evanrichards
commited on
Commit
•
139cb7c
1
Parent(s):
5d86c09
Training in progress, step 100
Browse files
adapter_config.json
CHANGED
@@ -23,374 +23,374 @@
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
-
"
|
|
|
27 |
"language_model.model.layers.0.mlp.gate_proj",
|
28 |
-
"language_model.model.layers.
|
29 |
-
"
|
30 |
-
"language_model.model.layers.
|
31 |
-
"
|
32 |
-
"
|
33 |
-
"
|
34 |
-
"
|
35 |
-
"
|
|
|
36 |
"language_model.model.layers.13.self_attn.v_proj",
|
37 |
-
"
|
38 |
-
"
|
39 |
-
"
|
40 |
-
"language_model.model.layers.
|
41 |
-
"vision_tower.vision_model.encoder.layers.
|
42 |
-
"
|
43 |
-
"language_model.model.layers.
|
44 |
-
"
|
45 |
-
"language_model.model.layers.
|
46 |
-
"language_model.model.layers.
|
47 |
-
"language_model.model.layers.
|
48 |
-
"language_model.model.layers.18.mlp.up_proj",
|
49 |
-
"language_model.model.layers.5.self_attn.v_proj",
|
50 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc2",
|
51 |
-
"language_model.model.layers.18.self_attn.k_proj",
|
52 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
|
53 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
|
54 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
|
55 |
-
"vision_tower.vision_model.encoder.layers.4.mlp.fc2",
|
56 |
-
"language_model.model.layers.23.self_attn.v_proj",
|
57 |
-
"language_model.model.layers.10.self_attn.o_proj",
|
58 |
-
"language_model.model.layers.30.mlp.gate_proj",
|
59 |
-
"language_model.model.layers.25.mlp.gate_proj",
|
60 |
-
"language_model.model.layers.0.self_attn.k_proj",
|
61 |
-
"vision_tower.vision_model.encoder.layers.15.mlp.fc1",
|
62 |
-
"vision_tower.vision_model.encoder.layers.20.mlp.fc1",
|
63 |
-
"language_model.model.layers.17.self_attn.q_proj",
|
64 |
-
"language_model.model.layers.26.self_attn.v_proj",
|
65 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
|
66 |
-
"language_model.model.layers.7.mlp.down_proj",
|
67 |
-
"language_model.model.layers.13.mlp.gate_proj",
|
68 |
-
"language_model.model.layers.27.self_attn.v_proj",
|
69 |
-
"language_model.model.layers.14.mlp.up_proj",
|
70 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
|
71 |
-
"language_model.model.layers.1.self_attn.v_proj",
|
72 |
-
"language_model.model.layers.30.self_attn.o_proj",
|
73 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
|
74 |
-
"language_model.model.layers.29.self_attn.o_proj",
|
75 |
-
"language_model.model.layers.4.self_attn.q_proj",
|
76 |
-
"language_model.model.layers.12.self_attn.o_proj",
|
77 |
-
"language_model.model.layers.25.self_attn.o_proj",
|
78 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
|
79 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
|
80 |
-
"language_model.model.layers.5.self_attn.q_proj",
|
81 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc1",
|
82 |
-
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
|
83 |
-
"language_model.model.layers.19.mlp.down_proj",
|
84 |
-
"language_model.model.layers.3.self_attn.v_proj",
|
85 |
-
"language_model.model.layers.21.mlp.gate_proj",
|
86 |
-
"language_model.model.layers.17.mlp.gate_proj",
|
87 |
-
"language_model.model.layers.14.self_attn.k_proj",
|
88 |
-
"language_model.model.layers.2.mlp.up_proj",
|
89 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
|
90 |
"language_model.model.layers.28.mlp.gate_proj",
|
91 |
-
"language_model.model.layers.4.mlp.gate_proj",
|
92 |
-
"language_model.model.layers.7.self_attn.v_proj",
|
93 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2",
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1",
|
|
|
|
|
|
|
|
|
95 |
"language_model.model.layers.16.self_attn.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
96 |
"language_model.model.layers.22.self_attn.q_proj",
|
97 |
-
"language_model.model.layers.
|
98 |
-
"language_model.model.layers.
|
99 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
100 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
|
101 |
-
"language_model.model.layers.
|
102 |
-
"vision_tower.vision_model.encoder.layers.
|
103 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
|
105 |
-
"
|
|
|
106 |
"language_model.model.layers.8.mlp.down_proj",
|
107 |
-
"
|
108 |
-
"
|
109 |
-
"
|
110 |
-
"language_model.model.layers.
|
111 |
-
"
|
112 |
-
"language_model.model.layers.
|
113 |
-
"
|
114 |
-
"
|
115 |
-
"
|
116 |
-
"
|
117 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
118 |
"language_model.model.layers.8.mlp.gate_proj",
|
119 |
-
"
|
120 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
|
121 |
-
"language_model.model.layers.11.self_attn.k_proj",
|
122 |
-
"language_model.model.layers.26.mlp.down_proj",
|
123 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
|
124 |
-
"language_model.model.layers.3.mlp.down_proj",
|
125 |
-
"language_model.model.layers.11.mlp.gate_proj",
|
126 |
-
"language_model.model.layers.22.self_attn.k_proj",
|
127 |
-
"language_model.model.layers.7.mlp.gate_proj",
|
128 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
|
129 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc1",
|
130 |
-
"language_model.model.layers.26.mlp.up_proj",
|
131 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
|
132 |
"language_model.model.layers.31.self_attn.o_proj",
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"language_model.model.layers.19.mlp.gate_proj",
|
136 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc2",
|
137 |
-
"language_model.model.layers.26.self_attn.k_proj",
|
138 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc2",
|
139 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc1",
|
140 |
-
"language_model.model.layers.16.mlp.down_proj",
|
141 |
"language_model.model.layers.28.self_attn.o_proj",
|
142 |
-
"vision_tower.vision_model.encoder.layers.
|
143 |
-
"vision_tower.vision_model.encoder.layers.
|
144 |
-
"language_model.model.layers.
|
145 |
-
"
|
146 |
-
"language_model.model.layers.13.self_attn.q_proj",
|
147 |
-
"language_model.model.layers.17.mlp.up_proj",
|
148 |
-
"language_model.model.layers.5.self_attn.o_proj",
|
149 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
|
150 |
-
"vision_tower.vision_model.encoder.layers.7.mlp.fc1",
|
151 |
-
"vision_tower.vision_model.encoder.layers.14.mlp.fc2",
|
152 |
-
"vision_tower.vision_model.encoder.layers.8.mlp.fc2",
|
153 |
-
"language_model.model.layers.1.mlp.down_proj",
|
154 |
-
"language_model.model.layers.9.mlp.up_proj",
|
155 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
|
156 |
-
"language_model.model.layers.26.mlp.gate_proj",
|
157 |
-
"language_model.model.layers.20.self_attn.k_proj",
|
158 |
-
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
|
159 |
-
"language_model.model.layers.4.mlp.down_proj",
|
160 |
-
"vision_tower.vision_model.encoder.layers.9.mlp.fc2",
|
161 |
-
"language_model.model.layers.5.mlp.gate_proj",
|
162 |
-
"language_model.model.layers.30.mlp.up_proj",
|
163 |
"language_model.model.layers.17.self_attn.k_proj",
|
164 |
-
"vision_tower.vision_model.encoder.layers.
|
165 |
-
"
|
166 |
-
"vision_tower.vision_model.encoder.layers.
|
167 |
-
"
|
168 |
-
"vision_tower.vision_model.encoder.layers.
|
169 |
-
"language_model.model.layers.8.self_attn.o_proj",
|
170 |
-
"language_model.model.layers.5.mlp.down_proj",
|
171 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
|
172 |
-
"language_model.model.layers.19.mlp.up_proj",
|
173 |
-
"language_model.model.layers.11.mlp.down_proj",
|
174 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
|
175 |
-
"
|
176 |
-
"
|
177 |
-
"vision_tower.vision_model.encoder.layers.
|
178 |
-
"
|
179 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
"language_model.model.layers.18.mlp.gate_proj",
|
181 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
|
182 |
"language_model.model.layers.25.self_attn.k_proj",
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
186 |
-
"
|
187 |
-
"language_model.model.layers.
|
188 |
-
"vision_tower.vision_model.encoder.layers.
|
189 |
-
"language_model.model.layers.
|
190 |
-
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
|
191 |
-
"language_model.model.layers.6.mlp.down_proj",
|
192 |
-
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
|
193 |
-
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
|
194 |
-
"language_model.model.layers.0.self_attn.q_proj",
|
195 |
-
"language_model.model.layers.12.self_attn.q_proj",
|
196 |
-
"language_model.model.layers.18.self_attn.v_proj",
|
197 |
-
"language_model.model.layers.6.self_attn.v_proj",
|
198 |
-
"language_model.model.layers.17.self_attn.o_proj",
|
199 |
-
"language_model.model.layers.22.self_attn.o_proj",
|
200 |
-
"vision_tower.vision_model.encoder.layers.17.mlp.fc2",
|
201 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
|
202 |
-
"language_model.model.layers.27.self_attn.q_proj",
|
203 |
-
"language_model.model.layers.25.self_attn.q_proj",
|
204 |
"language_model.model.layers.31.mlp.gate_proj",
|
205 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
|
206 |
-
"language_model.model.layers.30.self_attn.k_proj",
|
207 |
-
"language_model.model.layers.22.mlp.gate_proj",
|
208 |
-
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
|
209 |
-
"language_model.model.layers.24.self_attn.o_proj",
|
210 |
-
"language_model.model.layers.11.self_attn.q_proj",
|
211 |
-
"language_model.model.layers.3.self_attn.q_proj",
|
212 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
|
213 |
-
"language_model.model.layers.10.mlp.up_proj",
|
214 |
-
"language_model.model.layers.31.mlp.up_proj",
|
215 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
|
216 |
-
"language_model.model.layers.15.mlp.up_proj",
|
217 |
-
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
|
218 |
-
"vision_tower.vision_model.encoder.layers.5.mlp.fc2",
|
219 |
-
"language_model.model.layers.8.mlp.up_proj",
|
220 |
-
"language_model.model.layers.15.self_attn.k_proj",
|
221 |
-
"vision_tower.vision_model.encoder.layers.21.mlp.fc1",
|
222 |
-
"language_model.model.layers.10.self_attn.q_proj",
|
223 |
-
"language_model.model.layers.20.mlp.down_proj",
|
224 |
"language_model.model.layers.24.mlp.up_proj",
|
225 |
-
"language_model.model.layers.
|
226 |
-
"language_model.model.layers.
|
227 |
-
"language_model.model.layers.
|
228 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
229 |
"language_model.model.layers.30.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
"language_model.model.layers.9.mlp.gate_proj",
|
231 |
-
"
|
232 |
-
"
|
233 |
-
"
|
234 |
-
"language_model.model.layers.12.
|
235 |
-
"
|
236 |
-
"
|
237 |
-
"language_model.model.layers.
|
238 |
-
"language_model.model.layers.5.self_attn.k_proj",
|
239 |
-
"language_model.model.layers.26.self_attn.q_proj",
|
240 |
-
"language_model.model.layers.16.mlp.up_proj",
|
241 |
-
"language_model.model.layers.21.self_attn.q_proj",
|
242 |
-
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
|
243 |
-
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
|
244 |
-
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
|
245 |
-
"language_model.model.layers.4.self_attn.k_proj",
|
246 |
-
"language_model.model.layers.3.mlp.gate_proj",
|
247 |
-
"language_model.model.layers.18.mlp.down_proj",
|
248 |
-
"language_model.model.layers.11.mlp.up_proj",
|
249 |
-
"language_model.model.layers.26.self_attn.o_proj",
|
250 |
-
"language_model.model.layers.29.mlp.gate_proj",
|
251 |
-
"language_model.model.layers.29.mlp.up_proj",
|
252 |
-
"language_model.model.layers.22.self_attn.v_proj",
|
253 |
-
"language_model.model.layers.6.mlp.up_proj",
|
254 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1",
|
255 |
-
"language_model.model.layers.3.self_attn.o_proj",
|
256 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj",
|
257 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
|
258 |
-
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
|
259 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
|
260 |
-
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
|
261 |
-
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
|
262 |
-
"language_model.model.layers.27.mlp.up_proj",
|
263 |
-
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
|
264 |
-
"language_model.model.layers.20.mlp.gate_proj",
|
265 |
-
"vision_tower.vision_model.encoder.layers.16.mlp.fc1",
|
266 |
-
"vision_tower.vision_model.encoder.layers.10.mlp.fc2",
|
267 |
-
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
|
268 |
-
"vision_tower.vision_model.encoder.layers.2.mlp.fc1",
|
269 |
-
"language_model.model.layers.10.mlp.gate_proj",
|
270 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
|
271 |
-
"vision_tower.vision_model.encoder.layers.13.mlp.fc1",
|
272 |
-
"vision_tower.vision_model.encoder.layers.6.mlp.fc2",
|
273 |
-
"language_model.model.layers.20.self_attn.o_proj",
|
274 |
-
"language_model.model.layers.14.self_attn.v_proj",
|
275 |
-
"language_model.model.layers.0.mlp.down_proj",
|
276 |
-
"vision_tower.vision_model.encoder.layers.1.mlp.fc2",
|
277 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
|
278 |
-
"language_model.model.layers.0.self_attn.v_proj",
|
279 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
|
280 |
-
"
|
281 |
-
"language_model.model.layers.
|
282 |
-
"
|
283 |
-
"language_model.model.layers.
|
284 |
-
"language_model.model.layers.
|
285 |
-
"language_model.model.layers.
|
286 |
-
"vision_tower.vision_model.encoder.layers.
|
287 |
-
"language_model.model.layers.
|
288 |
-
"language_model.model.layers.
|
289 |
-
"language_model.model.layers.
|
290 |
-
"vision_tower.vision_model.encoder.layers.
|
291 |
-
"language_model.model.layers.
|
292 |
-
"vision_tower.vision_model.encoder.layers.
|
293 |
-
"
|
294 |
-
"vision_tower.vision_model.encoder.layers.
|
295 |
-
"
|
296 |
-
"language_model.model.layers.
|
297 |
-
"vision_tower.vision_model.encoder.layers.
|
298 |
-
"language_model.model.layers.
|
299 |
-
"
|
300 |
-
"language_model.model.layers.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
301 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
|
302 |
-
"
|
303 |
-
"vision_tower.vision_model.encoder.layers.
|
304 |
-
"
|
305 |
-
"
|
306 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
307 |
"language_model.model.layers.7.self_attn.o_proj",
|
308 |
-
"vision_tower.vision_model.encoder.layers.
|
309 |
-
"
|
310 |
-
"language_model.model.layers.
|
311 |
-
"
|
312 |
-
"
|
313 |
-
"language_model.model.layers.
|
314 |
-
"language_model.model.layers.
|
315 |
-
"language_model.model.layers.
|
316 |
-
"language_model.model.layers.
|
317 |
-
"vision_tower.vision_model.encoder.layers.
|
318 |
-
"language_model.model.layers.
|
319 |
-
"
|
320 |
-
"vision_tower.vision_model.encoder.layers.
|
321 |
-
"language_model.model.layers.31.self_attn.v_proj",
|
322 |
-
"language_model.model.layers.24.mlp.down_proj",
|
323 |
-
"language_model.model.layers.30.self_attn.q_proj",
|
324 |
-
"language_model.model.layers.0.self_attn.o_proj",
|
325 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
|
326 |
-
"language_model.model.layers.
|
327 |
-
"
|
328 |
-
"language_model.model.layers.
|
329 |
-
"
|
330 |
-
"
|
331 |
-
"
|
332 |
-
"language_model.model.layers.
|
333 |
-
"vision_tower.vision_model.encoder.layers.
|
334 |
-
"language_model.model.layers.24.mlp.gate_proj",
|
335 |
-
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
|
336 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
337 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1",
|
338 |
-
"language_model.model.layers.
|
339 |
-
"language_model.model.layers.1.mlp.up_proj",
|
340 |
-
"language_model.model.layers.21.mlp.up_proj",
|
341 |
-
"language_model.model.layers.27.mlp.down_proj",
|
342 |
-
"vision_tower.vision_model.encoder.layers.0.mlp.fc1",
|
343 |
"language_model.model.layers.20.self_attn.v_proj",
|
344 |
-
"language_model.model.layers.
|
345 |
-
"language_model.model.layers.
|
346 |
-
"
|
347 |
-
"
|
348 |
-
"
|
349 |
-
"
|
350 |
-
"language_model.model.layers.19.self_attn.o_proj",
|
351 |
-
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
|
352 |
-
"language_model.model.layers.24.self_attn.k_proj",
|
353 |
-
"language_model.model.layers.2.self_attn.q_proj",
|
354 |
-
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
|
355 |
-
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
|
356 |
-
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
|
357 |
-
"language_model.model.layers.4.self_attn.v_proj",
|
358 |
-
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
|
359 |
-
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
|
360 |
-
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
|
361 |
-
"language_model.model.layers.21.mlp.down_proj",
|
362 |
-
"language_model.model.layers.9.mlp.down_proj",
|
363 |
"language_model.model.layers.7.self_attn.q_proj",
|
364 |
-
"
|
365 |
-
"
|
366 |
-
"
|
367 |
-
"vision_tower.vision_model.encoder.layers.
|
368 |
-
"vision_tower.vision_model.encoder.layers.
|
369 |
-
"language_model.model.layers.14.
|
370 |
-
"language_model.model.layers.
|
371 |
-
"language_model.model.layers.
|
372 |
-
"
|
373 |
-
"vision_tower.vision_model.encoder.layers.
|
374 |
-
"language_model.model.layers.
|
375 |
-
"language_model.model.layers.
|
376 |
-
"vision_tower.vision_model.encoder.layers.
|
377 |
-
"language_model.model.layers.
|
378 |
-
"
|
379 |
-
"language_model.model.layers.
|
380 |
-
"
|
381 |
-
"vision_tower.vision_model.encoder.layers.
|
382 |
-
"language_model.model.layers.
|
383 |
-
"language_model.model.layers.6.self_attn.k_proj",
|
384 |
-
"language_model.model.layers.22.mlp.down_proj",
|
385 |
-
"language_model.model.layers.22.mlp.up_proj",
|
386 |
-
"language_model.model.layers.28.mlp.up_proj",
|
387 |
-
"language_model.model.layers.21.self_attn.o_proj",
|
388 |
"language_model.model.layers.14.self_attn.q_proj",
|
389 |
-
"
|
390 |
-
"vision_tower.vision_model.encoder.layers.
|
|
|
|
|
|
|
|
|
391 |
"language_model.model.layers.9.self_attn.q_proj",
|
392 |
-
"language_model.model.layers.
|
393 |
-
"
|
|
|
394 |
],
|
395 |
"task_type": null,
|
396 |
"use_dora": false,
|
|
|
23 |
"rank_pattern": {},
|
24 |
"revision": null,
|
25 |
"target_modules": [
|
26 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.k_proj",
|
27 |
+
"language_model.model.layers.26.mlp.up_proj",
|
28 |
"language_model.model.layers.0.mlp.gate_proj",
|
29 |
+
"language_model.model.layers.11.self_attn.k_proj",
|
30 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.k_proj",
|
31 |
+
"language_model.model.layers.25.self_attn.v_proj",
|
32 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.v_proj",
|
33 |
+
"language_model.model.layers.12.self_attn.q_proj",
|
34 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc2",
|
35 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.v_proj",
|
36 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc2",
|
37 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.q_proj",
|
38 |
"language_model.model.layers.13.self_attn.v_proj",
|
39 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.v_proj",
|
40 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.out_proj",
|
41 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.out_proj",
|
42 |
+
"language_model.model.layers.1.mlp.gate_proj",
|
43 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.k_proj",
|
44 |
+
"language_model.model.layers.26.self_attn.q_proj",
|
45 |
+
"language_model.model.layers.11.self_attn.q_proj",
|
46 |
+
"language_model.model.layers.20.self_attn.o_proj",
|
47 |
+
"language_model.model.layers.24.mlp.gate_proj",
|
48 |
+
"language_model.model.layers.12.mlp.up_proj",
|
49 |
+
"language_model.model.layers.17.self_attn.o_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
50 |
"language_model.model.layers.28.mlp.gate_proj",
|
|
|
|
|
51 |
"vision_tower.vision_model.encoder.layers.7.mlp.fc2",
|
52 |
+
"language_model.model.layers.29.mlp.up_proj",
|
53 |
+
"language_model.model.layers.16.self_attn.k_proj",
|
54 |
+
"language_model.model.layers.22.self_attn.v_proj",
|
55 |
+
"language_model.model.layers.3.mlp.up_proj",
|
56 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.v_proj",
|
57 |
+
"language_model.model.layers.5.self_attn.o_proj",
|
58 |
"vision_tower.vision_model.encoder.layers.4.mlp.fc1",
|
59 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.q_proj",
|
60 |
+
"language_model.model.layers.18.self_attn.k_proj",
|
61 |
+
"language_model.model.layers.29.self_attn.k_proj",
|
62 |
+
"language_model.model.layers.10.mlp.down_proj",
|
63 |
"language_model.model.layers.16.self_attn.q_proj",
|
64 |
+
"language_model.model.layers.15.self_attn.q_proj",
|
65 |
+
"language_model.model.layers.24.self_attn.v_proj",
|
66 |
+
"language_model.model.layers.0.mlp.up_proj",
|
67 |
+
"language_model.model.layers.14.mlp.gate_proj",
|
68 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.v_proj",
|
69 |
+
"language_model.model.layers.21.mlp.up_proj",
|
70 |
+
"language_model.model.layers.22.mlp.down_proj",
|
71 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc1",
|
72 |
+
"language_model.model.layers.5.mlp.up_proj",
|
73 |
+
"language_model.model.layers.9.self_attn.v_proj",
|
74 |
+
"language_model.model.layers.13.mlp.gate_proj",
|
75 |
+
"language_model.model.layers.2.self_attn.v_proj",
|
76 |
+
"language_model.model.layers.28.self_attn.v_proj",
|
77 |
+
"language_model.model.layers.19.mlp.gate_proj",
|
78 |
+
"language_model.model.layers.29.mlp.down_proj",
|
79 |
+
"language_model.model.layers.27.mlp.gate_proj",
|
80 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.k_proj",
|
81 |
+
"language_model.model.layers.18.mlp.up_proj",
|
82 |
+
"language_model.model.layers.25.mlp.down_proj",
|
83 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.q_proj",
|
84 |
+
"language_model.model.layers.28.mlp.up_proj",
|
85 |
+
"language_model.model.layers.25.self_attn.q_proj",
|
86 |
+
"language_model.model.layers.22.self_attn.o_proj",
|
87 |
+
"language_model.model.layers.3.mlp.gate_proj",
|
88 |
+
"language_model.model.layers.17.mlp.down_proj",
|
89 |
+
"language_model.model.layers.16.mlp.gate_proj",
|
90 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc2",
|
91 |
"language_model.model.layers.22.self_attn.q_proj",
|
92 |
+
"language_model.model.layers.16.mlp.down_proj",
|
93 |
+
"language_model.model.layers.3.self_attn.v_proj",
|
94 |
+
"language_model.model.layers.14.mlp.up_proj",
|
95 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc1",
|
96 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc2",
|
97 |
+
"language_model.model.layers.21.mlp.gate_proj",
|
98 |
+
"language_model.model.layers.11.mlp.gate_proj",
|
99 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.v_proj",
|
100 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.k_proj",
|
101 |
+
"language_model.model.layers.21.self_attn.v_proj",
|
102 |
+
"language_model.model.layers.21.mlp.down_proj",
|
103 |
+
"language_model.model.layers.15.mlp.up_proj",
|
104 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.k_proj",
|
105 |
+
"language_model.model.layers.10.self_attn.k_proj",
|
106 |
+
"language_model.model.layers.13.self_attn.o_proj",
|
107 |
+
"language_model.model.layers.15.self_attn.o_proj",
|
108 |
+
"language_model.model.layers.12.mlp.gate_proj",
|
109 |
+
"language_model.model.layers.29.mlp.gate_proj",
|
110 |
+
"language_model.model.layers.22.mlp.up_proj",
|
111 |
+
"language_model.model.layers.28.self_attn.q_proj",
|
112 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc1",
|
113 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc1",
|
114 |
+
"language_model.model.layers.16.self_attn.o_proj",
|
115 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc1",
|
116 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.k_proj",
|
117 |
"vision_tower.vision_model.encoder.layers.8.self_attn.k_proj",
|
118 |
+
"language_model.model.layers.1.self_attn.k_proj",
|
119 |
+
"vision_tower.vision_model.encoder.layers.22.mlp.fc2",
|
120 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.q_proj",
|
121 |
+
"language_model.model.layers.0.self_attn.v_proj",
|
122 |
+
"language_model.model.layers.8.self_attn.k_proj",
|
123 |
+
"language_model.model.layers.19.self_attn.o_proj",
|
124 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.out_proj",
|
125 |
+
"language_model.model.layers.10.self_attn.v_proj",
|
126 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.k_proj",
|
127 |
+
"language_model.model.layers.13.self_attn.q_proj",
|
128 |
+
"vision_tower.vision_model.encoder.layers.7.mlp.fc1",
|
129 |
"vision_tower.vision_model.encoder.layers.8.self_attn.q_proj",
|
130 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc1",
|
131 |
+
"language_model.model.layers.19.self_attn.k_proj",
|
132 |
"language_model.model.layers.8.mlp.down_proj",
|
133 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.q_proj",
|
134 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.k_proj",
|
135 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc1",
|
136 |
+
"language_model.model.layers.26.self_attn.v_proj",
|
137 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.q_proj",
|
138 |
+
"language_model.model.layers.8.self_attn.q_proj",
|
139 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc1",
|
140 |
+
"language_model.model.layers.9.self_attn.k_proj",
|
141 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.q_proj",
|
142 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.v_proj",
|
143 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.q_proj",
|
144 |
+
"language_model.model.layers.11.self_attn.v_proj",
|
145 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc1",
|
146 |
+
"language_model.model.layers.0.self_attn.o_proj",
|
147 |
+
"language_model.model.layers.18.self_attn.o_proj",
|
148 |
+
"vision_tower.vision_model.encoder.layers.6.mlp.fc1",
|
149 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.q_proj",
|
150 |
+
"vision_tower.vision_model.encoder.layers.2.mlp.fc2",
|
151 |
+
"language_model.model.layers.24.self_attn.q_proj",
|
152 |
"language_model.model.layers.8.mlp.gate_proj",
|
153 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.out_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
154 |
"language_model.model.layers.31.self_attn.o_proj",
|
155 |
+
"language_model.model.layers.5.self_attn.q_proj",
|
156 |
+
"language_model.model.layers.0.self_attn.k_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
"language_model.model.layers.28.self_attn.o_proj",
|
158 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.out_proj",
|
159 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.q_proj",
|
160 |
+
"language_model.model.layers.7.self_attn.v_proj",
|
161 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
162 |
"language_model.model.layers.17.self_attn.k_proj",
|
163 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.q_proj",
|
164 |
+
"language_model.model.layers.22.self_attn.k_proj",
|
165 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc1",
|
166 |
+
"language_model.model.layers.31.mlp.down_proj",
|
167 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
|
|
168 |
"vision_tower.vision_model.encoder.layers.23.self_attn.out_proj",
|
169 |
+
"language_model.model.layers.14.self_attn.k_proj",
|
170 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.v_proj",
|
171 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.v_proj",
|
172 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.q_proj",
|
173 |
+
"vision_tower.vision_model.encoder.layers.3.mlp.fc2",
|
174 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.out_proj",
|
175 |
+
"language_model.model.layers.7.mlp.gate_proj",
|
176 |
+
"vision_tower.vision_model.encoder.layers.10.mlp.fc2",
|
177 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.k_proj",
|
178 |
+
"language_model.model.layers.17.self_attn.q_proj",
|
179 |
+
"vision_tower.vision_model.encoder.layers.21.self_attn.k_proj",
|
180 |
+
"language_model.model.layers.2.self_attn.o_proj",
|
181 |
+
"language_model.model.layers.15.self_attn.k_proj",
|
182 |
+
"language_model.model.layers.3.self_attn.q_proj",
|
183 |
+
"language_model.model.layers.26.mlp.gate_proj",
|
184 |
+
"language_model.model.layers.14.mlp.down_proj",
|
185 |
+
"vision_tower.vision_model.encoder.layers.0.self_attn.out_proj",
|
186 |
+
"language_model.model.layers.5.self_attn.k_proj",
|
187 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.out_proj",
|
188 |
+
"language_model.model.layers.23.self_attn.k_proj",
|
189 |
+
"language_model.model.layers.2.mlp.down_proj",
|
190 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.k_proj",
|
191 |
+
"language_model.model.layers.3.self_attn.o_proj",
|
192 |
+
"language_model.model.layers.31.self_attn.q_proj",
|
193 |
+
"language_model.model.layers.27.mlp.down_proj",
|
194 |
+
"language_model.model.layers.2.self_attn.q_proj",
|
195 |
+
"language_model.model.layers.4.mlp.gate_proj",
|
196 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.v_proj",
|
197 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc1",
|
198 |
+
"language_model.model.layers.24.mlp.down_proj",
|
199 |
+
"language_model.model.layers.30.mlp.up_proj",
|
200 |
+
"vision_tower.vision_model.encoder.layers.12.mlp.fc1",
|
201 |
+
"language_model.model.layers.4.self_attn.k_proj",
|
202 |
+
"language_model.model.layers.6.mlp.down_proj",
|
203 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc2",
|
204 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.q_proj",
|
205 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.q_proj",
|
206 |
+
"language_model.model.layers.5.mlp.down_proj",
|
207 |
+
"language_model.model.layers.31.self_attn.v_proj",
|
208 |
+
"language_model.model.layers.7.mlp.up_proj",
|
209 |
+
"language_model.model.layers.2.mlp.up_proj",
|
210 |
+
"language_model.model.layers.13.mlp.down_proj",
|
211 |
+
"language_model.model.layers.15.mlp.gate_proj",
|
212 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.out_proj",
|
213 |
+
"language_model.model.layers.10.mlp.gate_proj",
|
214 |
"language_model.model.layers.18.mlp.gate_proj",
|
|
|
215 |
"language_model.model.layers.25.self_attn.k_proj",
|
216 |
+
"language_model.model.layers.21.self_attn.o_proj",
|
217 |
+
"language_model.model.layers.20.mlp.gate_proj",
|
218 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.out_proj",
|
219 |
+
"vision_tower.vision_model.encoder.layers.11.mlp.fc2",
|
220 |
+
"language_model.model.layers.1.mlp.down_proj",
|
221 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.k_proj",
|
222 |
+
"language_model.model.layers.27.self_attn.k_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
223 |
"language_model.model.layers.31.mlp.gate_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
224 |
"language_model.model.layers.24.mlp.up_proj",
|
225 |
+
"language_model.model.layers.5.mlp.gate_proj",
|
226 |
+
"language_model.model.layers.8.self_attn.o_proj",
|
227 |
+
"language_model.model.layers.11.mlp.up_proj",
|
228 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc1",
|
229 |
+
"language_model.model.layers.23.self_attn.o_proj",
|
230 |
+
"language_model.model.layers.26.mlp.down_proj",
|
231 |
+
"language_model.model.layers.13.mlp.up_proj",
|
232 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.v_proj",
|
233 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.k_proj",
|
234 |
+
"language_model.model.layers.21.self_attn.q_proj",
|
235 |
+
"vision_tower.vision_model.encoder.layers.7.self_attn.out_proj",
|
236 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.v_proj",
|
237 |
+
"language_model.model.layers.31.self_attn.k_proj",
|
238 |
+
"language_model.model.layers.30.mlp.down_proj",
|
239 |
+
"vision_tower.vision_model.encoder.layers.6.self_attn.out_proj",
|
240 |
+
