jbostock commited on
Commit
0221578
·
verified ·
1 Parent(s): a6cbf2d

Upload folder using huggingface_hub

Browse files
.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
+ runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/adapter_config.json ADDED
@@ -0,0 +1,451 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alora_invocation_tokens": null,
3
+ "alpha_pattern": {},
4
+ "arrow_config": null,
5
+ "auto_mapping": null,
6
+ "base_model_name_or_path": "/workspace/data/parents/mixed_4ep_prop",
7
+ "bias": "none",
8
+ "corda_config": null,
9
+ "ensure_weight_tying": false,
10
+ "eva_config": null,
11
+ "exclude_modules": null,
12
+ "fan_in_fan_out": null,
13
+ "inference_mode": true,
14
+ "init_lora_weights": true,
15
+ "layer_replication": null,
16
+ "layers_pattern": null,
17
+ "layers_to_transform": null,
18
+ "loftq_config": {},
19
+ "lora_alpha": 128,
20
+ "lora_bias": false,
21
+ "lora_dropout": 0.0,
22
+ "lora_ga_config": null,
23
+ "megatron_config": null,
24
+ "megatron_core": "megatron.core",
25
+ "modules_to_save": null,
26
+ "peft_type": "LORA",
27
+ "peft_version": "0.19.1",
28
+ "qalora_group_size": 16,
29
+ "r": 64,
30
+ "rank_pattern": {},
31
+ "revision": null,
32
+ "target_modules": [
33
+ "model.language_model.layers.48.mlp.gate_proj",
34
+ "model.language_model.layers.31.mlp.down_proj",
35
+ "model.language_model.layers.2.mlp.down_proj",
36
+ "model.language_model.layers.20.mlp.gate_proj",
37
+ "model.language_model.layers.54.mlp.down_proj",
38
+ "model.language_model.layers.19.self_attn.k_proj",
39
+ "model.language_model.layers.58.self_attn.k_proj",
40
+ "model.language_model.layers.58.self_attn.q_proj",
41
+ "model.language_model.layers.57.self_attn.k_proj",
42
+ "model.language_model.layers.11.mlp.gate_proj",
43
+ "model.language_model.layers.50.self_attn.k_proj",
44
+ "model.language_model.layers.13.mlp.down_proj",
45
+ "model.language_model.layers.21.mlp.gate_proj",
46
+ "model.language_model.layers.28.self_attn.q_proj",
47
+ "model.language_model.layers.17.mlp.down_proj",
48
+ "model.language_model.layers.39.self_attn.v_proj",
49
+ "model.language_model.layers.38.mlp.up_proj",
50
+ "model.language_model.layers.9.self_attn.k_proj",
51
+ "model.language_model.layers.4.mlp.down_proj",
52
+ "model.language_model.layers.9.mlp.down_proj",
53
+ "model.language_model.layers.13.mlp.up_proj",
54
+ "model.language_model.layers.14.self_attn.v_proj",
55
+ "model.language_model.layers.3.mlp.gate_proj",
56
+ "model.language_model.layers.57.self_attn.v_proj",
57
+ "model.language_model.layers.44.mlp.down_proj",
58
+ "model.language_model.layers.57.mlp.gate_proj",
59
+ "model.language_model.layers.56.mlp.down_proj",
60
+ "model.language_model.layers.35.mlp.down_proj",
61
+ "model.language_model.layers.15.mlp.up_proj",
62
+ "model.language_model.layers.48.mlp.up_proj",
63
+ "model.language_model.layers.50.self_attn.o_proj",
64
+ "model.language_model.layers.12.self_attn.o_proj",
65
+ "model.language_model.layers.8.self_attn.v_proj",
66
+ "model.language_model.layers.20.self_attn.k_proj",
67
+ "model.language_model.layers.50.self_attn.q_proj",
68
+ "model.language_model.layers.34.self_attn.k_proj",
69
+ "model.language_model.layers.34.self_attn.o_proj",
70
+ "model.language_model.layers.3.self_attn.q_proj",
71
+ "model.language_model.layers.47.mlp.up_proj",
72
+ "model.language_model.layers.27.self_attn.o_proj",
73
+ "model.language_model.layers.26.self_attn.v_proj",
74
+ "model.language_model.layers.14.mlp.gate_proj",
75
+ "model.language_model.layers.35.self_attn.k_proj",
76
+ "model.language_model.layers.12.mlp.up_proj",
77
+ "model.language_model.layers.40.self_attn.k_proj",
78
+ "model.language_model.layers.27.mlp.down_proj",
79
+ "model.language_model.layers.54.self_attn.k_proj",
80
+ "model.language_model.layers.21.mlp.down_proj",
81
+ "model.language_model.layers.43.self_attn.v_proj",
82
+ "model.language_model.layers.49.mlp.gate_proj",
83
+ "model.language_model.layers.48.mlp.down_proj",
84
+ "model.language_model.layers.28.self_attn.v_proj",
85
+ "model.language_model.layers.30.mlp.gate_proj",
86
+ "model.language_model.layers.43.self_attn.k_proj",
87
+ "model.language_model.layers.39.mlp.gate_proj",
88
+ "model.language_model.layers.42.self_attn.o_proj",
89
+ "model.language_model.layers.30.self_attn.k_proj",
90
+ "model.language_model.layers.7.mlp.gate_proj",
91
+ "model.language_model.layers.37.mlp.gate_proj",
92
+ "model.language_model.layers.25.mlp.up_proj",
93
+ "model.language_model.layers.51.self_attn.k_proj",
94
+ "model.language_model.layers.40.self_attn.q_proj",
95
+ "model.language_model.layers.29.mlp.up_proj",
96
+ "model.language_model.layers.39.self_attn.q_proj",
97
+ "model.language_model.layers.33.mlp.up_proj",
98
+ "model.language_model.layers.56.mlp.gate_proj",
99
+ "model.language_model.layers.34.self_attn.v_proj",
100
+ "model.language_model.layers.22.mlp.down_proj",
101
+ "model.language_model.layers.23.self_attn.o_proj",
102
+ "model.language_model.layers.49.self_attn.k_proj",
103
+ "model.language_model.layers.29.mlp.down_proj",
104
+ "model.language_model.layers.6.self_attn.v_proj",
105
+ "model.language_model.layers.53.mlp.gate_proj",
106
+ "model.language_model.layers.52.self_attn.v_proj",
107
+ "model.language_model.layers.38.mlp.down_proj",
108
+ "model.language_model.layers.18.self_attn.v_proj",
109
+ "model.language_model.layers.30.mlp.down_proj",
110
+ "model.language_model.layers.26.mlp.up_proj",
111
+ "model.language_model.layers.33.self_attn.o_proj",
112
+ "model.language_model.layers.49.self_attn.q_proj",
113
+ "model.language_model.layers.22.self_attn.v_proj",
114
+ "model.language_model.layers.57.mlp.down_proj",
115
+ "model.language_model.layers.10.self_attn.q_proj",
116
+ "model.language_model.layers.29.self_attn.q_proj",
117
+ "model.language_model.layers.34.mlp.gate_proj",
118
+ "model.language_model.layers.40.mlp.down_proj",
119
+ "model.language_model.layers.50.self_attn.v_proj",
120
+ "model.language_model.layers.5.self_attn.q_proj",
121
+ "model.language_model.layers.45.mlp.down_proj",
122
+ "model.language_model.layers.19.self_attn.v_proj",
123
+ "model.language_model.layers.55.self_attn.o_proj",
124
+ "model.language_model.layers.45.self_attn.v_proj",
125
+ "model.language_model.layers.16.mlp.down_proj",
126
+ "model.language_model.layers.20.self_attn.v_proj",
127
+ "model.language_model.layers.3.self_attn.v_proj",
128
+ "model.language_model.layers.3.self_attn.o_proj",
129
+ "model.language_model.layers.58.mlp.up_proj",
130
+ "model.language_model.layers.0.self_attn.o_proj",
131
+ "model.language_model.layers.10.mlp.down_proj",
132
+ "model.language_model.layers.22.self_attn.q_proj",
133
+ "model.language_model.layers.59.mlp.up_proj",
134
+ "model.language_model.layers.59.mlp.down_proj",
135
+ "model.language_model.layers.1.self_attn.v_proj",
136
+ "model.language_model.layers.2.mlp.up_proj",
137
+ "model.language_model.layers.50.mlp.gate_proj",
138
+ "model.language_model.layers.53.mlp.up_proj",
139
+ "model.language_model.layers.31.self_attn.o_proj",
140
+ "model.language_model.layers.0.mlp.up_proj",
141
+ "model.language_model.layers.47.mlp.down_proj",
142
+ "model.language_model.layers.38.self_attn.q_proj",
143
+ "model.language_model.layers.36.self_attn.v_proj",
144
+ "model.language_model.layers.7.self_attn.k_proj",
145
+ "model.language_model.layers.31.self_attn.k_proj",
146
+ "model.language_model.layers.11.self_attn.o_proj",
147
+ "model.language_model.layers.13.mlp.gate_proj",
148
+ "model.language_model.layers.39.self_attn.k_proj",
149
+ "model.language_model.layers.47.self_attn.o_proj",
150
+ "model.language_model.layers.48.self_attn.k_proj",
151
+ "model.language_model.layers.19.self_attn.o_proj",
152
+ "model.language_model.layers.11.mlp.up_proj",
153
+ "model.language_model.layers.36.self_attn.q_proj",
154
+ "model.language_model.layers.12.self_attn.k_proj",
155
+ "model.language_model.layers.5.mlp.up_proj",
156
+ "model.language_model.layers.33.mlp.gate_proj",
157
+ "model.language_model.layers.22.self_attn.o_proj",
158
+ "model.language_model.layers.43.self_attn.q_proj",
159
+ "model.language_model.layers.39.mlp.up_proj",
160
+ "model.language_model.layers.32.self_attn.k_proj",
161
+ "model.language_model.layers.17.mlp.gate_proj",
162
+ "model.language_model.layers.13.self_attn.q_proj",
163
+ "model.language_model.layers.47.self_attn.q_proj",
164
+ "model.language_model.layers.56.self_attn.o_proj",
165
+ "model.language_model.layers.22.self_attn.k_proj",
166
+ "model.language_model.layers.19.mlp.gate_proj",
167
+ "model.language_model.layers.26.self_attn.q_proj",
168
+ "model.language_model.layers.31.mlp.up_proj",
169
+ "model.language_model.layers.46.self_attn.o_proj",
170
+ "model.language_model.layers.1.mlp.gate_proj",
171
+ "model.language_model.layers.36.self_attn.k_proj",
172
+ "model.language_model.layers.4.self_attn.q_proj",
173
+ "model.language_model.layers.16.self_attn.q_proj",
174
+ "model.language_model.layers.59.self_attn.k_proj",
175
+ "model.language_model.layers.8.mlp.gate_proj",
176
+ "model.language_model.layers.37.mlp.up_proj",
177
+ "model.language_model.layers.56.mlp.up_proj",
178
+ "model.language_model.layers.49.mlp.down_proj",
179
+ "model.language_model.layers.22.mlp.gate_proj",
180
+ "model.language_model.layers.12.mlp.gate_proj",
181
+ "model.language_model.layers.2.self_attn.o_proj",
182
+ "model.language_model.layers.44.self_attn.k_proj",
183
+ "model.language_model.layers.4.mlp.up_proj",
184
+ "model.language_model.layers.16.self_attn.k_proj",
185
+ "model.language_model.layers.2.mlp.gate_proj",
186
+ "model.language_model.layers.36.self_attn.o_proj",
187
+ "model.language_model.layers.58.mlp.gate_proj",
188
+ "model.language_model.layers.42.self_attn.q_proj",
189
+ "model.language_model.layers.49.self_attn.o_proj",
190
+ "model.language_model.layers.45.self_attn.k_proj",
191
+ "model.language_model.layers.55.mlp.up_proj",
192
+ "model.language_model.layers.22.mlp.up_proj",
193
+ "model.language_model.layers.56.self_attn.v_proj",
194
+ "model.language_model.layers.48.self_attn.v_proj",
195
+ "model.language_model.layers.31.self_attn.v_proj",
196
+ "model.language_model.layers.41.self_attn.o_proj",
197
+ "model.language_model.layers.6.self_attn.q_proj",
198
+ "model.language_model.layers.54.mlp.gate_proj",
199
+ "model.language_model.layers.14.self_attn.k_proj",
200
+ "model.language_model.layers.18.self_attn.o_proj",
201
+ "model.language_model.layers.44.mlp.up_proj",
202
+ "model.language_model.layers.3.mlp.up_proj",
203
+ "model.language_model.layers.2.self_attn.q_proj",
204
+ "model.language_model.layers.51.self_attn.o_proj",
205
+ "model.language_model.layers.55.mlp.gate_proj",
206
+ "model.language_model.layers.45.self_attn.q_proj",
207
+ "model.language_model.layers.30.self_attn.v_proj",
208
+ "model.language_model.layers.21.self_attn.o_proj",
209
+ "model.language_model.layers.8.self_attn.k_proj",
210
+ "model.language_model.layers.4.self_attn.k_proj",
211
+ "model.language_model.layers.21.self_attn.q_proj",
212
+ "model.language_model.layers.46.mlp.gate_proj",
213
+ "model.language_model.layers.35.self_attn.q_proj",
214
+ "model.language_model.layers.36.mlp.gate_proj",
215
+ "model.language_model.layers.10.self_attn.k_proj",
216
+ "model.language_model.layers.45.mlp.up_proj",
217
+ "model.language_model.layers.42.mlp.up_proj",
218
+ "model.language_model.layers.37.self_attn.q_proj",
219
+ "model.language_model.layers.32.mlp.up_proj",
220
+ "model.language_model.layers.10.mlp.gate_proj",
221
+ "model.language_model.layers.59.self_attn.q_proj",
222
+ "model.language_model.layers.5.mlp.down_proj",
223
+ "model.language_model.layers.20.self_attn.q_proj",
224
+ "model.language_model.layers.15.self_attn.q_proj",
225
+ "model.language_model.layers.19.self_attn.q_proj",
226
+ "model.language_model.layers.23.mlp.up_proj",
227
+ "model.language_model.layers.38.self_attn.k_proj",
228
+ "model.language_model.layers.0.mlp.gate_proj",
229
+ "model.language_model.layers.9.mlp.gate_proj",
230
+ "model.language_model.layers.52.mlp.down_proj",
231
+ "model.language_model.layers.37.self_attn.o_proj",
232
+ "model.language_model.layers.0.mlp.down_proj",
233
+ "model.language_model.layers.47.mlp.gate_proj",
234
+ "model.language_model.layers.52.mlp.up_proj",
235
+ "model.language_model.layers.9.mlp.up_proj",
236
+ "model.language_model.layers.24.mlp.gate_proj",
237
+ "model.language_model.layers.27.self_attn.k_proj",
238
+ "model.language_model.layers.9.self_attn.v_proj",
239
+ "model.language_model.layers.52.self_attn.q_proj",
240
+ "model.language_model.layers.16.mlp.gate_proj",
241
+ "model.language_model.layers.8.self_attn.q_proj",
242
+ "model.language_model.layers.36.mlp.down_proj",
243
+ "model.language_model.layers.18.self_attn.q_proj",
244
+ "model.language_model.layers.28.mlp.down_proj",
245
+ "model.language_model.layers.11.self_attn.k_proj",
246
+ "model.language_model.layers.27.mlp.gate_proj",
247
+ "model.language_model.layers.43.mlp.up_proj",
248
+ "model.language_model.layers.49.self_attn.v_proj",
249
+ "model.language_model.layers.15.mlp.down_proj",
250
+ "model.language_model.layers.4.self_attn.v_proj",
251
+ "model.language_model.layers.14.self_attn.o_proj",
252
+ "model.language_model.layers.54.self_attn.o_proj",
253
+ "model.language_model.layers.53.self_attn.q_proj",
254
+ "model.language_model.layers.43.mlp.down_proj",
255
+ "model.language_model.layers.26.mlp.down_proj",
256
+ "model.language_model.layers.55.self_attn.k_proj",
257
+ "model.language_model.layers.24.self_attn.o_proj",
258
+ "model.language_model.layers.1.mlp.down_proj",
259
+ "model.language_model.layers.25.mlp.down_proj",
260
+ "model.language_model.layers.38.self_attn.v_proj",
261
+ "model.language_model.layers.40.mlp.up_proj",
262
+ "model.language_model.layers.20.mlp.down_proj",
263
+ "model.language_model.layers.53.mlp.down_proj",
264
+ "model.language_model.layers.43.mlp.gate_proj",
265
+ "model.language_model.layers.32.mlp.down_proj",
266
+ "model.language_model.layers.15.self_attn.o_proj",
267
+ "model.language_model.layers.21.self_attn.v_proj",
268
+ "model.language_model.layers.40.self_attn.v_proj",
269
+ "model.language_model.layers.43.self_attn.o_proj",
270
+ "model.language_model.layers.7.self_attn.o_proj",
271
+ "model.language_model.layers.27.mlp.up_proj",
272
+ "model.language_model.layers.8.mlp.up_proj",
273
+ "model.language_model.layers.40.mlp.gate_proj",
274
+ "model.language_model.layers.58.self_attn.o_proj",
275
+ "model.language_model.layers.8.mlp.down_proj",
276
+ "model.language_model.layers.13.self_attn.o_proj",
277
+ "model.language_model.layers.21.self_attn.k_proj",
278
+ "model.language_model.layers.5.self_attn.o_proj",
279
+ "model.language_model.layers.30.mlp.up_proj",
280
+ "model.language_model.layers.48.self_attn.o_proj",
281
+ "model.language_model.layers.42.self_attn.k_proj",
282
+ "model.language_model.layers.18.self_attn.k_proj",
283
+ "model.language_model.layers.14.self_attn.q_proj",
284
+ "model.language_model.layers.30.self_attn.q_proj",
285
+ "model.language_model.layers.34.self_attn.q_proj",
286
+ "model.language_model.layers.13.self_attn.k_proj",
287
+ "model.language_model.layers.20.self_attn.o_proj",
288
+ "model.language_model.layers.47.self_attn.k_proj",
289
+ "model.language_model.layers.27.self_attn.q_proj",
290
+ "model.language_model.layers.29.self_attn.o_proj",
291
+ "model.language_model.layers.5.mlp.gate_proj",
292
+ "model.language_model.layers.25.self_attn.k_proj",
293
+ "model.language_model.layers.42.mlp.gate_proj",
294
+ "model.language_model.layers.55.mlp.down_proj",
295
+ "model.language_model.layers.25.self_attn.q_proj",
296
+ "model.language_model.layers.39.mlp.down_proj",
297
+ "model.language_model.layers.57.mlp.up_proj",
298
+ "model.language_model.layers.29.mlp.gate_proj",
299
+ "model.language_model.layers.15.mlp.gate_proj",
300
+ "model.language_model.layers.0.self_attn.k_proj",
301
+ "model.language_model.layers.6.self_attn.k_proj",
302
+ "model.language_model.layers.17.mlp.up_proj",
303
+ "model.language_model.layers.21.mlp.up_proj",
304
+ "model.language_model.layers.28.self_attn.k_proj",
305
+ "model.language_model.layers.41.mlp.gate_proj",
306
+ "model.language_model.layers.6.self_attn.o_proj",
307
+ "model.language_model.layers.33.self_attn.q_proj",
308
+ "model.language_model.layers.20.mlp.up_proj",
309
+ "model.language_model.layers.42.self_attn.v_proj",
310
+ "model.language_model.layers.27.self_attn.v_proj",
311
+ "model.language_model.layers.19.mlp.up_proj",
312
+ "model.language_model.layers.1.self_attn.q_proj",
313
+ "model.language_model.layers.54.self_attn.q_proj",
314
+ "model.language_model.layers.39.self_attn.o_proj",
315
+ "model.language_model.layers.37.self_attn.v_proj",
316
+ "model.language_model.layers.46.self_attn.k_proj",
317
+ "model.language_model.layers.14.mlp.down_proj",
318
+ "model.language_model.layers.42.mlp.down_proj",
319
+ "model.language_model.layers.34.mlp.up_proj",
