Hugging Face's logo

Frostrabbit
/
TaiwanVarietyShowSubtitlesCapture

Text Generation
Transformers
TensorBoard
Safetensors
tinyllava
custom_code
Model card Files Metrics Community
Frostrabbit commited on
Commit
c059dc1
•
1 Parent(s): 96b9bdc

Upload model

Browse files
Files changed (16) hide show
  1. adapter_config.json +381 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +40 -0
  4. config.json +76 -0
  5. connector/pytorch_model.bin +3 -0
  6. language_model/config.json +34 -0
  7. language_model/pytorch_model.bin +3 -0
  8. log.txt +5 -0
  9. merges.txt +0 -0
  10. runs/Jun25_13-45-03_DESKTOP-38BQKTU/events.out.tfevents.1719294313.DESKTOP-38BQKTU +3 -0
  11. special_tokens_map.json +30 -0
  12. tokenizer_config.json +327 -0
  13. trainer_state.json +0 -0
  14. vision_tower/config.json +16 -0
  15. vision_tower/pytorch_model.bin +3 -0
  16. vocab.json +0 -0
adapter_config.json ADDED
@@ -0,0 +1,381 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 256,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 128,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "vision_tower._vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
24
+ "vision_tower._vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
25
+ "language_model.model.layers.17.mlp.fc2",
26
+ "language_model.model.layers.20.self_attn.dense",
27
+ "language_model.model.layers.11.self_attn.v_proj",
28
+ "vision_tower._vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
29
+ "vision_tower._vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
30
+ "vision_tower._vision_tower.vision_model.encoder.layers.10.mlp.fc2",
31
+ "language_model.model.layers.27.self_attn.dense",
32
+ "vision_tower._vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
33
+ "vision_tower._vision_tower.vision_model.encoder.layers.0.mlp.fc1",
34
+ "language_model.model.layers.17.self_attn.q_proj",
35
+ "vision_tower._vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
36
+ "language_model.model.layers.30.self_attn.q_proj",
37
+ "language_model.model.layers.6.mlp.fc2",
38
+ "language_model.model.layers.31.mlp.fc2",
39
+ "vision_tower._vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
40
+ "language_model.model.layers.14.self_attn.k_proj",
41
+ "language_model.model.layers.3.mlp.fc1",
42
+ "language_model.model.layers.30.self_attn.dense",
43
+ "vision_tower._vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
44
+ "vision_tower._vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
45
+ "language_model.model.layers.23.self_attn.q_proj",
46
+ "vision_tower._vision_tower.vision_model.encoder.layers.25.self_attn.k_proj",
47
+ "language_model.model.layers.4.mlp.fc2",
48
+ "vision_tower._vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
49
+ "language_model.model.layers.11.mlp.fc2",
50
+ "vision_tower._vision_tower.vision_model.encoder.layers.22.mlp.fc1",
51
+ "vision_tower._vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
52
+ "language_model.model.layers.3.self_attn.dense",
53
+ "language_model.model.layers.12.self_attn.v_proj",
54
+ "language_model.model.layers.18.self_attn.dense",
55
+ "vision_tower._vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
56
+ "language_model.model.layers.28.mlp.fc2",
57
+ "language_model.model.layers.10.mlp.fc2",
58
+ "vision_tower._vision_tower.vision_model.encoder.layers.26.mlp.fc2",
59
+ "vision_tower._vision_tower.vision_model.encoder.layers.10.mlp.fc1",
60
+ "language_model.model.layers.0.mlp.fc2",
61
+ "vision_tower._vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
62
+ "vision_tower._vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
63
+ "language_model.model.layers.12.mlp.fc2",
64
+ "vision_tower._vision_tower.vision_model.encoder.layers.16.mlp.fc2",
65
+ "language_model.model.layers.17.self_attn.dense",
66
+ "language_model.model.layers.3.self_attn.k_proj",
67
+ "vision_tower._vision_tower.vision_model.encoder.layers.16.mlp.fc1",
68
+ "language_model.model.layers.11.self_attn.k_proj",
69
+ "language_model.model.layers.12.self_attn.dense",
70
+ "language_model.model.layers.5.mlp.fc1",
71
+ "language_model.model.layers.5.mlp.fc2",
72
+ "language_model.model.layers.0.self_attn.q_proj",
73
+ "language_model.model.layers.28.mlp.fc1",
74
+ "vision_tower._vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
75
+ "vision_tower._vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
76
+ "vision_tower._vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
77
