mayank-mishra commited on
Commit
b078b78
·
verified ·
1 Parent(s): e41443f

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,725 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 100257,
3
+ "embedding_dropout": 0,
4
+ "eos_token_id": 100257,
5
+ "hidden_size": 1024,
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": 2752,
19
+ "mlp_type": "MLP"
20
+ },
21
+ {
22
+ "activation_function": "swiglu",
23
+ "add_bias": false,
24
+ "dropout": 0,
25
+ "intermediate_size": 2752,
26
+ "mlp_type": "MLP"
27
+ },
28
+ {
29
+ "activation_function": "swiglu",
30
+ "add_bias": false,
31
+ "dropout": 0,
32
+ "intermediate_size": 2752,
33
+ "mlp_type": "MLP"
34
+ },
35
+ {
36
+ "activation_function": "swiglu",
37
+ "add_bias": false,
38
+ "dropout": 0,
39
+ "intermediate_size": 2752,
40
+ "mlp_type": "MLP"
41
+ },
42
+ {
43
+ "activation_function": "swiglu",
44
+ "add_bias": false,
45
+ "dropout": 0,
46
+ "intermediate_size": 2752,
47
+ "mlp_type": "MLP"
48
+ },
49
+ {
50
+ "activation_function": "swiglu",
51
+ "add_bias": false,
52
+ "dropout": 0,
53
+ "intermediate_size": 2752,
54
+ "mlp_type": "MLP"
55
+ },
56
+ {
57
+ "activation_function": "swiglu",
58
+ "add_bias": false,
59
+ "dropout": 0,
60
+ "intermediate_size": 2752,
61
+ "mlp_type": "MLP"
62
+ },
63
+ {
64
+ "activation_function": "swiglu",
65
+ "add_bias": false,
66
+ "dropout": 0,
67
+ "intermediate_size": 2752,
68
+ "mlp_type": "MLP"
69
+ },
70
+ {
71
+ "activation_function": "swiglu",
72
+ "add_bias": false,
73
+ "dropout": 0,
74
+ "intermediate_size": 2752,
75
+ "mlp_type": "MLP"
76
+ },
77
+ {
78
+ "activation_function": "swiglu",
79
+ "add_bias": false,
80
+ "dropout": 0,
81
+ "intermediate_size": 2752,
82
+ "mlp_type": "MLP"
83
+ },
84
+ {
85
+ "activation_function": "swiglu",
86
+ "add_bias": false,
87
+ "dropout": 0,
88
+ "intermediate_size": 2752,
89
+ "mlp_type": "MLP"
90
+ },
91
+ {
92
+ "activation_function": "swiglu",
93
+ "add_bias": false,
94
+ "dropout": 0,
95
+ "intermediate_size": 2752,
96
+ "mlp_type": "MLP"
97
+ },
98
+ {
99
+ "activation_function": "swiglu",
100
+ "add_bias": false,
101
+ "dropout": 0,
102
+ "intermediate_size": 2752,
103
+ "mlp_type": "MLP"
104
+ },
105
+ {
106
+ "activation_function": "swiglu",
107
+ "add_bias": false,
108
+ "dropout": 0,
109
+ "intermediate_size": 2752,
110
+ "mlp_type": "MLP"
111
+ },
112
+ {
113
+ "activation_function": "swiglu",
114
+ "add_bias": false,
115
+ "dropout": 0,
116
+ "intermediate_size": 2752,
117
+ "mlp_type": "MLP"
118
+ },
119
+ {
120
+ "activation_function": "swiglu",
121
+ "add_bias": false,
122
+ "dropout": 0,
123
+ "intermediate_size": 2752,
124
+ "mlp_type": "MLP"
125
+ },
126
+ {
127
+ "activation_function": "swiglu",
128
+ "add_bias": false,
129
+ "dropout": 0,
130
+ "intermediate_size": 2752,
131
+ "mlp_type": "MLP"
132
+ },
133
+ {
134
+ "activation_function": "swiglu",
135
+ "add_bias": false,
136
+ "dropout": 0,
137
+ "intermediate_size": 2752,
138
+ "mlp_type": "MLP"
139
+ },
140
+ {
141
+ "activation_function": "swiglu",
142
+ "add_bias": false,
143
+ "dropout": 0,
144
+ "intermediate_size": 2752,
145
+ "mlp_type": "MLP"
146
+ },
147
+ {
148
+ "activation_function": "swiglu",
149
+ "add_bias": false,
150
+ "dropout": 0,
151
+ "intermediate_size": 2752,
152
+ "mlp_type": "MLP"
153
+ },
154
+ {
155
+ "activation_function": "swiglu",
156
+ "add_bias": false,
157
+ "dropout": 0,
158
+ "intermediate_size": 2752,
159
+ "mlp_type": "MLP"
160
+ },
161
+ {
162
+ "activation_function": "swiglu",
163
+ "add_bias": false,
164
+ "dropout": 0,
165
+ "intermediate_size": 2752,
166
+ "mlp_type": "MLP"
167
+ },
168
+ {
169
+ "activation_function": "swiglu",
170
+ "add_bias": false,
171
+ "dropout": 0,
172
+ "intermediate_size": 2752,
173
+ "mlp_type": "MLP"
174
+ },
175
+ {
176
+ "activation_function": "swiglu",
177
+ "add_bias": false,
178
+ "dropout": 0,
179
+ "intermediate_size": 2752,
180
+ "mlp_type": "MLP"
181
+ }
182
+ ],
183
+ "model_type": "gpt_base",
184
+ "normalization_function": "rmsnorm",
185
+ "num_layers": 24,
186
+ "pad_token_id": 100256,
187
+ "position_embedding_type": "nope",
188
+ "rope_dim": null,
189
+ "rope_scaling": null,
190
+ "rope_theta": 10000,
191
+ "router_aux_loss_coef": 0.001,
192
+ "sequence_mixer_blocks": [
193
+ {
194
+ "A_init_max": 16,
195
+ "A_init_min": 0,
196
+ "activation_function": "silu",
197
+ "add_bias": false,
198
+ "dt_init_floor": 0.0001,
199
+ "dt_init_max": 0.1,
200
+ "dt_init_min": 0.001,
201
+ "gradient_clipping": 1.0,
202
+ "k_head_dim": 64,
203
+ "kernel_size": 4,
204
+ "normalization_function": "rmsnorm",
205
+ "num_f_heads": 84,
206
+ "num_g_heads": 84,
207
+ "num_k_heads": 1,
208
+ "num_q_heads": 1,
209
+ "num_v_heads": 84,
210
+ "num_weight_heads": 84,
211
+ "sequence_mixer_type": "m2rnn",
212
+ "use_residual": true,
213
+ "v_head_dim": 16
214
+ },
215
+ {
216
+ "A_init_max": 16,
217
+ "A_init_min": 0,
218
+ "activation_function": "silu",
219
+ "add_bias": false,
220
+ "dt_init_floor": 0.0001,
221
+ "dt_init_max": 0.1,
222
+ "dt_init_min": 0.001,
223
+ "gradient_clipping": 1.0,
224
+ "k_head_dim": 64,
225
+ "kernel_size": 4,
226
+ "normalization_function": "rmsnorm",
227
+ "num_f_heads": 84,
228
+ "num_g_heads": 84,
229
+ "num_k_heads": 1,
230
+ "num_q_heads": 1,
231
+ "num_v_heads": 84,
232
+ "num_weight_heads": 84,
233
+ "sequence_mixer_type": "m2rnn",
234
+ "use_residual": true,
235
+ "v_head_dim": 16
236
+ },
237
+ {
238
+ "A_init_max": 16,
239
+ "A_init_min": 0,
240
+ "activation_function": "silu",
241
+ "add_bias": false,
242
+ "dt_init_floor": 0.0001,
243
+ "dt_init_max": 0.1,
244
+ "dt_init_min": 0.001,
245
+ "gradient_clipping": 1.0,
246
+ "k_head_dim": 64,
247
+ "kernel_size": 4,
248
+ "normalization_function": "rmsnorm",
249
+ "num_f_heads": 84,
250
+ "num_g_heads": 84,
251
+ "num_k_heads": 1,
252
+ "num_q_heads": 1,
253
+ "num_v_heads": 84,
254
+ "num_weight_heads": 84,
255
+ "sequence_mixer_type": "m2rnn",
256
+ "use_residual": true,
257
+ "v_head_dim": 16
258
+ },
259
+ {
260
+ "A_init_max": 16,
261
+ "A_init_min": 0,
262
+ "activation_function": "silu",
263
+ "add_bias": false,
264
+ "dt_init_floor": 0.0001,
265
+ "dt_init_max": 0.1,
266
+ "dt_init_min": 0.001,
267
+ "gradient_clipping": 1.0,
268
+ "k_head_dim": 64,
269
+ "kernel_size": 4,
270
+ "normalization_function": "rmsnorm",
271
+ "num_f_heads": 84,
272
+ "num_g_heads": 84,
273
+ "num_k_heads": 1,
274
+ "num_q_heads": 1,
275
+ "num_v_heads": 84,
276
+ "num_weight_heads": 84,
277
+ "sequence_mixer_type": "m2rnn",
278
+ "use_residual": true,
279
+ "v_head_dim": 16
280
+ },
281
+ {
282
+ "A_init_max": 16,
283
+ "A_init_min": 0,
284
+ "activation_function": "silu",
285
+ "add_bias": false,
286
+ "dt_init_floor": 0.0001,
287
+ "dt_init_max": 0.1,
288
+ "dt_init_min": 0.001,
289
+ "gradient_clipping": 1.0,
290
+ "k_head_dim": 64,
291
+ "kernel_size": 4,
292
+ "normalization_function": "rmsnorm",
293
+ "num_f_heads": 84,
294
+ "num_g_heads": 84,
295
+ "num_k_heads": 1,
296
+ "num_q_heads": 1,
297
+ "num_v_heads": 84,
298
+ "num_weight_heads": 84,
299
+ "sequence_mixer_type": "m2rnn",
300
+ "use_residual": true,
301
+ "v_head_dim": 16
302
+ },
303
+ {
304
+ "A_init_max": 16,
305
+ "A_init_min": 0,
306
+ "activation_function": "silu",
307
+ "add_bias": false,
308
+ "dt_init_floor": 0.0001,
309
+ "dt_init_max": 0.1,
310
+ "dt_init_min": 0.001,
311
+ "gradient_clipping": 1.0,
312
+ "k_head_dim": 64,
313
+ "kernel_size": 4,
314
+ "normalization_function": "rmsnorm",
315
+ "num_f_heads": 84,
316
+ "num_g_heads": 84,
317
+ "num_k_heads": 1,
318
+ "num_q_heads": 1,
319
+ "num_v_heads": 84,
320
+ "num_weight_heads": 84,
321
+ "sequence_mixer_type": "m2rnn",
322
+ "use_residual": true,
323
+ "v_head_dim": 16
324
+ },
325
+ {
326
+ "A_init_max": 16,
327
+ "A_init_min": 0,
328
+ "activation_function": "silu",
329
+ "add_bias": false,
330
+ "dt_init_floor": 0.0001,
331
+ "dt_init_max": 0.1,
332
+ "dt_init_min": 0.001,
333
+ "gradient_clipping": 1.0,
334
+ "k_head_dim": 64,
335
+ "kernel_size": 4,
336
+ "normalization_function": "rmsnorm",
337
+ "num_f_heads": 84,
338
+ "num_g_heads": 84,
339
+ "num_k_heads": 1,
340
+ "num_q_heads": 1,
341
+ "num_v_heads": 84,
342
+ "num_weight_heads": 84,
343
+ "sequence_mixer_type": "m2rnn",
344
+ "use_residual": true,
345
+ "v_head_dim": 16
346
+ },
347
+ {
348
+ "A_init_max": 16,
349
+ "A_init_min": 0,
350
+ "activation_function": "silu",
351
+ "add_bias": false,
352
+ "dt_init_floor": 0.0001,
353
+ "dt_init_max": 0.1,
354
+ "dt_init_min": 0.001,
355
+ "gradient_clipping": 1.0,
356
+ "k_head_dim": 64,
357
+ "kernel_size": 4,
358
+ "normalization_function": "rmsnorm",
359
+ "num_f_heads": 84,
360
+ "num_g_heads": 84,
361
+ "num_k_heads": 1,
362
+ "num_q_heads": 1,
363
+ "num_v_heads": 84,
364
+ "num_weight_heads": 84,
365
+ "sequence_mixer_type": "m2rnn",
366
+ "use_residual": true,
367
+ "v_head_dim": 16
368
+ },
369
+ {
370
+ "A_init_max": 16,
371
+ "A_init_min": 0,
372
+ "activation_function": "silu",
373
+ "add_bias": false,
374
+ "dt_init_floor": 0.0001,
375
+ "dt_init_max": 0.1,
376
+ "dt_init_min": 0.001,
377
+ "gradient_clipping": 1.0,
378
+ "k_head_dim": 64,
379
+ "kernel_size": 4,
380
+ "normalization_function": "rmsnorm",
381
+ "num_f_heads": 84,
382
+ "num_g_heads": 84,
383
+ "num_k_heads": 1,
384
+ "num_q_heads": 1,
385
+ "num_v_heads": 84,
386
+ "num_weight_heads": 84,
387
+ "sequence_mixer_type": "m2rnn",
388
+ "use_residual": true,
389
+ "v_head_dim": 16
390
+ },
391
+ {
392
+ "A_init_max": 16,
393
+ "A_init_min": 0,
394
+ "activation_function": "silu",
395
+ "add_bias": false,
396
+ "dt_init_floor": 0.0001,
397
+ "dt_init_max": 0.1,
398
+ "dt_init_min": 0.001,
399
+ "gradient_clipping": 1.0,
400
+ "k_head_dim": 64,
401
+ "kernel_size": 4,
402
+ "normalization_function": "rmsnorm",
403
+ "num_f_heads": 84,
404
+ "num_g_heads": 84,
405
+ "num_k_heads": 1,
406
+ "num_q_heads": 1,
407
+ "num_v_heads": 84,
408
+ "num_weight_heads": 84,
409
+ "sequence_mixer_type": "m2rnn",
410
+ "use_residual": true,
411
+ "v_head_dim": 16
412
+ },
413
+ {
414
+ "A_init_max": 16,
415
+ "A_init_min": 0,
416
+ "activation_function": "silu",
417
+ "add_bias": false,
418
+ "dt_init_floor": 0.0001,
419
+ "dt_init_max": 0.1,
420
+ "dt_init_min": 0.001,
421
+ "gradient_clipping": 1.0,
422
+ "k_head_dim": 64,
423
+ "kernel_size": 4,
424
+ "normalization_function": "rmsnorm",
425
+ "num_f_heads": 84,
426
+ "num_g_heads": 84,
427
+ "num_k_heads": 1,
428
+ "num_q_heads": 1,
429
+ "num_v_heads": 84,
430
+ "num_weight_heads": 84,
431
+ "sequence_mixer_type": "m2rnn",
432
+ "use_residual": true,
433
+ "v_head_dim": 16
434
+ },
435
+ {
436
+ "A_init_max": 16,
437
+ "A_init_min": 0,
438
+ "activation_function": "silu",
439
+ "add_bias": false,
440
+ "dt_init_floor": 0.0001,
441
+ "dt_init_max": 0.1,
442
+ "dt_init_min": 0.001,
443
+ "gradient_clipping": 1.0,
444
+ "k_head_dim": 64,
445
+ "kernel_size": 4,
446
+ "normalization_function": "rmsnorm",
447
+ "num_f_heads": 84,
448
+ "num_g_heads": 84,
449
+ "num_k_heads": 1,
450
+ "num_q_heads": 1,
451
+ "num_v_heads": 84,
452
+ "num_weight_heads": 84,
453
+ "sequence_mixer_type": "m2rnn",
454
+ "use_residual": true,
455
+ "v_head_dim": 16
456
+ },
457
+ {
458
+ "A_init_max": 16,
459
+ "A_init_min": 0,
460
+ "activation_function": "silu",
461
+ "add_bias": false,
462
+ "dt_init_floor": 0.0001,
463
+ "dt_init_max": 0.1,
464
+ "dt_init_min": 0.001,
465
+ "gradient_clipping": 1.0,
466
+ "k_head_dim": 64,
467
+ "kernel_size": 4,
468
+ "normalization_function": "rmsnorm",
469
+ "num_f_heads": 84,
470
+ "num_g_heads": 84,
471
+ "num_k_heads": 1,
472
+ "num_q_heads": 1,
473
+ "num_v_heads": 84,
474
+ "num_weight_heads": 84,
475
+ "sequence_mixer_type": "m2rnn",
476
+ "use_residual": true,
477
+ "v_head_dim": 16
478
+ },
479
+ {
480
+ "A_init_max": 16,
481
+ "A_init_min": 0,
482
+ "activation_function": "silu",
483
+ "add_bias": false,
484
+ "dt_init_floor": 0.0001,
485
+ "dt_init_max": 0.1,
486
+ "dt_init_min": 0.001,
487
+ "gradient_clipping": 1.0,
488
+ "k_head_dim": 64,
489
+ "kernel_size": 4,
490
+ "normalization_function": "rmsnorm",
491
+ "num_f_heads": 84,
492
+ "num_g_heads": 84,
493
+ "num_k_heads": 1,
494
+ "num_q_heads": 1,
495
+ "num_v_heads": 84,
496
+ "num_weight_heads": 84,
497
+ "sequence_mixer_type": "m2rnn",
498
+ "use_residual": true,
499
+ "v_head_dim": 16
500
+ },
501
+ {
502
+ "A_init_max": 16,
503
+ "A_init_min": 0,
504
+ "activation_function": "silu",
505
+ "add_bias": false,
506
+ "dt_init_floor": 0.0001,
507
+ "dt_init_max": 0.1,
508
+ "dt_init_min": 0.001,
509
+ "gradient_clipping": 1.0,
510
+ "k_head_dim": 64,
511
+ "kernel_size": 4,
512
+ "normalization_function": "rmsnorm",
513
+ "num_f_heads": 84,
514
+ "num_g_heads": 84,
515
+ "num_k_heads": 1,
516
+ "num_q_heads": 1,
517
+ "num_v_heads": 84,
518
+ "num_weight_heads": 84,
519
+ "sequence_mixer_type": "m2rnn",
520
+ "use_residual": true,
521
+ "v_head_dim": 16
522
+ },
523
+ {
524
+ "A_init_max": 16,
525
+ "A_init_min": 0,
526
+ "activation_function": "silu",
527
+ "add_bias": false,
528
+ "dt_init_floor": 0.0001,
529
+ "dt_init_max": 0.1,
530
+ "dt_init_min": 0.001,
531
+ "gradient_clipping": 1.0,
532
+ "k_head_dim": 64,
533
+ "kernel_size": 4,
534
+ "normalization_function": "rmsnorm",
535
+ "num_f_heads": 84,
536
+ "num_g_heads": 84,
537
+ "num_k_heads": 1,
538
+ "num_q_heads": 1,
539
+ "num_v_heads": 84,
540
+ "num_weight_heads": 84,
541
+ "sequence_mixer_type": "m2rnn",
542
+ "use_residual": true,
543
+ "v_head_dim": 16
544
+ },
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": 84,
558
+ "num_g_heads": 84,
559
+ "num_k_heads": 1,
560
+ "num_q_heads": 1,
561
+ "num_v_heads": 84,
562
+ "num_weight_heads": 84,
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": 84,
580
+ "num_g_heads": 84,
581
+ "num_k_heads": 1,
582
+ "num_q_heads": 1,
583
+ "num_v_heads": 84,
584
+ "num_weight_heads": 84,
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": 84,
602
+ "num_g_heads": 84,
603
+ "num_k_heads": 1,
604
+ "num_q_heads": 1,
605
+ "num_v_heads": 84,
606
+ "num_weight_heads": 84,
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": 84,
624
+ "num_g_heads": 84,
625
+ "num_k_heads": 1,
626
+ "num_q_heads": 1,
627
+ "num_v_heads": 84,
628
+ "num_weight_heads": 84,
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": 84,
646
+ "num_g_heads": 84,
647
+ "num_k_heads": 1,
648
+ "num_q_heads": 1,
649
+ "num_v_heads": 84,
650
+ "num_weight_heads": 84,
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": 84,
668
+ "num_g_heads": 84,
669
+ "num_k_heads": 1,
670
+ "num_q_heads": 1,
671
+ "num_v_heads": 84,
672
+ "num_weight_heads": 84,
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": 84,
690
+ "num_g_heads": 84,
691
+ "num_k_heads": 1,
692
+ "num_q_heads": 1,
693
+ "num_v_heads": 84,
694
+ "num_weight_heads": 84,
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": 84,
712
+ "num_g_heads": 84,
713
+ "num_k_heads": 1,
714
+ "num_q_heads": 1,
715
+ "num_v_heads": 84,
716
+ "num_weight_heads": 84,
717
+ "sequence_mixer_type": "m2rnn",
718
+ "use_residual": true,
719
+ "v_head_dim": 16
720
+ }
721
+ ],
722
+ "transformers_version": "4.57.3",
723
+ "use_cache": true,
724
+ "vocab_size": 100352
725
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e778f73116c1a712e8f0e53ab28ee9ac0c5e2123f0b45753aa84a5063962173f
3
+ size 821506728
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
+ }