Hugging Face's logo

gguichard
/
phi-4-mini-full_model_dwh_diff_extraction_data

Text Generation
Transformers
Safetensors
phi3
trl
sft
conversational
custom_code
text-generation-inference
Model card Files
xet
 Community
gguichard commited on
Commit
cbf2e8f
·
verified ·
1 Parent(s): ecb63b0

Upload tokenizer

Browse files
Files changed (8) hide show
  1. .gitattributes +1 -0
  2. added_tokens.json +12 -0
  3. chat_template.jinja +1 -0
  4. merges.txt +0 -0
  5. special_tokens_map.json +30 -0
  6. tokenizer.json +3 -0
  7. tokenizer_config.json +111 -0
  8. 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
+ }
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% 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 %}
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 sha256:382cc235b56c725945e149cc25f191da667c836655efd0857b004320e90e91ea
3
+ size 15524095
tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": false,
5
+ "added_tokens_decoder": {
6
+ "199999": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "200018": {
15
+ "content": "<|endofprompt|>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "200019": {
23
+ "content": "<|assistant|>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": true,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "200020": {
31
+ "content": "<|end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": true,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "200021": {
39
+ "content": "<|user|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": true,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "200022": {
47
+ "content": "<|system|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": true,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "200023": {
55
+ "content": "<|tool|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": true,
59
+ "single_word": false,
60
+ "special": false
61
+ },
62
+ "200024": {
63
+ "content": "<|/tool|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": true,
67
+ "single_word": false,
68
+ "special": false
69
+ },
70
+ "200025": {
71
+ "content": "<|tool_call|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": true,
75
+ "single_word": false,
76
+ "special": false
77
+ },
78
+ "200026": {
79
+ "content": "<|/tool_call|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": true,
83
+ "single_word": false,
84
+ "special": false
85
+ },
86
+ "200027": {
87
+ "content": "<|tool_response|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": true,
91
+ "single_word": false,
92
+ "special": false
93
+ },
94
+ "200028": {
95
+ "content": "<|tag|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": true,
99
+ "single_word": false,
100
+ "special": true
101
+ }
102
+ },
103
+ "bos_token": "<|endoftext|>",
104
+ "clean_up_tokenization_spaces": false,
105
+ "eos_token": "<|endoftext|>",
106
+ "extra_special_tokens": {},
107
+ "model_max_length": 131072,
108
+ "pad_token": "<|endoftext|>",
109
+ "tokenizer_class": "GPT2Tokenizer",
110
+ "unk_token": "<|endoftext|>"
111
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff