Hugging Face's logo

junnei
/
Phi-4-multimodal-instruct-ko-asr

Automatic Speech Recognition
Transformers
Safetensors
Korean
phi4mm
text-generation
custom_code
Eval Results
Model card Files Community
junnei commited on
Commit
592a51e
·
verified ·
1 Parent(s): 1e9394d

Upload tokenizer

Browse files
Files changed (7) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +12 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +30 -0
  5. tokenizer.json +3 -0
  6. tokenizer_config.json +131 -0
  7. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/tool_call|>": 200026,
3
+ "<|/tool|>": 200024,
4
+ "<|assistant|>": 200019,
5
+ "<|end|>": 200020,
6
+ "<|system|>": 200022,
7
+ "<|tag|>": 200028,
8
+ "<|tool_call|>": 200025,
9
+ "<|tool_response|>": 200027,
10
+ "<|tool|>": 200023,
11
+ "<|user|>": 200021
12
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85b25f7312e5ba9ebdb27682cb52f4274ccd8c545984576ba194670f646b2af0
3
+ size 15524647
tokenizer_config.json ADDED
@@ -0,0 +1,131 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "199999": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "200010": {
13
+ "content": "<|endoftext10|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "200011": {
21
+ "content": "<|endoftext11|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "200018": {
29
+ "content": "<|endofprompt|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "200019": {
37
+ "content": "<|assistant|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": true,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "200020": {
45
+ "content": "<|end|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": true,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "200021": {
53
+ "content": "<|user|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": true,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "200022": {
61
+ "content": "<|system|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": true,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "200023": {
69
+ "content": "<|tool|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": true,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "200024": {
77
+ "content": "<|/tool|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": true,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "200025": {
85
+ "content": "<|tool_call|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": true,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "200026": {
93
+ "content": "<|/tool_call|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": true,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "200027": {
101
+ "content": "<|tool_response|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": true,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "200028": {
109
+ "content": "<|tag|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": true,
113
+ "single_word": false,
114
+ "special": true
115
+ }
116
+ },
117
+ "bos_token": "<|endoftext|>",
118
+ "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
119
+ "clean_up_tokenization_spaces": false,
120
+ "eos_token": "<|endoftext|>",
121
+ "extra_special_tokens": {},
122
+ "max_length": null,
123
+ "model_max_length": 131072,
124
+ "pad_to_multiple_of": null,
125
+ "pad_token": "<|endoftext|>",
126
+ "pad_token_type_id": 0,
127
+ "padding_side": "right",
128
+ "processor_class": "Phi4MMProcessor",
129
+ "tokenizer_class": "GPT2Tokenizer",
130
+ "unk_token": "<|endoftext|>"
131
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff