zhxchen17 commited on
Commit
b063341
1 Parent(s): f73b7c8

Create README

Browse files
Files changed (1) hide show
  1. README +518 -0
README ADDED
@@ -0,0 +1,518 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ weight state dict:
2
+
3
+ tok_embeddings.weight
4
+ layers.0.attention.wqkv.q.weight
5
+ layers.0.attention.wqkv.q.scales_and_zeros
6
+ layers.0.attention.wqkv.k.weight
7
+ layers.0.attention.wqkv.k.scales_and_zeros
8
+ layers.0.attention.wqkv.v.weight
9
+ layers.0.attention.wqkv.v.scales_and_zeros
10
+ layers.0.attention.wo.weight
11
+ layers.0.attention.wo.scales_and_zeros
12
+ layers.0.feed_forward.w1.weight
13
+ layers.0.feed_forward.w1.scales_and_zeros
14
+ layers.0.feed_forward.w3.weight
15
+ layers.0.feed_forward.w3.scales_and_zeros
16
+ layers.0.feed_forward.w2.weight
17
+ layers.0.feed_forward.w2.scales_and_zeros
18
+ layers.0.ffn_norm.weight
19
+ layers.0.attention_norm.weight
20
+ layers.1.attention.wqkv.q.weight
21
+ layers.1.attention.wqkv.q.scales_and_zeros
22
+ layers.1.attention.wqkv.k.weight
23
+ layers.1.attention.wqkv.k.scales_and_zeros
24
+ layers.1.attention.wqkv.v.weight
25
+ layers.1.attention.wqkv.v.scales_and_zeros
26
+ layers.1.attention.wo.weight
27
+ layers.1.attention.wo.scales_and_zeros
28
+ layers.1.feed_forward.w1.weight
29
+ layers.1.feed_forward.w1.scales_and_zeros
30
+ layers.1.feed_forward.w3.weight
31
+ layers.1.feed_forward.w3.scales_and_zeros
32
+ layers.1.feed_forward.w2.weight
33
+ layers.1.feed_forward.w2.scales_and_zeros
34
+ layers.1.ffn_norm.weight
35
+ layers.1.attention_norm.weight
36
+ layers.2.attention.wqkv.q.weight
37
+ layers.2.attention.wqkv.q.scales_and_zeros
38
+ layers.2.attention.wqkv.k.weight
39
+ layers.2.attention.wqkv.k.scales_and_zeros
40
+ layers.2.attention.wqkv.v.weight
41
+ layers.2.attention.wqkv.v.scales_and_zeros
42
+ layers.2.attention.wo.weight
43
+ layers.2.attention.wo.scales_and_zeros
44
+ layers.2.feed_forward.w1.weight
45
+ layers.2.feed_forward.w1.scales_and_zeros
46
+ layers.2.feed_forward.w3.weight
47
+ layers.2.feed_forward.w3.scales_and_zeros
48
+ layers.2.feed_forward.w2.weight
49
+ layers.2.feed_forward.w2.scales_and_zeros
50
+ layers.2.ffn_norm.weight
51
+ layers.2.attention_norm.weight
52
+ layers.3.attention.wqkv.q.weight
53
+ layers.3.attention.wqkv.q.scales_and_zeros
54
+ layers.3.attention.wqkv.k.weight
55
+ layers.3.attention.wqkv.k.scales_and_zeros
56
+ layers.3.attention.wqkv.v.weight
57
+ layers.3.attention.wqkv.v.scales_and_zeros
58
+ layers.3.attention.wo.weight
59
+ layers.3.attention.wo.scales_and_zeros
60
+ layers.3.feed_forward.w1.weight
61
+ layers.3.feed_forward.w1.scales_and_zeros
62
+ layers.3.feed_forward.w3.weight
63
+ layers.3.feed_forward.w3.scales_and_zeros
64
+ layers.3.feed_forward.w2.weight
65
+ layers.3.feed_forward.w2.scales_and_zeros
66
+ layers.3.ffn_norm.weight
67
+ layers.3.attention_norm.weight
68
+ layers.4.attention.wqkv.q.weight
69
+ layers.4.attention.wqkv.q.scales_and_zeros
70
+ layers.4.attention.wqkv.k.weight
71
+ layers.4.attention.wqkv.k.scales_and_zeros
72
+ layers.4.attention.wqkv.v.weight
73
+ layers.4.attention.wqkv.v.scales_and_zeros
74