+ "vision_tower._vision_tower.vision_model.encoder.layers.8.mlp.fc2",
78
+ "vision_tower._vision_tower.vision_model.encoder.layers.6.mlp.fc2",
79
+ "language_model.model.layers.28.self_attn.v_proj",
80
+ "vision_tower._vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
81
+ "vision_tower._vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
82
+ "vision_tower._vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
83
+ "language_model.model.layers.10.self_attn.q_proj",
84
+ "vision_tower._vision_tower.vision_model.encoder.layers.2.mlp.fc2",
85
+ "language_model.model.layers.7.self_attn.v_proj",
86
+ "language_model.model.layers.16.mlp.fc1",
87
+ "language_model.model.layers.16.mlp.fc2",
88
+ "language_model.model.layers.13.self_attn.v_proj",
89
+ "vision_tower._vision_tower.vision_model.encoder.layers.26.mlp.fc1",
90
+ "vision_tower._vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
91
+ "language_model.model.layers.2.self_attn.k_proj",
92
+ "vision_tower._vision_tower.vision_model.encoder.layers.24.self_attn.out_proj",
93
+ "language_model.model.layers.29.mlp.fc1",
94
+ "vision_tower._vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
95
+ "language_model.model.layers.15.self_attn.q_proj",
96
+ "language_model.model.layers.27.self_attn.v_proj",
97
+ "vision_tower._vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
98
+ "vision_tower._vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
99
+ "vision_tower._vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
100
+ "vision_tower._vision_tower.vision_model.encoder.layers.24.self_attn.q_proj",
101
+ "language_model.model.layers.27.self_attn.q_proj",
102
+ "language_model.model.layers.16.self_attn.q_proj",
103
+ "vision_tower._vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
104
+ "language_model.model.layers.4.mlp.fc1",
105
+ "language_model.model.layers.6.mlp.fc1",
106
+ "vision_tower._vision_tower.vision_model.encoder.layers.3.mlp.fc1",
107
+ "language_model.model.layers.0.self_attn.dense",
108
+ "vision_tower._vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
109
+ "language_model.model.layers.7.mlp.fc2",
110
+ "vision_tower._vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
111
+ "vision_tower._vision_tower.vision_model.encoder.layers.22.mlp.fc2",
112
+ "vision_tower._vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
113
+ "vision_tower._vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
114
+ "vision_tower._vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
115
+ "language_model.model.layers.19.self_attn.k_proj",
116
+ "language_model.model.layers.14.self_attn.q_proj",
117
+ "language_model.model.layers.12.mlp.fc1",
118
+ "language_model.model.layers.20.mlp.fc1",
119
+ "vision_tower._vision_tower.vision_model.encoder.layers.13.mlp.fc1",
120
+ "vision_tower._vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
121
+ "language_model.model.layers.13.self_attn.q_proj",
122
+ "language_model.model.layers.5.self_attn.q_proj",
123
+ "vision_tower._vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
124
+ "vision_tower._vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
125
+ "language_model.model.layers.27.mlp.fc1",
126
+ "vision_tower._vision_tower.vision_model.encoder.layers.9.mlp.fc1",
127
+ "language_model.model.layers.0.self_attn.v_proj",
128
+ "language_model.model.layers.11.self_attn.dense",
129
+ "vision_tower._vision_tower.vision_model.encoder.layers.21.mlp.fc2",
130
+ "language_model.model.layers.30.mlp.fc2",
131
+ "vision_tower._vision_tower.vision_model.encoder.layers.13.mlp.fc2",
132
+ "vision_tower._vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
133
+ "language_model.model.layers.11.mlp.fc1",
134
+ "language_model.model.layers.5.self_attn.k_proj",
135
+ "vision_tower._vision_tower.vision_model.encoder.layers.14.mlp.fc1",
136
+ "language_model.model.layers.5.self_attn.v_proj",
137
+ "language_model.model.layers.4.self_attn.dense",
138
+ "language_model.model.layers.31.self_attn.q_proj",
139
+ "language_model.model.layers.11.self_attn.q_proj",
140
+ "vision_tower._vision_tower.vision_model.encoder.layers.11.mlp.fc2",
141
+ "language_model.model.layers.29.self_attn.k_proj",
142
+ "vision_tower._vision_tower.vision_model.encoder.layers.5.mlp.fc1",
143
+ "vision_tower._vision_tower.vision_model.encoder.layers.6.mlp.fc1",
144
+ "vision_tower._vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
145
+ "vision_tower._vision_tower.vision_model.encoder.layers.26.self_attn.k_proj",
146
+ "language_model.model.layers.29.mlp.fc2",
147
+ "language_model.model.layers.6.self_attn.dense",
148
+ "vision_tower._vision_tower.vision_model.encoder.layers.25.self_attn.q_proj",
149
+ "language_model.model.layers.27.mlp.fc2",
150
+ "language_model.model.layers.18.self_attn.k_proj",
151
+ "language_model.model.layers.26.self_attn.v_proj",
152
+ "language_model.model.layers.15.mlp.fc2",
153
+ "vision_tower._vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
154
+ "vision_tower._vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
155
+ "vision_tower._vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
156
+ "language_model.model.layers.30.self_attn.v_proj",
157
+ "language_model.model.layers.8.self_attn.dense",
158
+ "vision_tower._vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
159
+ "language_model.model.layers.25.mlp.fc1",
160
+ "language_model.model.layers.2.self_attn.dense",
161
+ "language_model.model.layers.21.self_attn.k_proj",
162
+ "vision_tower._vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
163
+ "language_model.model.layers.21.self_attn.dense",
164
+ "language_model.model.layers.22.self_attn.k_proj",
165
+ "vision_tower._vision_tower.vision_model.encoder.layers.7.mlp.fc1",
166
+ "vision_tower._vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
167
+ "language_model.model.layers.15.mlp.fc1",
168
+ "language_model.model.layers.7.self_attn.dense",
169
+ "vision_tower._vision_tower.vision_model.encoder.layers.0.mlp.fc2",
170
+ "language_model.model.layers.18.self_attn.v_proj",
171
+ "language_model.model.layers.18.self_attn.q_proj",
172
+ "language_model.model.layers.24.self_attn.q_proj",
173
+ "language_model.model.layers.8.self_attn.q_proj",
174
+ "vision_tower._vision_tower.vision_model.encoder.layers.12.mlp.fc2",
175
+ "vision_tower._vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
176
+ "language_model.model.layers.31.mlp.fc1",
177
+ "vision_tower._vision_tower.vision_model.encoder.layers.2.mlp.fc1",
178
+ "vision_tower._vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
179
+ "language_model.model.layers.25.self_attn.k_proj",
180
+ "language_model.model.layers.2.mlp.fc2",
181
+ "language_model.model.layers.1.self_attn.q_proj",
182
+ "language_model.model.layers.4.self_attn.k_proj",
183
+ "vision_tower._vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
184
+ "vision_tower._vision_tower.vision_model.encoder.layers.25.mlp.fc2",
185
+ "language_model.model.layers.25.self_attn.q_proj",
186
+ "vision_tower._vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
187
+ "vision_tower._vision_tower.vision_model.encoder.layers.19.mlp.fc1",
188
+ "vision_tower._vision_tower.vision_model.encoder.layers.25.mlp.fc1",
189
+ "language_model.model.layers.7.mlp.fc1",
190
+ "vision_tower._vision_tower.vision_model.encoder.layers.24.mlp.fc2",
191
+ "vision_tower._vision_tower.vision_model.encoder.layers.26.self_attn.q_proj",
192
+ "language_model.model.layers.27.self_attn.k_proj",
193
+ "language_model.model.layers.9.mlp.fc1",
194
+ "vision_tower._vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
195
+ "language_model.model.layers.10.self_attn.v_proj",
196
+ "vision_tower._vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
197
+ "language_model.model.layers.25.self_attn.dense",
198
+ "vision_tower._vision_tower.vision_model.encoder.layers.9.mlp.fc2",
199
+ "vision_tower._vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
200
+ "language_model.model.layers.12.self_attn.q_proj",
201
+ "vision_tower._vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
202
+ "language_model.model.layers.22.self_attn.dense",
203
+ "language_model.model.layers.20.self_attn.q_proj",
204
+ "vision_tower._vision_tower.vision_model.encoder.layers.5.mlp.fc2",
205
+ "language_model.model.layers.21.mlp.fc1",
206
+ "vision_tower._vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
207
+ "vision_tower._vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
208
+ "language_model.model.layers.4.self_attn.q_proj",
209
+ "vision_tower._vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
210
+ "vision_tower._vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
211
+ "vision_tower._vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
212
+ "language_model.model.layers.20.self_attn.k_proj",
213
+ "vision_tower._vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
214
+ "language_model.model.layers.13.self_attn.k_proj",
215
+ "language_model.model.layers.19.self_attn.v_proj",
216
+ "language_model.model.layers.31.self_attn.dense",
