Hugging Face's logo

nvidia
/
GLM-5.2-NVFP4

Text Generation
Safetensors
Model Optimizer
glm_moe_dsa
nvidia
ModelOpt
GLM-5
quantized
4-bit precision
FP4
fp4
conversational
8-bit precision
modelopt
Model card Files
xet
 Community
5
frida-a commited on
Commit
b0b2b68
·
verified ·
1 Parent(s): bc492b6

Delete config.json.orig

Browse files
Files changed (1) hide show
  1. config.json.orig +0 -496
config.json.orig DELETED
@@ -1,496 +0,0 @@
1
- {
2
- "architectures": [
3
- "GlmMoeDsaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 0,
8
- "dtype": "bfloat16",
9
- "eos_token_id": [
10
- 154820,
11
- 154827,
12
- 154829
13
- ],
14
- "ep_size": 1,
15
- "first_k_dense_replace": 3,
16
- "head_dim": 64,
17
- "hidden_act": "silu",
18
- "hidden_size": 6144,
19
- "index_head_dim": 128,
20
- "index_n_heads": 32,
21
- "index_share_for_mtp_iteration": true,
22
- "index_skip_topk_offset": 3,
23
- "index_topk": 2048,
24
- "index_topk_freq": 4,
25
- "index_topk_pattern": null,
26
- "indexer_rope_interleave": true,
27
- "indexer_types": [
28
- "full",
29
- "full",
30
- "full",
31
- "shared",
32
- "shared",
33
- "shared",
34
- "full",
35
- "shared",
36
- "shared",
37
- "shared",
38
- "full",
39
- "shared",
40
- "shared",
41
- "shared",
42
- "full",
43
- "shared",
44
- "shared",
45
- "shared",
46
- "full",
47
- "shared",
48
- "shared",
49
- "shared",
50
- "full",
51
- "shared",
52
- "shared",
53
- "shared",
54
- "full",
55
- "shared",
56
- "shared",
57
- "shared",
58
- "full",
59
- "shared",
60
- "shared",
61
- "shared",
62
- "full",
63
- "shared",
64
- "shared",
65
- "shared",
66
- "full",
67
- "shared",
68
- "shared",
69
- "shared",
70
- "full",
71
- "shared",
72
- "shared",
73
- "shared",
74
- "full",
75
- "shared",
76
- "shared",
77
- "shared",
78
- "full",
79
- "shared",
80
- "shared",
81
- "shared",
82
- "full",
83
- "shared",
84
- "shared",
85
- "shared",
86
- "full",
87
- "shared",
88
- "shared",
89
- "shared",
90
- "full",
91
- "shared",
92
- "shared",
93
- "shared",
94
- "full",
95
- "shared",
96
- "shared",
97
- "shared",
98
- "full",
99
- "shared",
100
- "shared",
101
- "shared",
102
- "full",
103
- "shared",
104
- "shared",
105
- "shared"
106
- ],
107
- "initializer_range": 0.02,
108
- "intermediate_size": 12288,
109
- "kv_lora_rank": 512,
110
- "layer_types": [
111
- "deepseek_sparse_attention",
112
- "deepseek_sparse_attention",
113
- "deepseek_sparse_attention",
114
- "deepseek_sparse_attention",
115
- "deepseek_sparse_attention",
116
- "deepseek_sparse_attention",
117
- "deepseek_sparse_attention",
118
- "deepseek_sparse_attention",
119
- "deepseek_sparse_attention",
120
- "deepseek_sparse_attention",
121
- "deepseek_sparse_attention",
122
- "deepseek_sparse_attention",
123
- "deepseek_sparse_attention",
124
- "deepseek_sparse_attention",
125
- "deepseek_sparse_attention",
126
- "deepseek_sparse_attention",
127
- "deepseek_sparse_attention",
128
- "deepseek_sparse_attention",
129
- "deepseek_sparse_attention",
130
- "deepseek_sparse_attention",
131
- "deepseek_sparse_attention",
132
- "deepseek_sparse_attention",
133
- "deepseek_sparse_attention",
134
- "deepseek_sparse_attention",
135
- "deepseek_sparse_attention",
136
- "deepseek_sparse_attention",
137
- "deepseek_sparse_attention",
138
- "deepseek_sparse_attention",
139
- "deepseek_sparse_attention",
140
- "deepseek_sparse_attention",
141
- "deepseek_sparse_attention",
142
- "deepseek_sparse_attention",
143
- "deepseek_sparse_attention",
144
- "deepseek_sparse_attention",
145
- "deepseek_sparse_attention",
146
- "deepseek_sparse_attention",
147
- "deepseek_sparse_attention",
148
- "deepseek_sparse_attention",
149
- "deepseek_sparse_attention",
150
- "deepseek_sparse_attention",
151
- "deepseek_sparse_attention",
152
- "deepseek_sparse_attention",
153
- "deepseek_sparse_attention",
154
- "deepseek_sparse_attention",
155
- "deepseek_sparse_attention",
156
- "deepseek_sparse_attention",
157
- "deepseek_sparse_attention",
158
- "deepseek_sparse_attention",
159
- "deepseek_sparse_attention",
160
- "deepseek_sparse_attention",
161
- "deepseek_sparse_attention",
162
- "deepseek_sparse_attention",
163
- "deepseek_sparse_attention",
164
- "deepseek_sparse_attention",
165
- "deepseek_sparse_attention",
166
- "deepseek_sparse_attention",
167
- "deepseek_sparse_attention",
168
- "deepseek_sparse_attention",
169
- "deepseek_sparse_attention",
170
- "deepseek_sparse_attention",
171
- "deepseek_sparse_attention",
172
- "deepseek_sparse_attention",
173
- "deepseek_sparse_attention",
174
- "deepseek_sparse_attention",
175
- "deepseek_sparse_attention",
176
- "deepseek_sparse_attention",
177
- "deepseek_sparse_attention",
178
- "deepseek_sparse_attention",
179
- "deepseek_sparse_attention",
180
- "deepseek_sparse_attention",
181
- "deepseek_sparse_attention",
182
- "deepseek_sparse_attention",
183
- "deepseek_sparse_attention",
184
- "deepseek_sparse_attention",
185
- "deepseek_sparse_attention",
186
- "deepseek_sparse_attention",
187
- "deepseek_sparse_attention",
188
- "deepseek_sparse_attention"
189
- ],
190
- "max_position_embeddings": 1048576,
191
- "mlp_bias": false,
192
- "mlp_layer_types": [
193
- "dense",
194
- "dense",
195
- "dense",
196
- "sparse",
197
- "sparse",
198
- "sparse",
199
- "sparse",
200
- "sparse",
201
- "sparse",
202
- "sparse",
203
- "sparse",
204
- "sparse",
205
- "sparse",
206
- "sparse",
207
- "sparse",
208
- "sparse",
209
- "sparse",
210
- "sparse",
211
- "sparse",
212
- "sparse",
213
- "sparse",
214
- "sparse",
215
- "sparse",
216
- "sparse",
217
- "sparse",
218
- "sparse",
219
- "sparse",
220
- "sparse",
221
- "sparse",
222
- "sparse",
223
- "sparse",
224
- "sparse",
225
- "sparse",
226
- "sparse",
227
- "sparse",
228
- "sparse",
229
- "sparse",
230
- "sparse",
231
- "sparse",
232
- "sparse",
233
- "sparse",
234
- "sparse",
235
- "sparse",
236
- "sparse",
237
- "sparse",
238
- "sparse",
239
- "sparse",
240
- "sparse",
241
- "sparse",
242
- "sparse",
243
- "sparse",
244
- "sparse",
245
- "sparse",
246
- "sparse",
247
- "sparse",
248
- "sparse",
249
- "sparse",
250
- "sparse",
251
- "sparse",
252
- "sparse",
253
- "sparse",
254
- "sparse",
255
- "sparse",
256
- "sparse",
257
- "sparse",
258
- "sparse",
259
- "sparse",
260
- "sparse",
261
- "sparse",
262
- "sparse",
263
- "sparse",
264
- "sparse",
265
- "sparse",
266
- "sparse",
267
- "sparse",
268
- "sparse",
269
- "sparse",
270
- "sparse"
271
- ],
272
- "model_type": "glm_moe_dsa",
273
- "moe_intermediate_size": 2048,
274
- "moe_layer_freq": 1,
