Hugging Face's logo

agp9
/
gemma-4-e2b-sos-lora

Text Generation
PEFT
Safetensors
lora
sft
unsloth
gemma-4
disaster-response
triage
medical
emergency
conversational
Model card Files
xet
 Community
agp9 commited on
Commit
030ee68
·
verified ·
1 Parent(s): 8a950a2

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +289 -0
tokenizer_config.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "is_local": false,
21
+ "mask_token": "<mask>",
22
+ "model_max_length": 131072,
23
+ "model_specific_special_tokens": {
24
+ "audio_token": "<|audio|>",
25
+ "boa_token": "<|audio>",
26
+ "boi_token": "<|image>",
27
+ "eoa_token": "<audio|>",
28
+ "eoc_token": "<channel|>",
29
+ "eoi_token": "<image|>",
30
+ "eot_token": "<turn|>",
31
+ "escape_token": "<|\"|>",
32
+ "etc_token": "<tool_call|>",
33
+ "etd_token": "<tool|>",
34
+ "etr_token": "<tool_response|>",
35
+ "image_token": "<|image|>",
36
+ "soc_token": "<|channel>",
37
+ "sot_token": "<|turn>",
38
+ "stc_token": "<|tool_call>",
39
+ "std_token": "<|tool>",
40
+ "str_token": "<|tool_response>",
41
+ "think_token": "<|think|>"
42
+ },
43
+ "pad_token": "<pad>",
44
+ "padding_side": "right",
45
+ "processor_class": "Gemma4Processor",
46
+ "response_schema": {
47
+ "properties": {
48
+ "content": {
49
+ "type": "string"
50
+ },
51
+ "role": {
52
+ "const": "assistant"
53
+ },
54
+ "thinking": {
55
+ "type": "string"
56
+ },
57
+ "tool_calls": {
58
+ "items": {
59
+ "properties": {
60
+ "function": {
61
+ "properties": {
62
+ "arguments": {
63
+ "additionalProperties": {},
64
+ "type": "object",
65
+ "x-parser": "gemma4-tool-call"
66
+ },
67
+ "name": {
68
+ "type": "string"
69
+ }
70
+ },
71
+ "type": "object",
72
+ "x-regex": "call\\:(?P<name>\\w+)(?P<arguments>\\{.*\\})"
73
+ },
74
+ "type": {
75
+ "const": "function"
76
+ }
77
+ },
78
+ "type": "object"
79
+ },
80
+ "type": "array",
81
+ "x-regex-iterator": "<\\|tool_call>(.*?)<tool_call\\|>"
82
+ }
83
+ },
84
+ "type": "object",
85
+ "x-regex": "(\\<\\|channel\\>thought\\n(?P<thinking>.*?)\\<channel\\|\\>)?(?P<tool_calls>\\<\\|tool_call\\>.*\\<tool_call\\|\\>)?(?P<content>(?:(?!\\<turn\\|\\>)(?!\\<\\|tool_response\\>).)+)?(?:\\<turn\\|\\>|\\<\\|tool_response\\>)?"
86
+ },
87
+ "soc_token": "<|channel>",
88
+ "sot_token": "<|turn>",
89
+ "stc_token": "<|tool_call>",
90
+ "std_token": "<|tool>",
91
+ "str_token": "<|tool_response>",
92
+ "think_token": "<|think|>",
93
+ "tokenizer_class": "GemmaTokenizer",
94
+ "unk_token": "<unk>",
95
+ "added_tokens_decoder": {
96
+ "0": {
97
+ "content": "<pad>",
98
+ "single_word": false,
99
+ "lstrip": false,
100
+ "rstrip": false,
101
+ "normalized": false,
102
+ "special": true
103
+ },
104
+ "1": {
105
+ "content": "<eos>",
106
+ "single_word": false,
107
+ "lstrip": false,
108
+ "rstrip": false,
109
+ "normalized": false,
110
+ "special": true
111
+ },
112
+ "2": {
113
+ "content": "<bos>",
114
+ "single_word": false,
115
+ "lstrip": false,
116
+ "rstrip": false,
117
+ "normalized": false,
118
+ "special": true
119
+ },
120
+ "3": {
121
+ "content": "<unk>",
122
+ "single_word": false,
123
+ "lstrip": false,
124
+ "rstrip": false,
125
+ "normalized": false,
126
+ "special": true
127
+ },
128
+ "4": {
129
+ "content": "<mask>",
130
+ "single_word": false,
131
+ "lstrip": false,
132
+ "rstrip": false,
133
+ "normalized": false,
134
+ "special": true
135
+ },
136
+ "46": {
137
+ "content": "<|tool>",
138
+ "single_word": false,
139
+ "lstrip": false,
140
+ "rstrip": false,
141
+ "normalized": false,
142
+ "special": true
143
+ },
144
+ "47": {
145
+ "content": "<tool|>",
146
+ "single_word": false,
147
+ "lstrip": false,
148
+ "rstrip": false,
149
+ "normalized": false,
150
+ "special": true
151
+ },
152
+ "48": {
153
+ "content": "<|tool_call>",
154
+ "single_word": false,
155
+ "lstrip": false,
156
+ "rstrip": false,
157
+ "normalized": false,
158
+ "special": true
159
+ },
160
+ "49": {
161
+ "content": "<tool_call|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": false,
166
+ "special": true
167
+ },
168
+ "50": {
169
+ "content": "<|tool_response>",
170
+ "single_word": false,
171
+ "lstrip": false,
172
+ "rstrip": false,
173
+ "normalized": false,
174
+ "special": true
175
+ },
176
+ "51": {
177
+ "content": "<tool_response|>",
178
+ "single_word": false,
179
+ "lstrip": false,
180
+ "rstrip": false,
181
+ "normalized": false,
182
+ "special": true
183
+ },
184
+ "52": {
185
+ "content": "<|\"|>",
186
+ "single_word": false,
187
+ "lstrip": false,
188
+ "rstrip": false,
189
+ "normalized": false,
190
+ "special": true
191
+ },
192
+ "98": {
193
+ "content": "<|think|>",
194
+ "single_word": false,
195
+ "lstrip": false,
196
+ "rstrip": false,
197
+ "normalized": false,
198
+ "special": true
199
+ },
200
+ "100": {
201
+ "content": "<|channel>",
202
+ "single_word": false,
203
+ "lstrip": false,
204
+ "rstrip": false,
205
+ "normalized": false,
206
+ "special": true
207
+ },
208
+ "101": {
209
+ "content": "<channel|>",
210
+ "single_word": false,
211
+ "lstrip": false,
212
+ "rstrip": false,
213
+ "normalized": false,
214
+ "special": true
215
+ },
216
+ "105": {
217
+ "content": "<|turn>",
218
+ "single_word": false,
219
+ "lstrip": false,
220
+ "rstrip": false,
221
+ "normalized": false,
222
+ "special": true
223
+ },
224
+ "106": {
225
+ "content": "<turn|>",
226
+ "single_word": false,
227
+ "lstrip": false,
228
+ "rstrip": false,
229
+ "normalized": false,
230
+ "special": true
231
+ },
232
+ "255999": {
233
+ "content": "<|image>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": false,
238
+ "special": true
239
+ },
240
+ "256000": {
241
+ "content": "<|audio>",
242
+ "single_word": false,
243
+ "lstrip": false,
244
+ "rstrip": false,
245
+ "normalized": false,
246
+ "special": true
247
+ },
248
+ "258880": {
249
+ "content": "<|image|>",
250
+ "single_word": false,
251
+ "lstrip": false,
252
+ "rstrip": false,
253
+ "normalized": false,
254
+ "special": true
255
+ },
256
+ "258881": {
257
+ "content": "<|audio|>",
258
+ "single_word": false,
259
+ "lstrip": false,
260
+ "rstrip": false,
261
+ "normalized": false,
262
+ "special": true
263
+ },
264
+ "258882": {
265
+ "content": "<image|>",
266
+ "single_word": false,
267
+ "lstrip": false,
268
+ "rstrip": false,
269
+ "normalized": false,
270
+ "special": true
271
+ },
272
+ "258883": {
273
+ "content": "<audio|>",
274
+ "single_word": false,
275
+ "lstrip": false,
276
+ "rstrip": false,
277
+ "normalized": false,
278
+ "special": true
279
+ },
280
+ "258884": {
281
+ "content": "<|video|>",
282
+ "single_word": false,
283
+ "lstrip": false,
284
+ "rstrip": false,
285
+ "normalized": false,
286
+ "special": true
287
+ }
288
+ }
289
+ }