+ layers.4.attention.wo.weight
75
+ layers.4.attention.wo.scales_and_zeros
76
+ layers.4.feed_forward.w1.weight
77
+ layers.4.feed_forward.w1.scales_and_zeros
78
+ layers.4.feed_forward.w3.weight
79
+ layers.4.feed_forward.w3.scales_and_zeros
80
+ layers.4.feed_forward.w2.weight
81
+ layers.4.feed_forward.w2.scales_and_zeros
82
+ layers.4.ffn_norm.weight
83
+ layers.4.attention_norm.weight
84
+ layers.5.attention.wqkv.q.weight
85
+ layers.5.attention.wqkv.q.scales_and_zeros
86
+ layers.5.attention.wqkv.k.weight
87
+ layers.5.attention.wqkv.k.scales_and_zeros
88
+ layers.5.attention.wqkv.v.weight
89
+ layers.5.attention.wqkv.v.scales_and_zeros
90
+ layers.5.attention.wo.weight
91
+ layers.5.attention.wo.scales_and_zeros
92
+ layers.5.feed_forward.w1.weight
93
+ layers.5.feed_forward.w1.scales_and_zeros
94
+ layers.5.feed_forward.w3.weight
95
+ layers.5.feed_forward.w3.scales_and_zeros
96
+ layers.5.feed_forward.w2.weight
97
+ layers.5.feed_forward.w2.scales_and_zeros
98
+ layers.5.ffn_norm.weight
99
+ layers.5.attention_norm.weight
100
+ layers.6.attention.wqkv.q.weight
101
+ layers.6.attention.wqkv.q.scales_and_zeros
102
+ layers.6.attention.wqkv.k.weight
103
+ layers.6.attention.wqkv.k.scales_and_zeros
104
+ layers.6.attention.wqkv.v.weight
105
+ layers.6.attention.wqkv.v.scales_and_zeros
106
+ layers.6.attention.wo.weight
107
+ layers.6.attention.wo.scales_and_zeros
108
+ layers.6.feed_forward.w1.weight
109
+ layers.6.feed_forward.w1.scales_and_zeros
110
+ layers.6.feed_forward.w3.weight
111
+ layers.6.feed_forward.w3.scales_and_zeros
112
+ layers.6.feed_forward.w2.weight
113
+ layers.6.feed_forward.w2.scales_and_zeros
114
+ layers.6.ffn_norm.weight
115
+ layers.6.attention_norm.weight
116
+ layers.7.attention.wqkv.q.weight
117
+ layers.7.attention.wqkv.q.scales_and_zeros
118
+ layers.7.attention.wqkv.k.weight
119
+ layers.7.attention.wqkv.k.scales_and_zeros
120
+ layers.7.attention.wqkv.v.weight
121
+ layers.7.attention.wqkv.v.scales_and_zeros
122
+ layers.7.attention.wo.weight
123
+ layers.7.attention.wo.scales_and_zeros
124
+ layers.7.feed_forward.w1.weight
125
+ layers.7.feed_forward.w1.scales_and_zeros
126
+ layers.7.feed_forward.w3.weight
127
+ layers.7.feed_forward.w3.scales_and_zeros
128
+ layers.7.feed_forward.w2.weight
129
+ layers.7.feed_forward.w2.scales_and_zeros
130
+ layers.7.ffn_norm.weight
131
+ layers.7.attention_norm.weight
132
+ layers.8.attention.wqkv.q.weight
133
+ layers.8.attention.wqkv.q.scales_and_zeros
134
+ layers.8.attention.wqkv.k.weight
135
+ layers.8.attention.wqkv.k.scales_and_zeros
136
+ layers.8.attention.wqkv.v.weight
137
+ layers.8.attention.wqkv.v.scales_and_zeros
138
+ layers.8.attention.wo.weight
139
+ layers.8.attention.wo.scales_and_zeros
140
+ layers.8.feed_forward.w1.weight
141
+ layers.8.feed_forward.w1.scales_and_zeros
142
+ layers.8.feed_forward.w3.weight
143
+ layers.8.feed_forward.w3.scales_and_zeros
144
+ layers.8.feed_forward.w2.weight
145
+ layers.8.feed_forward.w2.scales_and_zeros
146
+ layers.8.ffn_norm.weight
147
+ layers.8.attention_norm.weight
148
+ layers.9.attention.wqkv.q.weight
149
+ layers.9.attention.wqkv.q.scales_and_zeros
150
+ layers.9.attention.wqkv.k.weight
151
+ layers.9.attention.wqkv.k.scales_and_zeros
152
+ layers.9.attention.wqkv.v.weight
153
+ layers.9.attention.wqkv.v.scales_and_zeros
154
+ layers.9.attention.wo.weight
155
+ layers.9.attention.wo.scales_and_zeros
156
+ layers.9.feed_forward.w1.weight
157
+ layers.9.feed_forward.w1.scales_and_zeros
158
+ layers.9.feed_forward.w3.weight
159
+ layers.9.feed_forward.w3.scales_and_zeros
160
+ layers.9.feed_forward.w2.weight
161
+ layers.9.feed_forward.w2.scales_and_zeros
162
+ layers.9.ffn_norm.weight
163
+ layers.9.attention_norm.weight
164
+ layers.10.attention.wqkv.q.weight
165
+ layers.10.attention.wqkv.q.scales_and_zeros
166
+ layers.10.attention.wqkv.k.weight
167
+ layers.10.attention.wqkv.k.scales_and_zeros
168
+ layers.10.attention.wqkv.v.weight
169
+ layers.10.attention.wqkv.v.scales_and_zeros
170
+ layers.10.attention.wo.weight
171
+ layers.10.attention.wo.scales_and_zeros
172
+ layers.10.feed_forward.w1.weight
173
+ layers.10.feed_forward.w1.scales_and_zeros
174
+ layers.10.feed_forward.w3.weight
175
+ layers.10.feed_forward.w3.scales_and_zeros
176
+ layers.10.feed_forward.w2.weight
177
+ layers.10.feed_forward.w2.scales_and_zeros
178
+ layers.10.ffn_norm.weight
179
+ layers.10.attention_norm.weight
180
+ layers.11.attention.wqkv.q.weight
181
+ layers.11.attention.wqkv.q.scales_and_zeros
182
+ layers.11.attention.wqkv.k.weight
183
+ layers.11.attention.wqkv.k.scales_and_zeros
184
+ layers.11.attention.wqkv.v.weight
185
+ layers.11.attention.wqkv.v.scales_and_zeros
186
+ layers.11.attention.wo.weight
187
+ layers.11.attention.wo.scales_and_zeros
188
+ layers.11.feed_forward.w1.weight
189
+ layers.11.feed_forward.w1.scales_and_zeros
190
+ layers.11.feed_forward.w3.weight
191
+ layers.11.feed_forward.w3.scales_and_zeros
192
+ layers.11.feed_forward.w2.weight
193
+ layers.11.feed_forward.w2.scales_and_zeros
194
+ layers.11.ffn_norm.weight
195
+ layers.11.attention_norm.weight
196
+ layers.12.attention.wqkv.q.weight
197
+ layers.12.attention.wqkv.q.scales_and_zeros
198
+ layers.12.attention.wqkv.k.weight
199
+ layers.12.attention.wqkv.k.scales_and_zeros
200
+ layers.12.attention.wqkv.v.weight
201
+ layers.12.attention.wqkv.v.scales_and_zeros
202
+ layers.12.attention.wo.weight
203
+ layers.12.attention.wo.scales_and_zeros
204
+ layers.12.feed_forward.w1.weight
205
+ layers.12.feed_forward.w1.scales_and_zeros
206
+ layers.12.feed_forward.w3.weight
207
+ layers.12.feed_forward.w3.scales_and_zeros
208
+ layers.12.feed_forward.w2.weight
209
+ layers.12.feed_forward.w2.scales_and_zeros
210
+ layers.12.ffn_norm.weight
211
+ layers.12.attention_norm.weight
212
+ layers.13.attention.wqkv.q.weight
213
+ layers.13.attention.wqkv.q.scales_and_zeros
214
+ layers.13.attention.wqkv.k.weight
215
+ layers.13.attention.wqkv.k.scales_and_zeros
216
+ layers.13.attention.wqkv.v.weight
217
+ layers.13.attention.wqkv.v.scales_and_zeros
218
+ layers.13.attention.wo.weight
219
+ layers.13.attention.wo.scales_and_zeros
220
+ layers.13.feed_forward.w1.weight
221
+ layers.13.feed_forward.w1.scales_and_zeros
222
+ layers.13.feed_forward.w3.weight
223
+ layers.13.feed_forward.w3.scales_and_zeros
224
+ layers.13.feed_forward.w2.weight
225
+ layers.13.feed_forward.w2.scales_and_zeros
226
+ layers.13.ffn_norm.weight
227
+ layers.13.attention_norm.weight
228
+ layers.14.attention.wqkv.q.weight
229
+ layers.14.attention.wqkv.q.scales_and_zeros
230
+ layers.14.attention.wqkv.k.weight
231
+ layers.14.attention.wqkv.k.scales_and_zeros
232
+ layers.14.attention.wqkv.v.weight
233
+ layers.14.attention.wqkv.v.scales_and_zeros
234
+ layers.14.attention.wo.weight
235
+ layers.14.attention.wo.scales_and_zeros
236
+ layers.14.feed_forward.w1.weight
237
+ layers.14.feed_forward.w1.scales_and_zeros
238
+ layers.14.feed_forward.w3.weight
239
+ layers.14.feed_forward.w3.scales_and_zeros
240
+ layers.14.feed_forward.w2.weight
241
+ layers.14.feed_forward.w2.scales_and_zeros
242
+ layers.14.ffn_norm.weight
243
+ layers.14.attention_norm.weight
244
+ layers.15.attention.wqkv.q.weight
245
+ layers.15.attention.wqkv.q.scales_and_zeros
246
+ layers.15.attention.wqkv.k.weight
247
+ layers.15.attention.wqkv.k.scales_and_zeros
248
+ layers.15.attention.wqkv.v.weight
249
+ layers.15.attention.wqkv.v.scales_and_zeros
250
+ layers.15.attention.wo.weight
251
+ layers.15.attention.wo.scales_and_zeros
252
+ layers.15.feed_forward.w1.weight
253
+ layers.15.feed_forward.w1.scales_and_zeros
254
+ layers.15.feed_forward.w3.weight
255
+ layers.15.feed_forward.w3.scales_and_zeros
256
+ layers.15.feed_forward.w2.weight
257
+ layers.15.feed_forward.w2.scales_and_zeros
258
+ layers.15.ffn_norm.weight
259
+ layers.15.attention_norm.weight
260
+ layers.16.attention.wqkv.q.weight
261
+ layers.16.attention.wqkv.q.scales_and_zeros
262
+ layers.16.attention.wqkv.k.weight
263
+ layers.16.attention.wqkv.k.scales_and_zeros
264
+ layers.16.attention.wqkv.v.weight
265
+ layers.16.attention.wqkv.v.scales_and_zeros
266
+ layers.16.attention.wo.weight
267
+ layers.16.attention.wo.scales_and_zeros
268
+ layers.16.feed_forward.w1.weight
269
+ layers.16.feed_forward.w1.scales_and_zeros
270
+ layers.16.feed_forward.w3.weight
271
+ layers.16.feed_forward.w3.scales_and_zeros
272
+ layers.16.feed_forward.w2.weight
273
+ layers.16.feed_forward.w2.scales_and_zeros
274
+ layers.16.ffn_norm.weight
275
+ layers.16.attention_norm.weight
276
+ layers.17.attention.wqkv.q.weight
277
+ layers.17.attention.wqkv.q.scales_and_zeros
278
+ layers.17.attention.wqkv.k.weight
279
+ layers.17.attention.wqkv.k.scales_and_zeros
280
+ layers.17.attention.wqkv.v.weight
281
+ layers.17.attention.wqkv.v.scales_and_zeros
282
+ layers.17.attention.wo.weight
283
+ layers.17.attention.wo.scales_and_zeros
284
+ layers.17.feed_forward.w1.weight
285
+ layers.17.feed_forward.w1.scales_and_zeros
286
+ layers.17.feed_forward.w3.weight
287
+ layers.17.feed_forward.w3.scales_and_zeros
288
+ layers.17.feed_forward.w2.weight
289
+ layers.17.feed_forward.w2.scales_and_zeros
290
+ layers.17.ffn_norm.weight
291
+ layers.17.attention_norm.weight
292
+ layers.18.attention.wqkv.q.weight
293
+ layers.18.attention.wqkv.q.scales_and_zeros
294
+ layers.18.attention.wqkv.k.weight
295
+ layers.18.attention.wqkv.k.scales_and_zeros
296
+ layers.18.attention.wqkv.v.weight
297
+ layers.18.attention.wqkv.v.scales_and_zeros
298
+ layers.18.attention.wo.weight
299
+ layers.18.attention.wo.scales_and_zeros
300
+ layers.18.feed_forward.w1.weight
301
+ layers.18.feed_forward.w1.scales_and_zeros
302
+ layers.18.feed_forward.w3.weight
303
+ layers.18.feed_forward.w3.scales_and_zeros
304
+ layers.18.feed_forward.w2.weight
305
+ layers.18.feed_forward.w2.scales_and_zeros
306
+ layers.18.ffn_norm.weight
307
+ layers.18.attention_norm.weight
308
+ layers.19.attention.wqkv.q.weight
309
+ layers.19.attention.wqkv.q.scales_and_zeros
310
+ layers.19.attention.wqkv.k.weight
311
+ layers.19.attention.wqkv.k.scales_and_zeros
312
+ layers.19.attention.wqkv.v.weight
313
+ layers.19.attention.wqkv.v.scales_and_zeros
314
+ layers.19.attention.wo.weight
315
+ layers.19.attention.wo.scales_and_zeros
316
+ layers.19.feed_forward.w1.weight
317
+ layers.19.feed_forward.w1.scales_and_zeros
318
+ layers.19.feed_forward.w3.weight
319
+ layers.19.feed_forward.w3.scales_and_zeros
320
+ layers.19.feed_forward.w2.weight
321
+ layers.19.feed_forward.w2.scales_and_zeros
322
+ layers.19.ffn_norm.weight
323
+ layers.19.attention_norm.weight
324
+ layers.20.attention.wqkv.q.weight
325
+ layers.20.attention.wqkv.q.scales_and_zeros
326
+ layers.20.attention.wqkv.k.weight
327
+ layers.20.attention.wqkv.k.scales_and_zeros
328
+ layers.20.attention.wqkv.v.weight
329
+ layers.20.attention.wqkv.v.scales_and_zeros
330
+ layers.20.attention.wo.weight
331
+ layers.20.attention.wo.scales_and_zeros
332
+ layers.20.feed_forward.w1.weight
333
+ layers.20.feed_forward.w1.scales_and_zeros
334
+ layers.20.feed_forward.w3.weight
335
+ layers.20.feed_forward.w3.scales_and_zeros
336
+ layers.20.feed_forward.w2.weight
337
+ layers.20.feed_forward.w2.scales_and_zeros
338
+ layers.20.ffn_norm.weight
339
+ layers.20.attention_norm.weight
340
+ layers.21.attention.wqkv.q.weight
341
+ layers.21.attention.wqkv.q.scales_and_zeros
342
+ layers.21.attention.wqkv.k.weight
343
+ layers.21.attention.wqkv.k.scales_and_zeros
344
+ layers.21.attention.wqkv.v.weight
345
+ layers.21.attention.wqkv.v.scales_and_zeros
346
+ layers.21.attention.wo.weight
347
+ layers.21.attention.wo.scales_and_zeros
348
+ layers.21.feed_forward.w1.weight
349
+ layers.21.feed_forward.w1.scales_and_zeros
350
+ layers.21.feed_forward.w3.weight
351
+ layers.21.feed_forward.w3.scales_and_zeros
352
+ layers.21.feed_forward.w2.weight
353
+ layers.21.feed_forward.w2.scales_and_zeros
354
+ layers.21.ffn_norm.weight
355
+ layers.21.attention_norm.weight
356
+ layers.22.attention.wqkv.q.weight
357
+ layers.22.attention.wqkv.q.scales_and_zeros
358
+ layers.22.attention.wqkv.k.weight
359
+ layers.22.attention.wqkv.k.scales_and_zeros
360
+ layers.22.attention.wqkv.v.weight
361
+ layers.22.attention.wqkv.v.scales_and_zeros
362
+ layers.22.attention.wo.weight
363
+ layers.22.attention.wo.scales_and_zeros
364
+ layers.22.feed_forward.w1.weight
365
+ layers.22.feed_forward.w1.scales_and_zeros
366
+ layers.22.feed_forward.w3.weight
367
+ layers.22.feed_forward.w3.scales_and_zeros
368
+ layers.22.feed_forward.w2.weight
369
+ layers.22.feed_forward.w2.scales_and_zeros
370
+ layers.22.ffn_norm.weight