275
- "n_group": 1,
276
- "n_routed_experts": 256,
277
- "n_shared_experts": 1,
278
- "norm_topk_prob": true,
279
- "num_attention_heads": 64,
280
- "num_experts": 256,
281
- "num_experts_per_tok": 8,
282
- "num_hidden_layers": 78,
283
- "num_key_value_heads": 64,
284
- "num_nextn_predict_layers": 1,
285
- "pad_token_id": 154820,
286
- "pretraining_tp": 1,
287
- "q_lora_rank": 2048,
288
- "qk_head_dim": 256,
289
- "qk_nope_head_dim": 192,
290
- "qk_rope_head_dim": 64,
291
- "rms_norm_eps": 1e-05,
292
- "rope_interleave": true,
293
- "rope_parameters": {
294
- "rope_theta": 8000000,
295
- "rope_type": "default"
296
- },
297
- "routed_scaling_factor": 2.5,
298
- "scoring_func": "sigmoid",
299
- "tie_word_embeddings": false,
300
- "topk_group": 1,
301
- "topk_method": "noaux_tc",
302
- "transformers_version": "5.11.0",
303
- "use_cache": true,
304
- "v_head_dim": 256,
305
- "vocab_size": 154880,
306
- "quantization_config": {
307
- "config_groups": {
308
- "group_0": {
309
- "input_activations": {
310
- "dynamic": false,
311
- "num_bits": 4,
312
- "type": "float",
313
- "group_size": 16
314
- },
315
- "weights": {
316
- "dynamic": false,
317
- "num_bits": 4,
318
- "type": "float",
319
- "group_size": 16
320
- },
321
- "targets": [
322
- "Linear"
323
- ]
324
- }
325
- },
326
- "ignore": [
327
- "lm_head",
328
- "model.embed_tokens",
329
- "model.layers.0*",
330
- "model.layers.1.*",
331
- "model.layers.10.mlp.shared_experts*",
332
- "model.layers.10.self_attn*",
333
- "model.layers.11.mlp.shared_experts*",
334
- "model.layers.11.self_attn*",
335
- "model.layers.12.mlp.shared_experts*",
336
- "model.layers.12.self_attn*",
337
- "model.layers.13.mlp.shared_experts*",
338
- "model.layers.13.self_attn*",
339
- "model.layers.14.mlp.shared_experts*",
340
- "model.layers.14.self_attn*",
341
- "model.layers.15.mlp.shared_experts*",
342
- "model.layers.15.self_attn*",
343
- "model.layers.16.mlp.shared_experts*",
344
- "model.layers.16.self_attn*",
345
- "model.layers.17.mlp.shared_experts*",
346
- "model.layers.17.self_attn*",
347
- "model.layers.18.mlp.shared_experts*",
348
- "model.layers.18.self_attn*",
349
- "model.layers.19.mlp.shared_experts*",
350
- "model.layers.19.self_attn*",
351
- "model.layers.2.*",
352
- "model.layers.20.mlp.shared_experts*",
353
- "model.layers.20.self_attn*",
354
- "model.layers.21.mlp.shared_experts*",
355
- "model.layers.21.self_attn*",
356
- "model.layers.22.mlp.shared_experts*",
357
- "model.layers.22.self_attn*",
358
- "model.layers.23.mlp.shared_experts*",
359
- "model.layers.23.self_attn*",
360
- "model.layers.24.mlp.shared_experts*",
361
- "model.layers.24.self_attn*",
362
- "model.layers.25.mlp.shared_experts*",
363
- "model.layers.25.self_attn*",
364
- "model.layers.26.mlp.shared_experts*",
365
- "model.layers.26.self_attn*",
366
- "model.layers.27.mlp.shared_experts*",
367
- "model.layers.27.self_attn*",
368
- "model.layers.28.mlp.shared_experts*",
369
- "model.layers.28.self_attn*",
370
- "model.layers.29.mlp.shared_experts*",
371
- "model.layers.29.self_attn*",
372
- "model.layers.3.mlp.shared_experts*",
373
- "model.layers.3.self_attn*",
374
- "model.layers.30.mlp.shared_experts*",
375
- "model.layers.30.self_attn*",
376
