mayank-mishra commited on
Commit
3cb12fb
·
verified ·
1 Parent(s): e4d3feb

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,1429 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 100257,
3
+ "embedding_dropout": 0,
4
+ "eos_token_id": 100257,
5
+ "hidden_size": 1536,
6
+ "init_method": "normal",
7
+ "initializer_range": 0.02,
8
+ "layer_norm_epsilon": 1e-05,
9
+ "m_emb": null,
10
+ "m_residual": null,
11
+ "m_width": null,
12
+ "max_position_embeddings": 4096,
13
+ "mlp_blocks": [
14
+ {
15
+ "activation_function": "swiglu",
16
+ "add_bias": false,
17
+ "dropout": 0,
18
+ "intermediate_size": 256,
19
+ "mlp_type": "MoE",
20
+ "normalized_topk": true,
21
+ "num_experts": 128,
22
+ "num_experts_per_tok": 8,
23
+ "shared_expert_gating": false,
24
+ "shared_intermediate_size": 1024,
25
+ "use_interleaved_weights": true
26
+ },
27
+ {
28
+ "activation_function": "swiglu",
29
+ "add_bias": false,
30
+ "dropout": 0,
31
+ "intermediate_size": 256,
32
+ "mlp_type": "MoE",
33
+ "normalized_topk": true,
34
+ "num_experts": 128,
35
+ "num_experts_per_tok": 8,
36
+ "shared_expert_gating": false,
37
+ "shared_intermediate_size": 1024,
38
+ "use_interleaved_weights": true
39
+ },
40
+ {
41
+ "activation_function": "swiglu",
42
+ "add_bias": false,
43
+ "dropout": 0,
44
+ "intermediate_size": 256,
45
+ "mlp_type": "MoE",
46
+ "normalized_topk": true,
47
+ "num_experts": 128,
48
+ "num_experts_per_tok": 8,
49
+ "shared_expert_gating": false,
50
+ "shared_intermediate_size": 1024,
51
+ "use_interleaved_weights": true
52
+ },
53
+ {
54
+ "activation_function": "swiglu",
55
+ "add_bias": false,
56
+ "dropout": 0,
57
+ "intermediate_size": 256,
58
+ "mlp_type": "MoE",
59
+ "normalized_topk": true,
60
+ "num_experts": 128,
61
+ "num_experts_per_tok": 8,
62
+ "shared_expert_gating": false,
63
+ "shared_intermediate_size": 1024,
64
+ "use_interleaved_weights": true
65
+ },
66
+ {
67
+ "activation_function": "swiglu",
68
+ "add_bias": false,
69
+ "dropout": 0,
70
+ "intermediate_size": 256,
71
+ "mlp_type": "MoE",
72
+ "normalized_topk": true,
73
+ "num_experts": 128,
74
+ "num_experts_per_tok": 8,
75
+ "shared_expert_gating": false,
76
+ "shared_intermediate_size": 1024,
77
+ "use_interleaved_weights": true
78
+ },
79
+ {
80
+ "activation_function": "swiglu",
81
+ "add_bias": false,
82
+ "dropout": 0,
83
+ "intermediate_size": 256,
84
+ "mlp_type": "MoE",
85
+ "normalized_topk": true,
86
+ "num_experts": 128,
87
+ "num_experts_per_tok": 8,
88
+ "shared_expert_gating": false,
89
+ "shared_intermediate_size": 1024,
90
+ "use_interleaved_weights": true
91
+ },
92
+ {
93
+ "activation_function": "swiglu",
94
+ "add_bias": false,
95
+ "dropout": 0,
96
+ "intermediate_size": 256,
97
+ "mlp_type": "MoE",
98
+ "normalized_topk": true,
99
+ "num_experts": 128,
100
+ "num_experts_per_tok": 8,
101
+ "shared_expert_gating": false,
102
+ "shared_intermediate_size": 1024,
103
+ "use_interleaved_weights": true
104
+ },
105
+ {
106
+ "activation_function": "swiglu",
107
+ "add_bias": false,
108
+ "dropout": 0,
109
+ "intermediate_size": 256,
110
+ "mlp_type": "MoE",
111
+ "normalized_topk": true,
112
+ "num_experts": 128,
113
+ "num_experts_per_tok": 8,
114
+ "shared_expert_gating": false,
115
+ "shared_intermediate_size": 1024,
116
+ "use_interleaved_weights": true
117
+ },
118
+ {
119
+ "activation_function": "swiglu",
120
+ "add_bias": false,
121
+ "dropout": 0,
122
+ "intermediate_size": 256,
123
+ "mlp_type": "MoE",
124
+ "normalized_topk": true,
125
+ "num_experts": 128,
126
+ "num_experts_per_tok": 8,
127
+ "shared_expert_gating": false,
128
+ "shared_intermediate_size": 1024,
129
+ "use_interleaved_weights": true
130
+ },
131
+ {
132
+ "activation_function": "swiglu",
133
+ "add_bias": false,
134
+ "dropout": 0,
135
+ "intermediate_size": 256,
136
+ "mlp_type": "MoE",
137
+ "normalized_topk": true,
138
+ "num_experts": 128,
139
+ "num_experts_per_tok": 8,
140
+ "shared_expert_gating": false,
141
+ "shared_intermediate_size": 1024,
142
+ "use_interleaved_weights": true
143
+ },
144
+ {
145
+ "activation_function": "swiglu",
146
+ "add_bias": false,
147
+ "dropout": 0,
148
+ "intermediate_size": 256,
149
+ "mlp_type": "MoE",
150
+ "normalized_topk": true,
151
+ "num_experts": 128,
152
+ "num_experts_per_tok": 8,
153
+ "shared_expert_gating": false,
154
+ "shared_intermediate_size": 1024,
155
+ "use_interleaved_weights": true
156
+ },
157
+ {
158
+ "activation_function": "swiglu",
159
+ "add_bias": false,
160
+ "dropout": 0,
161
+ "intermediate_size": 256,
162
+ "mlp_type": "MoE",
163
+ "normalized_topk": true,
164
+ "num_experts": 128,
165
+ "num_experts_per_tok": 8,
166
+ "shared_expert_gating": false,
167
+ "shared_intermediate_size": 1024,
168
+ "use_interleaved_weights": true
169
+ },
170
+ {
171
+ "activation_function": "swiglu",
172
+ "add_bias": false,
173
+ "dropout": 0,
174
+ "intermediate_size": 256,
175
+ "mlp_type": "MoE",
176
+ "normalized_topk": true,
177
+ "num_experts": 128,
178
+ "num_experts_per_tok": 8,
179
+ "shared_expert_gating": false,
180
+ "shared_intermediate_size": 1024,
181
+ "use_interleaved_weights": true
182
+ },
183
+ {
184
+ "activation_function": "swiglu",
185
+ "add_bias": false,
186
+ "dropout": 0,
187
+ "intermediate_size": 256,
188
+ "mlp_type": "MoE",
189
+ "normalized_topk": true,
190
+ "num_experts": 128,
191
+ "num_experts_per_tok": 8,
192
+ "shared_expert_gating": false,
193
+ "shared_intermediate_size": 1024,
194
+ "use_interleaved_weights": true
195
+ },
196
+ {
197
+ "activation_function": "swiglu",
198
+ "add_bias": false,
199
+ "dropout": 0,
200
+ "intermediate_size": 256,
201
+ "mlp_type": "MoE",
202
+ "normalized_topk": true,
203
+ "num_experts": 128,
204
+ "num_experts_per_tok": 8,
205
+ "shared_expert_gating": false,
206
+ "shared_intermediate_size": 1024,
207
+ "use_interleaved_weights": true
208
+ },
209
+ {
210
+ "activation_function": "swiglu",
211
+ "add_bias": false,
212
+ "dropout": 0,
213
+ "intermediate_size": 256,
214
+ "mlp_type": "MoE",
215
+ "normalized_topk": true,
216
+ "num_experts": 128,
217
+ "num_experts_per_tok": 8,
218
+ "shared_expert_gating": false,
219
+ "shared_intermediate_size": 1024,
220
+ "use_interleaved_weights": true
221
+ },
222
+ {
223
+ "activation_function": "swiglu",
224
+ "add_bias": false,
225
+ "dropout": 0,
226
+ "intermediate_size": 256,
227
+ "mlp_type": "MoE",
228
+ "normalized_topk": true,
229
+ "num_experts": 128,
230
+ "num_experts_per_tok": 8,
231
+ "shared_expert_gating": false,
232
+ "shared_intermediate_size": 1024,
233
+ "use_interleaved_weights": true
234
+ },
235
+ {
236
+ "activation_function": "swiglu",
237
+ "add_bias": false,
238
+ "dropout": 0,
239
+ "intermediate_size": 256,
240
+ "mlp_type": "MoE",
241
+ "normalized_topk": true,
242
+ "num_experts": 128,
243
+ "num_experts_per_tok": 8,
244
+ "shared_expert_gating": false,
245
+ "shared_intermediate_size": 1024,
246
+ "use_interleaved_weights": true
247
+ },
248
+ {
249
+ "activation_function": "swiglu",
250
+ "add_bias": false,
251
+ "dropout": 0,
252
+ "intermediate_size": 256,
253
+ "mlp_type": "MoE",
254
+ "normalized_topk": true,
255
+ "num_experts": 128,
256
+ "num_experts_per_tok": 8,
257
+ "shared_expert_gating": false,
258
+ "shared_intermediate_size": 1024,
259
+ "use_interleaved_weights": true
260
+ },
261
+ {
262
+ "activation_function": "swiglu",
263
+ "add_bias": false,
264
+ "dropout": 0,
265
+ "intermediate_size": 256,
266
+ "mlp_type": "MoE",
267
+ "normalized_topk": true,
268
+ "num_experts": 128,
269
+ "num_experts_per_tok": 8,
270
+ "shared_expert_gating": false,
271
+ "shared_intermediate_size": 1024,
272
+ "use_interleaved_weights": true
273
+ },
274
+ {
275
+ "activation_function": "swiglu",
276
+ "add_bias": false,
277
+ "dropout": 0,
278
+ "intermediate_size": 256,
279
+ "mlp_type": "MoE",
280
+ "normalized_topk": true,
281
+ "num_experts": 128,
282
+ "num_experts_per_tok": 8,
283
+ "shared_expert_gating": false,
284
+ "shared_intermediate_size": 1024,
285
+ "use_interleaved_weights": true
286
+ },
287
+ {
288
+ "activation_function": "swiglu",
289
+ "add_bias": false,
290
+ "dropout": 0,
291
+ "intermediate_size": 256,
292
+ "mlp_type": "MoE",
293
+ "normalized_topk": true,
294
+ "num_experts": 128,
295
+ "num_experts_per_tok": 8,
296
+ "shared_expert_gating": false,
297
+ "shared_intermediate_size": 1024,
298
+ "use_interleaved_weights": true
299
+ },
300
+ {
301
+ "activation_function": "swiglu",
302
+ "add_bias": false,
303
+ "dropout": 0,
304
+ "intermediate_size": 256,
305
+ "mlp_type": "MoE",
306
+ "normalized_topk": true,
307
+ "num_experts": 128,
308
+ "num_experts_per_tok": 8,
309
+ "shared_expert_gating": false,
310
+ "shared_intermediate_size": 1024,
311
+ "use_interleaved_weights": true
312
+ },
313
+ {
314
+ "activation_function": "swiglu",
315
+ "add_bias": false,
316
+ "dropout": 0,
317
+ "intermediate_size": 256,
318
+ "mlp_type": "MoE",
319
+ "normalized_topk": true,
320
+ "num_experts": 128,
321
+ "num_experts_per_tok": 8,
322
+ "shared_expert_gating": false,
323
+ "shared_intermediate_size": 1024,
324
+ "use_interleaved_weights": true
325
+ },
326
+ {
327
+ "activation_function": "swiglu",
328
+ "add_bias": false,
329
+ "dropout": 0,
330
+ "intermediate_size": 256,
331
+ "mlp_type": "MoE",
332
+ "normalized_topk": true,
333
+ "num_experts": 128,
334
+ "num_experts_per_tok": 8,
335
+ "shared_expert_gating": false,
336
+ "shared_intermediate_size": 1024,
337
+ "use_interleaved_weights": true
338
+ },
339
+ {
340
+ "activation_function": "swiglu",
341
+ "add_bias": false,
342
+ "dropout": 0,
343
+ "intermediate_size": 256,
344
+ "mlp_type": "MoE",
345
+ "normalized_topk": true,
346
+ "num_experts": 128,
347
+ "num_experts_per_tok": 8,
348
+ "shared_expert_gating": false,
349
+ "shared_intermediate_size": 1024,
350
+ "use_interleaved_weights": true
351
+ },
352
+ {
353
+ "activation_function": "swiglu",
354
+ "add_bias": false,
355
+ "dropout": 0,
356
+ "intermediate_size": 256,
357
+ "mlp_type": "MoE",
358
+ "normalized_topk": true,
359
+ "num_experts": 128,
360
+ "num_experts_per_tok": 8,
361
+ "shared_expert_gating": false,
362
+ "shared_intermediate_size": 1024,
363
+ "use_interleaved_weights": true
364
+ },
365
+ {
366
+ "activation_function": "swiglu",
367
+ "add_bias": false,
368
+ "dropout": 0,
369
+ "intermediate_size": 256,
370
+ "mlp_type": "MoE",
371
+ "normalized_topk": true,
372
+ "num_experts": 128,
373
+ "num_experts_per_tok": 8,
374
+ "shared_expert_gating": false,
375
+ "shared_intermediate_size": 1024,
376
+ "use_interleaved_weights": true
377
+ },
378
+ {
379
+ "activation_function": "swiglu",
380
+ "add_bias": false,
381
+ "dropout": 0,
382
+ "intermediate_size": 256,
383
+ "mlp_type": "MoE",
384
+ "normalized_topk": true,
385
+ "num_experts": 128,
386
+ "num_experts_per_tok": 8,
387
+ "shared_expert_gating": false,
388
+ "shared_intermediate_size": 1024,
389
+ "use_interleaved_weights": true
390
+ },
391
+ {
392
+ "activation_function": "swiglu",
393
+ "add_bias": false,
394
+ "dropout": 0,
395
+ "intermediate_size": 256,
396
+ "mlp_type": "MoE",
397
+ "normalized_topk": true,
398
+ "num_experts": 128,
399
+ "num_experts_per_tok": 8,
400
+ "shared_expert_gating": false,
401
+ "shared_intermediate_size": 1024,
402
+ "use_interleaved_weights": true
403
+ },
404
+ {
405
+ "activation_function": "swiglu",
406
+ "add_bias": false,
407
+ "dropout": 0,
408
+ "intermediate_size": 256,
409
+ "mlp_type": "MoE",
410
+ "normalized_topk": true,
411
+ "num_experts": 128,
412
+ "num_experts_per_tok": 8,
413
+ "shared_expert_gating": false,
414
+ "shared_intermediate_size": 1024,
415
+ "use_interleaved_weights": true
416
+ },
417
+ {
418
+ "activation_function": "swiglu",
419
+ "add_bias": false,
420
+ "dropout": 0,
421
+ "intermediate_size": 256,
422
+ "mlp_type": "MoE",
423
+ "normalized_topk": true,
424
+ "num_experts": 128,
425
+ "num_experts_per_tok": 8,
426
+ "shared_expert_gating": false,
427
+ "shared_intermediate_size": 1024,
428
+ "use_interleaved_weights": true
429
+ },
430
+ {
431
+ "activation_function": "swiglu",
432
+ "add_bias": false,
433
+ "dropout": 0,
434
+ "intermediate_size": 256,
435
+ "mlp_type": "MoE",
436
+ "normalized_topk": true,
437
+ "num_experts": 128,
438
+ "num_experts_per_tok": 8,
439
+ "shared_expert_gating": false,
440
+ "shared_intermediate_size": 1024,
441
+ "use_interleaved_weights": true
442
+ },
443
+ {
444
+ "activation_function": "swiglu",
445
+ "add_bias": false,
446
+ "dropout": 0,
447
+ "intermediate_size": 256,
448
+ "mlp_type": "MoE",
449
+ "normalized_topk": true,
450
+ "num_experts": 128,
451
+ "num_experts_per_tok": 8,
452
+ "shared_expert_gating": false,
453
+ "shared_intermediate_size": 1024,
454
+ "use_interleaved_weights": true
455
+ },
456
+ {
457
+ "activation_function": "swiglu",
458
+ "add_bias": false,
459
+ "dropout": 0,
460
+ "intermediate_size": 256,
461
+ "mlp_type": "MoE",
462
+ "normalized_topk": true,
463
+ "num_experts": 128,
464
+ "num_experts_per_tok": 8,
465
+ "shared_expert_gating": false,
466
+ "shared_intermediate_size": 1024,
467
+ "use_interleaved_weights": true
468
+ },
469
+ {
470
+ "activation_function": "swiglu",
471
+ "add_bias": false,
472
+ "dropout": 0,
473
+ "intermediate_size": 256,
474
+ "mlp_type": "MoE",
475
+ "normalized_topk": true,
476
+ "num_experts": 128,
477
+ "num_experts_per_tok": 8,
478
+ "shared_expert_gating": false,
479
+ "shared_intermediate_size": 1024,
480
+ "use_interleaved_weights": true
481
+ },
482
+ {
483
+ "activation_function": "swiglu",
484
+ "add_bias": false,
485
+ "dropout": 0,
486
+ "intermediate_size": 256,
487
+ "mlp_type": "MoE",
488
+ "normalized_topk": true,
489
+ "num_experts": 128,
490
+ "num_experts_per_tok": 8,
491
+ "shared_expert_gating": false,
492
+ "shared_intermediate_size": 1024,
493
+ "use_interleaved_weights": true
494
+ },
495
+ {
496
+ "activation_function": "swiglu",
497
+ "add_bias": false,
498
+ "dropout": 0,
499
+ "intermediate_size": 256,
500
+ "mlp_type": "MoE",
501
+ "normalized_topk": true,
502
+ "num_experts": 128,
503
+ "num_experts_per_tok": 8,
504
+ "shared_expert_gating": false,
505
+ "shared_intermediate_size": 1024,
506
+ "use_interleaved_weights": true
507
+ },
508
+ {
509
+ "activation_function": "swiglu",
510
+ "add_bias": false,
511
+ "dropout": 0,
512
+ "intermediate_size": 256,
513
+ "mlp_type": "MoE",
514
+ "normalized_topk": true,
515
+ "num_experts": 128,
516
+ "num_experts_per_tok": 8,
517
+ "shared_expert_gating": false,
518
+ "shared_intermediate_size": 1024,
519
+ "use_interleaved_weights": true
520
+ },
521
+ {
522
+ "activation_function": "swiglu",
523
+ "add_bias": false,
524
+ "dropout": 0,
525
+ "intermediate_size": 256,
526
+ "mlp_type": "MoE",
527
+ "normalized_topk": true,
528
+ "num_experts": 128,
529
+ "num_experts_per_tok": 8,
530
+ "shared_expert_gating": false,
531
+ "shared_intermediate_size": 1024,
532
+ "use_interleaved_weights": true
533
+ }
534
+ ],
535
+ "model_type": "gpt_base",
536
+ "normalization_function": "rmsnorm",
537
+ "num_layers": 40,
538
+ "pad_token_id": 100256,
539
+ "position_embedding_type": "nope",
540
+ "rope_dim": null,
541
+ "rope_scaling": null,
542
+ "rope_theta": 10000,
543
+ "router_aux_loss_coef": 0.001,
544
+ "sequence_mixer_blocks": [
545
+ {
546
+ "A_init_max": 16,
547
+ "A_init_min": 0,
548
+ "activation_function": "silu",
549
+ "add_bias": false,
550
+ "dt_init_floor": 0.0001,
551
+ "dt_init_max": 0.1,
552
+ "dt_init_min": 0.001,
553
+ "gradient_clipping": 1.0,
554
+ "k_head_dim": 64,
555
+ "kernel_size": 4,
556
+ "normalization_function": "rmsnorm",
557
+ "num_f_heads": 132,
558
+ "num_g_heads": 132,
559
+ "num_k_heads": 1,
560
+ "num_q_heads": 1,
561
+ "num_v_heads": 132,
562
+ "num_weight_heads": 132,
563
+ "sequence_mixer_type": "m2rnn",
564
+ "use_residual": true,
565
+ "v_head_dim": 16
566
+ },
567
+ {
568
+ "A_init_max": 16,
569
+ "A_init_min": 0,
570
+ "activation_function": "silu",
571
+ "add_bias": false,
572
+ "dt_init_floor": 0.0001,
573
+ "dt_init_max": 0.1,
574
+ "dt_init_min": 0.001,
575
+ "gradient_clipping": 1.0,
576
+ "k_head_dim": 64,
577
+ "kernel_size": 4,
578
+ "normalization_function": "rmsnorm",
579
+ "num_f_heads": 132,
580
+ "num_g_heads": 132,
581
+ "num_k_heads": 1,
582
+ "num_q_heads": 1,
583
+ "num_v_heads": 132,
584
+ "num_weight_heads": 132,
585
+ "sequence_mixer_type": "m2rnn",
586
+ "use_residual": true,
587
+ "v_head_dim": 16
588
+ },
589
+ {
590
+ "A_init_max": 16,
591
+ "A_init_min": 0,
592
+ "activation_function": "silu",
593
+ "add_bias": false,
594
+ "dt_init_floor": 0.0001,
595
+ "dt_init_max": 0.1,
596
+ "dt_init_min": 0.001,
597
+ "gradient_clipping": 1.0,
598
+ "k_head_dim": 64,
599
+ "kernel_size": 4,
600
+ "normalization_function": "rmsnorm",
601
+ "num_f_heads": 132,
602
+ "num_g_heads": 132,
603
+ "num_k_heads": 1,
604
+ "num_q_heads": 1,
605
+ "num_v_heads": 132,
606
+ "num_weight_heads": 132,
607
+ "sequence_mixer_type": "m2rnn",
608
+ "use_residual": true,
609
+ "v_head_dim": 16
610
+ },
611
+ {
612
+ "A_init_max": 16,
613
+ "A_init_min": 0,
614
+ "activation_function": "silu",
615
+ "add_bias": false,
616
+ "dt_init_floor": 0.0001,
617
+ "dt_init_max": 0.1,
618
+ "dt_init_min": 0.001,
619
+ "gradient_clipping": 1.0,
620
+ "k_head_dim": 64,
621
+ "kernel_size": 4,
622
+ "normalization_function": "rmsnorm",
623
+ "num_f_heads": 132,
624
+ "num_g_heads": 132,
625
+ "num_k_heads": 1,
626
+ "num_q_heads": 1,
627
+ "num_v_heads": 132,
628
+ "num_weight_heads": 132,
629
+ "sequence_mixer_type": "m2rnn",
630
+ "use_residual": true,
631
+ "v_head_dim": 16
632
+ },
633
+ {
634
+ "A_init_max": 16,
635
+ "A_init_min": 0,
636
+ "activation_function": "silu",
637
+ "add_bias": false,
638
+ "dt_init_floor": 0.0001,
639
+ "dt_init_max": 0.1,
640
+ "dt_init_min": 0.001,
641
+ "gradient_clipping": 1.0,
642
+ "k_head_dim": 64,
643
+ "kernel_size": 4,
644
+ "normalization_function": "rmsnorm",
645
+ "num_f_heads": 132,
646
+ "num_g_heads": 132,
647
+ "num_k_heads": 1,
648
+ "num_q_heads": 1,
649
+ "num_v_heads": 132,
650
+ "num_weight_heads": 132,
651
+ "sequence_mixer_type": "m2rnn",
652
+ "use_residual": true,
653
+ "v_head_dim": 16
654
+ },
655
+ {
656
+ "A_init_max": 16,
657
+ "A_init_min": 0,
658
+ "activation_function": "silu",
659
+ "add_bias": false,
660
+ "dt_init_floor": 0.0001,
661
+ "dt_init_max": 0.1,
662
+ "dt_init_min": 0.001,
663
+ "gradient_clipping": 1.0,
664
+ "k_head_dim": 64,
665
+ "kernel_size": 4,
666
+ "normalization_function": "rmsnorm",
667
+ "num_f_heads": 132,
668
+ "num_g_heads": 132,
669
+ "num_k_heads": 1,
670
+ "num_q_heads": 1,
671
+ "num_v_heads": 132,
672
+ "num_weight_heads": 132,
673
+ "sequence_mixer_type": "m2rnn",
674
+ "use_residual": true,
675
+ "v_head_dim": 16
676
+ },
677
+ {
678
+ "A_init_max": 16,
679
+ "A_init_min": 0,
680
+ "activation_function": "silu",
681
+ "add_bias": false,
682
+ "dt_init_floor": 0.0001,
683
+ "dt_init_max": 0.1,
684
+ "dt_init_min": 0.001,
685
+ "gradient_clipping": 1.0,
686
+ "k_head_dim": 64,
687
+ "kernel_size": 4,
688
+ "normalization_function": "rmsnorm",
689
+ "num_f_heads": 132,
690
+ "num_g_heads": 132,
691
+ "num_k_heads": 1,
692
+ "num_q_heads": 1,
693
+ "num_v_heads": 132,
694
+ "num_weight_heads": 132,
695
+ "sequence_mixer_type": "m2rnn",
696
+ "use_residual": true,
697
+ "v_head_dim": 16
698
+ },
699
+ {
700
+ "A_init_max": 16,
701
+ "A_init_min": 0,
702
+ "activation_function": "silu",
703
+ "add_bias": false,
704
+ "dt_init_floor": 0.0001,
705
+ "dt_init_max": 0.1,
706
+ "dt_init_min": 0.001,
707
+ "gradient_clipping": 1.0,
708
+ "k_head_dim": 64,
709
+ "kernel_size": 4,
710
+ "normalization_function": "rmsnorm",
711
+ "num_f_heads": 132,
712
+ "num_g_heads": 132,
713
+ "num_k_heads": 1,
714
+ "num_q_heads": 1,
715
+ "num_v_heads": 132,
716
+ "num_weight_heads": 132,
717
+ "sequence_mixer_type": "m2rnn",
718
+ "use_residual": true,
719
+ "v_head_dim": 16
720
+ },
721
+ {
722
+ "A_init_max": 16,
723
+ "A_init_min": 0,
724
+ "activation_function": "silu",
725
+ "add_bias": false,
726
+ "dt_init_floor": 0.0001,
727
+ "dt_init_max": 0.1,
728
+ "dt_init_min": 0.001,
729
+ "gradient_clipping": 1.0,
730
+ "k_head_dim": 64,
731
+ "kernel_size": 4,
732
+ "normalization_function": "rmsnorm",
733
+ "num_f_heads": 132,
734
+ "num_g_heads": 132,
735
+ "num_k_heads": 1,
736
+ "num_q_heads": 1,
737
+ "num_v_heads": 132,
738
+ "num_weight_heads": 132,
739
+ "sequence_mixer_type": "m2rnn",
740
+ "use_residual": true,
741
+ "v_head_dim": 16
742
+ },
743
+ {
744
+ "A_init_max": 16,
745
+ "A_init_min": 0,
746
+ "activation_function": "silu",
747
+ "add_bias": false,
748
+ "dt_init_floor": 0.0001,
749
+ "dt_init_max": 0.1,
750
+ "dt_init_min": 0.001,
751
+ "gradient_clipping": 1.0,
752
+ "k_head_dim": 64,
753
+ "kernel_size": 4,
754
+ "normalization_function": "rmsnorm",
755
+ "num_f_heads": 132,
756
+ "num_g_heads": 132,
757
+ "num_k_heads": 1,
758
+ "num_q_heads": 1,
759
+ "num_v_heads": 132,
760
+ "num_weight_heads": 132,
761
+ "sequence_mixer_type": "m2rnn",
762
+ "use_residual": true,
763
+ "v_head_dim": 16
764
+ },
765
+ {
766
+ "A_init_max": 16,
767
+ "A_init_min": 0,
768
+ "activation_function": "silu",
769
+ "add_bias": false,
770
+ "dt_init_floor": 0.0001,
771
+ "dt_init_max": 0.1,
772
+ "dt_init_min": 0.001,
773
+ "gradient_clipping": 1.0,
774
+ "k_head_dim": 64,
775
+ "kernel_size": 4,
776
+ "normalization_function": "rmsnorm",
777
+ "num_f_heads": 132,
778
+ "num_g_heads": 132,
779
+ "num_k_heads": 1,
780
+ "num_q_heads": 1,
781
+ "num_v_heads": 132,
782
+ "num_weight_heads": 132,
783
+ "sequence_mixer_type": "m2rnn",
784
+ "use_residual": true,
785
+ "v_head_dim": 16
786
+ },
787
+ {
788
+ "A_init_max": 16,
789
+ "A_init_min": 0,
790
+ "activation_function": "silu",
791
+ "add_bias": false,
792
+ "dt_init_floor": 0.0001,
793
+ "dt_init_max": 0.1,
794
+ "dt_init_min": 0.001,
795
+ "gradient_clipping": 1.0,
796
+ "k_head_dim": 64,
797
+ "kernel_size": 4,
798
+ "normalization_function": "rmsnorm",
799
+ "num_f_heads": 132,
800
+ "num_g_heads": 132,
801
+ "num_k_heads": 1,
802
+ "num_q_heads": 1,
803
+ "num_v_heads": 132,
804
+ "num_weight_heads": 132,
805
+ "sequence_mixer_type": "m2rnn",
806
+ "use_residual": true,
807
+ "v_head_dim": 16
808
+ },
809
+ {
810
+ "A_init_max": 16,
811
+ "A_init_min": 0,
812
+ "activation_function": "silu",
813
+ "add_bias": false,
814
+ "dt_init_floor": 0.0001,
815
+ "dt_init_max": 0.1,
816
+ "dt_init_min": 0.001,
817
+ "gradient_clipping": 1.0,
818
+ "k_head_dim": 64,
819
+ "kernel_size": 4,
820
+ "normalization_function": "rmsnorm",
821
+ "num_f_heads": 132,
822
+ "num_g_heads": 132,
823
+ "num_k_heads": 1,
824
+ "num_q_heads": 1,
825
+ "num_v_heads": 132,
826
+ "num_weight_heads": 132,
827
+ "sequence_mixer_type": "m2rnn",
828
+ "use_residual": true,
829
+ "v_head_dim": 16
830
+ },
831
+ {
832
+ "A_init_max": 16,
833
+ "A_init_min": 0,
834
+ "activation_function": "silu",
835
+ "add_bias": false,
836
+ "dt_init_floor": 0.0001,
837
+ "dt_init_max": 0.1,
838
+ "dt_init_min": 0.001,
839
+ "gradient_clipping": 1.0,
840
+ "k_head_dim": 64,
841
+ "kernel_size": 4,
842
+ "normalization_function": "rmsnorm",
843
+ "num_f_heads": 132,
844
+ "num_g_heads": 132,
845
+ "num_k_heads": 1,
846
+ "num_q_heads": 1,
847
+ "num_v_heads": 132,
848
+ "num_weight_heads": 132,
849
+ "sequence_mixer_type": "m2rnn",
850
+ "use_residual": true,
851
+ "v_head_dim": 16
852
+ },
853
+ {
854
+ "A_init_max": 16,
855
+ "A_init_min": 0,
856
+ "activation_function": "silu",
857
+ "add_bias": false,
858
+ "dt_init_floor": 0.0001,
859
+ "dt_init_max": 0.1,
860
+ "dt_init_min": 0.001,
861
+ "gradient_clipping": 1.0,
862
+ "k_head_dim": 64,
863
+ "kernel_size": 4,
864
+ "normalization_function": "rmsnorm",
865
+ "num_f_heads": 132,
866
+ "num_g_heads": 132,
867
+ "num_k_heads": 1,
868
+ "num_q_heads": 1,
869
+ "num_v_heads": 132,
870
+ "num_weight_heads": 132,
871
+ "sequence_mixer_type": "m2rnn",
872
+ "use_residual": true,
873
+ "v_head_dim": 16
874
+ },
875
+ {
876
+ "A_init_max": 16,
877
+ "A_init_min": 0,
878
+ "activation_function": "silu",
879
+ "add_bias": false,
880
+ "dt_init_floor": 0.0001,
881
+ "dt_init_max": 0.1,
882
+ "dt_init_min": 0.001,
883
+ "gradient_clipping": 1.0,
884
+ "k_head_dim": 64,
885
+ "kernel_size": 4,
886
+ "normalization_function": "rmsnorm",
887
+ "num_f_heads": 132,
888
+ "num_g_heads": 132,
889
+ "num_k_heads": 1,
890
+ "num_q_heads": 1,
891
+ "num_v_heads": 132,
892
+ "num_weight_heads": 132,
893
+ "sequence_mixer_type": "m2rnn",
894
+ "use_residual": true,
895
+ "v_head_dim": 16
896
+ },
897
+ {
898
+ "A_init_max": 16,
899
+ "A_init_min": 0,
900
+ "activation_function": "silu",
901
+ "add_bias": false,
902
+ "dt_init_floor": 0.0001,
903
+ "dt_init_max": 0.1,
904
+ "dt_init_min": 0.001,
905
+ "gradient_clipping": 1.0,
906
+ "k_head_dim": 64,
907
+ "kernel_size": 4,
908
+ "normalization_function": "rmsnorm",
909
+ "num_f_heads": 132,
910
+ "num_g_heads": 132,
911
+ "num_k_heads": 1,
912
+ "num_q_heads": 1,
913
+ "num_v_heads": 132,
914
+ "num_weight_heads": 132,
915
+ "sequence_mixer_type": "m2rnn",
916
+ "use_residual": true,
917
+ "v_head_dim": 16
918
+ },
919
+ {
920
+ "A_init_max": 16,
921
+ "A_init_min": 0,
922
+ "activation_function": "silu",
923
+ "add_bias": false,
924
+ "dt_init_floor": 0.0001,
925
+ "dt_init_max": 0.1,
926
+ "dt_init_min": 0.001,
927
+ "gradient_clipping": 1.0,
928
+ "k_head_dim": 64,
929
+ "kernel_size": 4,
930
+ "normalization_function": "rmsnorm",
931
+ "num_f_heads": 132,
932
+ "num_g_heads": 132,
933
+ "num_k_heads": 1,
934
+ "num_q_heads": 1,
935
+ "num_v_heads": 132,
936
+ "num_weight_heads": 132,
937
+ "sequence_mixer_type": "m2rnn",
938
+ "use_residual": true,
939
+ "v_head_dim": 16
940
+ },
941
+ {
942
+ "A_init_max": 16,
943
+ "A_init_min": 0,
944
+ "activation_function": "silu",
945
+ "add_bias": false,
946
+ "dt_init_floor": 0.0001,
947
+ "dt_init_max": 0.1,
948
+ "dt_init_min": 0.001,
949
+ "gradient_clipping": 1.0,
950
+ "k_head_dim": 64,
951
+ "kernel_size": 4,
952
+ "normalization_function": "rmsnorm",
953
+ "num_f_heads": 132,
954
+ "num_g_heads": 132,
955
+ "num_k_heads": 1,
956
+ "num_q_heads": 1,
957
+ "num_v_heads": 132,
958
+ "num_weight_heads": 132,
959
+ "sequence_mixer_type": "m2rnn",
960
+ "use_residual": true,
961
+ "v_head_dim": 16
962
+ },
963
+ {
964
+ "A_init_max": 16,
965
+ "A_init_min": 0,
966
+ "activation_function": "silu",
967
+ "add_bias": false,
968
+ "dt_init_floor": 0.0001,
969
+ "dt_init_max": 0.1,
970
+ "dt_init_min": 0.001,
971
+ "gradient_clipping": 1.0,
972
+ "k_head_dim": 64,
973
+ "kernel_size": 4,
974
+ "normalization_function": "rmsnorm",
975
+ "num_f_heads": 132,
976
+ "num_g_heads": 132,
977
+ "num_k_heads": 1,
978
+ "num_q_heads": 1,
979
+ "num_v_heads": 132,
980
+ "num_weight_heads": 132,
981
+ "sequence_mixer_type": "m2rnn",
982
+ "use_residual": true,
983
+ "v_head_dim": 16
984
+ },
985
+ {
986
+ "A_init_max": 16,
987
+ "A_init_min": 0,
988
+ "activation_function": "silu",
989
+ "add_bias": false,
990
+ "dt_init_floor": 0.0001,
991
+ "dt_init_max": 0.1,
992
+ "dt_init_min": 0.001,
993
+ "gradient_clipping": 1.0,
994
+ "k_head_dim": 64,
995
+ "kernel_size": 4,
996
+ "normalization_function": "rmsnorm",
997
+ "num_f_heads": 132,
998
+ "num_g_heads": 132,
999
+ "num_k_heads": 1,
1000
+ "num_q_heads": 1,
1001
+ "num_v_heads": 132,
1002
+ "num_weight_heads": 132,
1003
+ "sequence_mixer_type": "m2rnn",
1004
+ "use_residual": true,
1005
+ "v_head_dim": 16
1006
+ },
1007
+ {
1008
+ "A_init_max": 16,
1009
+ "A_init_min": 0,
1010
+ "activation_function": "silu",
1011
+ "add_bias": false,
1012
+ "dt_init_floor": 0.0001,
1013
+ "dt_init_max": 0.1,
1014
+ "dt_init_min": 0.001,
1015
+ "gradient_clipping": 1.0,
1016
+ "k_head_dim": 64,
1017
+ "kernel_size": 4,
1018
+ "normalization_function": "rmsnorm",
1019
+ "num_f_heads": 132,
1020
+ "num_g_heads": 132,
1021
+ "num_k_heads": 1,
1022
+ "num_q_heads": 1,
1023
+ "num_v_heads": 132,
1024
+ "num_weight_heads": 132,
1025
+ "sequence_mixer_type": "m2rnn",
1026
+ "use_residual": true,
1027
+ "v_head_dim": 16
1028
+ },
1029
+ {
1030
+ "A_init_max": 16,
1031
+ "A_init_min": 0,
1032
+ "activation_function": "silu",
1033
+ "add_bias": false,
1034
+ "dt_init_floor": 0.0001,
1035
+ "dt_init_max": 0.1,
1036
+ "dt_init_min": 0.001,
1037
+ "gradient_clipping": 1.0,
1038
+ "k_head_dim": 64,
1039
+ "kernel_size": 4,
1040
+ "normalization_function": "rmsnorm",
1041
+ "num_f_heads": 132,
1042
+ "num_g_heads": 132,
1043
+ "num_k_heads": 1,
1044
+ "num_q_heads": 1,
1045
+ "num_v_heads": 132,
1046
+ "num_weight_heads": 132,
1047
+ "sequence_mixer_type": "m2rnn",
1048
+ "use_residual": true,
1049
+ "v_head_dim": 16
1050
+ },
1051
+ {
1052
+ "A_init_max": 16,
1053
+ "A_init_min": 0,
1054
+ "activation_function": "silu",
1055
+ "add_bias": false,
1056
+ "dt_init_floor": 0.0001,
1057
+ "dt_init_max": 0.1,
1058
+ "dt_init_min": 0.001,
1059
+ "gradient_clipping": 1.0,
1060
+ "k_head_dim": 64,
1061
+ "kernel_size": 4,
1062
+ "normalization_function": "rmsnorm",
1063
+ "num_f_heads": 132,
1064
+ "num_g_heads": 132,
1065
+ "num_k_heads": 1,
1066
+ "num_q_heads": 1,
1067
+ "num_v_heads": 132,
1068
+ "num_weight_heads": 132,
1069
+ "sequence_mixer_type": "m2rnn",
1070
+ "use_residual": true,
1071
+ "v_head_dim": 16
1072
+ },
1073
+ {
1074
+ "A_init_max": 16,
1075
+ "A_init_min": 0,
1076
+ "activation_function": "silu",
1077
+ "add_bias": false,
1078
+ "dt_init_floor": 0.0001,
1079
+ "dt_init_max": 0.1,
1080
+ "dt_init_min": 0.001,
1081
+ "gradient_clipping": 1.0,
1082
+ "k_head_dim": 64,
1083
+ "kernel_size": 4,
1084
+ "normalization_function": "rmsnorm",
1085
+ "num_f_heads": 132,
1086
+ "num_g_heads": 132,
1087
+ "num_k_heads": 1,
1088
+ "num_q_heads": 1,
1089
+ "num_v_heads": 132,
1090
+ "num_weight_heads": 132,
1091
+ "sequence_mixer_type": "m2rnn",
1092
+ "use_residual": true,
1093
+ "v_head_dim": 16
1094
+ },
1095
+ {
1096
+ "A_init_max": 16,
1097
+ "A_init_min": 0,
1098
+ "activation_function": "silu",
1099
+ "add_bias": false,
1100
+ "dt_init_floor": 0.0001,
1101
+ "dt_init_max": 0.1,
1102
+ "dt_init_min": 0.001,
1103
+ "gradient_clipping": 1.0,
1104
+ "k_head_dim": 64,
1105
+ "kernel_size": 4,
1106
+ "normalization_function": "rmsnorm",
1107
+ "num_f_heads": 132,
1108
+ "num_g_heads": 132,
1109
+ "num_k_heads": 1,
1110
+ "num_q_heads": 1,
1111
+ "num_v_heads": 132,
1112
+ "num_weight_heads": 132,
1113
+ "sequence_mixer_type": "m2rnn",
1114
+ "use_residual": true,
1115
+ "v_head_dim": 16
1116
+ },
1117
+ {
1118
+ "A_init_max": 16,
1119
+ "A_init_min": 0,
1120
+ "activation_function": "silu",
1121
+ "add_bias": false,
1122
+ "dt_init_floor": 0.0001,
1123
+ "dt_init_max": 0.1,
1124
+ "dt_init_min": 0.001,
1125
+ "gradient_clipping": 1.0,
1126
+ "k_head_dim": 64,
1127
+ "kernel_size": 4,
1128
+ "normalization_function": "rmsnorm",
1129
+ "num_f_heads": 132,
1130
+ "num_g_heads": 132,
1131
+ "num_k_heads": 1,
1132
+ "num_q_heads": 1,
1133
+ "num_v_heads": 132,
1134
+ "num_weight_heads": 132,
1135
+ "sequence_mixer_type": "m2rnn",
1136
+ "use_residual": true,
1137
+ "v_head_dim": 16
1138
+ },
1139
+ {
1140
+ "A_init_max": 16,
1141
+ "A_init_min": 0,
1142
+ "activation_function": "silu",
1143
+ "add_bias": false,
1144
+ "dt_init_floor": 0.0001,
1145
+ "dt_init_max": 0.1,
1146
+ "dt_init_min": 0.001,
1147
+ "gradient_clipping": 1.0,
1148
+ "k_head_dim": 64,
1149
+ "kernel_size": 4,
1150
+ "normalization_function": "rmsnorm",
1151
+ "num_f_heads": 132,
1152
+ "num_g_heads": 132,
1153
+ "num_k_heads": 1,
1154
+ "num_q_heads": 1,
1155
+ "num_v_heads": 132,
1156
+ "num_weight_heads": 132,
1157
+ "sequence_mixer_type": "m2rnn",
1158
+ "use_residual": true,
1159
+ "v_head_dim": 16
1160
+ },
1161
+ {
1162
+ "A_init_max": 16,
1163
+ "A_init_min": 0,
1164
+ "activation_function": "silu",
1165
+ "add_bias": false,
1166
+ "dt_init_floor": 0.0001,
1167
+ "dt_init_max": 0.1,
1168
+ "dt_init_min": 0.001,
1169
+ "gradient_clipping": 1.0,
1170
+ "k_head_dim": 64,
1171
+ "kernel_size": 4,
1172
+ "normalization_function": "rmsnorm",
1173
+ "num_f_heads": 132,
1174
+ "num_g_heads": 132,
1175
+ "num_k_heads": 1,
1176
+ "num_q_heads": 1,
1177
+ "num_v_heads": 132,
1178
+ "num_weight_heads": 132,
1179
+ "sequence_mixer_type": "m2rnn",
1180
+ "use_residual": true,
1181
+ "v_head_dim": 16
1182
+ },
1183
+ {
1184
+ "A_init_max": 16,
1185
+ "A_init_min": 0,
1186
+ "activation_function": "silu",
1187
+ "add_bias": false,
1188
+ "dt_init_floor": 0.0001,
1189
+ "dt_init_max": 0.1,
1190
+ "dt_init_min": 0.001,
1191
+ "gradient_clipping": 1.0,
1192
+ "k_head_dim": 64,
1193
+ "kernel_size": 4,
1194
+ "normalization_function": "rmsnorm",
1195
+ "num_f_heads": 132,
1196
+ "num_g_heads": 132,
1197
+ "num_k_heads": 1,
1198
+ "num_q_heads": 1,
1199
+ "num_v_heads": 132,
1200
+ "num_weight_heads": 132,
1201
+ "sequence_mixer_type": "m2rnn",
1202
+ "use_residual": true,
1203
+ "v_head_dim": 16
1204
+ },
1205
+ {
1206
+ "A_init_max": 16,
1207
+ "A_init_min": 0,
1208
+ "activation_function": "silu",
1209
+ "add_bias": false,
1210
+ "dt_init_floor": 0.0001,
1211
+ "dt_init_max": 0.1,
1212
+ "dt_init_min": 0.001,
1213
+ "gradient_clipping": 1.0,
1214
+ "k_head_dim": 64,
1215
+ "kernel_size": 4,
1216
+ "normalization_function": "rmsnorm",
1217
+ "num_f_heads": 132,
1218
+ "num_g_heads": 132,
1219
+ "num_k_heads": 1,
1220
+ "num_q_heads": 1,
1221
+ "num_v_heads": 132,
1222
+ "num_weight_heads": 132,
1223
+ "sequence_mixer_type": "m2rnn",
1224
+ "use_residual": true,
1225
+ "v_head_dim": 16
1226
+ },
1227
+ {
1228
+ "A_init_max": 16,
1229
+ "A_init_min": 0,
1230
+ "activation_function": "silu",
1231
+ "add_bias": false,
1232
+ "dt_init_floor": 0.0001,
1233
+ "dt_init_max": 0.1,
1234
+ "dt_init_min": 0.001,
1235
+ "gradient_clipping": 1.0,
1236
+ "k_head_dim": 64,
1237
+ "kernel_size": 4,
1238
+ "normalization_function": "rmsnorm",
1239
+ "num_f_heads": 132,
1240
+ "num_g_heads": 132,
1241
+ "num_k_heads": 1,
1242
+ "num_q_heads": 1,
1243
+ "num_v_heads": 132,
1244
+ "num_weight_heads": 132,
1245
+ "sequence_mixer_type": "m2rnn",
1246
+ "use_residual": true,
1247
+ "v_head_dim": 16
1248
+ },
1249
+ {
1250
+ "A_init_max": 16,
1251
+ "A_init_min": 0,
1252
+ "activation_function": "silu",
1253
+ "add_bias": false,
1254
+ "dt_init_floor": 0.0001,
1255
+ "dt_init_max": 0.1,
1256
+ "dt_init_min": 0.001,
1257
+ "gradient_clipping": 1.0,
1258
+ "k_head_dim": 64,
1259
+ "kernel_size": 4,
1260
+ "normalization_function": "rmsnorm",
1261
+ "num_f_heads": 132,
1262
+ "num_g_heads": 132,
1263
+ "num_k_heads": 1,
1264
+ "num_q_heads": 1,
1265
+ "num_v_heads": 132,
1266
+ "num_weight_heads": 132,
1267
+ "sequence_mixer_type": "m2rnn",
1268
+ "use_residual": true,
1269
+ "v_head_dim": 16
1270
+ },
1271
+ {
1272
+ "A_init_max": 16,
1273
+ "A_init_min": 0,
1274
+ "activation_function": "silu",
1275
+ "add_bias": false,
1276
+ "dt_init_floor": 0.0001,
1277
+ "dt_init_max": 0.1,
1278
+ "dt_init_min": 0.001,
1279
+ "gradient_clipping": 1.0,
1280
+ "k_head_dim": 64,
1281
+ "kernel_size": 4,
1282
+ "normalization_function": "rmsnorm",
1283
+ "num_f_heads": 132,
1284
+ "num_g_heads": 132,
1285
+ "num_k_heads": 1,
1286
+ "num_q_heads": 1,
1287
+ "num_v_heads": 132,
1288
+ "num_weight_heads": 132,
1289
+ "sequence_mixer_type": "m2rnn",
1290
+ "use_residual": true,
1291
+ "v_head_dim": 16
1292
+ },
1293
+ {
1294
+ "A_init_max": 16,
1295
+ "A_init_min": 0,
1296
+ "activation_function": "silu",
1297
+ "add_bias": false,
1298
+ "dt_init_floor": 0.0001,
1299
+ "dt_init_max": 0.1,
1300
+ "dt_init_min": 0.001,
1301
+ "gradient_clipping": 1.0,
1302
+ "k_head_dim": 64,
1303
+ "kernel_size": 4,
1304
+ "normalization_function": "rmsnorm",
1305
+ "num_f_heads": 132,
1306
+ "num_g_heads": 132,
1307
+ "num_k_heads": 1,
1308
+ "num_q_heads": 1,
1309
+ "num_v_heads": 132,
1310
+ "num_weight_heads": 132,
1311
+ "sequence_mixer_type": "m2rnn",
1312
+ "use_residual": true,
1313
+ "v_head_dim": 16
1314
+ },
1315
+ {
1316
+ "A_init_max": 16,
1317
+ "A_init_min": 0,
1318
+ "activation_function": "silu",
1319
+ "add_bias": false,
1320
+ "dt_init_floor": 0.0001,
1321
+ "dt_init_max": 0.1,
1322
+ "dt_init_min": 0.001,
1323
+ "gradient_clipping": 1.0,
1324
+ "k_head_dim": 64,
1325
+ "kernel_size": 4,
1326
+ "normalization_function": "rmsnorm",
1327
+ "num_f_heads": 132,
1328
+ "num_g_heads": 132,
1329
+ "num_k_heads": 1,
1330
+ "num_q_heads": 1,
1331
+ "num_v_heads": 132,
1332
+ "num_weight_heads": 132,
1333
+ "sequence_mixer_type": "m2rnn",
1334
+ "use_residual": true,
1335
+ "v_head_dim": 16
1336
+ },
1337
+ {
1338
+ "A_init_max": 16,
1339
+ "A_init_min": 0,
1340
+ "activation_function": "silu",
1341
+ "add_bias": false,
1342
+ "dt_init_floor": 0.0001,
1343
+ "dt_init_max": 0.1,
1344
+ "dt_init_min": 0.001,
1345
+ "gradient_clipping": 1.0,
1346
+ "k_head_dim": 64,
1347
+ "kernel_size": 4,
1348
+ "normalization_function": "rmsnorm",
1349
+ "num_f_heads": 132,
1350
+ "num_g_heads": 132,
1351
+ "num_k_heads": 1,
1352
+ "num_q_heads": 1,
1353
+ "num_v_heads": 132,
1354
+ "num_weight_heads": 132,
1355
+ "sequence_mixer_type": "m2rnn",
1356
+ "use_residual": true,
1357
+ "v_head_dim": 16
1358
+ },
1359
+ {
1360
+ "A_init_max": 16,
1361
+ "A_init_min": 0,
1362
+ "activation_function": "silu",
1363
+ "add_bias": false,
1364
+ "dt_init_floor": 0.0001,
1365
+ "dt_init_max": 0.1,
1366
+ "dt_init_min": 0.001,
1367
+ "gradient_clipping": 1.0,
1368
+ "k_head_dim": 64,
1369
+ "kernel_size": 4,
1370
+ "normalization_function": "rmsnorm",
1371
+ "num_f_heads": 132,
1372
+ "num_g_heads": 132,
1373
+ "num_k_heads": 1,
1374
+ "num_q_heads": 1,
1375
+ "num_v_heads": 132,
1376
+ "num_weight_heads": 132,
1377
+ "sequence_mixer_type": "m2rnn",
1378
+ "use_residual": true,
1379
+ "v_head_dim": 16
1380
+ },
1381
+ {
1382
+ "A_init_max": 16,
1383
+ "A_init_min": 0,
1384
+ "activation_function": "silu",
1385
+ "add_bias": false,
1386
+ "dt_init_floor": 0.0001,
1387
+ "dt_init_max": 0.1,
1388
+ "dt_init_min": 0.001,
1389
+ "gradient_clipping": 1.0,
1390
+ "k_head_dim": 64,
1391
+ "kernel_size": 4,
1392
+ "normalization_function": "rmsnorm",
1393
+ "num_f_heads": 132,
1394
+ "num_g_heads": 132,
1395
+ "num_k_heads": 1,
1396
+ "num_q_heads": 1,
1397
+ "num_v_heads": 132,
1398
+ "num_weight_heads": 132,
1399
+ "sequence_mixer_type": "m2rnn",
1400
+ "use_residual": true,
1401
+ "v_head_dim": 16
1402
+ },
1403
+ {
1404
+ "A_init_max": 16,
1405
+ "A_init_min": 0,
1406
+ "activation_function": "silu",
1407
+ "add_bias": false,
1408
+ "dt_init_floor": 0.0001,
1409
+ "dt_init_max": 0.1,
1410
+ "dt_init_min": 0.001,
1411
+ "gradient_clipping": 1.0,
1412
+ "k_head_dim": 64,
1413
+ "kernel_size": 4,
1414
+ "normalization_function": "rmsnorm",
1415
+ "num_f_heads": 132,
1416
+ "num_g_heads": 132,
1417
+ "num_k_heads": 1,
1418
+ "num_q_heads": 1,
1419
+ "num_v_heads": 132,
1420
+ "num_weight_heads": 132,
1421
+ "sequence_mixer_type": "m2rnn",
1422
+ "use_residual": true,
1423
+ "v_head_dim": 16
1424
+ }
1425
+ ],
1426
+ "transformers_version": "4.57.3",
1427
+ "use_cache": true,
1428
+ "vocab_size": 100352
1429
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d4aa0dd6c7e3aa5da3161dec52f242457d9cfcd9b392f38b9fc2d1a85dd0c2d
3
+ size 4988790776
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad84b47724e66442d5bdcb5d78f094415e912fb37cb9cdf1a629604fe56e3ea3
3
+ size 4859821056
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863c7cb01918445986a8e4c61e905cfaaa073a87293ea97d8cbcabcce107c066
3
+ size 3747097312
model.safetensors.index.json ADDED
@@ -0,0 +1,609 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 13595637376
4
+ },
5
+ "weight_map": {
6
+ "transformer.wte.weight": "model-00001-of-00003.safetensors",
7
+ "transformer.h.7.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
8
+ "transformer.h.8.ln_1.weight": "model-00001-of-00003.safetensors",
9
+ "transformer.h.8.sequence_mixer.D": "model-00001-of-00003.safetensors",
10
+ "transformer.h.8.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
11
+ "transformer.h.8.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
12
+ "transformer.h.8.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
13
+ "transformer.h.13.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
14
+ "transformer.h.13.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
15
+ "transformer.h.13.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
16
+ "transformer.h.13.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
17
+ "transformer.h.13.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
18
+ "transformer.h.13.ln_2.weight": "model-00001-of-00003.safetensors",
19
+ "transformer.h.13.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
20
+ "transformer.h.13.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
21
+ "transformer.h.13.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
22
+ "transformer.h.15.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
23
+ "transformer.h.16.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
24
+ "transformer.h.16.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
25
+ "transformer.h.16.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
26
+ "transformer.h.16.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
27
+ "transformer.h.16.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
28
+ "transformer.h.16.ln_2.weight": "model-00001-of-00003.safetensors",
29
+ "transformer.h.16.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
30
+ "transformer.h.16.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
31
+ "transformer.h.21.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
32
+ "transformer.h.21.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
33
+ "transformer.h.21.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
34
+ "transformer.h.21.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
35
+ "transformer.h.21.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
36
+ "transformer.h.21.ln_2.weight": "model-00001-of-00003.safetensors",
37
+ "transformer.h.21.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
38
+ "transformer.h.21.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
39
+ "transformer.h.26.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
40
+ "transformer.h.26.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
41
+ "transformer.h.26.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
42
+ "transformer.h.26.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
43
+ "transformer.h.26.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
44
+ "transformer.h.26.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
45
+ "transformer.h.28.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
46
+ "transformer.h.29.ln_1.weight": "model-00001-of-00003.safetensors",
47
+ "transformer.h.29.sequence_mixer.D": "model-00001-of-00003.safetensors",
48
+ "transformer.h.29.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
49
+ "transformer.h.29.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
50
+ "transformer.h.29.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
51
+ "transformer.h.29.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
52
+ "transformer.h.31.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
53
+ "transformer.h.32.ln_1.weight": "model-00001-of-00003.safetensors",
54
+ "transformer.h.32.sequence_mixer.D": "model-00001-of-00003.safetensors",
55
+ "transformer.h.32.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
56
+ "transformer.h.32.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
57
+ "transformer.h.32.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
58
+ "transformer.h.32.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
59
+ "transformer.h.34.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
60
+ "transformer.h.35.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
61
+ "transformer.h.35.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
62
+ "transformer.h.35.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
63
+ "transformer.h.35.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
64
+ "transformer.h.35.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
65
+ "transformer.h.35.ln_2.weight": "model-00001-of-00003.safetensors",
66
+ "transformer.h.35.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
67
+ "transformer.h.35.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
68
+ "transformer.h.0.ln_1.weight": "model-00001-of-00003.safetensors",
69
+ "transformer.h.0.ln_2.weight": "model-00001-of-00003.safetensors",
70
+ "transformer.h.0.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
71
+ "transformer.h.1.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
72
+ "transformer.h.1.ln_2.weight": "model-00001-of-00003.safetensors",
73
+ "transformer.h.1.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
74
+ "transformer.h.1.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
75
+ "transformer.h.1.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
76
+ "transformer.h.2.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
77
+ "transformer.h.2.ln_2.weight": "model-00001-of-00003.safetensors",
78
+ "transformer.h.2.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
79
+ "transformer.h.2.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
80
+ "transformer.h.5.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
81
+ "transformer.h.8.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
82
+ "transformer.h.8.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
83
+ "transformer.h.8.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
84
+ "transformer.h.8.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
85
+ "transformer.h.8.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
86
+ "transformer.h.8.ln_2.weight": "model-00001-of-00003.safetensors",
87
+ "transformer.h.8.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
88
+ "transformer.h.8.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
89
+ "transformer.h.8.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
90
+ "transformer.h.9.ln_1.weight": "model-00001-of-00003.safetensors",
91
+ "transformer.h.9.sequence_mixer.D": "model-00001-of-00003.safetensors",
92
+ "transformer.h.9.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
93
+ "transformer.h.9.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
94
+ "transformer.h.9.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
95
+ "transformer.h.9.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
96
+ "transformer.h.11.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
97
+ "transformer.h.12.ln_1.weight": "model-00001-of-00003.safetensors",
98
+ "transformer.h.12.sequence_mixer.D": "model-00001-of-00003.safetensors",
99
+ "transformer.h.12.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
100
+ "transformer.h.12.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
101
+ "transformer.h.12.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
102
+ "transformer.h.12.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
103
+ "transformer.h.14.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
104
+ "transformer.h.15.ln_1.weight": "model-00001-of-00003.safetensors",
105
+ "transformer.h.15.sequence_mixer.D": "model-00001-of-00003.safetensors",
106
+ "transformer.h.15.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
107
+ "transformer.h.15.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
108
+ "transformer.h.15.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
109
+ "transformer.h.15.ln_2.weight": "model-00001-of-00003.safetensors",
110
+ "transformer.h.15.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
111
+ "transformer.h.15.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
112
+ "transformer.h.20.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
113
+ "transformer.h.20.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
114
+ "transformer.h.20.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
115
+ "transformer.h.20.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
116
+ "transformer.h.20.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
117
+ "transformer.h.20.ln_2.weight": "model-00001-of-00003.safetensors",
118
+ "transformer.h.20.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
119
+ "transformer.h.20.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
120
+ "transformer.h.25.ln_1.weight": "model-00001-of-00003.safetensors",
121
+ "transformer.h.25.sequence_mixer.D": "model-00001-of-00003.safetensors",
122
+ "transformer.h.25.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
123
+ "transformer.h.25.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
124
+ "transformer.h.25.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
125
+ "transformer.h.25.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
126
+ "transformer.h.25.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
127
+ "transformer.h.25.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
128
+ "transformer.h.25.ln_2.weight": "model-00001-of-00003.safetensors",
129
+ "transformer.h.25.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
130
+ "transformer.h.25.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
131
+ "transformer.h.30.ln_1.weight": "model-00001-of-00003.safetensors",
132
+ "transformer.h.30.sequence_mixer.D": "model-00001-of-00003.safetensors",
133
+ "transformer.h.30.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
134
+ "transformer.h.30.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
135
+ "transformer.h.30.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
136
+ "transformer.h.30.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
137
+ "transformer.h.32.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
138
+ "transformer.h.33.ln_1.weight": "model-00001-of-00003.safetensors",
139
+ "transformer.h.33.sequence_mixer.D": "model-00001-of-00003.safetensors",
140
+ "transformer.h.33.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
141
+ "transformer.h.33.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
142
+ "transformer.h.33.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
143
+ "transformer.h.33.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
144
+ "transformer.h.35.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
145
+ "transformer.h.36.ln_1.weight": "model-00001-of-00003.safetensors",
146
+ "transformer.h.36.sequence_mixer.D": "model-00001-of-00003.safetensors",
147
+ "transformer.h.36.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
148
+ "transformer.h.36.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
149
+ "transformer.h.36.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
150
+ "transformer.h.0.sequence_mixer.D": "model-00001-of-00003.safetensors",
151
+ "transformer.h.0.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
152
+ "transformer.h.1.ln_1.weight": "model-00001-of-00003.safetensors",
153
+ "transformer.h.1.sequence_mixer.D": "model-00001-of-00003.safetensors",
154
+ "transformer.h.1.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
155
+ "transformer.h.1.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
156
+ "transformer.h.2.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
157
+ "transformer.h.2.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
158
+ "transformer.h.2.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
159
+ "transformer.h.2.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
160
+ "transformer.h.2.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
161
+ "transformer.h.2.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
162
+ "transformer.h.4.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
163
+ "transformer.h.4.ln_2.weight": "model-00001-of-00003.safetensors",
164
+ "transformer.h.4.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
165
+ "transformer.h.4.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
166
+ "transformer.h.8.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
167
+ "transformer.h.11.ln_1.weight": "model-00001-of-00003.safetensors",
168
+ "transformer.h.11.sequence_mixer.D": "model-00001-of-00003.safetensors",
169
+ "transformer.h.11.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
170
+ "transformer.h.11.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
171
+ "transformer.h.11.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
172
+ "transformer.h.11.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
173
+ "transformer.h.14.ln_1.weight": "model-00001-of-00003.safetensors",
174
+ "transformer.h.14.sequence_mixer.D": "model-00001-of-00003.safetensors",
175
+ "transformer.h.14.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
176
+ "transformer.h.14.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
177
+ "transformer.h.14.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
178
+ "transformer.h.14.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
179
+ "transformer.h.17.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
180
+ "transformer.h.17.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
181
+ "transformer.h.17.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
182
+ "transformer.h.17.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
183
+ "transformer.h.17.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
184
+ "transformer.h.17.ln_2.weight": "model-00001-of-00003.safetensors",
185
+ "transformer.h.17.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
186
+ "transformer.h.17.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
187
+ "transformer.h.21.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
188
+ "transformer.h.22.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
189
+ "transformer.h.22.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
190
+ "transformer.h.22.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
191
+ "transformer.h.22.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
192
+ "transformer.h.22.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
193
+ "transformer.h.22.ln_2.weight": "model-00001-of-00003.safetensors",
194
+ "transformer.h.22.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
195
+ "transformer.h.22.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
196
+ "transformer.h.27.ln_1.weight": "model-00001-of-00003.safetensors",
197
+ "transformer.h.27.sequence_mixer.D": "model-00001-of-00003.safetensors",
198
+ "transformer.h.27.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
199
+ "transformer.h.27.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
200
+ "transformer.h.27.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
201
+ "transformer.h.27.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
202
+ "transformer.h.29.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
203
+ "transformer.h.30.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
204
+ "transformer.h.30.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
205
+ "transformer.h.30.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
206
+ "transformer.h.30.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
207
+ "transformer.h.30.sequence_mixer.g_norm.weight": "model-00001-of-00003.safetensors",
208
+ "transformer.h.30.ln_2.weight": "model-00001-of-00003.safetensors",
209
+ "transformer.h.30.mlp_block.gate.weight": "model-00001-of-00003.safetensors",
210
+ "transformer.h.30.mlp_block.c_fc.weight": "model-00001-of-00003.safetensors",
211
+ "transformer.h.35.ln_1.weight": "model-00001-of-00003.safetensors",
212
+ "transformer.h.35.sequence_mixer.D": "model-00001-of-00003.safetensors",
213
+ "transformer.h.35.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
214
+ "transformer.h.35.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
215
+ "transformer.h.35.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
216
+ "transformer.h.35.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
217
+ "transformer.h.37.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
218
+ "transformer.h.38.ln_1.weight": "model-00001-of-00003.safetensors",
219
+ "transformer.h.38.sequence_mixer.D": "model-00001-of-00003.safetensors",
220
+ "transformer.h.38.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
221
+ "transformer.h.38.sequence_mixer.input_projection.weight": "model-00001-of-00003.safetensors",
222
+ "transformer.h.38.mlp_block.c_fc_shared.weight": "model-00001-of-00003.safetensors",
223
+ "transformer.h.38.mlp_block.c_proj.weight": "model-00001-of-00003.safetensors",
224
+ "transformer.h.0.sequence_mixer.state_weight": "model-00001-of-00003.safetensors",
225
+ "transformer.h.0.mlp_block.c_proj_shared.weight": "model-00001-of-00003.safetensors",
226
+ "transformer.h.1.sequence_mixer.decay_gate.A_log": "model-00001-of-00003.safetensors",
227
+ "transformer.h.1.sequence_mixer.decay_gate.dt_bias": "model-00001-of-00003.safetensors",
228
+ "transformer.h.1.sequence_mixer.conv1d.weight": "model-00001-of-00003.safetensors",
229
+ "transformer.h.1.sequence_mixer.output_projection.weight": "model-00001-of-00003.safetensors",
230
+ "transformer.h.1.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
231
+ "transformer.h.3.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
232
+ "transformer.h.4.ln_1.weight": "model-00002-of-00003.safetensors",
233
+ "transformer.h.4.sequence_mixer.D": "model-00002-of-00003.safetensors",
234
+ "transformer.h.4.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
235
+ "transformer.h.4.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
236
+ "transformer.h.4.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
237
+ "transformer.h.4.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
238
+ "transformer.h.4.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
239
+ "transformer.h.4.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
240
+ "transformer.h.4.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
241
+ "transformer.h.4.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
242
+ "transformer.h.6.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
243
+ "transformer.h.7.ln_1.weight": "model-00002-of-00003.safetensors",
244
+ "transformer.h.7.sequence_mixer.D": "model-00002-of-00003.safetensors",
245
+ "transformer.h.7.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
246
+ "transformer.h.7.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
247
+ "transformer.h.7.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
248
+ "transformer.h.7.ln_2.weight": "model-00002-of-00003.safetensors",
249
+ "transformer.h.7.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
250
+ "transformer.h.7.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
251
+ "transformer.h.12.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
252
+ "transformer.h.12.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
253
+ "transformer.h.12.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
254
+ "transformer.h.12.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
255
+ "transformer.h.12.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
256
+ "transformer.h.12.ln_2.weight": "model-00002-of-00003.safetensors",
257
+ "transformer.h.12.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
258
+ "transformer.h.12.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
259
+ "transformer.h.16.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
260
+ "transformer.h.17.ln_1.weight": "model-00002-of-00003.safetensors",
261
+ "transformer.h.17.sequence_mixer.D": "model-00002-of-00003.safetensors",
262
+ "transformer.h.17.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
263
+ "transformer.h.17.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
264
+ "transformer.h.17.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
265
+ "transformer.h.17.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
266
+ "transformer.h.19.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
267
+ "transformer.h.20.ln_1.weight": "model-00002-of-00003.safetensors",
268
+ "transformer.h.20.sequence_mixer.D": "model-00002-of-00003.safetensors",
269
+ "transformer.h.20.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
270
+ "transformer.h.20.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
271
+ "transformer.h.20.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
272
+ "transformer.h.20.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
273
+ "transformer.h.22.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
274
+ "transformer.h.23.ln_1.weight": "model-00002-of-00003.safetensors",
275
+ "transformer.h.23.sequence_mixer.D": "model-00002-of-00003.safetensors",
276
+ "transformer.h.23.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
277
+ "transformer.h.23.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
278
+ "transformer.h.23.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
279
+ "transformer.h.23.ln_2.weight": "model-00002-of-00003.safetensors",
280
+ "transformer.h.23.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
281
+ "transformer.h.23.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
282
+ "transformer.h.28.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
283
+ "transformer.h.28.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
284
+ "transformer.h.28.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
285
+ "transformer.h.28.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
286
+ "transformer.h.28.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
287
+ "transformer.h.28.ln_2.weight": "model-00002-of-00003.safetensors",
288
+ "transformer.h.28.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
289
+ "transformer.h.28.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
290
+ "transformer.h.33.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
291
+ "transformer.h.33.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
292
+ "transformer.h.33.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
293
+ "transformer.h.33.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
294
+ "transformer.h.33.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
295
+ "transformer.h.33.ln_2.weight": "model-00002-of-00003.safetensors",
296
+ "transformer.h.33.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
297
+ "transformer.h.33.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
298
+ "transformer.h.38.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
299
+ "transformer.h.38.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
300
+ "transformer.h.38.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
301
+ "transformer.h.38.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
302
+ "transformer.h.38.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
303
+ "transformer.h.38.ln_2.weight": "model-00002-of-00003.safetensors",
304
+ "transformer.h.38.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
305
+ "transformer.h.38.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
306
+ "transformer.h.0.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
307
+ "transformer.h.2.ln_1.weight": "model-00002-of-00003.safetensors",
308
+ "transformer.h.2.sequence_mixer.D": "model-00002-of-00003.safetensors",
309
+ "transformer.h.2.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
310
+ "transformer.h.2.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
311
+ "transformer.h.2.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
312
+ "transformer.h.3.ln_1.weight": "model-00002-of-00003.safetensors",
313
+ "transformer.h.3.sequence_mixer.D": "model-00002-of-00003.safetensors",
314
+ "transformer.h.3.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
315
+ "transformer.h.3.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
316
+ "transformer.h.3.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
317
+ "transformer.h.3.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
318
+ "transformer.h.3.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
319
+ "transformer.h.3.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
320
+ "transformer.h.3.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
321
+ "transformer.h.3.ln_2.weight": "model-00002-of-00003.safetensors",
322
+ "transformer.h.3.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
323
+ "transformer.h.3.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
324
+ "transformer.h.7.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
325
+ "transformer.h.7.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
326
+ "transformer.h.7.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
327
+ "transformer.h.7.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
328
+ "transformer.h.7.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
329
+ "transformer.h.7.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
330
+ "transformer.h.9.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
331
+ "transformer.h.10.ln_1.weight": "model-00002-of-00003.safetensors",
332
+ "transformer.h.10.sequence_mixer.D": "model-00002-of-00003.safetensors",
333
+ "transformer.h.10.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
334
+ "transformer.h.10.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
335
+ "transformer.h.10.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
336
+ "transformer.h.10.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
337
+ "transformer.h.10.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
338
+ "transformer.h.10.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
339
+ "transformer.h.10.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
340
+ "transformer.h.10.ln_2.weight": "model-00002-of-00003.safetensors",
341
+ "transformer.h.10.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
342
+ "transformer.h.10.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
343
+ "transformer.h.15.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
344
+ "transformer.h.15.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
345
+ "transformer.h.15.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
346
+ "transformer.h.15.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
347
+ "transformer.h.15.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
348
+ "transformer.h.15.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
349
+ "transformer.h.17.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
350
+ "transformer.h.18.ln_1.weight": "model-00002-of-00003.safetensors",
351
+ "transformer.h.18.sequence_mixer.D": "model-00002-of-00003.safetensors",
352
+ "transformer.h.18.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
353
+ "transformer.h.18.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
354
+ "transformer.h.18.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
355
+ "transformer.h.18.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
356
+ "transformer.h.18.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
357
+ "transformer.h.18.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
358
+ "transformer.h.18.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
359
+ "transformer.h.18.ln_2.weight": "model-00002-of-00003.safetensors",
360
+ "transformer.h.18.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
361
+ "transformer.h.18.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
362
+ "transformer.h.23.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
363
+ "transformer.h.23.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
364
+ "transformer.h.23.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
365
+ "transformer.h.23.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
366
+ "transformer.h.23.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
367
+ "transformer.h.23.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
368
+ "transformer.h.25.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
369
+ "transformer.h.26.ln_1.weight": "model-00002-of-00003.safetensors",
370
+ "transformer.h.26.sequence_mixer.D": "model-00002-of-00003.safetensors",
371
+ "transformer.h.26.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
372
+ "transformer.h.26.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
373
+ "transformer.h.26.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
374
+ "transformer.h.26.ln_2.weight": "model-00002-of-00003.safetensors",
375
+ "transformer.h.26.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
376
+ "transformer.h.26.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
377
+ "transformer.h.31.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
378
+ "transformer.h.31.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
379
+ "transformer.h.31.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
380
+ "transformer.h.31.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
381
+ "transformer.h.31.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
382
+ "transformer.h.31.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
383
+ "transformer.h.33.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
384
+ "transformer.h.34.ln_1.weight": "model-00002-of-00003.safetensors",
385
+ "transformer.h.34.sequence_mixer.D": "model-00002-of-00003.safetensors",
386
+ "transformer.h.34.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
387
+ "transformer.h.34.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
388
+ "transformer.h.34.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
389
+ "transformer.h.34.ln_2.weight": "model-00002-of-00003.safetensors",
390
+ "transformer.h.34.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
391
+ "transformer.h.34.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
392
+ "transformer.h.39.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
393
+ "transformer.h.39.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
394
+ "transformer.h.39.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
395
+ "transformer.h.39.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
396
+ "transformer.h.39.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
397
+ "transformer.h.0.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
398
+ "transformer.h.0.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
399
+ "transformer.h.1.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
400
+ "transformer.h.5.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
401
+ "transformer.h.5.ln_2.weight": "model-00002-of-00003.safetensors",
402
+ "transformer.h.5.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
403
+ "transformer.h.5.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
404
+ "transformer.h.10.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
405
+ "transformer.h.10.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
406
+ "transformer.h.12.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
407
+ "transformer.h.13.ln_1.weight": "model-00002-of-00003.safetensors",
408
+ "transformer.h.13.sequence_mixer.D": "model-00002-of-00003.safetensors",
409
+ "transformer.h.13.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
410
+ "transformer.h.13.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
411
+ "transformer.h.13.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
412
+ "transformer.h.18.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
413
+ "transformer.h.18.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
414
+ "transformer.h.20.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
415
+ "transformer.h.21.ln_1.weight": "model-00002-of-00003.safetensors",
416
+ "transformer.h.21.sequence_mixer.D": "model-00002-of-00003.safetensors",
417
+ "transformer.h.21.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
418
+ "transformer.h.21.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
419
+ "transformer.h.21.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
420
+ "transformer.h.21.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
421
+ "transformer.h.23.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
422
+ "transformer.h.24.ln_1.weight": "model-00002-of-00003.safetensors",
423
+ "transformer.h.24.sequence_mixer.D": "model-00002-of-00003.safetensors",
424
+ "transformer.h.24.sequence_mixer.state_weight": "model-00002-of-00003.safetensors",
425
+ "transformer.h.24.sequence_mixer.input_projection.weight": "model-00002-of-00003.safetensors",
426
+ "transformer.h.24.mlp_block.c_fc_shared.weight": "model-00002-of-00003.safetensors",
427
+ "transformer.h.24.mlp_block.c_proj.weight": "model-00002-of-00003.safetensors",
428
+ "transformer.h.26.mlp_block.c_proj_shared.weight": "model-00002-of-00003.safetensors",
429
+ "transformer.h.27.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
430
+ "transformer.h.27.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
431
+ "transformer.h.27.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
432
+ "transformer.h.27.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
433
+ "transformer.h.27.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
434
+ "transformer.h.27.ln_2.weight": "model-00002-of-00003.safetensors",
435
+ "transformer.h.27.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
436
+ "transformer.h.27.mlp_block.c_fc.weight": "model-00002-of-00003.safetensors",
437
+ "transformer.h.32.sequence_mixer.decay_gate.A_log": "model-00002-of-00003.safetensors",
438
+ "transformer.h.32.sequence_mixer.decay_gate.dt_bias": "model-00002-of-00003.safetensors",
439
+ "transformer.h.32.sequence_mixer.conv1d.weight": "model-00002-of-00003.safetensors",
440
+ "transformer.h.32.sequence_mixer.output_projection.weight": "model-00002-of-00003.safetensors",
441
+ "transformer.h.32.sequence_mixer.g_norm.weight": "model-00002-of-00003.safetensors",
442
+ "transformer.h.32.ln_2.weight": "model-00002-of-00003.safetensors",
443
+ "transformer.h.32.mlp_block.gate.weight": "model-00002-of-00003.safetensors",
444
+ "transformer.h.32.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
445
+ "transformer.h.37.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
446
+ "transformer.h.37.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
447
+ "transformer.h.37.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
448
+ "transformer.h.37.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
449
+ "transformer.h.37.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
450
+ "transformer.h.37.ln_2.weight": "model-00003-of-00003.safetensors",
451
+ "transformer.h.37.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
452
+ "transformer.h.37.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
453
+ "transformer.h.0.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
454
+ "transformer.h.0.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
455
+ "transformer.h.0.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
456
+ "transformer.h.4.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
457
+ "transformer.h.5.ln_1.weight": "model-00003-of-00003.safetensors",
458
+ "transformer.h.5.sequence_mixer.D": "model-00003-of-00003.safetensors",
459
+ "transformer.h.5.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
460
+ "transformer.h.5.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
461
+ "transformer.h.5.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
462
+ "transformer.h.6.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
463
+ "transformer.h.6.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
464
+ "transformer.h.6.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
465
+ "transformer.h.6.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
466
+ "transformer.h.6.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
467
+ "transformer.h.6.ln_2.weight": "model-00003-of-00003.safetensors",
468
+ "transformer.h.6.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
469
+ "transformer.h.6.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
470
+ "transformer.h.10.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
471
+ "transformer.h.11.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
472
+ "transformer.h.11.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
473
+ "transformer.h.11.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
474
+ "transformer.h.11.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
475
+ "transformer.h.11.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
476
+ "transformer.h.11.ln_2.weight": "model-00003-of-00003.safetensors",
477
+ "transformer.h.11.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
478
+ "transformer.h.11.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
479
+ "transformer.h.16.ln_1.weight": "model-00003-of-00003.safetensors",
480
+ "transformer.h.16.sequence_mixer.D": "model-00003-of-00003.safetensors",
481
+ "transformer.h.16.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
482
+ "transformer.h.16.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
483
+ "transformer.h.16.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
484
+ "transformer.h.16.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
485
+ "transformer.h.19.ln_1.weight": "model-00003-of-00003.safetensors",
486
+ "transformer.h.19.sequence_mixer.D": "model-00003-of-00003.safetensors",
487
+ "transformer.h.19.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
488
+ "transformer.h.19.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
489
+ "transformer.h.19.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
490
+ "transformer.h.19.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
491
+ "transformer.h.22.ln_1.weight": "model-00003-of-00003.safetensors",
492
+ "transformer.h.22.sequence_mixer.D": "model-00003-of-00003.safetensors",
493
+ "transformer.h.22.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
494
+ "transformer.h.22.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
495
+ "transformer.h.22.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
496
+ "transformer.h.22.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
497
+ "transformer.h.24.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
498
+ "transformer.h.25.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
499
+ "transformer.h.25.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
500
+ "transformer.h.25.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
501
+ "transformer.h.27.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
502
+ "transformer.h.28.ln_1.weight": "model-00003-of-00003.safetensors",
503
+ "transformer.h.28.sequence_mixer.D": "model-00003-of-00003.safetensors",
504
+ "transformer.h.28.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
505
+ "transformer.h.28.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
506
+ "transformer.h.28.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
507
+ "transformer.h.28.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
508
+ "transformer.h.30.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
509
+ "transformer.h.31.ln_1.weight": "model-00003-of-00003.safetensors",
510
+ "transformer.h.31.sequence_mixer.D": "model-00003-of-00003.safetensors",
511
+ "transformer.h.31.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
512
+ "transformer.h.31.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
513
+ "transformer.h.31.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
514
+ "transformer.h.31.ln_2.weight": "model-00003-of-00003.safetensors",
515
+ "transformer.h.31.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
516
+ "transformer.h.31.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
517
+ "transformer.h.36.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
518
+ "transformer.h.36.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
519
+ "transformer.h.36.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
520
+ "transformer.h.36.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
521
+ "transformer.h.36.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
522
+ "transformer.h.36.ln_2.weight": "model-00003-of-00003.safetensors",
523
+ "transformer.h.36.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
524
+ "transformer.h.36.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
525
+ "transformer.h.36.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
526
+ "transformer.h.38.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
527
+ "transformer.h.39.ln_1.weight": "model-00003-of-00003.safetensors",
528
+ "transformer.h.39.sequence_mixer.D": "model-00003-of-00003.safetensors",
529
+ "transformer.h.39.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
530
+ "transformer.h.39.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
531
+ "transformer.h.39.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
532
+ "transformer.h.39.ln_2.weight": "model-00003-of-00003.safetensors",
533
+ "transformer.h.39.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
534
+ "transformer.h.39.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
535
+ "transformer.h.39.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
536
+ "transformer.h.0.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
537
+ "transformer.h.0.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
538
+ "transformer.h.3.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
539
+ "transformer.h.3.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
540
+ "transformer.h.5.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
541
+ "transformer.h.5.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
542
+ "transformer.h.5.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
543
+ "transformer.h.5.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
544
+ "transformer.h.5.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
545
+ "transformer.h.6.ln_1.weight": "model-00003-of-00003.safetensors",
546
+ "transformer.h.6.sequence_mixer.D": "model-00003-of-00003.safetensors",
547
+ "transformer.h.6.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
548
+ "transformer.h.6.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
549
+ "transformer.h.6.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
550
+ "transformer.h.6.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
551
+ "transformer.h.9.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
552
+ "transformer.h.9.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
553
+ "transformer.h.9.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
554
+ "transformer.h.9.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
555
+ "transformer.h.9.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
556
+ "transformer.h.9.ln_2.weight": "model-00003-of-00003.safetensors",
557
+ "transformer.h.9.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
558
+ "transformer.h.9.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
559
+ "transformer.h.13.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
560
+ "transformer.h.14.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
561
+ "transformer.h.14.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
562
+ "transformer.h.14.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
563
+ "transformer.h.14.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
564
+ "transformer.h.14.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
565
+ "transformer.h.14.ln_2.weight": "model-00003-of-00003.safetensors",
566
+ "transformer.h.14.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
567
+ "transformer.h.14.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
568
+ "transformer.h.18.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
569
+ "transformer.h.19.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
570
+ "transformer.h.19.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
571
+ "transformer.h.19.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
572
+ "transformer.h.19.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
573
+ "transformer.h.19.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
574
+ "transformer.h.19.ln_2.weight": "model-00003-of-00003.safetensors",
575
+ "transformer.h.19.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
576
+ "transformer.h.19.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
577
+ "transformer.h.24.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
578
+ "transformer.h.24.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
579
+ "transformer.h.24.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
580
+ "transformer.h.24.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
581
