craftslab commited on
Commit
0f7eaec
·
verified ·
1 Parent(s): 27b10c6

Upload v1.0/gemma-4-e2b-it_q4/tokenizer_config.json with huggingface_hub

Browse files
v1.0/gemma-4-e2b-it_q4/tokenizer_config.json ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_token": "<|audio|>",
3
+ "backend": "tokenizers",
4
+ "boa_token": "<|audio>",
5
+ "boi_token": "<|image>",
6
+ "bos_token": "<bos>",
7
+ "eoa_token": "<audio|>",
8
+ "eoc_token": "<channel|>",
9
+ "eoi_token": "<image|>",
10
+ "eos_token": "<eos>",
11
+ "eot_token": "<turn|>",
12
+ "escape_token": "<|\"|>",
13
+ "etc_token": "<tool_call|>",
14
+ "etd_token": "<tool|>",
15
+ "etr_token": "<tool_response|>",
16
+ "extra_special_tokens": [
17
+ "<|video|>"
18
+ ],
19
+ "image_token": "<|image|>",
20
+ "mask_token": "<mask>",
21
+ "model_max_length": 1000000000000000019884624838656,
22
+ "pad_token": "<pad>",
23
+ "padding_side": "left",
24
+ "processor_class": "Gemma4Processor",
25
+ "response_schema": {
26
+ "type": "object",
27
+ "properties": {
28
+ "role": {
29
+ "const": "assistant"
30
+ },
31
+ "thinking": {
32
+ "type": "string"
33
+ },
34
+ "content": {
35
+ "type": "string"
36
+ },
37
+ "tool_calls": {
38
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>",
39
+ "type": "array",
40
+ "items": {
41
+ "type": "object",
42
+ "properties": {
43
+ "type": {
44
+ "const": "function"
45
+ },
46
+ "function": {
47
+ "type": "object",
48
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})",
49
+ "properties": {
50
+ "name": {
51
+ "type": "string"
52
+ },
53
+ "arguments": {
54
+ "type": "object",
55
+ "x-parser": "gemma4-tool-call",
56
+ "additionalProperties": {}
57
+ }
58
+ }
59
+ }
60
+ }
61
+ }
62
+ }
63
+ },
64
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
65
+ },
66
+ "response_template": {
67
+ "defaults": {
68
+ "role": "assistant"
69
+ },
70
+ "fields": {
71
+ "content": {
72
+ "close": [
73
+ "<turn|>",
74
+ "<|tool_response>",
75
+ "<eos>"
76
+ ],
77
+ "content": "text"
78
+ },
79
+ "thinking": {
80
+ "close": "<channel|>",
81
+ "content": "text",
82
+ "open": "<|channel>thought\n"
83
+ },
84
+ "tool_calls": {
85
+ "close": "<tool_call|>",
86
+ "content": "json",
87
+ "content_args": {
88
+ "string_delims": [
89
+ [
90
+ "<|\"|>",
91
+ "<|\"|>"
92
+ ]
93
+ ],
94
+ "unquoted_keys": true
95
+ },
96
+ "open_pattern": "<\\|tool_call>call:(?P<name>\\w+)",
97
+ "repeats": true,
98
+ "transform": {
99
+ "function": {
100
+ "arguments": "{content}",
101
+ "name": "{name}"
102
+ },
103
+ "type": "function"
104
+ }
105
+ }
106
+ },
107
+ "start_anchor": [
108
+ "<|turn>model\n",
109
+ "<tool_response|>"
110
+ ]
111
+ },
112
+ "soc_token": "<|channel>",
113
+ "sot_token": "<|turn>",
114
+ "stc_token": "<|tool_call>",
115
+ "std_token": "<|tool>",
116
+ "str_token": "<|tool_response>",
117
+ "think_token": "<|think|>",
118
+ "tokenizer_class": "GemmaTokenizer",
119
+ "unk_token": "<unk>"
120
+ }