
- "32007": {
87
- "content": "<|end|>",
88
- "lstrip": false,
89
- "normalized": false,
90
- "rstrip": true,
91
- "single_word": false,
92
- "special": true
93
- },
94
- "32008": {
95
- "content": "<|placeholder5|>",
96
- "lstrip": false,
97
- "normalized": false,
98
- "rstrip": true,
99
- "single_word": false,
100
- "special": true
101
- },
102
- "32009": {
103
- "content": "<|placeholder6|>",
104
- "lstrip": false,
105
- "normalized": false,
106
- "rstrip": true,
107
- "single_word": false,
108
- "special": true
109
- },
110
- "32010": {
111
- "content": "<|user|>",
112
- "lstrip": false,
113
- "normalized": false,
114
- "rstrip": true,
115
- "single_word": false,
116
- "special": true
117
- }
118
- },
119
- "bos_token": "<s>",
120
- "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% else %}{{'<|' + message['role'] + '|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% endif %}",
121
- "clean_up_tokenization_spaces": false,
122
- "eos_token": "<|endoftext|>",
123
- "extra_special_tokens": {},
124
- "legacy": false,
125
- "model_max_length": 131072,
126
- "pad_token": "<|placeholder6|>",
127
- "padding_side": "left",
128
- "sp_model_kwargs": {},
129
- "tokenizer_class": "LlamaTokenizer",
130
- "unk_token": "<unk>",
131
- "use_default_system_prompt": false
132
  }
 
1
  {
2
+ "add_bos_token": false,
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
  },
118
+ "bos_token": "<s>",
119
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
120
+ "clean_up_tokenization_spaces": false,
121
+ "eos_token": "<|endoftext|>",
122
+ "legacy": false,
123
+ "model_max_length": 131072,
124
+ "pad_token": "<|endoftext|>",
125
+ "padding_side": "left",
126
+ "sp_model_kwargs": {},
127
+ "tokenizer_class": "LlamaTokenizer",
128
+ "unk_token": "<unk>",
129
+ "use_default_system_prompt": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  }