"language_model.model.layers.29.self_attn.q_proj",
|
241 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.out_proj",
|
242 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.v_proj",
|
243 |
+
"vision_tower.vision_model.encoder.layers.19.mlp.fc1",
|
244 |
"language_model.model.layers.30.self_attn.v_proj",
|
245 |
+
"language_model.model.layers.23.mlp.down_proj",
|
246 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.k_proj",
|
247 |
+
"language_model.model.layers.4.mlp.down_proj",
|
248 |
+
"language_model.model.layers.6.self_attn.o_proj",
|
249 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.q_proj",
|
250 |
+
"vision_tower.vision_model.encoder.layers.13.mlp.fc2",
|
251 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc2",
|
252 |
"language_model.model.layers.9.mlp.gate_proj",
|
253 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.q_proj",
|
254 |
+
"language_model.model.layers.27.self_attn.q_proj",
|
255 |
+
"language_model.model.layers.7.mlp.down_proj",
|
256 |
+
"language_model.model.layers.12.mlp.down_proj",
|
257 |
+
"language_model.model.layers.27.self_attn.v_proj",
|
258 |
+
"vision_tower.vision_model.encoder.layers.15.mlp.fc2",
|
259 |
+
"language_model.model.layers.23.self_attn.q_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
260 |
"vision_tower.vision_model.encoder.layers.3.mlp.fc1",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
261 |
"vision_tower.vision_model.encoder.layers.22.self_attn.q_proj",
|
262 |
+
"language_model.model.layers.1.mlp.up_proj",
|
263 |
+
"language_model.model.layers.12.self_attn.k_proj",
|
264 |
+
"vision_tower.vision_model.encoder.layers.20.self_attn.out_proj",
|
265 |
+
"language_model.model.layers.16.mlp.up_proj",
|
266 |
+
"language_model.model.layers.11.self_attn.o_proj",
|
267 |
+
"language_model.model.layers.29.self_attn.v_proj",
|
268 |
+
"vision_tower.vision_model.encoder.layers.8.mlp.fc2",
|
269 |
+
"language_model.model.layers.0.self_attn.q_proj",
|
270 |
+
"language_model.model.layers.8.self_attn.v_proj",
|
271 |
+
"language_model.model.layers.23.self_attn.v_proj",
|
272 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc1",
|
273 |
+
"language_model.model.layers.23.mlp.up_proj",
|
274 |
+
"vision_tower.vision_model.encoder.layers.0.mlp.fc2",
|
275 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.out_proj",
|
276 |
+
"vision_tower.vision_model.encoder.layers.16.mlp.fc2",
|
277 |
+
"language_model.model.layers.12.self_attn.o_proj",
|
278 |
+
"language_model.model.layers.3.self_attn.k_proj",
|
279 |
+
"vision_tower.vision_model.encoder.layers.15.self_attn.q_proj",
|
280 |
+
"language_model.model.layers.3.mlp.down_proj",
|
281 |
+
"language_model.model.layers.27.mlp.up_proj",
|
282 |
+
"language_model.model.layers.4.self_attn.o_proj",
|
283 |
+
"language_model.model.layers.27.self_attn.o_proj",
|
284 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.q_proj",
|
285 |
+
"vision_tower.vision_model.encoder.layers.4.self_attn.q_proj",
|
286 |
+
"vision_tower.vision_model.encoder.layers.20.mlp.fc1",
|
287 |
+
"language_model.model.layers.19.mlp.down_proj",
|
288 |
+
"language_model.model.layers.10.mlp.up_proj",
|
289 |
+
"language_model.model.layers.18.self_attn.q_proj",
|
290 |
"vision_tower.vision_model.encoder.layers.18.self_attn.q_proj",
|
291 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.k_proj",
|
292 |
+
"vision_tower.vision_model.encoder.layers.11.self_attn.q_proj",
|
293 |
+
"language_model.model.layers.15.self_attn.v_proj",
|
294 |
+
"language_model.model.layers.22.mlp.gate_proj",
|
295 |
+
"language_model.model.layers.30.self_attn.o_proj",
|
296 |
+
"language_model.model.layers.10.self_attn.q_proj",
|
297 |
+
"language_model.model.layers.17.self_attn.v_proj",
|
298 |
+
"vision_tower.vision_model.encoder.layers.21.mlp.fc2",
|
299 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc2",
|
300 |
+
"language_model.model.layers.8.mlp.up_proj",
|
301 |
+
"language_model.model.layers.12.self_attn.v_proj",
|
302 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.out_proj",
|
303 |
+
"language_model.model.layers.6.self_attn.k_proj",
|
304 |
+
"language_model.model.layers.9.mlp.up_proj",
|
305 |
+
"language_model.model.layers.11.mlp.down_proj",
|
306 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.out_proj",
|
307 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.k_proj",
|
308 |
+
"language_model.model.layers.6.mlp.up_proj",
|
309 |
"language_model.model.layers.7.self_attn.o_proj",
|
310 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.k_proj",
|
311 |
+
"language_model.model.layers.21.self_attn.k_proj",
|
312 |
+
"language_model.model.layers.24.self_attn.k_proj",
|
313 |
+
"language_model.model.layers.29.self_attn.o_proj",
|
314 |
+
"language_model.model.layers.19.self_attn.v_proj",
|
315 |
+
"language_model.model.layers.18.self_attn.v_proj",
|
316 |
+
"language_model.model.layers.25.mlp.gate_proj",
|
317 |
+
"language_model.model.layers.20.mlp.up_proj",
|
318 |
+
"language_model.model.layers.10.self_attn.o_proj",
|
319 |
+
"vision_tower.vision_model.encoder.layers.23.mlp.fc2",
|
320 |
+
"language_model.model.layers.5.self_attn.v_proj",
|
321 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.v_proj",
|
322 |
+
"vision_tower.vision_model.encoder.layers.22.self_attn.v_proj",
|
|
|
|
|
|
|
|
|
323 |
"vision_tower.vision_model.encoder.layers.21.self_attn.out_proj",
|
324 |
+
"language_model.model.layers.0.mlp.down_proj",
|
325 |
+
"language_model.model.layers.18.mlp.down_proj",
|
326 |
+
"language_model.model.layers.20.self_attn.q_proj",
|
327 |
+
"vision_tower.vision_model.encoder.layers.8.self_attn.out_proj",
|
328 |
+
"vision_tower.vision_model.encoder.layers.1.mlp.fc1",
|
329 |
+
"language_model.model.layers.15.mlp.down_proj",
|
330 |
+
"language_model.model.layers.26.self_attn.o_proj",
|
331 |
+
"vision_tower.vision_model.encoder.layers.4.mlp.fc2",
|
|
|
|
|
332 |
"vision_tower.vision_model.encoder.layers.21.self_attn.v_proj",
|
333 |
+
"language_model.model.layers.16.self_attn.v_proj",
|
334 |
+
"language_model.model.layers.1.self_attn.o_proj",
|
335 |
+
"vision_tower.vision_model.encoder.layers.1.self_attn.v_proj",
|
336 |
+
"vision_tower.vision_model.encoder.layers.2.self_attn.out_proj",
|
337 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.k_proj",
|
338 |
+
"language_model.model.layers.31.mlp.up_proj",
|
339 |
+
"language_model.model.layers.14.self_attn.o_proj",
|
340 |
+
"language_model.model.layers.20.mlp.down_proj",
|
341 |
+
"language_model.model.layers.4.self_attn.v_proj",
|
342 |
+
"vision_tower.vision_model.encoder.layers.17.mlp.fc2",
|
343 |
+
"vision_tower.vision_model.encoder.layers.9.self_attn.v_proj",
|
344 |
+
"vision_tower.vision_model.encoder.layers.9.mlp.fc1",
|
345 |
+
"language_model.model.layers.30.mlp.gate_proj",
|
346 |
+
"language_model.model.layers.24.self_attn.o_proj",
|
347 |
+
"language_model.model.layers.19.self_attn.q_proj",
|
348 |
+
"language_model.model.layers.6.mlp.gate_proj",
|
349 |
+
"language_model.model.layers.6.self_attn.v_proj",
|
350 |
+
"language_model.model.layers.17.mlp.gate_proj",
|
351 |
+
"language_model.model.layers.25.mlp.up_proj",
|
352 |
+
"vision_tower.vision_model.encoder.layers.14.mlp.fc1",
|
353 |
+
"vision_tower.vision_model.encoder.layers.3.self_attn.k_proj",
|
354 |
"vision_tower.vision_model.encoder.layers.22.mlp.fc1",
|
355 |
+
"language_model.model.layers.4.self_attn.q_proj",
|
|
|
|
|
|
|
|
|
356 |
"language_model.model.layers.20.self_attn.v_proj",
|
357 |
+
"language_model.model.layers.9.self_attn.o_proj",
|
358 |
+
"language_model.model.layers.13.self_attn.k_proj",
|
359 |
+
"language_model.model.layers.30.self_attn.q_proj",
|
360 |
+
"language_model.model.layers.20.self_attn.k_proj",
|
361 |
+
"language_model.model.layers.4.mlp.up_proj",
|
362 |
+
"language_model.model.layers.17.mlp.up_proj",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
363 |
"language_model.model.layers.7.self_attn.q_proj",
|
364 |
+
"vision_tower.vision_model.encoder.layers.5.self_attn.q_proj",
|
365 |
+
"vision_tower.vision_model.encoder.layers.14.self_attn.out_proj",
|
366 |
+
"language_model.model.layers.25.self_attn.o_proj",
|
367 |
+
"vision_tower.vision_model.encoder.layers.12.self_attn.out_proj",
|
368 |
+
"vision_tower.vision_model.encoder.layers.19.self_attn.v_proj",
|
369 |
+
"language_model.model.layers.14.self_attn.v_proj",
|
370 |
+
"language_model.model.layers.7.self_attn.k_proj",
|
371 |
+
"language_model.model.layers.30.self_attn.k_proj",
|
372 |
+
"language_model.model.layers.26.self_attn.k_proj",
|
373 |
+
"vision_tower.vision_model.encoder.layers.5.mlp.fc2",
|
374 |
+
"language_model.model.layers.9.mlp.down_proj",
|
375 |
+
"language_model.model.layers.23.mlp.gate_proj",
|
376 |
+
"vision_tower.vision_model.encoder.layers.17.self_attn.out_proj",
|
377 |
+
"language_model.model.layers.19.mlp.up_proj",
|
378 |
+
"vision_tower.vision_model.encoder.layers.23.self_attn.v_proj",
|
379 |
+
"language_model.model.layers.1.self_attn.v_proj",
|
380 |
+
"language_model.model.layers.6.self_attn.q_proj",
|
381 |
+
"vision_tower.vision_model.encoder.layers.10.self_attn.k_proj",
|
382 |
+
"language_model.model.layers.28.mlp.down_proj",
|
|
|
|
|
|
|
|
|
|
|
383 |
"language_model.model.layers.14.self_attn.q_proj",
|
384 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.k_proj",
|
385 |
+
"vision_tower.vision_model.encoder.layers.18.self_attn.k_proj",
|
386 |
+
"language_model.model.layers.1.self_attn.q_proj",
|
387 |
+
"language_model.model.layers.28.self_attn.k_proj",
|
388 |
+
"vision_tower.vision_model.encoder.layers.13.self_attn.v_proj",
|
389 |
+
"vision_tower.vision_model.encoder.layers.18.mlp.fc2",
|
390 |
"language_model.model.layers.9.self_attn.q_proj",
|
391 |
+
"language_model.model.layers.2.mlp.gate_proj",
|
392 |
+
"language_model.model.layers.2.self_attn.k_proj",
|
393 |
+
"vision_tower.vision_model.encoder.layers.16.self_attn.v_proj"
|
394 |
],
|
395 |
"task_type": null,
|
396 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 784448728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:290f553dcaddf2bed8f6638d63e2b67f068cb5f9b3033bcea428c66c77a1497a
|
3 |
size 784448728
|
runs/Aug27_17-45-20_36ce2d0b5352/events.out.tfevents.1724780732.36ce2d0b5352.4984.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6ed33dc237e444f8bdd850ffc10cd808ce45141354c5449c4765593b046a0f2
|
3 |
+
size 12645
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e27db6ae0e78a55fe66e7a0c99c5078752751b388e037dbac39a74b6f976464d
|
3 |
size 5176
|