217
+ "vision_tower._vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
218
+ "language_model.model.layers.1.self_attn.k_proj",
219
+ "vision_tower._vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
220
+ "vision_tower._vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
221
+ "language_model.model.layers.14.mlp.fc2",
222
+ "language_model.model.layers.23.self_attn.dense",
223
+ "language_model.model.layers.16.self_attn.k_proj",
224
+ "vision_tower._vision_tower.vision_model.encoder.layers.25.self_attn.out_proj",
225
+ "language_model.model.layers.30.mlp.fc1",
226
+ "language_model.model.layers.28.self_attn.dense",
227
+ "language_model.model.layers.30.self_attn.k_proj",
228
+ "language_model.model.layers.15.self_attn.k_proj",
229
+ "language_model.model.layers.24.mlp.fc1",
230
+ "language_model.model.layers.17.self_attn.k_proj",
231
+ "vision_tower._vision_tower.vision_model.encoder.layers.24.self_attn.k_proj",
232
+ "vision_tower._vision_tower.vision_model.encoder.layers.26.self_attn.out_proj",
233
+ "vision_tower._vision_tower.vision_model.encoder.layers.3.mlp.fc2",
234
+ "language_model.model.layers.8.self_attn.v_proj",
235
+ "vision_tower._vision_tower.vision_model.encoder.layers.24.mlp.fc1",
236
+ "language_model.model.layers.19.self_attn.dense",
237
+ "vision_tower._vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
238
+ "vision_tower._vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
239
+ "language_model.model.layers.3.mlp.fc2",
240
+ "language_model.model.layers.22.mlp.fc2",
241
+ "vision_tower._vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
242
+ "vision_tower._vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
243
+ "vision_tower._vision_tower.vision_model.encoder.layers.23.mlp.fc2",
244
+ "vision_tower._vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
245
+ "language_model.model.layers.24.self_attn.dense",
246
+ "vision_tower._vision_tower.vision_model.encoder.layers.20.mlp.fc1",
247
+ "vision_tower._vision_tower.vision_model.encoder.layers.1.mlp.fc2",
248
+ "vision_tower._vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
249
+ "vision_tower._vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
250
+ "vision_tower._vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
251
+ "language_model.model.layers.21.self_attn.v_proj",
252
+ "language_model.model.layers.13.mlp.fc2",
253
+ "language_model.model.layers.10.self_attn.dense",
254
+ "vision_tower._vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
255
+ "vision_tower._vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
256
+ "language_model.model.layers.26.self_attn.k_proj",
257
+ "vision_tower._vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
258
+ "language_model.model.layers.31.self_attn.k_proj",
259
+ "language_model.model.layers.15.self_attn.v_proj",
260
+ "vision_tower._vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
261
+ "vision_tower._vision_tower.vision_model.encoder.layers.15.mlp.fc1",
262
+ "language_model.model.layers.0.self_attn.k_proj",
263
+ "language_model.model.layers.19.mlp.fc1",
264
+ "vision_tower._vision_tower.vision_model.encoder.layers.15.mlp.fc2",
265
+ "language_model.model.layers.25.mlp.fc2",
266
+ "language_model.model.layers.9.self_attn.q_proj",
267
+ "language_model.model.layers.6.self_attn.v_proj",
268
+ "language_model.model.layers.21.self_attn.q_proj",
269
+ "vision_tower._vision_tower.vision_model.encoder.layers.18.mlp.fc1",
270
+ "language_model.model.layers.16.self_attn.dense",
271
+ "language_model.model.layers.2.self_attn.q_proj",
272
+ "language_model.model.layers.22.self_attn.q_proj",
273
+ "language_model.model.layers.31.self_attn.v_proj",
274
+ "language_model.model.layers.26.mlp.fc1",
275
+ "vision_tower._vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
276
+ "language_model.model.layers.7.self_attn.q_proj",
277
+ "language_model.model.layers.9.mlp.fc2",
278
+ "vision_tower._vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
279
+ "vision_tower._vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
280
+ "vision_tower._vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
281
+ "language_model.model.layers.28.self_attn.q_proj",
282
+ "vision_tower._vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
283
+ "vision_tower._vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
284
+ "vision_tower._vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
285
+ "language_model.model.layers.4.self_attn.v_proj",
286
+ "vision_tower._vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
287
+ "vision_tower._vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
288
+ "vision_tower._vision_tower.vision_model.encoder.layers.23.mlp.fc1",
289
+ "language_model.model.layers.22.mlp.fc1",
290
+ "language_model.model.layers.8.mlp.fc2",
291
+ "language_model.model.layers.2.self_attn.v_proj",
292
+ "language_model.model.layers.15.self_attn.dense",
293
+ "language_model.model.layers.1.mlp.fc2",
294
+ "language_model.model.layers.28.self_attn.k_proj",
295
+ "language_model.model.layers.17.mlp.fc1",
296
+ "vision_tower._vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
297
+ "language_model.model.layers.26.self_attn.dense",
298
+ "language_model.model.layers.14.self_attn.v_proj",
299
+ "vision_tower._vision_tower.vision_model.encoder.layers.8.mlp.fc1",
300
+ "language_model.model.layers.3.self_attn.v_proj",
301
+ "vision_tower._vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
302
+ "language_model.model.layers.18.mlp.fc2",
303
+ "vision_tower._vision_tower.vision_model.encoder.layers.25.self_attn.v_proj",
304
+ "language_model.model.layers.8.mlp.fc1",
305
+ "language_model.model.layers.23.self_attn.v_proj",
306
+ "language_model.model.layers.21.mlp.fc2",
307
+ "language_model.model.layers.14.mlp.fc1",
308
+ "language_model.model.layers.25.self_attn.v_proj",
309
+ "vision_tower._vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
310
+ "language_model.model.layers.29.self_attn.q_proj",
311
+ "vision_tower._vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
312
+ "language_model.model.layers.26.mlp.fc2",
313
+ "vision_tower._vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
314
+ "language_model.model.layers.8.self_attn.k_proj",
315
+ "vision_tower._vision_tower.vision_model.encoder.layers.19.mlp.fc2",
316
+ "language_model.model.layers.13.mlp.fc1",
317
+ "vision_tower._vision_tower.vision_model.encoder.layers.7.mlp.fc2",
318
+ "vision_tower._vision_tower.vision_model.encoder.layers.26.self_attn.v_proj",
319
+ "language_model.model.layers.10.self_attn.k_proj",
320
+ "language_model.model.layers.9.self_attn.dense",
321
+ "language_model.model.layers.13.self_attn.dense",
322
+ "vision_tower._vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
323
+ "vision_tower._vision_tower.vision_model.encoder.layers.18.mlp.fc2",
324
+ "language_model.model.layers.29.self_attn.dense",
325
+ "language_model.model.layers.6.self_attn.q_proj",
326
+ "vision_tower._vision_tower.vision_model.encoder.layers.20.mlp.fc2",
327
+ "vision_tower._vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
328
+ "vision_tower._vision_tower.vision_model.encoder.layers.1.mlp.fc1",
329
+ "language_model.model.layers.26.self_attn.q_proj",
330
+ "vision_tower._vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
331
+ "language_model.model.layers.9.self_attn.k_proj",
332
+ "language_model.model.layers.12.self_attn.k_proj",
333
+ "language_model.model.layers.20.mlp.fc2",
334
+ "language_model.model.layers.24.self_attn.k_proj",
335
+ "language_model.model.layers.7.self_attn.k_proj",
336
+ "vision_tower._vision_tower.vision_model.encoder.layers.17.mlp.fc1",
337
+ "language_model.model.layers.24.self_attn.v_proj",
338
+ "language_model.model.layers.10.mlp.fc1",
339
+ "vision_tower._vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
340
+ "vision_tower._vision_tower.vision_model.encoder.layers.12.mlp.fc1",
341
+ "vision_tower._vision_tower.vision_model.encoder.layers.4.mlp.fc1",
342
+ "language_model.model.layers.22.self_attn.v_proj",
343
+ "vision_tower._vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
344
+ "vision_tower._vision_tower.vision_model.encoder.layers.17.mlp.fc2",
345
+ "language_model.model.layers.19.self_attn.q_proj",
346
+ "vision_tower._vision_tower.vision_model.encoder.layers.21.mlp.fc1",
347
+ "language_model.model.layers.3.self_attn.q_proj",
348
+ "language_model.model.layers.2.mlp.fc1",
349
+ "vision_tower._vision_tower.vision_model.encoder.layers.11.mlp.fc1",
350
+ "vision_tower._vision_tower.vision_model.encoder.layers.14.mlp.fc2",
351
+ "vision_tower._vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
352
+ "language_model.model.layers.5.self_attn.dense",
353
+ "language_model.model.layers.16.self_attn.v_proj",
354
+ "vision_tower._vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
355
+ "vision_tower._vision_tower.vision_model.encoder.layers.4.mlp.fc2",
356
+ "language_model.model.layers.6.self_attn.k_proj",