+ "transformer.h.24.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
582
+ "transformer.h.24.ln_2.weight": "model-00003-of-00003.safetensors",
583
+ "transformer.h.24.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
584
+ "transformer.h.24.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
585
+ "transformer.h.29.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
586
+ "transformer.h.29.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
587
+ "transformer.h.29.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
588
+ "transformer.h.29.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
589
+ "transformer.h.29.sequence_mixer.g_norm.weight": "model-00003-of-00003.safetensors",
590
+ "transformer.h.29.ln_2.weight": "model-00003-of-00003.safetensors",
591
+ "transformer.h.29.mlp_block.gate.weight": "model-00003-of-00003.safetensors",
592
+ "transformer.h.29.mlp_block.c_fc.weight": "model-00003-of-00003.safetensors",
593
+ "transformer.h.34.sequence_mixer.decay_gate.A_log": "model-00003-of-00003.safetensors",
594
+ "transformer.h.34.sequence_mixer.decay_gate.dt_bias": "model-00003-of-00003.safetensors",
595
+ "transformer.h.34.sequence_mixer.conv1d.weight": "model-00003-of-00003.safetensors",
596
+ "transformer.h.34.sequence_mixer.output_projection.weight": "model-00003-of-00003.safetensors",
597
+ "transformer.h.34.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
598
+ "transformer.h.34.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
599
+ "transformer.h.36.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
600
+ "transformer.h.37.ln_1.weight": "model-00003-of-00003.safetensors",
601
+ "transformer.h.37.sequence_mixer.D": "model-00003-of-00003.safetensors",
602
+ "transformer.h.37.sequence_mixer.state_weight": "model-00003-of-00003.safetensors",
603
+ "transformer.h.37.sequence_mixer.input_projection.weight": "model-00003-of-00003.safetensors",
604
+ "transformer.h.37.mlp_block.c_fc_shared.weight": "model-00003-of-00003.safetensors",
605
+ "transformer.h.37.mlp_block.c_proj.weight": "model-00003-of-00003.safetensors",
606
+ "transformer.h.39.mlp_block.c_proj_shared.weight": "model-00003-of-00003.safetensors",
607
+ "transformer.ln_f.weight": "model-00003-of-00003.safetensors"
608
+ }
609
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|end_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|end_of_text|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|unk|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,784 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "100256": {
6
+ "content": "<|pad|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "100257": {
14
+ "content": "<|end_of_text|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "100258": {
22
+ "content": "<|fim_prefix|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "100259": {
30
+ "content": "<|fim_middle|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "100260": {
38
+ "content": "<|fim_suffix|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "100261": {
46
+ "content": "<|fim_pad|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "100262": {
54
+ "content": "<|filename|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "100263": {
62
+ "content": "<|reponame|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "100264": {
70
+ "content": "<|start_of_role|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "100265": {
78
+ "content": "<|end_of_role|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "100266": {
86
+ "content": "<|tool_call|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "100267": {
94
+ "content": "<|start_of_plugin|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "100268": {
102
+ "content": "<|end_of_plugin|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "100269": {
110
+ "content": "<|unk|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "100270": {
118
+ "content": "<|unused_1|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "100271": {
126
+ "content": "<|unused_2|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "100272": {
134
+ "content": "<|unused_3|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "100273": {
142
+ "content": "<|unused_4|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "100274": {
150
+ "content": "<|unused_5|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "100275": {
158
+ "content": "<|unused_6|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "100276": {
166
+ "content": "<|unused_7|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "100277": {
174
+ "content": "<|unused_8|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "100278": {
182
+ "content": "<|unused_9|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "100279": {
190
+ "content": "<|unused_10|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "100280": {
198
+ "content": "<|unused_11|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "100281": {
206
+ "content": "<|unused_12|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "100282": {
214
+ "content": "<|unused_13|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "100283": {
222
+ "content": "<|unused_14|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "100284": {
230
+ "content": "<|unused_15|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "100285": {
238
+ "content": "<|unused_16|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "100286": {
246
+ "content": "<|unused_17|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "100287": {
254
+ "content": "<|unused_18|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "100288": {
262
+ "content": "<|unused_19|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "100289": {
270
+ "content": "<|unused_20|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "100290": {
278
+ "content": "<|unused_21|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "100291": {
286
+ "content": "<|unused_22|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "100292": {
294
+ "content": "<|unused_23|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "100293": {
302
+ "content": "<|unused_24|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "100294": {
310
+ "content": "<|unused_25|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "100295": {
318
+ "content": "<|unused_26|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "100296": {
326
+ "content": "<|unused_27|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "100297": {
334
+ "content": "<|unused_28|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "100298": {
342
+ "content": "<|unused_29|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "100299": {
350
+ "content": "<|unused_30|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "100300": {
358
+ "content": "<|unused_31|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "100301": {
366
+ "content": "<|unused_32|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "100302": {
374
+ "content": "<|unused_33|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "100303": {
382
+ "content": "<|unused_34|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "100304": {
390
+ "content": "<|unused_35|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "100305": {
398
+ "content": "<|unused_36|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "100306": {
406
+ "content": "<|unused_37|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "100307": {
414
+ "content": "<|unused_38|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "100308": {
422
+ "content": "<|unused_39|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "100309": {
430
+ "content": "<|unused_40|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "100310": {
438
+ "content": "<|unused_41|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "100311": {
446
+ "content": "<|unused_42|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "100312": {
454
+ "content": "<|unused_43|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "100313": {
462
+ "content": "<|unused_44|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "100314": {
470
+ "content": "<|unused_45|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "100315": {
478
+ "content": "<|unused_46|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "100316": {
486
+ "content": "<|unused_47|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "100317": {
494
+ "content": "<|unused_48|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "100318": {
502
+ "content": "<|unused_49|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "100319": {
510
+ "content": "<|unused_50|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "100320": {
518
+ "content": "<|unused_51|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "100321": {
526
+ "content": "<|unused_52|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "100322": {
534
+ "content": "<|unused_53|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "100323": {
542
+ "content": "<|unused_54|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "100324": {
550
+ "content": "<|unused_55|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "100325": {
558
+ "content": "<|unused_56|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "100326": {
566
+ "content": "<|unused_57|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "100327": {
574
+ "content": "<|unused_58|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "100328": {
582
+ "content": "<|unused_59|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "100329": {
590
+ "content": "<|unused_60|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "100330": {
598
+ "content": "<|unused_61|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "100331": {
606
+ "content": "<|unused_62|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "100332": {
614
+ "content": "<|unused_63|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "100333": {
622
+ "content": "<|unused_64|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "100334": {
630
+ "content": "<|unused_65|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "100335": {
638
+ "content": "<|unused_66|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "100336": {
646
+ "content": "<|unused_67|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "100337": {
654
+ "content": "<|unused_68|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "100338": {
662
+ "content": "<|unused_69|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "100339": {
670
+ "content": "<|unused_70|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "100340": {
678
+ "content": "<|unused_71|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "100341": {
686
+ "content": "<|unused_72|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "100342": {
694
+ "content": "<|unused_73|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "100343": {
702
+ "content": "<|unused_74|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "100344": {
710
+ "content": "<|unused_75|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "100345": {
718
+ "content": "<|unused_76|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "100346": {
726
+ "content": "<|unused_77|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "100347": {
734
+ "content": "<|unused_78|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "100348": {
742
+ "content": "<|unused_79|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "100349": {
750
+ "content": "<|unused_80|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "100350": {
758
+ "content": "<|unused_81|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "100351": {
766
+ "content": "<|unused_82|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ }
773
+ },
774
+ "bos_token": "<|end_of_text|>",
775
+ "clean_up_tokenization_spaces": false,
776
+ "eod_token": "<|end_of_text|>",
777
+ "eos_token": "<|end_of_text|>",
778
+ "extra_special_tokens": {},
779
+ "model_max_length": 1000000000000000019884624838656,
780
+ "pad_token": "<|pad|>",
781
+ "padding_side": "left",
782
+ "tokenizer_class": "GPT2Tokenizer",
783
+ "unk_token": "<|unk|>"
784
+ }