lbourdois commited on
Commit
7a33d9e
·
verified ·
1 Parent(s): bc6709e

Improve language tag

Browse files

Hi! As the model is multilingual, this is a PR to add other languages than English to the language tag to improve the referencing. Note that 29 languages are announced in the README, but only 13 are explicitly listed. I was therefore only able to add these 13 languages.

Files changed (1) hide show
  1. README.md +537 -523
README.md CHANGED
@@ -1,524 +1,538 @@
1
- ---
2
- base_model:
3
- - Qwen/Qwen2.5-72B-Instruct
4
- library_name: transformers
5
- tags:
6
- - mergekit
7
- - merge
8
- license: other
9
- ---
10
-
11
- ## Qwen2.5-143B-Doubled72B-Instruct-Mergekit-Merge by Solshine (Caleb DeLeeuw)
12
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/654527ce2a13610acc25d921/xJlbOzfDQ7PkR1SYwKIJN.png)
13
-
14
- # merge
15
-
16
- This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
17
-
18
- This model recieved no post merge retraining (yet) and minimal testing. Please contribute any feedback or evaluations of any kind via the community tab.
19
-
20
- # License
21
-
22
- Hippocratic License 3.0 + Ecocide module, + Extractive Industries module, + Copyleft
23
- [![Hippocratic License HL3-CL-ECO-EXTR](https://img.shields.io/static/v1?label=Hippocratic%20License&message=HL3-CL-ECO-EXTR&labelColor=5e2751&color=bc8c3d)](https://firstdonoharm.dev/version/3/0/cl-eco-extr.html)
24
- https://firstdonoharm.dev/version/3/0/cl-eco-extr.txt
25
-
26
- ## Merge Details
27
- ### Merge Method
28
-
29
- This model was merged using the passthrough merge method. Every layer is doubled in order, from Qwen/Qwen2.5-72B-Instruct, creating 143B parameters. No additional fine-tune has been done in this merged model.
30
-
31
- ### Models Merged
32
-
33
- The following models were included in the merge:
34
- * [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
35
-
36
- ### Configuration
37
-
38
- The following YAML configuration was used to produce this model:
39
-
40
- ```yaml
41
- slices:
42
- - sources:
43
- - model: Qwen/Qwen2.5-72B-Instruct
44
- layer_range: [0, 1]
45
- - sources:
46
- - model: Qwen/Qwen2.5-72B-Instruct
47
- layer_range: [0, 1]
48
- - sources:
49
- - model: Qwen/Qwen2.5-72B-Instruct
50
- layer_range: [1, 2]
51
- - sources:
52
- - model: Qwen/Qwen2.5-72B-Instruct
53
- layer_range: [1, 2]
54
- - sources:
55
- - model: Qwen/Qwen2.5-72B-Instruct
56
- layer_range: [2, 3]
57
- - sources:
58
- - model: Qwen/Qwen2.5-72B-Instruct
59
- layer_range: [2, 3]
60
- - sources:
61
- - model: Qwen/Qwen2.5-72B-Instruct
62
- layer_range: [3, 4]
63
- - sources:
64
- - model: Qwen/Qwen2.5-72B-Instruct
65
- layer_range: [3, 4]
66
- - sources:
67
- - model: Qwen/Qwen2.5-72B-Instruct
68
- layer_range: [4, 5]
69
- - sources:
70
- - model: Qwen/Qwen2.5-72B-Instruct
71
- layer_range: [4, 5]
72
- - sources:
73
- - model: Qwen/Qwen2.5-72B-Instruct
74
- layer_range: [5, 6]
75
- - sources:
76
- - model: Qwen/Qwen2.5-72B-Instruct
77
- layer_range: [5, 6]
78
- - sources:
79
- - model: Qwen/Qwen2.5-72B-Instruct
80
- layer_range: [6, 7]
81
- - sources:
82
- - model: Qwen/Qwen2.5-72B-Instruct
83
- layer_range: [6, 7]
84
- - sources:
85
- - model: Qwen/Qwen2.5-72B-Instruct
86
- layer_range: [7, 8]
87
- - sources:
88
- - model: Qwen/Qwen2.5-72B-Instruct
89
- layer_range: [7, 8]
90
- - sources:
91
- - model: Qwen/Qwen2.5-72B-Instruct
92
- layer_range: [8, 9]
93
- - sources:
94
- - model: Qwen/Qwen2.5-72B-Instruct
95
- layer_range: [8, 9]
96
- - sources:
97
- - model: Qwen/Qwen2.5-72B-Instruct
98
- layer_range: [9, 10]
99
- - sources:
100
- - model: Qwen/Qwen2.5-72B-Instruct
101
- layer_range: [9, 10]
102
- - sources:
103
- - model: Qwen/Qwen2.5-72B-Instruct
104
- layer_range: [10, 11]
105
- - sources:
106
- - model: Qwen/Qwen2.5-72B-Instruct
107
- layer_range: [10, 11]
108
- - sources:
109
- - model: Qwen/Qwen2.5-72B-Instruct
110
- layer_range: [11, 12]
111
- - sources:
112
- - model: Qwen/Qwen2.5-72B-Instruct
113
- layer_range: [11, 12]
114
- - sources:
115
- - model: Qwen/Qwen2.5-72B-Instruct
116
- layer_range: [12, 13]
117
- - sources:
118
- - model: Qwen/Qwen2.5-72B-Instruct
119
- layer_range: [12, 13]
120
- - sources:
121
- - model: Qwen/Qwen2.5-72B-Instruct
122
- layer_range: [13, 14]
123
- - sources:
124
- - model: Qwen/Qwen2.5-72B-Instruct
125
- layer_range: [13, 14]
126
- - sources:
127
- - model: Qwen/Qwen2.5-72B-Instruct
128
- layer_range: [14, 15]
129
- - sources:
130
- - model: Qwen/Qwen2.5-72B-Instruct
131
- layer_range: [14, 15]
132
- - sources:
133
- - model: Qwen/Qwen2.5-72B-Instruct
134
- layer_range: [15, 16]
135
- - sources:
136
- - model: Qwen/Qwen2.5-72B-Instruct
137
- layer_range: [15, 16]
138
- - sources:
139
- - model: Qwen/Qwen2.5-72B-Instruct
140
- layer_range: [16, 17]
141
- - sources:
142
- - model: Qwen/Qwen2.5-72B-Instruct
143
- layer_range: [16, 17]
144
- - sources:
145
- - model: Qwen/Qwen2.5-72B-Instruct
146
- layer_range: [17, 18]
147
- - sources:
148
- - model: Qwen/Qwen2.5-72B-Instruct
149
- layer_range: [17, 18]
150
- - sources:
151
- - model: Qwen/Qwen2.5-72B-Instruct
152
- layer_range: [18, 19]
153
- - sources:
154
- - model: Qwen/Qwen2.5-72B-Instruct
155
- layer_range: [18, 19]
156
- - sources:
157
- - model: Qwen/Qwen2.5-72B-Instruct
158
- layer_range: [19, 20]
159
- - sources:
160
- - model: Qwen/Qwen2.5-72B-Instruct
161
- layer_range: [19, 20]
162
- - sources:
163
- - model: Qwen/Qwen2.5-72B-Instruct
164
- layer_range: [20, 21]
165
- - sources:
166
- - model: Qwen/Qwen2.5-72B-Instruct
167
- layer_range: [20, 21]
168
- - sources:
169
- - model: Qwen/Qwen2.5-72B-Instruct
170
- layer_range: [21, 22]
171
- - sources:
172
- - model: Qwen/Qwen2.5-72B-Instruct
173
- layer_range: [21, 22]
174
- - sources:
175
- - model: Qwen/Qwen2.5-72B-Instruct
176
- layer_range: [22, 23]
177
- - sources:
178
- - model: Qwen/Qwen2.5-72B-Instruct
179
- layer_range: [22, 23]
180
- - sources:
181
- - model: Qwen/Qwen2.5-72B-Instruct
182
- layer_range: [23, 24]
183
- - sources:
184
- - model: Qwen/Qwen2.5-72B-Instruct
185
- layer_range: [23, 24]
186
- - sources:
187
- - model: Qwen/Qwen2.5-72B-Instruct
188
- layer_range: [24, 25]
189
- - sources:
190
- - model: Qwen/Qwen2.5-72B-Instruct
191
- layer_range: [24, 25]
192
- - sources:
193
- - model: Qwen/Qwen2.5-72B-Instruct
194
- layer_range: [25, 26]
195
- - sources:
196
- - model: Qwen/Qwen2.5-72B-Instruct
197
- layer_range: [25, 26]
198
- - sources:
199
- - model: Qwen/Qwen2.5-72B-Instruct
200
- layer_range: [26, 27]
201
- - sources:
202
- - model: Qwen/Qwen2.5-72B-Instruct
203
- layer_range: [26, 27]
204
- - sources:
205
- - model: Qwen/Qwen2.5-72B-Instruct
206
- layer_range: [27, 28]
207
- - sources:
208
- - model: Qwen/Qwen2.5-72B-Instruct
209
- layer_range: [27, 28]
210
- - sources:
211
- - model: Qwen/Qwen2.5-72B-Instruct
212
- layer_range: [28, 29]
213
- - sources:
214
- - model: Qwen/Qwen2.5-72B-Instruct
215
- layer_range: [28, 29]
216
- - sources:
217
- - model: Qwen/Qwen2.5-72B-Instruct
218
- layer_range: [29, 30]
219
- - sources:
220
- - model: Qwen/Qwen2.5-72B-Instruct
221
- layer_range: [29, 30]
222
- - sources:
223
- - model: Qwen/Qwen2.5-72B-Instruct
224
- layer_range: [30, 31]
225
- - sources:
226
- - model: Qwen/Qwen2.5-72B-Instruct
227
- layer_range: [30, 31]
228
- - sources:
229
- - model: Qwen/Qwen2.5-72B-Instruct
230
- layer_range: [31, 32]
231
- - sources:
232
- - model: Qwen/Qwen2.5-72B-Instruct
233
- layer_range: [31, 32]
234
- - sources:
235
- - model: Qwen/Qwen2.5-72B-Instruct
236
- layer_range: [32, 33]
237
- - sources:
238
- - model: Qwen/Qwen2.5-72B-Instruct
239
- layer_range: [32, 33]
240
- - sources:
241
- - model: Qwen/Qwen2.5-72B-Instruct
242
- layer_range: [33, 34]
243
- - sources:
244
- - model: Qwen/Qwen2.5-72B-Instruct
245
- layer_range: [33, 34]
246
- - sources:
247
- - model: Qwen/Qwen2.5-72B-Instruct
248
- layer_range: [34, 35]
249
- - sources:
250
- - model: Qwen/Qwen2.5-72B-Instruct
251
- layer_range: [34, 35]
252
- - sources:
253
- - model: Qwen/Qwen2.5-72B-Instruct
254
- layer_range: [35, 36]
255
- - sources:
256
- - model: Qwen/Qwen2.5-72B-Instruct
257
- layer_range: [35, 36]
258
- - sources:
259
- - model: Qwen/Qwen2.5-72B-Instruct
260
- layer_range: [36, 37]
261
- - sources:
262
- - model: Qwen/Qwen2.5-72B-Instruct
263
- layer_range: [36, 37]
264
- - sources:
265
- - model: Qwen/Qwen2.5-72B-Instruct
266
- layer_range: [37, 38]
267
- - sources:
268
- - model: Qwen/Qwen2.5-72B-Instruct
269
- layer_range: [37, 38]
270
- - sources:
271
- - model: Qwen/Qwen2.5-72B-Instruct
272
- layer_range: [38, 39]
273
- - sources:
274
- - model: Qwen/Qwen2.5-72B-Instruct
275
- layer_range: [38, 39]
276
- - sources:
277
- - model: Qwen/Qwen2.5-72B-Instruct
278
- layer_range: [39, 40]
279
- - sources:
280
- - model: Qwen/Qwen2.5-72B-Instruct
281
- layer_range: [39, 40]
282
- - sources:
283
- - model: Qwen/Qwen2.5-72B-Instruct
284
- layer_range: [40, 41]
285
- - sources:
286
- - model: Qwen/Qwen2.5-72B-Instruct
287
- layer_range: [40, 41]
288
- - sources:
289
- - model: Qwen/Qwen2.5-72B-Instruct
290
- layer_range: [41, 42]
291
- - sources:
292
- - model: Qwen/Qwen2.5-72B-Instruct
293
- layer_range: [41, 42]
294
- - sources:
295
- - model: Qwen/Qwen2.5-72B-Instruct
296
- layer_range: [42, 43]
297
- - sources:
298
- - model: Qwen/Qwen2.5-72B-Instruct
299
- layer_range: [42, 43]
300
- - sources:
301
- - model: Qwen/Qwen2.5-72B-Instruct
302
- layer_range: [43, 44]
303
- - sources:
304
- - model: Qwen/Qwen2.5-72B-Instruct
305
- layer_range: [43, 44]
306
- - sources:
307
- - model: Qwen/Qwen2.5-72B-Instruct
308
- layer_range: [44, 45]
309
- - sources:
310
- - model: Qwen/Qwen2.5-72B-Instruct
311
- layer_range: [44, 45]
312
- - sources:
313
- - model: Qwen/Qwen2.5-72B-Instruct
314
- layer_range: [45, 46]
315
- - sources:
316
- - model: Qwen/Qwen2.5-72B-Instruct
317
- layer_range: [45, 46]
318
- - sources:
319
- - model: Qwen/Qwen2.5-72B-Instruct
320
- layer_range: [46, 47]
321
- - sources:
322
- - model: Qwen/Qwen2.5-72B-Instruct
323
- layer_range: [46, 47]
324
- - sources:
325
- - model: Qwen/Qwen2.5-72B-Instruct
326
- layer_range: [47, 48]
327
- - sources:
328
- - model: Qwen/Qwen2.5-72B-Instruct
329
- layer_range: [47, 48]
330
- - sources:
331
- - model: Qwen/Qwen2.5-72B-Instruct
332
- layer_range: [48, 49]
333
- - sources:
334
- - model: Qwen/Qwen2.5-72B-Instruct
335
- layer_range: [48, 49]
336
- - sources:
337
- - model: Qwen/Qwen2.5-72B-Instruct
338
- layer_range: [49, 50]
339
- - sources:
340
- - model: Qwen/Qwen2.5-72B-Instruct
341
- layer_range: [49, 50]
342
- - sources:
343
- - model: Qwen/Qwen2.5-72B-Instruct
344
- layer_range: [50, 51]
345
- - sources:
346
- - model: Qwen/Qwen2.5-72B-Instruct
347
- layer_range: [50, 51]
348
- - sources:
349
- - model: Qwen/Qwen2.5-72B-Instruct
350
- layer_range: [51, 52]
351
- - sources:
352
- - model: Qwen/Qwen2.5-72B-Instruct
353
- layer_range: [51, 52]
354
- - sources:
355
- - model: Qwen/Qwen2.5-72B-Instruct
356
- layer_range: [52, 53]
357
- - sources:
358
- - model: Qwen/Qwen2.5-72B-Instruct
359
- layer_range: [52, 53]
360
- - sources:
361
- - model: Qwen/Qwen2.5-72B-Instruct
362
- layer_range: [53, 54]
363
- - sources:
364
- - model: Qwen/Qwen2.5-72B-Instruct
365
- layer_range: [53, 54]
366
- - sources:
367
- - model: Qwen/Qwen2.5-72B-Instruct
368
- layer_range: [54, 55]
369
- - sources:
370
- - model: Qwen/Qwen2.5-72B-Instruct
371
- layer_range: [54, 55]
372
- - sources:
373
- - model: Qwen/Qwen2.5-72B-Instruct
374
- layer_range: [55, 56]
375
- - sources:
376
- - model: Qwen/Qwen2.5-72B-Instruct
377
- layer_range: [55, 56]
378
- - sources:
379
- - model: Qwen/Qwen2.5-72B-Instruct
380
- layer_range: [56, 57]
381
- - sources:
382
- - model: Qwen/Qwen2.5-72B-Instruct
383
- layer_range: [56, 57]
384
- - sources:
385
- - model: Qwen/Qwen2.5-72B-Instruct
386
- layer_range: [57, 58]
387
- - sources:
388
- - model: Qwen/Qwen2.5-72B-Instruct
389
- layer_range: [57, 58]
390
- - sources:
391
- - model: Qwen/Qwen2.5-72B-Instruct
392
- layer_range: [58, 59]
393
- - sources:
394
- - model: Qwen/Qwen2.5-72B-Instruct
395
- layer_range: [58, 59]
396
- - sources:
397
- - model: Qwen/Qwen2.5-72B-Instruct
398
- layer_range: [59, 60]
399
- - sources:
400
- - model: Qwen/Qwen2.5-72B-Instruct
401
- layer_range: [59, 60]
402
- - sources:
403
- - model: Qwen/Qwen2.5-72B-Instruct
404
- layer_range: [60, 61]
405
- - sources:
406
- - model: Qwen/Qwen2.5-72B-Instruct
407
- layer_range: [60, 61]
408
- - sources:
409
- - model: Qwen/Qwen2.5-72B-Instruct
410
- layer_range: [61, 62]
411
- - sources:
412
- - model: Qwen/Qwen2.5-72B-Instruct
413
- layer_range: [61, 62]
414
- - sources:
415
- - model: Qwen/Qwen2.5-72B-Instruct
416
- layer_range: [62, 63]
417
- - sources:
418
- - model: Qwen/Qwen2.5-72B-Instruct
419
- layer_range: [62, 63]
420
- - sources:
421
- - model: Qwen/Qwen2.5-72B-Instruct
422
- layer_range: [63, 64]
423
- - sources:
424
- - model: Qwen/Qwen2.5-72B-Instruct
425
- layer_range: [63, 64]
426
- - sources:
427
- - model: Qwen/Qwen2.5-72B-Instruct
428
- layer_range: [64, 65]
429
- - sources:
430
- - model: Qwen/Qwen2.5-72B-Instruct
431
- layer_range: [64, 65]
432
- - sources:
433
- - model: Qwen/Qwen2.5-72B-Instruct
434
- layer_range: [65, 66]
435
- - sources:
436
- - model: Qwen/Qwen2.5-72B-Instruct
437
- layer_range: [65, 66]
438
- - sources:
439
- - model: Qwen/Qwen2.5-72B-Instruct
440
- layer_range: [66, 67]
441
- - sources:
442
- - model: Qwen/Qwen2.5-72B-Instruct
443
- layer_range: [66, 67]
444
- - sources:
445
- - model: Qwen/Qwen2.5-72B-Instruct
446
- layer_range: [67, 68]
447
- - sources:
448
- - model: Qwen/Qwen2.5-72B-Instruct
449
- layer_range: [67, 68]
450
- - sources:
451
- - model: Qwen/Qwen2.5-72B-Instruct
452
- layer_range: [68, 69]
453
- - sources:
454
- - model: Qwen/Qwen2.5-72B-Instruct
455
- layer_range: [68, 69]
456
- - sources:
457
- - model: Qwen/Qwen2.5-72B-Instruct
458
- layer_range: [69, 70]
459
- - sources:
460
- - model: Qwen/Qwen2.5-72B-Instruct
461
- layer_range: [69, 70]
462
- - sources:
463
- - model: Qwen/Qwen2.5-72B-Instruct
464
- layer_range: [70, 71]
465
- - sources:
466
- - model: Qwen/Qwen2.5-72B-Instruct
467
- layer_range: [70, 71]
468
- - sources:
469
- - model: Qwen/Qwen2.5-72B-Instruct
470
- layer_range: [71, 72]
471
- - sources:
472
- - model: Qwen/Qwen2.5-72B-Instruct
473
- layer_range: [71, 72]
474
- - sources:
475
- - model: Qwen/Qwen2.5-72B-Instruct
476
- layer_range: [72, 73]
477
- - sources:
478
- - model: Qwen/Qwen2.5-72B-Instruct
479
- layer_range: [72, 73]
480
- - sources:
481
- - model: Qwen/Qwen2.5-72B-Instruct
482
- layer_range: [73, 74]
483
- - sources:
484
- - model: Qwen/Qwen2.5-72B-Instruct
485
- layer_range: [73, 74]
486
- - sources:
487
- - model: Qwen/Qwen2.5-72B-Instruct
488
- layer_range: [74, 75]
489
- - sources:
490
- - model: Qwen/Qwen2.5-72B-Instruct
491
- layer_range: [74, 75]
492
- - sources:
493
- - model: Qwen/Qwen2.5-72B-Instruct
494
- layer_range: [75, 76]
495
- - sources:
496
- - model: Qwen/Qwen2.5-72B-Instruct
497
- layer_range: [75, 76]
498
- - sources:
499
- - model: Qwen/Qwen2.5-72B-Instruct
500
- layer_range: [76, 77]
501
- - sources:
502
- - model: Qwen/Qwen2.5-72B-Instruct
503
- layer_range: [76, 77]
504
- - sources:
505
- - model: Qwen/Qwen2.5-72B-Instruct
506
- layer_range: [77, 78]
507
- - sources:
508
- - model: Qwen/Qwen2.5-72B-Instruct
509
- layer_range: [77, 78]
510
- - sources:
511
- - model: Qwen/Qwen2.5-72B-Instruct
512
- layer_range: [78, 79]
513
- - sources:
514
- - model: Qwen/Qwen2.5-72B-Instruct
515
- layer_range: [78, 79]
516
- - sources:
517
- - model: Qwen/Qwen2.5-72B-Instruct
518
- layer_range: [79, 80]
519
- - sources:
520
- - model: Qwen/Qwen2.5-72B-Instruct
521
- layer_range: [79, 80]
522
- merge_method: passthrough
523
- dtype: float16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
524
  ```
 
1
+ ---
2
+ base_model:
3
+ - Qwen/Qwen2.5-72B-Instruct
4
+ library_name: transformers
5
+ tags:
6
+ - mergekit
7
+ - merge
8
+ license: other
9
+ language:
10
+ - zho
11
+ - eng
12
+ - fra
13
+ - spa
14
+ - por
15
+ - deu
16
+ - ita
17
+ - rus
18
+ - jpn
19
+ - kor
20
+ - vie
21
+ - tha
22
+ - ara
23
+ ---
24
+
25
+ ## Qwen2.5-143B-Doubled72B-Instruct-Mergekit-Merge by Solshine (Caleb DeLeeuw)
26
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/654527ce2a13610acc25d921/xJlbOzfDQ7PkR1SYwKIJN.png)
27
+
28
+ # merge
29
+
30
+ This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
31
+
32
+ This model recieved no post merge retraining (yet) and minimal testing. Please contribute any feedback or evaluations of any kind via the community tab.
33
+
34
+ # License
35
+
36
+ Hippocratic License 3.0 + Ecocide module, + Extractive Industries module, + Copyleft
37
+ [![Hippocratic License HL3-CL-ECO-EXTR](https://img.shields.io/static/v1?label=Hippocratic%20License&message=HL3-CL-ECO-EXTR&labelColor=5e2751&color=bc8c3d)](https://firstdonoharm.dev/version/3/0/cl-eco-extr.html)
38
+ https://firstdonoharm.dev/version/3/0/cl-eco-extr.txt
39
+
40
+ ## Merge Details
41
+ ### Merge Method
42
+
43
+ This model was merged using the passthrough merge method. Every layer is doubled in order, from Qwen/Qwen2.5-72B-Instruct, creating 143B parameters. No additional fine-tune has been done in this merged model.
44
+
45
+ ### Models Merged
46
+
47
+ The following models were included in the merge:
48
+ * [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct)
49
+
50
+ ### Configuration
51
+
52
+ The following YAML configuration was used to produce this model:
53
+
54
+ ```yaml
55
+ slices:
56
+ - sources:
57
+ - model: Qwen/Qwen2.5-72B-Instruct
58
+ layer_range: [0, 1]
59
+ - sources:
60
+ - model: Qwen/Qwen2.5-72B-Instruct
61
+ layer_range: [0, 1]
62
+ - sources:
63
+ - model: Qwen/Qwen2.5-72B-Instruct
64
+ layer_range: [1, 2]
65
+ - sources:
66
+ - model: Qwen/Qwen2.5-72B-Instruct
67
+ layer_range: [1, 2]
68
+ - sources:
69
+ - model: Qwen/Qwen2.5-72B-Instruct
70
+ layer_range: [2, 3]
71
+ - sources:
72
+ - model: Qwen/Qwen2.5-72B-Instruct
73
+ layer_range: [2, 3]
74
+ - sources:
75
+ - model: Qwen/Qwen2.5-72B-Instruct
76
+ layer_range: [3, 4]
77
+ - sources:
78
+ - model: Qwen/Qwen2.5-72B-Instruct
79
+ layer_range: [3, 4]
80
+ - sources:
81
+ - model: Qwen/Qwen2.5-72B-Instruct
82
+ layer_range: [4, 5]
83
+ - sources:
84
+ - model: Qwen/Qwen2.5-72B-Instruct
85
+ layer_range: [4, 5]
86
+ - sources:
87
+ - model: Qwen/Qwen2.5-72B-Instruct
88
+ layer_range: [5, 6]
89
+ - sources:
90
+ - model: Qwen/Qwen2.5-72B-Instruct
91
+ layer_range: [5, 6]
92
+ - sources:
93
+ - model: Qwen/Qwen2.5-72B-Instruct
94
+ layer_range: [6, 7]
95
+ - sources:
96
+ - model: Qwen/Qwen2.5-72B-Instruct
97
+ layer_range: [6, 7]
98
+ - sources:
99
+ - model: Qwen/Qwen2.5-72B-Instruct
100
+ layer_range: [7, 8]
101
+ - sources:
102
+ - model: Qwen/Qwen2.5-72B-Instruct
103
+ layer_range: [7, 8]
104
+ - sources:
105
+ - model: Qwen/Qwen2.5-72B-Instruct
106
+ layer_range: [8, 9]
107
+ - sources:
108
+ - model: Qwen/Qwen2.5-72B-Instruct
109
+ layer_range: [8, 9]
110
+ - sources:
111
+ - model: Qwen/Qwen2.5-72B-Instruct
112
+ layer_range: [9, 10]
113
+ - sources:
114
+ - model: Qwen/Qwen2.5-72B-Instruct
115
+ layer_range: [9, 10]
116
+ - sources:
117
+ - model: Qwen/Qwen2.5-72B-Instruct
118
+ layer_range: [10, 11]
119
+ - sources:
120
+ - model: Qwen/Qwen2.5-72B-Instruct
121
+ layer_range: [10, 11]
122
+ - sources:
123
+ - model: Qwen/Qwen2.5-72B-Instruct
124
+ layer_range: [11, 12]
125
+ - sources:
126
+ - model: Qwen/Qwen2.5-72B-Instruct
127
+ layer_range: [11, 12]
128
+ - sources:
129
+ - model: Qwen/Qwen2.5-72B-Instruct
130
+ layer_range: [12, 13]
131
+ - sources:
132
+ - model: Qwen/Qwen2.5-72B-Instruct
133
+ layer_range: [12, 13]
134
+ - sources:
135
+ - model: Qwen/Qwen2.5-72B-Instruct
136
+ layer_range: [13, 14]
137
+ - sources:
138
+ - model: Qwen/Qwen2.5-72B-Instruct
139
+ layer_range: [13, 14]
140
+ - sources:
141
+ - model: Qwen/Qwen2.5-72B-Instruct
142
+ layer_range: [14, 15]
143
+ - sources:
144
+ - model: Qwen/Qwen2.5-72B-Instruct
145
+ layer_range: [14, 15]
146
+ - sources:
147
+ - model: Qwen/Qwen2.5-72B-Instruct
148
+ layer_range: [15, 16]
149
+ - sources:
150
+ - model: Qwen/Qwen2.5-72B-Instruct
151
+ layer_range: [15, 16]
152
+ - sources:
153
+ - model: Qwen/Qwen2.5-72B-Instruct
154
+ layer_range: [16, 17]
155
+ - sources:
156
+ - model: Qwen/Qwen2.5-72B-Instruct
157
+ layer_range: [16, 17]
158
+ - sources:
159
+ - model: Qwen/Qwen2.5-72B-Instruct
160
+ layer_range: [17, 18]
161
+ - sources:
162
+ - model: Qwen/Qwen2.5-72B-Instruct
163
+ layer_range: [17, 18]
164
+ - sources:
165
+ - model: Qwen/Qwen2.5-72B-Instruct
166
+ layer_range: [18, 19]
167
+ - sources:
168
+ - model: Qwen/Qwen2.5-72B-Instruct
169
+ layer_range: [18, 19]
170
+ - sources:
171
+ - model: Qwen/Qwen2.5-72B-Instruct
172
+ layer_range: [19, 20]
173
+ - sources:
174
+ - model: Qwen/Qwen2.5-72B-Instruct
175
+ layer_range: [19, 20]
176
+ - sources:
177
+ - model: Qwen/Qwen2.5-72B-Instruct
178
+ layer_range: [20, 21]
179
+ - sources:
180
+ - model: Qwen/Qwen2.5-72B-Instruct
181
+ layer_range: [20, 21]
182
+ - sources:
183
+ - model: Qwen/Qwen2.5-72B-Instruct
184
+ layer_range: [21, 22]
185
+ - sources:
186
+ - model: Qwen/Qwen2.5-72B-Instruct
187
+ layer_range: [21, 22]
188
+ - sources:
189
+ - model: Qwen/Qwen2.5-72B-Instruct
190
+ layer_range: [22, 23]
191
+ - sources:
192
+ - model: Qwen/Qwen2.5-72B-Instruct
193
+ layer_range: [22, 23]
194
+ - sources:
195
+ - model: Qwen/Qwen2.5-72B-Instruct
196
+ layer_range: [23, 24]
197
+ - sources:
198
+ - model: Qwen/Qwen2.5-72B-Instruct
199
+ layer_range: [23, 24]
200
+ - sources:
201
+ - model: Qwen/Qwen2.5-72B-Instruct
202
+ layer_range: [24, 25]
203
+ - sources:
204
+ - model: Qwen/Qwen2.5-72B-Instruct
205
+ layer_range: [24, 25]
206
+ - sources:
207
+ - model: Qwen/Qwen2.5-72B-Instruct
208
+ layer_range: [25, 26]
209
+ - sources:
210
+ - model: Qwen/Qwen2.5-72B-Instruct
211
+ layer_range: [25, 26]
212
+ - sources:
213
+ - model: Qwen/Qwen2.5-72B-Instruct
214
+ layer_range: [26, 27]
215
+ - sources:
216
+ - model: Qwen/Qwen2.5-72B-Instruct
217
+ layer_range: [26, 27]
218
+ - sources:
219
+ - model: Qwen/Qwen2.5-72B-Instruct
220
+ layer_range: [27, 28]
221
+ - sources:
222
+ - model: Qwen/Qwen2.5-72B-Instruct
223
+ layer_range: [27, 28]
224
+ - sources:
225
+ - model: Qwen/Qwen2.5-72B-Instruct
226
+ layer_range: [28, 29]
227
+ - sources:
228
+ - model: Qwen/Qwen2.5-72B-Instruct
229
+ layer_range: [28, 29]
230
+ - sources:
231
+ - model: Qwen/Qwen2.5-72B-Instruct
232
+ layer_range: [29, 30]
233
+ - sources:
234
+ - model: Qwen/Qwen2.5-72B-Instruct
235
+ layer_range: [29, 30]
236
+ - sources:
237
+ - model: Qwen/Qwen2.5-72B-Instruct
238
+ layer_range: [30, 31]
239
+ - sources:
240
+ - model: Qwen/Qwen2.5-72B-Instruct
241
+ layer_range: [30, 31]
242
+ - sources:
243
+ - model: Qwen/Qwen2.5-72B-Instruct
244
+ layer_range: [31, 32]
245
+ - sources:
246
+ - model: Qwen/Qwen2.5-72B-Instruct
247
+ layer_range: [31, 32]
248
+ - sources:
249
+ - model: Qwen/Qwen2.5-72B-Instruct
250
+ layer_range: [32, 33]
251
+ - sources:
252
+ - model: Qwen/Qwen2.5-72B-Instruct
253
+ layer_range: [32, 33]
254
+ - sources:
255
+ - model: Qwen/Qwen2.5-72B-Instruct
256
+ layer_range: [33, 34]
257
+ - sources:
258
+ - model: Qwen/Qwen2.5-72B-Instruct
259
+ layer_range: [33, 34]
260
+ - sources:
261
+ - model: Qwen/Qwen2.5-72B-Instruct
262
+ layer_range: [34, 35]
263
+ - sources:
264
+ - model: Qwen/Qwen2.5-72B-Instruct
265
+ layer_range: [34, 35]
266
+ - sources:
267
+ - model: Qwen/Qwen2.5-72B-Instruct
268
+ layer_range: [35, 36]
269
+ - sources:
270
+ - model: Qwen/Qwen2.5-72B-Instruct
271
+ layer_range: [35, 36]
272
+ - sources:
273
+ - model: Qwen/Qwen2.5-72B-Instruct
274
+ layer_range: [36, 37]
275
+ - sources:
276
+ - model: Qwen/Qwen2.5-72B-Instruct
277
+ layer_range: [36, 37]
278
+ - sources:
279
+ - model: Qwen/Qwen2.5-72B-Instruct
280
+ layer_range: [37, 38]
281
+ - sources:
282
