Upload folder using huggingface_hub
Browse files- README.md +472 -0
- config.json +28 -0
- mergekit_config.yml +444 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
README.md
ADDED
@@ -0,0 +1,472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
library_name: transformers
|
4 |
+
tags:
|
5 |
+
- mergekit
|
6 |
+
- merge
|
7 |
+
|
8 |
+
---
|
9 |
+
# Bagel-Multiverse-20B-exp40-3-bf16
|
10 |
+
|
11 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
+
|
13 |
+
## Merge Details
|
14 |
+
### Merge Method
|
15 |
+
|
16 |
+
This model was merged using the passthrough merge method.
|
17 |
+
|
18 |
+
### Models Merged
|
19 |
+
|
20 |
+
The following models were included in the merge:
|
21 |
+
* E:/Bagel-Multiverse-20B-bg
|
22 |
+
|
23 |
+
### Configuration
|
24 |
+
|
25 |
+
The following YAML configuration was used to produce this model:
|
26 |
+
|
27 |
+
```yaml
|
28 |
+
# Six splits plus "end game
|
29 |
+
# "D" starts at plus .1 VS D/O proj.
|
30 |
+
# 40 plus.
|
31 |
+
# Formula 3
|
32 |
+
|
33 |
+
slices:
|
34 |
+
- sources:
|
35 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
36 |
+
layer_range: [0, 48]
|
37 |
+
|
38 |
+
# D/G Block Settings.
|
39 |
+
# split 1: .11 to .61 [.04 G] [4 layers]
|
40 |
+
# split 2: .15 to .41 [.08 G] [4 layers]
|
41 |
+
# split 3: .19 to .35 [.23 G] [12 layers]
|
42 |
+
# split 4: .11 to .41 [.244 G] [4 layers]
|
43 |
+
# split 5: .15 to .3 [.248 G] [4 layers]
|
44 |
+
# spilt 6: .19 to .3 [.256 G] [7 layers]
|
45 |
+
# final [D/G]: .33,.44,.55,.66,.77/.88 [5 layers]
|
46 |
+
|
47 |
+
# conc layers
|
48 |
+
# split 1
|
49 |
+
|
50 |
+
- sources:
|
51 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
52 |
+
layer_range: [48,49]
|
53 |
+
parameters:
|
54 |
+
scale:
|
55 |
+
- filter: o_proj
|
56 |
+
value: 0.01
|
57 |
+
- filter: down_proj
|
58 |
+
value: 0.01
|
59 |
+
- value: 0.11
|
60 |
+
- sources:
|
61 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
62 |
+
layer_range: [48,49]
|
63 |
+
parameters:
|
64 |
+
scale:
|
65 |
+
- filter: o_proj
|
66 |
+
value: 0.02
|
67 |
+
- filter: down_proj
|
68 |
+
value: 0.02
|
69 |
+
- value: 0.12
|
70 |
+
- sources:
|
71 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
72 |
+
layer_range: [48,49]
|
73 |
+
parameters:
|
74 |
+
scale:
|
75 |
+
- filter: o_proj
|
76 |
+
value: 0.03
|
77 |
+
- filter: down_proj
|
78 |
+
value: 0.03
|
79 |
+
- value: 0.13
|
80 |
+
|
81 |
+
- sources:
|
82 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
83 |
+
layer_range: [48,49]
|
84 |
+
parameters:
|
85 |
+
scale:
|
86 |
+
- filter: o_proj
|
87 |
+
value: 0.04
|
88 |
+
- filter: down_proj
|
89 |
+
value: 0.04
|
90 |
+
- value: 0.61
|
91 |
+
|
92 |
+
# split 2, SURGE D THEN D drop .46, continues @ D .15 (from .13)
|
93 |
+
|
94 |
+
- sources:
|
95 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
96 |
+
layer_range: [48,49]
|
97 |
+
parameters:
|
98 |
+
scale:
|
99 |
+
- filter: o_proj
|
100 |
+
value: 0.05
|
101 |
+
- filter: down_proj
|
102 |
+
value: 0.05
|
103 |
+
- value: 0.15
|
104 |
+
- sources:
|
105 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
106 |
+
layer_range: [48,49]
|
107 |
+
parameters:
|
108 |
+
scale:
|
109 |
+
- filter: o_proj
|
110 |
+
value: 0.06
|
111 |
+
- filter: down_proj
|
112 |
+
value: 0.06
|
113 |
+
- value: 0.16
|
114 |
+
- sources:
|
115 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
116 |
+
layer_range: [48,49]
|
117 |
+
parameters:
|
118 |
+
scale:
|
119 |
+
- filter: o_proj
|
120 |
+
value: 0.07
|
121 |
+
- filter: down_proj
|
122 |
+
value: 0.07
|
123 |
+
- value: 0.17
|
124 |
+
- sources:
|
125 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
126 |
+
layer_range: [48,49]
|
127 |
+
parameters:
|
128 |
+
scale:
|
129 |
+
- filter: o_proj
|
130 |
+
value: 0.08
|
131 |
+
- filter: down_proj
|
132 |
+
value: 0.08
|
133 |
+
- value: 0.41
|
134 |
+
|
135 |
+
# split 3, SURGE D to .41, D drop .21 ... follows .17 previous
|
136 |
+
|
137 |
+
- sources:
|
138 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
139 |
+
layer_range: [48,49]
|
140 |
+
parameters:
|
141 |
+
scale:
|
142 |
+
- filter: o_proj
|
143 |
+
value: 0.09
|
144 |
+
- filter: down_proj
|
145 |
+
value: 0.09
|
146 |
+
- value: 0.19
|
147 |
+
- sources:
|
148 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
149 |
+
layer_range: [48,49]
|
150 |
+
parameters:
|
151 |
+
scale:
|
152 |
+
- filter: o_proj
|
153 |
+
value: 0.10
|
154 |
+
- filter: down_proj
|
155 |
+
value: 0.10
|
156 |
+
- value: 0.20
|
157 |
+
- sources:
|
158 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
159 |
+
layer_range: [48,49]
|
160 |
+
parameters:
|
161 |
+
scale:
|
162 |
+
- filter: o_proj
|
163 |
+
value: 0.11
|
164 |
+
- filter: down_proj
|
165 |
+
value: 0.11
|
166 |
+
- value: .22
|
167 |
+
- sources:
|
168 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
169 |
+
layer_range: [48,49]
|
170 |
+
parameters:
|
171 |
+
scale:
|
172 |
+
- filter: o_proj
|
173 |
+
value: 0.12
|
174 |
+
- filter: down_proj
|
175 |
+
value: 0.12
|
176 |
+
- value: .24
|
177 |
+
- sources:
|
178 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
179 |
+
layer_range: [48,49]
|
180 |
+
parameters:
|
181 |
+
scale:
|
182 |
+
- filter: o_proj
|
183 |
+
value: 0.13
|
184 |
+
- filter: down_proj
|
185 |
+
value: 0.13
|
186 |
+
- value: .26
|
187 |
+
- sources:
|
188 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
189 |
+
layer_range: [48,49]
|
190 |
+
parameters:
|
191 |
+
scale:
|
192 |
+
- filter: o_proj
|
193 |
+
value: 0.14
|
194 |
+
- filter: down_proj
|
195 |
+
value: 0.14
|
196 |
+
- value: .28
|
197 |
+
- sources:
|
198 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
199 |
+
layer_range: [48,49]
|
200 |
+
parameters:
|
201 |
+
scale:
|
202 |
+
- filter: o_proj
|
203 |
+
value: 0.15
|
204 |
+
- filter: down_proj
|
205 |
+
value: 0.15
|
206 |
+
- value: .30
|
207 |
+
- sources:
|
208 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
209 |
+
layer_range: [48,49]
|
210 |
+
parameters:
|
211 |
+
scale:
|
212 |
+
- filter: o_proj
|
213 |
+
value: 0.16
|
214 |
+
- filter: down_proj
|
215 |
+
value: 0.16
|
216 |
+
- value: .31
|
217 |
+
- sources:
|
218 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
219 |
+
layer_range: [48,49]
|
220 |
+
parameters:
|
221 |
+
scale:
|
222 |
+
- filter: o_proj
|
223 |
+
value: 0.20
|
224 |
+
- filter: down_proj
|
225 |
+
value: 0.20
|
226 |
+
- value: .32
|
227 |
+
- sources:
|
228 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
229 |
+
layer_range: [48,49]
|
230 |
+
parameters:
|
231 |
+
scale:
|
232 |
+
- filter: o_proj
|
233 |
+
value: 0.21
|
234 |
+
- filter: down_proj
|
235 |
+
value: 0.21
|
236 |
+
- value: .33
|
237 |
+
- sources:
|
238 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
239 |
+
layer_range: [48,49]
|
240 |
+
parameters:
|
241 |
+
scale:
|
242 |
+
- filter: o_proj
|
243 |
+
value: 0.22
|
244 |
+
- filter: down_proj
|
245 |
+
value: 0.22
|
246 |
+
- value: .34
|
247 |
+
- sources:
|
248 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
249 |
+
layer_range: [48,49]
|
250 |
+
parameters:
|
251 |
+
scale:
|
252 |
+
- filter: o_proj
|
253 |
+
value: 0.23
|
254 |
+
- filter: down_proj
|
255 |
+
value: 0.23
|
256 |
+
- value: .35
|
257 |
+
|
258 |
+
# split 4 , NO SURGE D, "D" down drop of .24 ; reverts to .11 (the very first "D" setting )
|
259 |
+
|
260 |
+
- sources:
|
261 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
262 |
+
layer_range: [48,49]
|
263 |
+
parameters:
|
264 |
+
scale:
|
265 |
+
- filter: o_proj
|
266 |
+
value: 0.24
|
267 |
+
- filter: down_proj
|
268 |
+
value: 0.24
|
269 |
+
- value: 0.11
|
270 |
+
- sources:
|
271 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
272 |
+
layer_range: [48,49]
|
273 |
+
parameters:
|
274 |
+
scale:
|
275 |
+
- filter: o_proj
|
276 |
+
value: 0.241
|
277 |
+
- filter: down_proj
|
278 |
+
value: 0.241
|
279 |
+
- value: 0.12
|
280 |
+
- sources:
|
281 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
282 |
+
layer_range: [48,49]
|
283 |
+
parameters:
|
284 |
+
scale:
|
285 |
+
- filter: o_proj
|
286 |
+
value: 0.242
|
287 |
+
- filter: down_proj
|
288 |
+
value: 0.243
|
289 |
+
- value: 0.13
|
290 |
+
- sources:
|
291 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
292 |
+
layer_range: [48,49]
|
293 |
+
parameters:
|
294 |
+
scale:
|
295 |
+
- filter: o_proj
|
296 |
+
value: 0.244
|
297 |
+
- filter: down_proj
|
298 |
+
value: 0.244
|
299 |
+
- value: 0.61
|
300 |
+
|
301 |
+
# split 5, D Surge to .61, drop to .15 (following .13)
|
302 |
+
|
303 |
+
- sources:
|
304 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
305 |
+
layer_range: [48,49]
|
306 |
+
parameters:
|
307 |
+
scale:
|
308 |
+
- filter: o_proj
|
309 |
+
value: 0.245
|
310 |
+
- filter: down_proj
|
311 |
+
value: 0.245
|
312 |
+
- value: 0.15
|
313 |
+
- sources:
|
314 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
315 |
+
layer_range: [48,49]
|
316 |
+
parameters:
|
317 |
+
scale:
|
318 |
+
- filter: o_proj
|
319 |
+
value: 0.246
|
320 |
+
- filter: down_proj
|
321 |
+
value: 0.246
|
322 |
+
- value: 0.16
|
323 |
+
- sources:
|
324 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
325 |
+
layer_range: [48,49]
|
326 |
+
parameters:
|
327 |
+
scale:
|
328 |
+
- filter: o_proj
|
329 |
+
value: 0.247
|
330 |
+
- filter: down_proj
|
331 |
+
value: 0.247
|
332 |
+
- value: 0.17
|
333 |
+
- sources:
|
334 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
335 |
+
layer_range: [48,49]
|
336 |
+
parameters:
|
337 |
+
scale:
|
338 |
+
- filter: o_proj
|
339 |
+
value: 0.248
|
340 |
+
- filter: down_proj
|
341 |
+
value: 0.248
|
342 |
+
- value: 0.41
|
343 |
+
|
344 |
+
# split 6, D surge to .41 , then follows .17
|
345 |
+
|
346 |
+
- sources:
|
347 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
348 |
+
layer_range: [48,49]
|
349 |
+
parameters:
|
350 |
+
scale:
|
351 |
+
- filter: o_proj
|
352 |
+
value: 0.249
|
353 |
+
- filter: down_proj
|
354 |
+
value: 0.249
|
355 |
+
- value: 0.19
|
356 |
+
- sources:
|
357 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
358 |
+
layer_range: [48,49]
|
359 |
+
parameters:
|
360 |
+
scale:
|
361 |
+
- filter: o_proj
|
362 |
+
value: 0.250
|
363 |
+
- filter: down_proj
|
364 |
+
value: 0.250
|
365 |
+
- value: 0.20
|
366 |
+
- sources:
|
367 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
368 |
+
layer_range: [48,49]
|
369 |
+
parameters:
|
370 |
+
scale:
|
371 |
+
- filter: o_proj
|
372 |
+
value: 0.251
|
373 |
+
- filter: down_proj
|
374 |
+
value: 0.251
|
375 |
+
- value: .22
|
376 |
+
- sources:
|
377 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
378 |
+
layer_range: [48,49]
|
379 |
+
parameters:
|
380 |
+
scale:
|
381 |
+
- filter: o_proj
|
382 |
+
value: 0.252
|
383 |
+
- filter: down_proj
|
384 |
+
value: 0.252
|
385 |
+
- value: .24
|
386 |
+
- sources:
|
387 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
388 |
+
layer_range: [48,49]
|
389 |
+
parameters:
|
390 |
+
scale:
|
391 |
+
- filter: o_proj
|
392 |
+
value: 0.253
|
393 |
+
- filter: down_proj
|
394 |
+
value: 0.254
|
395 |
+
- value: .26
|
396 |
+
- sources:
|
397 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
398 |
+
layer_range: [48,49]
|
399 |
+
parameters:
|
400 |
+
scale:
|
401 |
+
- filter: o_proj
|
402 |
+
value: 0.255
|
403 |
+
- filter: down_proj
|
404 |
+
value: 0.255
|
405 |
+
- value: .28
|
406 |
+
- sources:
|
407 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
408 |
+
layer_range: [48,49]
|
409 |
+
parameters:
|
410 |
+
scale:
|
411 |
+
- filter: o_proj
|
412 |
+
value: 0.256
|
413 |
+
- filter: down_proj
|
414 |
+
value: 0.256
|
415 |
+
- value: .30
|
416 |
+
|
417 |
+
# O PROJ, DPROJ to .3333 /
|
418 |
+
# end game
|
419 |
+
|
420 |
+
- sources:
|
421 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
422 |
+
layer_range: [48,49]
|
423 |
+
parameters:
|
424 |
+
scale:
|
425 |
+
- filter: o_proj
|
426 |
+
value: 0.3333333333333
|
427 |
+
- filter: down_proj
|
428 |
+
value: 0.3333333333333
|
429 |
+
- value: 0.3333333333333
|
430 |
+
- sources:
|
431 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
432 |
+
layer_range: [48,49]
|
433 |
+
parameters:
|
434 |
+
scale:
|
435 |
+
- filter: o_proj
|
436 |
+
value: 0.4444444444444
|
437 |
+
- filter: down_proj
|
438 |
+
value: 0.4444444444444
|
439 |
+
- value: 0.4444444444444
|
440 |
+
- sources:
|
441 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
442 |
+
layer_range: [48,49]
|
443 |
+
parameters:
|
444 |
+
scale:
|
445 |
+
- filter: o_proj
|
446 |
+
value: 0.5555555555555
|
447 |
+
- filter: down_proj
|
448 |
+
value: 0.5555555555555
|
449 |
+
- value: 0.5555555555555
|
450 |
+
- sources:
|
451 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
452 |
+
layer_range: [48,49]
|
453 |
+
parameters:
|
454 |
+
scale:
|
455 |
+
- filter: o_proj
|
456 |
+
value: 0.6666666666666
|
457 |
+
- filter: down_proj
|
458 |
+
value: 0.6666666666666
|
459 |
+
- value: 0.6666666666666
|
460 |
+
- sources:
|
461 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
462 |
+
layer_range: [48,49]
|
463 |
+
parameters:
|
464 |
+
scale:
|
465 |
+
- filter: o_proj
|
466 |
+
value: 0.777777777777
|
467 |
+
- filter: down_proj
|
468 |
+
value: 0.777777777777
|
469 |
+
- value: 0.888888888888
|
470 |
+
merge_method: passthrough
|
471 |
+
dtype: float16
|
472 |
+
```
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "E:/Bagel-Multiverse-20B-bg",
|
3 |
+
"add_gates": false,
|
4 |
+
"architectures": [
|
5 |
+
"MistralForCausalLM"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 4096,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 14336,
|
15 |
+
"max_position_embeddings": 32768,
|
16 |
+
"model_type": "mistral",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 88,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"sliding_window": 4096,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float16",
|
25 |
+
"transformers_version": "4.43.3",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,444 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# Six splits plus "end game
|
2 |
+
# "D" starts at plus .1 VS D/O proj.
|
3 |
+
# 40 plus.
|
4 |
+
# Formula 3
|
5 |
+
|
6 |
+
slices:
|
7 |
+
- sources:
|
8 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
9 |
+
layer_range: [0, 48]
|
10 |
+
|
11 |
+
# D/G Block Settings.
|
12 |
+
# split 1: .11 to .61 [.04 G] [4 layers]
|
13 |
+
# split 2: .15 to .41 [.08 G] [4 layers]
|
14 |
+
# split 3: .19 to .35 [.23 G] [12 layers]
|
15 |
+
# split 4: .11 to .41 [.244 G] [4 layers]
|
16 |
+
# split 5: .15 to .3 [.248 G] [4 layers]
|
17 |
+
# spilt 6: .19 to .3 [.256 G] [7 layers]
|
18 |
+
# final [D/G]: .33,.44,.55,.66,.77/.88 [5 layers]
|
19 |
+
|
20 |
+
# conc layers
|
21 |
+
# split 1
|
22 |
+
|
23 |
+
- sources:
|
24 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
25 |
+
layer_range: [48,49]
|
26 |
+
parameters:
|
27 |
+
scale:
|
28 |
+
- filter: o_proj
|
29 |
+
value: 0.01
|
30 |
+
- filter: down_proj
|
31 |
+
value: 0.01
|
32 |
+
- value: 0.11
|
33 |
+
- sources:
|
34 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
35 |
+
layer_range: [48,49]
|
36 |
+
parameters:
|
37 |
+
scale:
|
38 |
+
- filter: o_proj
|
39 |
+
value: 0.02
|
40 |
+
- filter: down_proj
|
41 |
+
value: 0.02
|
42 |
+
- value: 0.12
|
43 |
+
- sources:
|
44 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
45 |
+
layer_range: [48,49]
|
46 |
+
parameters:
|
47 |
+
scale:
|
48 |
+
- filter: o_proj
|
49 |
+
value: 0.03
|
50 |
+
- filter: down_proj
|
51 |
+
value: 0.03
|
52 |
+
- value: 0.13
|
53 |
+
|
54 |
+
- sources:
|
55 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
56 |
+
layer_range: [48,49]
|
57 |
+
parameters:
|
58 |
+
scale:
|
59 |
+
- filter: o_proj
|
60 |
+
value: 0.04
|
61 |
+
- filter: down_proj
|
62 |
+
value: 0.04
|
63 |
+
- value: 0.61
|
64 |
+
|
65 |
+
# split 2, SURGE D THEN D drop .46, continues @ D .15 (from .13)
|
66 |
+
|
67 |
+
- sources:
|
68 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
69 |
+
layer_range: [48,49]
|
70 |
+
parameters:
|
71 |
+
scale:
|
72 |
+
- filter: o_proj
|
73 |
+
value: 0.05
|
74 |
+
- filter: down_proj
|
75 |
+
value: 0.05
|
76 |
+
- value: 0.15
|
77 |
+
- sources:
|
78 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
79 |
+
layer_range: [48,49]
|
80 |
+
parameters:
|
81 |
+
scale:
|
82 |
+
- filter: o_proj
|
83 |
+
value: 0.06
|
84 |
+
- filter: down_proj
|
85 |
+
value: 0.06
|
86 |
+
- value: 0.16
|
87 |
+
- sources:
|
88 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
89 |
+
layer_range: [48,49]
|
90 |
+
parameters:
|
91 |
+
scale:
|
92 |
+
- filter: o_proj
|
93 |
+
value: 0.07
|
94 |
+
- filter: down_proj
|
95 |
+
value: 0.07
|
96 |
+
- value: 0.17
|
97 |
+
- sources:
|
98 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
99 |
+
layer_range: [48,49]
|
100 |
+
parameters:
|
101 |
+
scale:
|
102 |
+
- filter: o_proj
|
103 |
+
value: 0.08
|
104 |
+
- filter: down_proj
|
105 |
+
value: 0.08
|
106 |
+
- value: 0.41
|
107 |
+
|
108 |
+
# split 3, SURGE D to .41, D drop .21 ... follows .17 previous
|
109 |
+
|
110 |
+
- sources:
|
111 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
112 |
+
layer_range: [48,49]
|
113 |
+
parameters:
|
114 |
+
scale:
|
115 |
+
- filter: o_proj
|
116 |
+
value: 0.09
|
117 |
+
- filter: down_proj
|
118 |
+
value: 0.09
|
119 |
+
- value: 0.19
|
120 |
+
- sources:
|
121 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
122 |
+
layer_range: [48,49]
|
123 |
+
parameters:
|
124 |
+
scale:
|
125 |
+
- filter: o_proj
|
126 |
+
value: 0.10
|
127 |
+
- filter: down_proj
|
128 |
+
value: 0.10
|
129 |
+
- value: 0.20
|
130 |
+
- sources:
|
131 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
132 |
+
layer_range: [48,49]
|
133 |
+
parameters:
|
134 |
+
scale:
|
135 |
+
- filter: o_proj
|
136 |
+
value: 0.11
|
137 |
+
- filter: down_proj
|
138 |
+
value: 0.11
|
139 |
+
- value: .22
|
140 |
+
- sources:
|
141 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
142 |
+
layer_range: [48,49]
|
143 |
+
parameters:
|
144 |
+
scale:
|
145 |
+
- filter: o_proj
|
146 |
+
value: 0.12
|
147 |
+
- filter: down_proj
|
148 |
+
value: 0.12
|
149 |
+
- value: .24
|
150 |
+
- sources:
|
151 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
152 |
+
layer_range: [48,49]
|
153 |
+
parameters:
|
154 |
+
scale:
|
155 |
+
- filter: o_proj
|
156 |
+
value: 0.13
|
157 |
+
- filter: down_proj
|
158 |
+
value: 0.13
|
159 |
+
- value: .26
|
160 |
+
- sources:
|
161 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
162 |
+
layer_range: [48,49]
|
163 |
+
parameters:
|
164 |
+
scale:
|
165 |
+
- filter: o_proj
|
166 |
+
value: 0.14
|
167 |
+
- filter: down_proj
|
168 |
+
value: 0.14
|
169 |
+
- value: .28
|
170 |
+
- sources:
|
171 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
172 |
+
layer_range: [48,49]
|
173 |
+
parameters:
|
174 |
+
scale:
|
175 |
+
- filter: o_proj
|
176 |
+
value: 0.15
|
177 |
+
- filter: down_proj
|
178 |
+
value: 0.15
|
179 |
+
- value: .30
|
180 |
+
- sources:
|
181 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
182 |
+
layer_range: [48,49]
|
183 |
+
parameters:
|
184 |
+
scale:
|
185 |
+
- filter: o_proj
|
186 |
+
value: 0.16
|
187 |
+
- filter: down_proj
|
188 |
+
value: 0.16
|
189 |
+
- value: .31
|
190 |
+
- sources:
|
191 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
192 |
+
layer_range: [48,49]
|
193 |
+
parameters:
|
194 |
+
scale:
|
195 |
+
- filter: o_proj
|
196 |
+
value: 0.20
|
197 |
+
- filter: down_proj
|
198 |
+
value: 0.20
|
199 |
+
- value: .32
|
200 |
+
- sources:
|
201 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
202 |
+
layer_range: [48,49]
|
203 |
+
parameters:
|
204 |
+
scale:
|
205 |
+
- filter: o_proj
|
206 |
+
value: 0.21
|
207 |
+
- filter: down_proj
|
208 |
+
value: 0.21
|
209 |
+
- value: .33
|
210 |
+
- sources:
|
211 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
212 |
+
layer_range: [48,49]
|
213 |
+
parameters:
|
214 |
+
scale:
|
215 |
+
- filter: o_proj
|
216 |
+
value: 0.22
|
217 |
+
- filter: down_proj
|
218 |
+
value: 0.22
|
219 |
+
- value: .34
|
220 |
+
- sources:
|
221 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
222 |
+
layer_range: [48,49]
|
223 |
+
parameters:
|
224 |
+
scale:
|
225 |
+
- filter: o_proj
|
226 |
+
value: 0.23
|
227 |
+
- filter: down_proj
|
228 |
+
value: 0.23
|
229 |
+
- value: .35
|
230 |
+
|
231 |
+
# split 4 , NO SURGE D, "D" down drop of .24 ; reverts to .11 (the very first "D" setting )
|
232 |
+
|
233 |
+
- sources:
|
234 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
235 |
+
layer_range: [48,49]
|
236 |
+
parameters:
|
237 |
+
scale:
|
238 |
+
- filter: o_proj
|
239 |
+
value: 0.24
|
240 |
+
- filter: down_proj
|
241 |
+
value: 0.24
|
242 |
+
- value: 0.11
|
243 |
+
- sources:
|
244 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
245 |
+
layer_range: [48,49]
|
246 |
+
parameters:
|
247 |
+
scale:
|
248 |
+
- filter: o_proj
|
249 |
+
value: 0.241
|
250 |
+
- filter: down_proj
|
251 |
+
value: 0.241
|
252 |
+
- value: 0.12
|
253 |
+
- sources:
|
254 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
255 |
+
layer_range: [48,49]
|
256 |
+
parameters:
|
257 |
+
scale:
|
258 |
+
- filter: o_proj
|
259 |
+
value: 0.242
|
260 |
+
- filter: down_proj
|
261 |
+
value: 0.243
|
262 |
+
- value: 0.13
|
263 |
+
- sources:
|
264 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
265 |
+
layer_range: [48,49]
|
266 |
+
parameters:
|
267 |
+
scale:
|
268 |
+
- filter: o_proj
|
269 |
+
value: 0.244
|
270 |
+
- filter: down_proj
|
271 |
+
value: 0.244
|
272 |
+
- value: 0.61
|
273 |
+
|
274 |
+
# split 5, D Surge to .61, drop to .15 (following .13)
|
275 |
+
|
276 |
+
- sources:
|
277 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
278 |
+
layer_range: [48,49]
|
279 |
+
parameters:
|
280 |
+
scale:
|
281 |
+
- filter: o_proj
|
282 |
+
value: 0.245
|
283 |
+
- filter: down_proj
|
284 |
+
value: 0.245
|
285 |
+
- value: 0.15
|
286 |
+
- sources:
|
287 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
288 |
+
layer_range: [48,49]
|
289 |
+
parameters:
|
290 |
+
scale:
|
291 |
+
- filter: o_proj
|
292 |
+
value: 0.246
|
293 |
+
- filter: down_proj
|
294 |
+
value: 0.246
|
295 |
+
- value: 0.16
|
296 |
+
- sources:
|
297 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
298 |
+
layer_range: [48,49]
|
299 |
+
parameters:
|
300 |
+
scale:
|
301 |
+
- filter: o_proj
|
302 |
+
value: 0.247
|
303 |
+
- filter: down_proj
|
304 |
+
value: 0.247
|
305 |
+
- value: 0.17
|
306 |
+
- sources:
|
307 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
308 |
+
layer_range: [48,49]
|
309 |
+
parameters:
|
310 |
+
scale:
|
311 |
+
- filter: o_proj
|
312 |
+
value: 0.248
|
313 |
+
- filter: down_proj
|
314 |
+
value: 0.248
|
315 |
+
- value: 0.41
|
316 |
+
|
317 |
+
# split 6, D surge to .41 , then follows .17
|
318 |
+
|
319 |
+
- sources:
|
320 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
321 |
+
layer_range: [48,49]
|
322 |
+
parameters:
|
323 |
+
scale:
|
324 |
+
- filter: o_proj
|
325 |
+
value: 0.249
|
326 |
+
- filter: down_proj
|
327 |
+
value: 0.249
|
328 |
+
- value: 0.19
|
329 |
+
- sources:
|
330 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
331 |
+
layer_range: [48,49]
|
332 |
+
parameters:
|
333 |
+
scale:
|
334 |
+
- filter: o_proj
|
335 |
+
value: 0.250
|
336 |
+
- filter: down_proj
|
337 |
+
value: 0.250
|
338 |
+
- value: 0.20
|
339 |
+
- sources:
|
340 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
341 |
+
layer_range: [48,49]
|
342 |
+
parameters:
|
343 |
+
scale:
|
344 |
+
- filter: o_proj
|
345 |
+
value: 0.251
|
346 |
+
- filter: down_proj
|
347 |
+
value: 0.251
|
348 |
+
- value: .22
|
349 |
+
- sources:
|
350 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
351 |
+
layer_range: [48,49]
|
352 |
+
parameters:
|
353 |
+
scale:
|
354 |
+
- filter: o_proj
|
355 |
+
value: 0.252
|
356 |
+
- filter: down_proj
|
357 |
+
value: 0.252
|
358 |
+
- value: .24
|
359 |
+
- sources:
|
360 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
361 |
+
layer_range: [48,49]
|
362 |
+
parameters:
|
363 |
+
scale:
|
364 |
+
- filter: o_proj
|
365 |
+
value: 0.253
|
366 |
+
- filter: down_proj
|
367 |
+
value: 0.254
|
368 |
+
- value: .26
|
369 |
+
- sources:
|
370 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
371 |
+
layer_range: [48,49]
|
372 |
+
parameters:
|
373 |
+
scale:
|
374 |
+
- filter: o_proj
|
375 |
+
value: 0.255
|
376 |
+
- filter: down_proj
|
377 |
+
value: 0.255
|
378 |
+
- value: .28
|
379 |
+
- sources:
|
380 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
381 |
+
layer_range: [48,49]
|
382 |
+
parameters:
|
383 |
+
scale:
|
384 |
+
- filter: o_proj
|
385 |
+
value: 0.256
|
386 |
+
- filter: down_proj
|
387 |
+
value: 0.256
|
388 |
+
- value: .30
|
389 |
+
|
390 |
+
# O PROJ, DPROJ to .3333 /
|
391 |
+
# end game
|
392 |
+
|
393 |
+
- sources:
|
394 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
395 |
+
layer_range: [48,49]
|
396 |
+
parameters:
|
397 |
+
scale:
|
398 |
+
- filter: o_proj
|
399 |
+
value: 0.3333333333333
|
400 |
+
- filter: down_proj
|
401 |
+
value: 0.3333333333333
|
402 |
+
- value: 0.3333333333333
|
403 |
+
- sources:
|
404 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
405 |
+
layer_range: [48,49]
|
406 |
+
parameters:
|
407 |
+
scale:
|
408 |
+
- filter: o_proj
|
409 |
+
value: 0.4444444444444
|
410 |
+
- filter: down_proj
|
411 |
+
value: 0.4444444444444
|
412 |
+
- value: 0.4444444444444
|
413 |
+
- sources:
|
414 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
415 |
+
layer_range: [48,49]
|
416 |
+
parameters:
|
417 |
+
scale:
|
418 |
+
- filter: o_proj
|
419 |
+
value: 0.5555555555555
|
420 |
+
- filter: down_proj
|
421 |
+
value: 0.5555555555555
|
422 |
+
- value: 0.5555555555555
|
423 |
+
- sources:
|
424 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
425 |
+
layer_range: [48,49]
|
426 |
+
parameters:
|
427 |
+
scale:
|
428 |
+
- filter: o_proj
|
429 |
+
value: 0.6666666666666
|
430 |
+
- filter: down_proj
|
431 |
+
value: 0.6666666666666
|
432 |
+
- value: 0.6666666666666
|
433 |
+
- sources:
|
434 |
+
- model: E:/Bagel-Multiverse-20B-bg
|
435 |
+
layer_range: [48,49]
|
436 |
+
parameters:
|
437 |
+
scale:
|
438 |
+
- filter: o_proj
|
439 |
+
value: 0.777777777777
|
440 |
+
- filter: down_proj
|
441 |
+
value: 0.777777777777
|
442 |
+
- value: 0.888888888888
|
443 |
+
merge_method: passthrough
|
444 |
+
dtype: float16
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 38912008192}, "weight_map": {"lm_head.weight": "model-00001-of-00041.safetensors", "model.embed_tokens.weight": "model-00001-of-00041.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00041.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00041.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00041.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00041.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00041.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00041.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00041.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00041.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00041.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00041.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00041.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00041.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00041.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00041.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00041.