357
+ "language_model.model.layers.23.mlp.fc2",
358
+ "language_model.model.layers.1.self_attn.dense",
359
+ "language_model.model.layers.0.mlp.fc1",
360
+ "vision_tower._vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
361
+ "language_model.model.layers.17.self_attn.v_proj",
362
+ "language_model.model.layers.9.self_attn.v_proj",
363
+ "language_model.model.layers.23.self_attn.k_proj",
364
+ "vision_tower._vision_tower.vision_model.encoder.layers.24.self_attn.v_proj",
365
+ "language_model.model.layers.14.self_attn.dense",
366
+ "language_model.model.layers.20.self_attn.v_proj",
367
+ "language_model.model.layers.23.mlp.fc1",
368
+ "language_model.model.layers.24.mlp.fc2",
369
+ "language_model.model.layers.1.self_attn.v_proj",
370
+ "language_model.model.layers.19.mlp.fc2",
371
+ "language_model.model.layers.18.mlp.fc1",
372
+ "language_model.model.layers.1.mlp.fc1",
373
+ "language_model.model.layers.29.self_attn.v_proj",
374
+ "vision_tower._vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
375
+ "vision_tower._vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
376
+ "vision_tower._vision_tower.vision_model.encoder.layers.8.self_attn.k_proj"
377
+ ],
378
+ "task_type": "CAUSAL_LM",
379
+ "use_dora": false,
380
+ "use_rslora": false
381
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3390b5b55136a68dea6d316f28ae3a26f167ff82f9c69adb725d21e9e5537a
3
+ size 516726728
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "\t\t": 50294,
3
+ "\t\t\t": 50293,
4
+ "\t\t\t\t": 50292,
5
+ "\t\t\t\t\t": 50291,
6
+ "\t\t\t\t\t\t": 50290,
7
+ "\t\t\t\t\t\t\t": 50289,
8
+ "\t\t\t\t\t\t\t\t": 50288,
9
+ "\t\t\t\t\t\t\t\t\t": 50287,
10
+ " ": 50286,
11
+ " ": 50285,
12
+ " ": 50284,
13
+ " ": 50283,
14
+ " ": 50282,
15
+ " ": 50281,
16
+ " ": 50280,
17
+ " ": 50279,
18
+ " ": 50278,
19
+ " ": 50277,
20
+ " ": 50276,
21
+ " ": 50275,
22
+ " ": 50274,
23
+ " ": 50273,
24
+ " ": 50272,
25
+ " ": 50271,
26
+ " ": 50270,
27
+ " ": 50269,
28
+ " ": 50268,
29
+ " ": 50267,
30
+ " ": 50266,
31
+ " ": 50265,
32
+ " ": 50264,
33
+ " ": 50263,
34
+ " ": 50262,
35
+ " ": 50261,
36
+ " ": 50260,
37
+ " ": 50259,
38
+ " ": 50258,
39
+ " ": 50257
40
+ }
config.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B",
3
+ "architectures": [
4
+ "TinyLlavaForConditionalGeneration"
5
+ ],
6
+ "auto_map": {
7
+ "AutoConfig": "tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B--configuration.TinyLlavaConfig",
8
+ "AutoModelForCausalLM": "tinyllava/TinyLLaVA-Phi-2-SigLIP-3.1B--modeling_tinyllava_phi.TinyLlavaForConditionalGeneration"
9
+ },
10
+ "cache_dir": null,
11
+ "connector_type": "mlp2x_gelu",
12
+ "hidden_size": 2560,
13
+ "ignore_index": -100,
14
+ "image_aspect_ratio": "square",
15
+ "image_token_index": -200,
16
+ "llm_model_name_or_path": "microsoft/phi-2",
17
+ "model_type": "tinyllava",
18
+ "num_queries": 128,
19
+ "num_resampler_layers": 3,
20
+ "pad_token": "<|endoftext|>",
21
+ "resampler_hidden_size": 768,
22
+ "text_config": {
23
+ "_name_or_path": "microsoft/phi-2",
24
+ "architectures": [
25
+ "PhiForCausalLM"
26
+ ],
27
+ "auto_map": {
28
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
29
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
30
+ },
31
+ "bos_token_id": 50256,
32
+ "embd_pdrop": 0.0,
33
+ "eos_token_id": 50256,
34
+ "hidden_act": "gelu_new",
35
+ "hidden_size": 2560,
36
+ "intermediate_size": 10240,
37
+ "layer_norm_eps": 1e-05,
38
+ "model_type": "phi",
39
+ "num_hidden_layers": 32,
40
+ "partial_rotary_factor": 0.4,
41
+ "qk_layernorm": false,
42
+ "resid_pdrop": 0.1,
43
+ "torch_dtype": "float16",
44
+ "vocab_size": 51200
45
+ },
46
+ "tokenizer_model_max_length": 3072,
47
+ "tokenizer_name_or_path": "microsoft/phi-2",
48
+ "tokenizer_padding_side": "right",
49
+ "tokenizer_use_fast": false,
50
+ "torch_dtype": "float16",
51
+ "transformers_version": "4.39.3",
52
+ "tune_type_connector": "full",
53
+ "tune_type_llm": "lora",
54
+ "tune_type_vision_tower": "lora",
55
+ "tune_vision_tower_from_layer": 0,
56
+ "use_cache": true,
57
+ "vision_config": {
58
+ "hidden_act": "gelu_pytorch_tanh",
59
+ "hidden_size": 1152,
60
+ "image_size": 384,
61
+ "intermediate_size": 4304,
62
+ "layer_norm_eps": 1e-06,
63
+ "model_name_or_path": "google/siglip-so400m-patch14-384",
64
+ "model_name_or_path2": "",
65
+ "model_type": "siglip_vision_model",
66
+ "num_attention_heads": 16,
67
+ "num_hidden_layers": 27,
68
+ "patch_size": 14
69
+ },
70
+ "vision_feature_layer": -2,