+ - model: Qwen/Qwen2.5-72B-Instruct
283
+ layer_range: [37, 38]
284
+ - sources:
285
+ - model: Qwen/Qwen2.5-72B-Instruct
286
+ layer_range: [38, 39]
287
+ - sources:
288
+ - model: Qwen/Qwen2.5-72B-Instruct
289
+ layer_range: [38, 39]
290
+ - sources:
291
+ - model: Qwen/Qwen2.5-72B-Instruct
292
+ layer_range: [39, 40]
293
+ - sources:
294
+ - model: Qwen/Qwen2.5-72B-Instruct
295
+ layer_range: [39, 40]
296
+ - sources:
297
+ - model: Qwen/Qwen2.5-72B-Instruct
298
+ layer_range: [40, 41]
299
+ - sources:
300
+ - model: Qwen/Qwen2.5-72B-Instruct
301
+ layer_range: [40, 41]
302
+ - sources:
303
+ - model: Qwen/Qwen2.5-72B-Instruct
304
+ layer_range: [41, 42]
305
+ - sources:
306
+ - model: Qwen/Qwen2.5-72B-Instruct
307
+ layer_range: [41, 42]
308
+ - sources:
309
+ - model: Qwen/Qwen2.5-72B-Instruct
310
+ layer_range: [42, 43]
311
+ - sources:
312
+ - model: Qwen/Qwen2.5-72B-Instruct
313
+ layer_range: [42, 43]
314
+ - sources:
315
+ - model: Qwen/Qwen2.5-72B-Instruct
316
+ layer_range: [43, 44]
317
+ - sources:
318
+ - model: Qwen/Qwen2.5-72B-Instruct
319
+ layer_range: [43, 44]
320
+ - sources:
321
+ - model: Qwen/Qwen2.5-72B-Instruct
322
+ layer_range: [44, 45]
323
+ - sources:
324
+ - model: Qwen/Qwen2.5-72B-Instruct
325
+ layer_range: [44, 45]
326
+ - sources:
327
+ - model: Qwen/Qwen2.5-72B-Instruct
328
+ layer_range: [45, 46]
329
+ - sources:
330
+ - model: Qwen/Qwen2.5-72B-Instruct
331
+ layer_range: [45, 46]
332
+ - sources:
333
+ - model: Qwen/Qwen2.5-72B-Instruct
334
+ layer_range: [46, 47]
335
+ - sources:
336
+ - model: Qwen/Qwen2.5-72B-Instruct
337
+ layer_range: [46, 47]
338
+ - sources:
339
+ - model: Qwen/Qwen2.5-72B-Instruct
340
+ layer_range: [47, 48]
341
+ - sources:
342
+ - model: Qwen/Qwen2.5-72B-Instruct
343
+ layer_range: [47, 48]
344
+ - sources:
345
+ - model: Qwen/Qwen2.5-72B-Instruct
346
+ layer_range: [48, 49]
347
+ - sources:
348
+ - model: Qwen/Qwen2.5-72B-Instruct
349
+ layer_range: [48, 49]
350
+ - sources:
351
+ - model: Qwen/Qwen2.5-72B-Instruct
352
+ layer_range: [49, 50]
353
+ - sources:
354
+ - model: Qwen/Qwen2.5-72B-Instruct
355
+ layer_range: [49, 50]
356
+ - sources:
357
+ - model: Qwen/Qwen2.5-72B-Instruct
358
+ layer_range: [50, 51]
359
+ - sources:
360
+ - model: Qwen/Qwen2.5-72B-Instruct
361
+ layer_range: [50, 51]
362
+ - sources:
363
+ - model: Qwen/Qwen2.5-72B-Instruct
364
+ layer_range: [51, 52]
365
+ - sources:
366
+ - model: Qwen/Qwen2.5-72B-Instruct
367
+ layer_range: [51, 52]
368
+ - sources:
369
+ - model: Qwen/Qwen2.5-72B-Instruct
370
+ layer_range: [52, 53]
371
+ - sources:
372
+ - model: Qwen/Qwen2.5-72B-Instruct
373
+ layer_range: [52, 53]
374
+ - sources:
375
+ - model: Qwen/Qwen2.5-72B-Instruct
376
+ layer_range: [53, 54]
377
+ - sources:
378
+ - model: Qwen/Qwen2.5-72B-Instruct
379
+ layer_range: [53, 54]
380
+ - sources:
381
+ - model: Qwen/Qwen2.5-72B-Instruct
382
+ layer_range: [54, 55]
383
+ - sources:
384
+ - model: Qwen/Qwen2.5-72B-Instruct
385
+ layer_range: [54, 55]
386
+ - sources:
387
+ - model: Qwen/Qwen2.5-72B-Instruct
388
+ layer_range: [55, 56]
389
+ - sources:
390
+ - model: Qwen/Qwen2.5-72B-Instruct
391
+ layer_range: [55, 56]
392
+ - sources:
393
+ - model: Qwen/Qwen2.5-72B-Instruct
394
+ layer_range: [56, 57]
395
+ - sources:
396
+ - model: Qwen/Qwen2.5-72B-Instruct
397
+ layer_range: [56, 57]
398
+ - sources:
399
+ - model: Qwen/Qwen2.5-72B-Instruct
400
+ layer_range: [57, 58]
401
+ - sources:
402
+ - model: Qwen/Qwen2.5-72B-Instruct
403
+ layer_range: [57, 58]
404
+ - sources:
405
+ - model: Qwen/Qwen2.5-72B-Instruct
406
+ layer_range: [58, 59]
407
+ - sources:
408
+ - model: Qwen/Qwen2.5-72B-Instruct
409
+ layer_range: [58, 59]
410
