Hugging Face's logo

hf-tiny-v2
/
tiny-random-VaultGemmaModel

Safetensors
vaultgemma
Model card Files
xet
 Community
hf-transformers-bot commited on
Commit
461a76c
·
verified ·
1 Parent(s): 0452cd1

Update tiny models for VaultGemmaModel

Browse files
Files changed (5) hide show
  1. .gitattributes +1 -0
  2. config.json +38 -0
  3. model.safetensors +3 -0
  4. tokenizer.json +3 -0
  5. tokenizer_config.json +267 -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
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "VaultGemmaModel"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_logit_softcapping": 50.0,
8
+ "bos_token_id": 2,
9
+ "dtype": "float32",
10
+ "eos_token_id": 1,
11
+ "final_logit_softcapping": 30.0,
12
+ "head_dim": 16,
13
+ "hidden_activation": "gelu_pytorch_tanh",
14
+ "hidden_size": 32,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 32,
17
+ "layer_types": [
18
+ "sliding_attention",
19
+ "full_attention"
20
+ ],
21
+ "max_position_embeddings": 512,
22
+ "model_type": "vaultgemma",
23
+ "num_attention_heads": 2,
24
+ "num_hidden_layers": 2,
25
+ "num_key_value_heads": 2,
26
+ "pad_token_id": 0,
27
+ "query_pre_attn_scalar": 256,
28
+ "rms_norm_eps": 1e-06,
29
+ "rope_parameters": {
30
+ "rope_theta": 10000.0,
31
+ "rope_type": "default"
32
+ },
33
+ "sliding_window": 4096,
34
+ "tie_word_embeddings": false,
35
+ "transformers_version": "5.16.0.dev0",
36
+ "use_cache": true,
37
+ "vocab_size": 256000
38
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:528beb122c573770bf752e3fe775d14dd05d1755ff08ad525e97f600a75c56f2
3
+ size 32828008
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898b4e22daaad6c17e720937f679f0ff289ff0daf802a51bcd3a4634b33e633f
3
+ size 34358146
tokenizer_config.json ADDED
@@ -0,0 +1,267 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<bos>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "<eos>",
6
+ "extra_special_tokens": [
7
+ "<pad>",
8
+ "<eos>",
9
+ "<bos>",
10
+ "<mask>",
11
+ "<2mass>",
12
+ "[@BOS@]",
13
+ "[multimodal]",
14
+ "<ctrl1>",
15
+ "<ctrl2>",
16
+ "<ctrl3>",
17
+ "<ctrl4>",
18
+ "<ctrl5>",
19
+ "<ctrl6>",
20
+ "<ctrl7>",
21
+ "<ctrl8>",
22
+ "<ctrl9>",
23
+ "<ctrl10>",
24
+ "<ctrl11>",
25
+ "<ctrl12>",
26
+ "<ctrl13>",
27
+ "<ctrl14>",
28
+ "<ctrl15>",
29
+ "<ctrl16>",
30
+ "<ctrl17>",
31
+ "<ctrl18>",
32
+ "<ctrl19>",
33
+ "<ctrl20>",
34
+ "<ctrl21>",
35
+ "<ctrl22>",
36
+ "<ctrl23>",
37
+ "<ctrl24>",
38
+ "<ctrl25>",
39
+ "<ctrl26>",
40
+ "<ctrl27>",
41
+ "<ctrl28>",
42
+ "<ctrl29>",
43
+ "<ctrl30>",
44
+ "<ctrl31>",
45
+ "<ctrl32>",
46
+ "<ctrl33>",
47
+ "<ctrl34>",
48
+ "<ctrl35>",
49
+ "<ctrl36>",
50
+ "<ctrl37>",
51
+ "<ctrl38>",
52
+ "<ctrl39>",
53
+ "<ctrl40>",
54
+ "<ctrl41>",
55
+ "<ctrl42>",
56
+ "<ctrl43>",
57
+ "<ctrl44>",
58
+ "<ctrl45>",
59
+ "<ctrl46>",
60
+ "<ctrl47>",
61
+ "<ctrl48>",
62
+ "<ctrl49>",
63
+ "<ctrl50>",
64
+ "<ctrl51>",
65
+ "<ctrl52>",
66
+ "<ctrl53>",
67
+ "<ctrl54>",
68
+ "<ctrl55>",
69
+ "<ctrl56>",
70
+ "<ctrl57>",
71
+ "<ctrl58>",
72
+ "<ctrl59>",
73
+ "<ctrl60>",
74
+ "<ctrl61>",
75
+ "<ctrl62>",
76
+ "<ctrl63>",
77
+ "<ctrl64>",
78
+ "<ctrl65>",
79
+ "<ctrl66>",
80
+ "<ctrl67>",
81
+ "<ctrl68>",
82
+ "<ctrl69>",
83
+ "<ctrl70>",
84
+ "<ctrl71>",
85
+ "<ctrl72>",
86
+ "<ctrl73>",
87
+ "<ctrl74>",
88
+ "<ctrl75>",
89
+ "<ctrl76>",
90
+ "<ctrl77>",
91
+ "<ctrl78>",
92
+ "<ctrl79>",
93
+ "<ctrl80>",
94
+ "<ctrl81>",
95
+ "<ctrl82>",
96
+ "<ctrl83>",
97
+ "<ctrl84>",
98
+ "<ctrl85>",
99
+ "<ctrl86>",
100
+ "<ctrl87>",
101
+ "<ctrl88>",
102
+ "<ctrl89>",
103
+ "<ctrl90>",
104
+ "<ctrl91>",
105
+ "<ctrl92>",
106
+ "<ctrl93>",
107
+ "<ctrl94>",
108
+ "<ctrl95>",
109
+ "<ctrl96>",
110
+ "<ctrl97>",
111
+ "<ctrl98>",
112
+ "<ctrl99>",
113
+ "<ctrl100>",
114
+ "\n",
115
+ "\n\n",
116
+ "\n\n\n",
117
+ "\n\n\n\n",
118
+ "\n\n\n\n\n",
119
+ "\n\n\n\n\n\n",
120
+ "\n\n\n\n\n\n\n",
121
+ "\n\n\n\n\n\n\n\n",
122
+ "\n\n\n\n\n\n\n\n\n",
123
+ "\n\n\n\n\n\n\n\n\n\n",
124
+ "\n\n\n\n\n\n\n\n\n\n\n",
125
+ "\n\n\n\n\n\n\n\n\n\n\n\n",
126
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n",
127
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
128
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
129
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
130
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
131
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
132
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
133
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
134
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
135
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
136
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
137
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
138
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
139
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
140
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
141
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
142
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
143
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
144
+ "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
145
+ "▁▁",
146
+ "▁▁▁",
147
+ "▁▁▁▁",
148
+ "▁▁▁▁▁",
149
+ "▁▁▁▁▁▁",
150
+ "▁▁▁▁▁▁▁",
151
+ "▁▁▁▁▁▁▁▁",
152
+ "▁▁▁▁▁▁▁▁▁",
153
+ "▁▁▁▁▁▁▁▁▁▁",
154
+ "▁▁▁▁▁▁▁▁▁▁▁",
155
+ "▁▁▁▁▁▁▁▁▁▁▁▁",
156
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁",
157
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
158
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
159
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
160
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
161
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
162
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
163
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
164
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
165
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
166
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
167
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
168
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
169
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
170
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
171
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
172
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
173
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
174
+ "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
175
+ "<table>",
176
+ "<caption>",
177
+ "<thead>",
178
+ "<tbody>",
179
+ "<tfoot>",
180
+ "<tr>",
181
+ "<th>",
182
+ "<td>",
183
+ "</table>",
184
+ "</caption>",
185
+ "</thead>",
186
+ "</tbody>",
187
+ "</tfoot>",
188
+ "</tr>",
189
+ "</th>",
190
+ "</td>",
191
+ "<h1>",
192
+ "<h2>",
193
+ "<h3>",
194
+ "<h4>",
195
+ "<h5>",
196
+ "<h6>",
197
+ "<blockquote>",
198
+ "</h1>",
199
+ "</h2>",
200
+ "</h3>",
201
+ "</h4>",
202
+ "</h5>",
203
+ "</h6>",
204
+ "</blockquote>",
205
+ "<strong>",
206
+ "<em>",
207
+ "<b>",
208
+ "<i>",
209
+ "<u>",
210
+ "<s>",
211
+ "<sub>",
212
+ "<sup>",
213
+ "<code>",
214
+ "</strong>",
215
+ "</em>",
216
+ "</b>",
217
+ "</i>",
218
+ "</u>",
219
+ "</s>",
220
+ "</sub>",
221
+ "</sup>",
222
+ "</code>",
223
+ "[toxicity=0]",
224
+ "\t\t",
225
+ "\t\t\t",
226
+ "\t\t\t\t",
227
+ "\t\t\t\t\t",
228
+ "\t\t\t\t\t\t",
229
+ "\t\t\t\t\t\t\t",
230
+ "\t\t\t\t\t\t\t\t",
231
+ "\t\t\t\t\t\t\t\t\t",
232
+ "\t\t\t\t\t\t\t\t\t\t",
233
+ "\t\t\t\t\t\t\t\t\t\t\t",
234
+ "\t\t\t\t\t\t\t\t\t\t\t\t",
235
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t",
236
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
237
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
238
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
239
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
240
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
241
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
242
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
243
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
244
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
245
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
246
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
247
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
248
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
249
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
250
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
251
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
252
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
253
+ "\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t",
254
+ "<start_of_image>"
255
+ ],
256
+ "is_local": true,
257
+ "local_files_only": false,
258
+ "mask_token": "<mask>",
259
+ "model_max_length": 512,
260
+ "pad_token": "<pad>",
261
+ "sp_model_kwargs": {},
262
+ "spaces_between_special_tokens": false,
263
+ "tokenizer_class": "GemmaTokenizer",
264
+ "unk_token": "<unk>",
265
+ "use_default_system_prompt": false,
266
+ "vocab_file": "/home/runner/.cache/huggingface/hub/models--google--vaultgemma-1b/snapshots/f9624dafc1760cb2f6039e86e12055d6559d7abb/tokenizer.model"
267
+ }