371
+ layers.22.attention_norm.weight
372
+ layers.23.attention.wqkv.q.weight
373
+ layers.23.attention.wqkv.q.scales_and_zeros
374
+ layers.23.attention.wqkv.k.weight
375
+ layers.23.attention.wqkv.k.scales_and_zeros
376
+ layers.23.attention.wqkv.v.weight
377
+ layers.23.attention.wqkv.v.scales_and_zeros
378
+ layers.23.attention.wo.weight
379
+ layers.23.attention.wo.scales_and_zeros
380
+ layers.23.feed_forward.w1.weight
381
+ layers.23.feed_forward.w1.scales_and_zeros
382
+ layers.23.feed_forward.w3.weight
383
+ layers.23.feed_forward.w3.scales_and_zeros
384
+ layers.23.feed_forward.w2.weight
385
+ layers.23.feed_forward.w2.scales_and_zeros
386
+ layers.23.ffn_norm.weight
387
+ layers.23.attention_norm.weight
388
+ layers.24.attention.wqkv.q.weight
389
+ layers.24.attention.wqkv.q.scales_and_zeros
390
+ layers.24.attention.wqkv.k.weight
391
+ layers.24.attention.wqkv.k.scales_and_zeros
392
+ layers.24.attention.wqkv.v.weight
393
+ layers.24.attention.wqkv.v.scales_and_zeros
394
+ layers.24.attention.wo.weight
395
+ layers.24.attention.wo.scales_and_zeros
396
+ layers.24.feed_forward.w1.weight
397
+ layers.24.feed_forward.w1.scales_and_zeros
398
+ layers.24.feed_forward.w3.weight
399
+ layers.24.feed_forward.w3.scales_and_zeros
400
+ layers.24.feed_forward.w2.weight
401
+ layers.24.feed_forward.w2.scales_and_zeros
402
+ layers.24.ffn_norm.weight
403
+ layers.24.attention_norm.weight
404
+ layers.25.attention.wqkv.q.weight
405
+ layers.25.attention.wqkv.q.scales_and_zeros
406
+ layers.25.attention.wqkv.k.weight
407
+ layers.25.attention.wqkv.k.scales_and_zeros
408
+ layers.25.attention.wqkv.v.weight
409
+ layers.25.attention.wqkv.v.scales_and_zeros
410
+ layers.25.attention.wo.weight
411
+ layers.25.attention.wo.scales_and_zeros
412
+ layers.25.feed_forward.w1.weight
413
+ layers.25.feed_forward.w1.scales_and_zeros
414
+ layers.25.feed_forward.w3.weight
415
+ layers.25.feed_forward.w3.scales_and_zeros
416
+ layers.25.feed_forward.w2.weight
417
+ layers.25.feed_forward.w2.scales_and_zeros
418
+ layers.25.ffn_norm.weight
419
+ layers.25.attention_norm.weight
420
+ layers.26.attention.wqkv.q.weight
421
+ layers.26.attention.wqkv.q.scales_and_zeros
422
+ layers.26.attention.wqkv.k.weight
423
+ layers.26.attention.wqkv.k.scales_and_zeros
424
+ layers.26.attention.wqkv.v.weight
425
+ layers.26.attention.wqkv.v.scales_and_zeros
426
+ layers.26.attention.wo.weight
427
+ layers.26.attention.wo.scales_and_zeros
428
+ layers.26.feed_forward.w1.weight
429
+ layers.26.feed_forward.w1.scales_and_zeros
430
+ layers.26.feed_forward.w3.weight
431
+ layers.26.feed_forward.w3.scales_and_zeros
432
+ layers.26.feed_forward.w2.weight
433
+ layers.26.feed_forward.w2.scales_and_zeros
434
+ layers.26.ffn_norm.weight
435
+ layers.26.attention_norm.weight
436
+ layers.27.attention.wqkv.q.weight
437
+ layers.27.attention.wqkv.q.scales_and_zeros
438
+ layers.27.attention.wqkv.k.weight
439
+ layers.27.attention.wqkv.k.scales_and_zeros
440
+ layers.27.attention.wqkv.v.weight
441
+ layers.27.attention.wqkv.v.scales_and_zeros
442
+ layers.27.attention.wo.weight
443
+ layers.27.attention.wo.scales_and_zeros