71
+ "vision_feature_select_strategy": "patch",
72
+ "vision_hidden_size": 1152,
73
+ "vision_model_name_or_path": "google/siglip-so400m-patch14-384",
74
+ "vision_model_name_or_path2": "",
75
+ "vocab_size": 51200
76
+ }
connector/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d44143dda360513e7eb8f4d840425bd3eef72dfb7b64d46a526d74bedd35039
3
+ size 19017283
language_model/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/phi-2",
3
+ "architectures": [
4
+ "PhiForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "auto_map": {
8
+ "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
9
+ "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
10
+ },
11
+ "bos_token_id": 50256,
12
+ "embd_pdrop": 0.0,
13
+ "eos_token_id": 50256,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_size": 2560,
16
+ "initializer_range": 0.02,
17
+ "intermediate_size": 10240,
18
+ "layer_norm_eps": 1e-05,
19
+ "max_position_embeddings": 2048,
20
+ "model_type": "phi",
21
+ "num_attention_heads": 32,
22
+ "num_hidden_layers": 32,
23
+ "num_key_value_heads": 32,
24
+ "partial_rotary_factor": 0.4,
25
+ "qk_layernorm": false,
26
+ "resid_pdrop": 0.1,
27
+ "rope_scaling": null,
28
+ "rope_theta": 10000.0,
29
+ "tie_word_embeddings": false,
30
+ "torch_dtype": "float16",
31
+ "transformers_version": "4.39.3",
32
+ "use_cache": true,
33
+ "vocab_size": 51200
34
+ }
language_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4945b530889bc4b7beda28ff1c28aa8972b2f810e5567e07b22985232e169e1e
3
+ size 5559516641
log.txt ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ 2024-06-25 13:45:10,065 | INFO: Adding LoRA adapters...
2
+ 2024-06-25 13:45:11,927 | INFO: Total Parameters: 258306048, Total Trainable Parameters: 258306048
3
+ 2024-06-25 13:45:11,928 | INFO: Trainable Parameters:
4
+ 2024-06-25 13:45:12,099 | INFO: Added key: store_based_barrier_key:2 to store for rank: 0
5
+ 2024-06-25 13:45:12,099 | INFO: Rank 0: Completed store-based barrier for key:store_based_barrier_key:2 with 1 nodes.
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Jun25_13-45-03_DESKTOP-38BQKTU/events.out.tfevents.1719294313.DESKTOP-38BQKTU ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3adcd25d82e98029c5a22930f4c06b0b1130916a4e7ba23878c961b7ec6a1e72
3
+ size 270217
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_config.json ADDED
@@ -0,0 +1,327 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "50257": {
14
+ "content": " ",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": false
20
+ },
21
+ "50258": {
22
+ "content": " ",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "50259": {
30
+ "content": " ",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": false
36
+ },
37
+ "50260": {
38
+ "content": " ",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": false
44
+ },
45
+ "50261": {
46
+ "content": " ",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": false
52
+ },
53
+ "50262": {
54
+ "content": " ",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": false
60
+ },
61
+ "50263": {
62
+ "content": " ",
63
+ "lstrip": false,
64
+ "normalized": true,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": false
68
+ },
69
+ "50264": {
70
+ "content": " ",
71
+ "lstrip": false,
72
+ "normalized": true,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": false
76
+ },
77
+ "50265": {
78
+ "content": " ",
79
+ "lstrip": false,
80
+ "normalized": true,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": false
84
+ },
85
+ "50266": {
86
+ "content": " ",
87
+ "lstrip": false,
88
+ "normalized": true,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": false
92
+ },
93
+ "50267": {
94
+ "content": " ",
95
+ "lstrip": false,
96
+ "normalized": true,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": false
100
+ },
101
+ "50268": {
102
+ "content": " ",
103
+ "lstrip": false,
104
+ "normalized": true,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": false
108
+ },
109
+ "50269": {
110
+ "content": " ",
111
+ "lstrip": false,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": false
116
+ },
117
+ "50270": {
118
+ "content": " ",
119
+ "lstrip": false,
120
+ "normalized": true,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "50271": {
126
+ "content": " ",
127
+ "lstrip": false,
128
+ "normalized": true,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "50272": {
134
+ "content": " ",
135
+ "lstrip": false,
136
+ "normalized": true,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "50273": {