320
+ "model.language_model.layers.2.self_attn.v_proj",
321
+ "model.language_model.layers.57.self_attn.q_proj",
322
+ "model.language_model.layers.50.mlp.down_proj",
323
+ "model.language_model.layers.17.self_attn.k_proj",
324
+ "model.language_model.layers.44.self_attn.q_proj",
325
+ "model.language_model.layers.5.self_attn.k_proj",
326
+ "model.language_model.layers.55.self_attn.v_proj",
327
+ "model.language_model.layers.24.mlp.up_proj",
328
+ "model.language_model.layers.38.self_attn.o_proj",
329
+ "model.language_model.layers.9.self_attn.o_proj",
330
+ "model.language_model.layers.40.self_attn.o_proj",
331
+ "model.language_model.layers.35.mlp.gate_proj",
332
+ "model.language_model.layers.7.self_attn.q_proj",
333
+ "model.language_model.layers.3.mlp.down_proj",
334
+ "model.language_model.layers.25.self_attn.o_proj",
335
+ "model.language_model.layers.16.self_attn.v_proj",
336
+ "model.language_model.layers.32.self_attn.v_proj",
337
+ "model.language_model.layers.46.mlp.down_proj",
338
+ "model.language_model.layers.16.self_attn.o_proj",
339
+ "model.language_model.layers.23.mlp.gate_proj",
340
+ "model.language_model.layers.31.self_attn.q_proj",
341
+ "model.language_model.layers.53.self_attn.o_proj",
342
+ "model.language_model.layers.9.self_attn.q_proj",
343
+ "model.language_model.layers.30.self_attn.o_proj",
344
+ "model.language_model.layers.51.mlp.gate_proj",
345
+ "model.language_model.layers.32.self_attn.o_proj",
346
+ "model.language_model.layers.28.mlp.gate_proj",
347
+ "model.language_model.layers.59.mlp.gate_proj",
348
+ "model.language_model.layers.18.mlp.up_proj",
349
+ "model.language_model.layers.7.mlp.down_proj",
350
+ "model.language_model.layers.51.self_attn.q_proj",
351
+ "model.language_model.layers.10.self_attn.v_proj",
352
+ "model.language_model.layers.7.mlp.up_proj",
353
+ "model.language_model.layers.11.self_attn.q_proj",
354
+ "model.language_model.layers.12.self_attn.v_proj",
355
+ "model.language_model.layers.41.self_attn.k_proj",
356
+ "model.language_model.layers.46.self_attn.v_proj",
357
+ "model.language_model.layers.51.mlp.up_proj",
358
+ "model.language_model.layers.12.mlp.down_proj",
359
+ "model.language_model.layers.54.mlp.up_proj",
360
+ "model.language_model.layers.45.self_attn.o_proj",
361
+ "model.language_model.layers.15.self_attn.k_proj",
362
+ "model.language_model.layers.24.self_attn.q_proj",
363
+ "model.language_model.layers.6.mlp.gate_proj",
364
+ "model.language_model.layers.44.mlp.gate_proj",
365
+ "model.language_model.layers.23.mlp.down_proj",
366
+ "model.language_model.layers.45.mlp.gate_proj",
367
+ "model.language_model.layers.57.self_attn.o_proj",
368
+ "model.language_model.layers.58.mlp.down_proj",
369
+ "model.language_model.layers.23.self_attn.q_proj",
370
+ "model.language_model.layers.15.self_attn.v_proj",
371
+ "model.language_model.layers.0.self_attn.q_proj",
372
+ "model.language_model.layers.37.self_attn.k_proj",
373
+ "model.language_model.layers.28.mlp.up_proj",
374
+ "model.language_model.layers.52.self_attn.k_proj",
375
+ "model.language_model.layers.6.mlp.down_proj",
376
+ "model.language_model.layers.58.self_attn.v_proj",
377
+ "model.language_model.layers.11.mlp.down_proj",
378
+ "model.language_model.layers.33.self_attn.v_proj",
379
+ "model.language_model.layers.32.mlp.gate_proj",
380
+ "model.language_model.layers.24.self_attn.k_proj",
381
+ "model.language_model.layers.16.mlp.up_proj",
382
+ "model.language_model.layers.38.mlp.gate_proj",
383
+ "model.language_model.layers.17.self_attn.o_proj",
384
+ "model.language_model.layers.33.self_attn.k_proj",
385
+ "model.language_model.layers.1.mlp.up_proj",
386
+ "model.language_model.layers.35.self_attn.o_proj",
387
+ "model.language_model.layers.24.self_attn.v_proj",
388
+ "model.language_model.layers.32.self_attn.q_proj",
389
+ "model.language_model.layers.41.mlp.up_proj",
390
+ "model.language_model.layers.1.self_attn.o_proj",
391
+ "model.language_model.layers.1.self_attn.k_proj",
392
+ "model.language_model.layers.2.self_attn.k_proj",
393
+ "model.language_model.layers.37.mlp.down_proj",
394
+ "model.language_model.layers.28.self_attn.o_proj",
395
+ "model.language_model.layers.33.mlp.down_proj",
396
+ "model.language_model.layers.18.mlp.down_proj",
397
+ "model.language_model.layers.34.mlp.down_proj",
398
+ "model.language_model.layers.35.mlp.up_proj",
399
+ "model.language_model.layers.26.self_attn.o_proj",
400
+ "model.language_model.layers.8.self_attn.o_proj",
401
+ "model.language_model.layers.12.self_attn.q_proj",
402
+ "model.language_model.layers.46.self_attn.q_proj",
403
+ "model.language_model.layers.10.self_attn.o_proj",
404
+ "model.language_model.layers.49.mlp.up_proj",
405
+ "model.language_model.layers.51.mlp.down_proj",
406
+ "model.language_model.layers.26.mlp.gate_proj",
407
+ "model.language_model.layers.53.self_attn.k_proj",
408
+ "model.language_model.layers.18.mlp.gate_proj",
409
+ "model.language_model.layers.4.mlp.gate_proj",
410
+ "model.language_model.layers.26.self_attn.k_proj",
411
+ "model.language_model.layers.23.self_attn.k_proj",
412
+ "model.language_model.layers.51.self_attn.v_proj",
413
+ "model.language_model.layers.14.mlp.up_proj",
414
+ "model.language_model.layers.29.self_attn.k_proj",
415
+ "model.language_model.layers.13.self_attn.v_proj",
416
+ "model.language_model.layers.55.self_attn.q_proj",
417
+ "model.language_model.layers.6.mlp.up_proj",
418
+ "model.language_model.layers.25.mlp.gate_proj",
419
+ "model.language_model.layers.59.self_attn.o_proj",
420
+ "model.language_model.layers.44.self_attn.v_proj",
421
+ "model.language_model.layers.52.self_attn.o_proj",
422
+ "model.language_model.layers.17.self_attn.q_proj",
423
+ "model.language_model.layers.44.self_attn.o_proj",
424
+ "model.language_model.layers.19.mlp.down_proj",
425
+ "model.language_model.layers.4.self_attn.o_proj",
426
+ "model.language_model.layers.7.self_attn.v_proj",
427
+ "model.language_model.layers.56.self_attn.k_proj",
428
+ "model.language_model.layers.50.mlp.up_proj",
429
+ "model.language_model.layers.52.mlp.gate_proj",
430
+ "model.language_model.layers.36.mlp.up_proj",
431
+ "model.language_model.layers.24.mlp.down_proj",
432
+ "model.language_model.layers.3.self_attn.k_proj",
433
+ "model.language_model.layers.41.self_attn.q_proj",
434
+ "model.language_model.layers.41.mlp.down_proj",
435
+ "model.language_model.layers.48.self_attn.q_proj",
436
+ "model.language_model.layers.46.mlp.up_proj",
437
+ "model.language_model.layers.10.mlp.up_proj",
438
+ "model.language_model.layers.0.self_attn.v_proj",
439
+ "model.language_model.layers.54.self_attn.v_proj",
440
+ "model.language_model.layers.25.self_attn.v_proj",
441
+ "model.language_model.layers.31.mlp.gate_proj",
442
+ "model.language_model.layers.56.self_attn.q_proj"
443
+ ],
444
+ "target_parameters": [],
445
+ "task_type": "CAUSAL_LM",
446
+ "trainable_token_indices": null,
447
+ "use_bdlora": null,
448
+ "use_dora": false,
449
+ "use_qalora": false,
450
+ "use_rslora": false
451
+ }
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8ec9d7714320a5f953ba85f76d61f93888a8c96bc71d4b3591294980b957da5
3
+ size 1958995176
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/chat_template.jinja ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{ bos_token }}
2
+ {%- if messages[0]['role'] == 'system' -%}
3
+ {%- if messages[0]['content'] is string -%}
4
+ {%- set first_user_prefix = messages[0]['content'] + '
5
+
6
+ ' -%}
7
+ {%- else -%}
8
+ {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
9
+
10
+ ' -%}
11
+ {%- endif -%}
12
+ {%- set loop_messages = messages[1:] -%}
13
+ {%- else -%}
14
+ {%- set first_user_prefix = "" -%}
15
+ {%- set loop_messages = messages -%}
16
+ {%- endif -%}
17
+ {%- for message in loop_messages -%}
18
+ {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
19
+ {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
20
+ {%- endif -%}
21
+ {%- if (message['role'] == 'assistant') -%}
22
+ {%- set role = "model" -%}
23
+ {%- else -%}
24
+ {%- set role = message['role'] -%}
25
+ {%- endif -%}
26
+ {{ '<|turn>' + role + '
27
+ ' + (first_user_prefix if loop.first else "") }}
28
+ {%- if message['content'] is string -%}
29
+ {{ message['content'] | trim }}
30
+ {%- elif message['content'] is iterable -%}
31
+ {%- for item in message['content'] -%}
32
+ {%- if item['type'] == 'image' -%}
33
+ {{ '<|image>' }}
34
+ {%- elif item['type'] == 'text' -%}
35
+ {{ item['text'] | trim }}
36
+ {%- endif -%}
37
+ {%- endfor -%}
38
+ {%- else -%}
39
+ {{ raise_exception("Invalid content type") }}
40
+ {%- endif -%}
41
+ {{ '<turn|>
42
+ ' }}
43
+ {%- endfor -%}
44
+ {%- if add_generation_prompt -%}
45
+ {{'<|turn>model
46
+ '}}
47
+ {%- endif -%}
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/config.json ADDED
@@ -0,0 +1,177 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Gemma4ForConditionalGeneration"
4
+ ],
5
+ "audio_config": null,
6
+ "audio_token_id": 258881,
7
+ "boa_token_id": 256000,
8
+ "boi_token_id": 255999,
9
+ "bos_token_id": 2,
10
+ "dtype": "bfloat16",
11
+ "eoa_token_id": 258883,
12
+ "eoa_token_index": 258883,
13
+ "eoi_token_id": 258882,
14
+ "eos_token_id": 1,
15
+ "image_token_id": 258880,
16
+ "initializer_range": 0.02,
17
+ "model_type": "gemma4",
18
+ "pad_token_id": 0,
19
+ "text_config": {
20
+ "attention_bias": false,
21
+ "attention_dropout": 0.0,
22
+ "attention_k_eq_v": true,
23
+ "bos_token_id": 2,
24
+ "dtype": "bfloat16",
25
+ "enable_moe_block": false,
26
+ "eos_token_id": 1,
27
+ "expert_intermediate_size": null,
28
+ "final_logit_softcapping": 30.0,
29
+ "global_head_dim": 512,
30
+ "head_dim": 256,
31
+ "hidden_activation": "gelu_pytorch_tanh",
32
+ "hidden_size": 5376,
33
+ "hidden_size_per_layer_input": 0,
34
+ "initializer_range": 0.02,
35
+ "intermediate_size": 21504,
36
+ "layer_types": [
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention",
40
+ "sliding_attention",
41
+ "sliding_attention",
42
+ "full_attention",
43
+ "sliding_attention",
44
+ "sliding_attention",
45
+ "sliding_attention",
46
+ "sliding_attention",
47
+ "sliding_attention",
48
+ "full_attention",
49
+ "sliding_attention",
50
+ "sliding_attention",
51
+ "sliding_attention",
52
+ "sliding_attention",
53
+ "sliding_attention",
54
+ "full_attention",
55
+ "sliding_attention",
56
+ "sliding_attention",
57
+ "sliding_attention",
58
+ "sliding_attention",
59
+ "sliding_attention",
60
+ "full_attention",
61
+ "sliding_attention",
62
+ "sliding_attention",
63
+ "sliding_attention",
64
+ "sliding_attention",
65
+ "sliding_attention",
66
+ "full_attention",
67
+ "sliding_attention",
68
+ "sliding_attention",
69
+ "sliding_attention",
70
+ "sliding_attention",
71
+ "sliding_attention",
72
+ "full_attention",
73
+ "sliding_attention",
74
+ "sliding_attention",
75
+ "sliding_attention",
76
+ "sliding_attention",
77
+ "sliding_attention",
78
+ "full_attention",
79
+ "sliding_attention",
80
+ "sliding_attention",
81
+ "sliding_attention",
82
+ "sliding_attention",
83
+ "sliding_attention",
84
+ "full_attention",
85
+ "sliding_attention",
86
+ "sliding_attention",
87
+ "sliding_attention",
88
+ "sliding_attention",
89
+ "sliding_attention",
90
+ "full_attention",
91
+ "sliding_attention",
92
+ "sliding_attention",
93
+ "sliding_attention",
94
+ "sliding_attention",
95
+ "sliding_attention",
96
+ "full_attention"
97
+ ],
98
+ "max_position_embeddings": 262144,
99
+ "model_type": "gemma4_text",
100
+ "moe_intermediate_size": null,
101
+ "num_attention_heads": 32,
102
+ "num_experts": null,
103
+ "num_global_key_value_heads": 4,
104
+ "num_hidden_layers": 60,
105
+ "num_key_value_heads": 16,
106
+ "num_kv_shared_layers": 0,
107
+ "pad_token_id": 0,
108
+ "rms_norm_eps": 1e-06,
109
+ "rope_parameters": {
110
+ "full_attention": {
111
+ "partial_rotary_factor": 0.25,
112
+ "rope_theta": 1000000.0,
113
+ "rope_type": "proportional"
114
+ },
115
+ "sliding_attention": {
116
+ "rope_theta": 10000.0,
117
+ "rope_type": "default"
118
+ }
119
+ },
120
+ "sliding_window": 1024,
121
+ "tie_word_embeddings": true,
122
+ "top_k_experts": null,
123
+ "use_bidirectional_attention": "vision",
124
+ "use_cache": false,
125
+ "use_double_wide_mlp": false,
126
+ "vocab_size": 262144,
127
+ "vocab_size_per_layer_input": 262144
128
+ },
129
+ "tie_word_embeddings": true,
130
+ "transformers_version": "5.9.0",
131
+ "use_cache": false,
132
+ "video_token_id": 258884,
133
+ "vision_config": {
134
+ "_name_or_path": "",
135
+ "architectures": null,
136
+ "attention_bias": false,
137
+ "attention_dropout": 0.0,
138
+ "chunk_size_feed_forward": 0,
139
+ "default_output_length": 280,
140
+ "dtype": "bfloat16",
141
+ "global_head_dim": 72,
142
+ "head_dim": 72,