444
+ layers.27.feed_forward.w1.weight
445
+ layers.27.feed_forward.w1.scales_and_zeros
446
+ layers.27.feed_forward.w3.weight
447
+ layers.27.feed_forward.w3.scales_and_zeros
448
+ layers.27.feed_forward.w2.weight
449
+ layers.27.feed_forward.w2.scales_and_zeros
450
+ layers.27.ffn_norm.weight
451
+ layers.27.attention_norm.weight
452
+ layers.28.attention.wqkv.q.weight
453
+ layers.28.attention.wqkv.q.scales_and_zeros
454
+ layers.28.attention.wqkv.k.weight
455
+ layers.28.attention.wqkv.k.scales_and_zeros
456
+ layers.28.attention.wqkv.v.weight
457
+ layers.28.attention.wqkv.v.scales_and_zeros
458
+ layers.28.attention.wo.weight
459
+ layers.28.attention.wo.scales_and_zeros
460
+ layers.28.feed_forward.w1.weight
461
+ layers.28.feed_forward.w1.scales_and_zeros
462
+ layers.28.feed_forward.w3.weight
463
+ layers.28.feed_forward.w3.scales_and_zeros
464
+ layers.28.feed_forward.w2.weight
465
+ layers.28.feed_forward.w2.scales_and_zeros
466
+ layers.28.ffn_norm.weight
467
+ layers.28.attention_norm.weight
468
+ layers.29.attention.wqkv.q.weight
469
+ layers.29.attention.wqkv.q.scales_and_zeros
470
+ layers.29.attention.wqkv.k.weight
471
+ layers.29.attention.wqkv.k.scales_and_zeros
472
+ layers.29.attention.wqkv.v.weight
473
+ layers.29.attention.wqkv.v.scales_and_zeros
474
+ layers.29.attention.wo.weight
475
+ layers.29.attention.wo.scales_and_zeros
476
+ layers.29.feed_forward.w1.weight
477
+ layers.29.feed_forward.w1.scales_and_zeros
478
+ layers.29.feed_forward.w3.weight
479
+ layers.29.feed_forward.w3.scales_and_zeros
480
+ layers.29.feed_forward.w2.weight
481
+ layers.29.feed_forward.w2.scales_and_zeros
482
+ layers.29.ffn_norm.weight
483
+ layers.29.attention_norm.weight
484
+ layers.30.attention.wqkv.q.weight
485
+ layers.30.attention.wqkv.q.scales_and_zeros
486
+ layers.30.attention.wqkv.k.weight
487
+ layers.30.attention.wqkv.k.scales_and_zeros
488
+ layers.30.attention.wqkv.v.weight
489
+ layers.30.attention.wqkv.v.scales_and_zeros
490
+ layers.30.attention.wo.weight
491
+ layers.30.attention.wo.scales_and_zeros
492
+ layers.30.feed_forward.w1.weight
493
+ layers.30.feed_forward.w1.scales_and_zeros
494
+ layers.30.feed_forward.w3.weight
495
+ layers.30.feed_forward.w3.scales_and_zeros
496
+ layers.30.feed_forward.w2.weight
497
+ layers.30.feed_forward.w2.scales_and_zeros
498
+ layers.30.ffn_norm.weight
499
+ layers.30.attention_norm.weight
500
+ layers.31.attention.wqkv.q.weight
501
+ layers.31.attention.wqkv.q.scales_and_zeros
502
+ layers.31.attention.wqkv.k.weight
503
+ layers.31.attention.wqkv.k.scales_and_zeros
504
+ layers.31.attention.wqkv.v.weight
505
+ layers.31.attention.wqkv.v.scales_and_zeros
506
+ layers.31.attention.wo.weight
507
+ layers.31.attention.wo.scales_and_zeros
508
+ layers.31.feed_forward.w1.weight
509
+ layers.31.feed_forward.w1.scales_and_zeros
510
+ layers.31.feed_forward.w3.weight
511
+ layers.31.feed_forward.w3.scales_and_zeros
512
+ layers.31.feed_forward.w2.weight
513
+ layers.31.feed_forward.w2.scales_and_zeros
514
+ layers.31.ffn_norm.weight
515
+ layers.31.attention_norm.weight
516
+ norm.weight
517
+ output.weight
518
+ output.scales_and_zeros