+ - sources:
411
+ - model: Qwen/Qwen2.5-72B-Instruct
412
+ layer_range: [59, 60]
413
+ - sources:
414
+ - model: Qwen/Qwen2.5-72B-Instruct
415
+ layer_range: [59, 60]
416
+ - sources:
417
+ - model: Qwen/Qwen2.5-72B-Instruct
418
+ layer_range: [60, 61]
419
+ - sources:
420
+ - model: Qwen/Qwen2.5-72B-Instruct
421
+ layer_range: [60, 61]
422
+ - sources:
423
+ - model: Qwen/Qwen2.5-72B-Instruct
424
+ layer_range: [61, 62]
425
+ - sources:
426
+ - model: Qwen/Qwen2.5-72B-Instruct
427
+ layer_range: [61, 62]
428
+ - sources:
429
+ - model: Qwen/Qwen2.5-72B-Instruct
430
+ layer_range: [62, 63]
431
+ - sources:
432
+ - model: Qwen/Qwen2.5-72B-Instruct
433
+ layer_range: [62, 63]
434
+ - sources:
435
+ - model: Qwen/Qwen2.5-72B-Instruct
436
+ layer_range: [63, 64]
437
+ - sources:
438
+ - model: Qwen/Qwen2.5-72B-Instruct
439
+ layer_range: [63, 64]
440
+ - sources:
441
+ - model: Qwen/Qwen2.5-72B-Instruct
442
+ layer_range: [64, 65]
443
+ - sources:
444
+ - model: Qwen/Qwen2.5-72B-Instruct
445
+ layer_range: [64, 65]
446
+ - sources:
447
+ - model: Qwen/Qwen2.5-72B-Instruct
448
+ layer_range: [65, 66]
449
+ - sources:
450
+ - model: Qwen/Qwen2.5-72B-Instruct
451
+ layer_range: [65, 66]
452
+ - sources:
453
+ - model: Qwen/Qwen2.5-72B-Instruct
454
+ layer_range: [66, 67]
455
+ - sources:
456
+ - model: Qwen/Qwen2.5-72B-Instruct
457
+ layer_range: [66, 67]
458
+ - sources:
459
+ - model: Qwen/Qwen2.5-72B-Instruct
460
+ layer_range: [67, 68]
461
+ - sources:
462
+ - model: Qwen/Qwen2.5-72B-Instruct
463
+ layer_range: [67, 68]
464
+ - sources:
465
+ - model: Qwen/Qwen2.5-72B-Instruct
466
+ layer_range: [68, 69]
467
+ - sources:
468
+ - model: Qwen/Qwen2.5-72B-Instruct
469
+ layer_range: [68, 69]
470
+ - sources:
471
+ - model: Qwen/Qwen2.5-72B-Instruct
472
+ layer_range: [69, 70]
473
+ - sources:
474
+ - model: Qwen/Qwen2.5-72B-Instruct
475
+ layer_range: [69, 70]
476
+ - sources:
477
+ - model: Qwen/Qwen2.5-72B-Instruct
478
+ layer_range: [70, 71]
479
+ - sources:
480
+ - model: Qwen/Qwen2.5-72B-Instruct
481
+ layer_range: [70, 71]
482
+ - sources:
483
+ - model: Qwen/Qwen2.5-72B-Instruct
484
+ layer_range: [71, 72]
485
+ - sources:
486
+ - model: Qwen/Qwen2.5-72B-Instruct
487
+ layer_range: [71, 72]
488
+ - sources:
489
+ - model: Qwen/Qwen2.5-72B-Instruct
490
+ layer_range: [72, 73]
491
+ - sources:
492
+ - model: Qwen/Qwen2.5-72B-Instruct
493
+ layer_range: [72, 73]
494
+ - sources:
495
+ - model: Qwen/Qwen2.5-72B-Instruct
496
+ layer_range: [73, 74]
497
+ - sources:
498
+ - model: Qwen/Qwen2.5-72B-Instruct
499
+ layer_range: [73, 74]
500
+ - sources:
501
+ - model: Qwen/Qwen2.5-72B-Instruct
502
+ layer_range: [74, 75]
503
+ - sources:
504
+ - model: Qwen/Qwen2.5-72B-Instruct
505
+ layer_range: [74, 75]
506
+ - sources:
507
+ - model: Qwen/Qwen2.5-72B-Instruct
508
+ layer_range: [75, 76]
509
+ - sources:
510
+ - model: Qwen/Qwen2.5-72B-Instruct
511
+ layer_range: [75, 76]
512
+ - sources:
513
+ - model: Qwen/Qwen2.5-72B-Instruct
514
+ layer_range: [76, 77]
515
+ - sources:
516
+ - model: Qwen/Qwen2.5-72B-Instruct
517
+ layer_range: [76, 77]
518
+ - sources:
519
+ - model: Qwen/Qwen2.5-72B-Instruct
520
+ layer_range: [77, 78]
521
+ - sources:
522
+ - model: Qwen/Qwen2.5-72B-Instruct
523
+ layer_range: [77, 78]
524
+ - sources:
525
+ - model: Qwen/Qwen2.5-72B-Instruct
526
+ layer_range: [78, 79]
527
+ - sources:
528
+ - model: Qwen/Qwen2.5-72B-Instruct
529
+ layer_range: [78, 79]
530
+ - sources:
531
+ - model: Qwen/Qwen2.5-72B-Instruct
532
+ layer_range: [79, 80]
533
+ - sources:
534
+ - model: Qwen/Qwen2.5-72B-Instruct
535
+ layer_range: [79, 80]
536
+ merge_method: passthrough
537
+ dtype: float16
538
  ```