143
+ "hidden_activation": "gelu_pytorch_tanh",
144
+ "hidden_size": 1152,
145
+ "id2label": {
146
+ "0": "LABEL_0",
147
+ "1": "LABEL_1"
148
+ },
149
+ "initializer_range": 0.02,
150
+ "intermediate_size": 4304,
151
+ "is_encoder_decoder": false,
152
+ "label2id": {
153
+ "LABEL_0": 0,
154
+ "LABEL_1": 1
155
+ },
156
+ "max_position_embeddings": 131072,
157
+ "model_type": "gemma4_vision",
158
+ "num_attention_heads": 16,
159
+ "num_hidden_layers": 27,
160
+ "num_key_value_heads": 16,
161
+ "output_attentions": false,
162
+ "output_hidden_states": false,
163
+ "patch_size": 16,
164
+ "pooling_kernel_size": 3,
165
+ "position_embedding_size": 10240,
166
+ "problem_type": null,
167
+ "return_dict": true,
168
+ "rms_norm_eps": 1e-06,
169
+ "rope_parameters": {
170
+ "rope_theta": 100.0,
171
+ "rope_type": "default"
172
+ },
173
+ "standardize": true,
174
+ "use_clipped_linears": false
175
+ },
176
+ "vision_soft_tokens_per_image": 280
177
+ }
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/debug.log ADDED
The diff for this file is too large to render. See raw diff
 
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/processor_config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "audio_ms_per_token": 40,
3
+ "audio_seq_length": 750,
4
+ "feature_extractor": {
5
+ "dither": 0.0,
6
+ "feature_extractor_type": "Gemma4AudioFeatureExtractor",
7
+ "feature_size": 128,
8
+ "fft_length": 512,
9
+ "fft_overdrive": false,
10
+ "frame_length": 320,
11
+ "hop_length": 160,
12
+ "input_scale_factor": 1.0,
13
+ "max_frequency": 8000.0,
14
+ "mel_floor": 0.001,
15
+ "min_frequency": 0.0,
16
+ "padding_side": "right",
17
+ "padding_value": 0.0,
18
+ "per_bin_mean": null,
19
+ "per_bin_stddev": null,
20
+ "preemphasis": 0.0,
21
+ "preemphasis_htk_flavor": true,
22
+ "return_attention_mask": true,
23
+ "sampling_rate": 16000
24
+ },
25
+ "image_processor": {
26
+ "do_convert_rgb": true,
27
+ "do_normalize": false,
28
+ "do_rescale": true,
29
+ "do_resize": true,
30
+ "image_mean": [
31
+ 0.0,
32
+ 0.0,
33
+ 0.0
34
+ ],
35
+ "image_processor_type": "Gemma4ImageProcessor",
36
+ "image_seq_length": 280,
37
+ "image_std": [
38
+ 1.0,
39
+ 1.0,
40
+ 1.0
41
+ ],
42
+ "max_soft_tokens": 280,
43
+ "patch_size": 16,
44
+ "pooling_kernel_size": 3,
45
+ "resample": 3,
46
+ "rescale_factor": 0.00392156862745098
47
+ },
48
+ "image_seq_length": 280,
49
+ "processor_class": "Gemma4Processor",
50
+ "video_processor": {
51
+ "do_convert_rgb": true,
52
+ "do_normalize": true,
53
+ "do_rescale": true,
54
+ "do_resize": true,
55
+ "do_sample_frames": true,
56
+ "image_mean": [
57
+ 0.0,
58
+ 0.0,
59
+ 0.0
60
+ ],
61
+ "image_std": [
62
+ 1.0,
63
+ 1.0,
64
+ 1.0
65
+ ],
66
+ "max_soft_tokens": 70,
67
+ "num_frames": 32,
68
+ "patch_size": 16,
69
+ "pooling_kernel_size": 3,
70
+ "resample": 3,
71
+ "rescale_factor": 0.00392156862745098,
72
+ "return_metadata": false,
73
+ "video_processor_type": "Gemma4VideoProcessor"
74
+ }
75
+ }
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
3
+ size 32170070
runs/dose_p3swap_ep4/arms/p3mix_205_swap_ep4/adapter/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
21
+ "local_files_only": false,
22
+ "mask_token": "<mask>",
23
+ "model_max_length": 1000000000000000019884624838656,
24
+ "model_specific_special_tokens": {
25
+ "audio_token": "<|audio|>",
26
+ "boa_token": "<|audio>",
27
+ "boi_token": "<|image>",
28
+ "eoa_token": "<audio|>",
29
+ "eoc_token": "<channel|>",
30
+ "eoi_token": "<image|>",
31
+ "eot_token": "<turn|>",
32
+ "escape_token": "<|\"|>",
33
+ "etc_token": "<tool_call|>",
34
+ "etd_token": "<tool|>",
35
+ "etr_token": "<tool_response|>",
36
+ "image_token": "<|image|>",
37
+ "soc_token": "<|channel>",
38
+ "sot_token": "<|turn>",
39
+ "stc_token": "<|tool_call>",
40
+ "std_token": "<|tool>",
41
+ "str_token": "<|tool_response>",
42
+ "think_token": "<|think|>"
43
+ },
44
+ "pad_token": "<pad>",
45
+ "padding_side": "left",
46
+ "processor_class": "Gemma4Processor",
47
+ "soc_token": "<|channel>",
48
+ "sot_token": "<|turn>",
49
+ "stc_token": "<|tool_call>",
50
+ "std_token": "<|tool>",
51
+ "str_token": "<|tool_response>",
52
+ "think_token": "<|think|>",
53
+ "tokenizer_class": "GemmaTokenizer",
54
+ "unk_token": "<unk>"
55
+ }