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00041.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00041.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00041.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00041.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00041.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00041.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00041.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00041.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00041.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00041.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00041.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00041.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00041.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00041.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00041.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00041.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00041.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00041.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00041.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00041.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00041.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00041.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00041.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00041.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00041.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00041.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00041.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00041.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00041.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00041.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00041.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00041.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00041.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00041.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00041.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00041.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00041.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00041.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00041.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00041.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00041.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00041.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00041.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00041.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00041.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00041.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00041.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00041.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00041.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00041.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00041.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00041.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00041.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00041.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00041.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00041.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00041.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00041.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00041.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00041.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00041.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00041.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00041.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00041.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00041.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00041.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00041.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00041.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00041.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00041.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00041.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00041.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00041.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00041.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00041.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00041.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00041.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00041.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00041.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00041.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00041.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00041.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00041.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00041.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00041.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00041.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00041.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00041.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00041.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00041.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00041.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00041.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00041.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00041.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00041.safetensors", "model.layers.42.input_layernorm.weight": "model-00017-of-00041.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00041.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00041.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00041.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00041.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00041.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00041.safetensors", "model.layers.44.input_layernorm.weight": "model-00018-of-00041.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00018-of-00041.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00041.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00041.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00041.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00041.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00019-of-00041.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00041.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00041.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00041.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00041.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00041.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00041.safetensors", "model.layers.87.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.86.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.85.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.84.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.83.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.82.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.81.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.80.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.79.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.78.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.77.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.76.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.75.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.74.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.73.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.72.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.71.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.70.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.69.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.68.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.67.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.66.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.65.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.64.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.63.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.62.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.61.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.60.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.56.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.55.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.54.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.53.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.52.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.51.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.50.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.49.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.48.input_layernorm.weight": "model-00020-of-00041.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00020-of-00041.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00021-of-00041.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00022-of-00041.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00023-of-00041.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00024-of-00041.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00025-of-00041.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00025-of-00041.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00025-of-00041.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00025-of-00041.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00025-of-00041.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00025-of-00041.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00026-of-00041.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00027-of-00041.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00041.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00029-of-00041.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00030-of-00041.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00030-of-00041.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00030-of-00041.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00030-of-00041.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00031-of-00041.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00032-of-00041.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00033-of-00041.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00034-of-00041.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00035-of-00041.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00035-of-00041.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00041.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00035-of-00041.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00035-of-00041.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00036-of-00041.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00037-of-00041.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00037-of-00041.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00038-of-00041.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00038-of-00041.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.input_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.input_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00039-of-00041.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00039-of-00041.safetensors", "model.layers.7.input_layernorm.weight": "model-00039-of-00041.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00039-of-00041.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00040-of-00041.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00040-of-00041.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00040-of-00041.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00040-of-00041.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00040-of-00041.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.input_layernorm.weight": "model-00040-of-00041.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00040-of-00041.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00040-of-00041.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00040-of-00041.safetensors", "model.layers.9.input_layernorm.weight": "model-00040-of-00041.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00040-of-00041.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00040-of-00041.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00041-of-00041.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00041-of-00041.safetensors", "model.norm.weight": "model-00041-of-00041.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% elif message['role'] == 'system' %}{{ '### System:\n' + message['content'] + '\n' }}{% endif %}{% endfor %}",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 32768,
|
38 |
+
"pad_token": "<unk>",
|
39 |
+
"padding_side": "left",
|
40 |
+
"sp_model_kwargs": {},
|
41 |
+
"spaces_between_special_tokens": false,
|
42 |
+
"tokenizer_class": "LlamaTokenizer",
|
43 |
+
"unk_token": "<unk>",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|