Text Generation
Transformers
PyTorch
English
gpt_neox
causal-lm
pythia
text-generation-inference
Inference Endpoints
File size: 42,028 Bytes
ab8dfc6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
{
  "metadata": {
    "total_size": 13848822848
  },
  "weight_map": {
    "embed_out.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.embed_in.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.final_layer_norm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.0.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.24.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.3.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.30.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.dense.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.dense.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.masked_bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.attention.rotary_emb.inv_freq": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
    "gpt_neox.layers.4.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.dense.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.dense.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.masked_bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.attention.rotary_emb.inv_freq": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
    "gpt_neox.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin"
  }
}