142
+ "content": " ",
143
+ "lstrip": false,
144
+ "normalized": true,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "50274": {
150
+ "content": " ",
151
+ "lstrip": false,
152
+ "normalized": true,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "50275": {
158
+ "content": " ",
159
+ "lstrip": false,
160
+ "normalized": true,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "50276": {
166
+ "content": " ",
167
+ "lstrip": false,
168
+ "normalized": true,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "50277": {
174
+ "content": " ",
175
+ "lstrip": false,
176
+ "normalized": true,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "50278": {
182
+ "content": " ",
183
+ "lstrip": false,
184
+ "normalized": true,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "50279": {
190
+ "content": " ",
191
+ "lstrip": false,
192
+ "normalized": true,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "50280": {
198
+ "content": " ",
199
+ "lstrip": false,
200
+ "normalized": true,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "50281": {
206
+ "content": " ",
207
+ "lstrip": false,
208
+ "normalized": true,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ },
213
+ "50282": {
214
+ "content": " ",
215
+ "lstrip": false,
216
+ "normalized": true,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": false
220
+ },
221
+ "50283": {
222
+ "content": " ",
223
+ "lstrip": false,
224
+ "normalized": true,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": false
228
+ },
229
+ "50284": {
230
+ "content": " ",
231
+ "lstrip": false,
232
+ "normalized": true,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": false
236
+ },
237
+ "50285": {
238
+ "content": " ",
239
+ "lstrip": false,
240
+ "normalized": true,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": false
244
+ },
245
+ "50286": {
246
+ "content": " ",
247
+ "lstrip": false,
248
+ "normalized": true,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": false
252
+ },
253
+ "50287": {
254
+ "content": "\t\t\t\t\t\t\t\t\t",
255
+ "lstrip": false,
256
+ "normalized": true,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": false
260
+ },
261
+ "50288": {
262
+ "content": "\t\t\t\t\t\t\t\t",
263
+ "lstrip": false,
264
+ "normalized": true,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": false
268
+ },
269
+ "50289": {
270
+ "content": "\t\t\t\t\t\t\t",
271
+ "lstrip": false,
272
+ "normalized": true,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": false
276
+ },
277
+ "50290": {
278
+ "content": "\t\t\t\t\t\t",
279
+ "lstrip": false,
280
+ "normalized": true,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": false
284
+ },
285
+ "50291": {
286
+ "content": "\t\t\t\t\t",
287
+ "lstrip": false,
288
+ "normalized": true,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": false
292
+ },
293
+ "50292": {
294
+ "content": "\t\t\t\t",
295
+ "lstrip": false,
296
+ "normalized": true,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": false
300
+ },
301
+ "50293": {
302
+ "content": "\t\t\t",
303
+ "lstrip": false,
304
+ "normalized": true,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": false
308
+ },
309
+ "50294": {
310
+ "content": "\t\t",
311
+ "lstrip": false,
312
+ "normalized": true,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": false
316
+ }
317
+ },
318
+ "bos_token": "<|endoftext|>",
319
+ "clean_up_tokenization_spaces": true,
320
+ "eos_token": "<|endoftext|>",
321
+ "errors": "replace",
322
+ "model_max_length": 3072,
323
+ "pad_token": "<|endoftext|>",
324
+ "padding_side": "right",
325
+ "tokenizer_class": "CodeGenTokenizer",
326
+ "unk_token": "<|endoftext|>"
327
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
vision_tower/config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_dropout": 0.0,
3
+ "hidden_act": "gelu_pytorch_tanh",
4
+ "hidden_size": 1152,
5
+ "image_size": 384,
6
+ "intermediate_size": 4304,
7
+ "layer_norm_eps": 1e-06,
8
+ "model_name_or_path": "google/siglip-so400m-patch14-384",
9
+ "model_name_or_path2": "",
10
+ "model_type": "siglip_vision_model",
11
+ "num_attention_heads": 16,
12
+ "num_channels": 3,
13
+ "num_hidden_layers": 27,
14
+ "patch_size": 14,
15
+ "transformers_version": "4.39.3"
16
+ }
vision_tower/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc455f9e03c3a08d32524dc4d58768dd24ccdcdc76c765aa485a6fe257297c25
3
+ size 856602125
vocab.json ADDED
The diff for this file is too large to render. See raw diff