- "model.layers.31.mlp.shared_experts*",
377
- "model.layers.31.self_attn*",
378
- "model.layers.32.mlp.shared_experts*",
379
- "model.layers.32.self_attn*",
380
- "model.layers.33.mlp.shared_experts*",
381
- "model.layers.33.self_attn*",
382
- "model.layers.34.mlp.shared_experts*",
383
- "model.layers.34.self_attn*",
384
- "model.layers.35.mlp.shared_experts*",
385
- "model.layers.35.self_attn*",
386
- "model.layers.36.mlp.shared_experts*",
387
- "model.layers.36.self_attn*",
388
- "model.layers.37.mlp.shared_experts*",
389
- "model.layers.37.self_attn*",
390
- "model.layers.38.mlp.shared_experts*",
391
- "model.layers.38.self_attn*",
392
- "model.layers.39.mlp.shared_experts*",
393
- "model.layers.39.self_attn*",
394
- "model.layers.4.mlp.shared_experts*",
395
- "model.layers.4.self_attn*",
396
- "model.layers.40.mlp.shared_experts*",
397
- "model.layers.40.self_attn*",
398
- "model.layers.41.mlp.shared_experts*",
399
- "model.layers.41.self_attn*",
400
- "model.layers.42.mlp.shared_experts*",
401
- "model.layers.42.self_attn*",
402
- "model.layers.43.mlp.shared_experts*",
403
- "model.layers.43.self_attn*",
404
- "model.layers.44.mlp.shared_experts*",
405
- "model.layers.44.self_attn*",
406
- "model.layers.45.mlp.shared_experts*",
407
- "model.layers.45.self_attn*",
408
- "model.layers.46.mlp.shared_experts*",
409
- "model.layers.46.self_attn*",
410
- "model.layers.47.mlp.shared_experts*",
411
- "model.layers.47.self_attn*",
412
- "model.layers.48.mlp.shared_experts*",
413
- "model.layers.48.self_attn*",
414
- "model.layers.49.mlp.shared_experts*",
415
- "model.layers.49.self_attn*",
416
- "model.layers.5.mlp.shared_experts*",
417
- "model.layers.5.self_attn*",
418
- "model.layers.50.mlp.shared_experts*",
419
- "model.layers.50.self_attn*",
420
- "model.layers.51.mlp.shared_experts*",
421
- "model.layers.51.self_attn*",
422
- "model.layers.52.mlp.shared_experts*",
423
- "model.layers.52.self_attn*",
424
- "model.layers.53.mlp.shared_experts*",
425
- "model.layers.53.self_attn*",
426
- "model.layers.54.mlp.shared_experts*",
427
- "model.layers.54.self_attn*",
428
- "model.layers.55.mlp.shared_experts*",
429
- "model.layers.55.self_attn*",
430
- "model.layers.56.mlp.shared_experts*",
431
- "model.layers.56.self_attn*",
432
- "model.layers.57.mlp.shared_experts*",
433
- "model.layers.57.self_attn*",
434
- "model.layers.58.mlp.shared_experts*",
435
- "model.layers.58.self_attn*",
436
- "model.layers.59.mlp.shared_experts*",
437
- "model.layers.59.self_attn*",
438
- "model.layers.6.mlp.shared_experts*",
439
- "model.layers.6.self_attn*",
440
- "model.layers.60.mlp.shared_experts*",
441
- "model.layers.60.self_attn*",
442
- "model.layers.61.mlp.shared_experts*",
443
- "model.layers.61.self_attn*",
444
- "model.layers.62.mlp.shared_experts*",
445
- "model.layers.62.self_attn*",
446
- "model.layers.63.mlp.shared_experts*",
447
- "model.layers.63.self_attn*",
448
- "model.layers.64.mlp.shared_experts*",
449
- "model.layers.64.self_attn*",
450
- "model.layers.65.mlp.shared_experts*",
451
- "model.layers.65.self_attn*",
452
- "model.layers.66.mlp.shared_experts*",
453
- "model.layers.66.self_attn*",
454
- "model.layers.67.mlp.shared_experts*",
455
- "model.layers.67.self_attn*",
456
- "model.layers.68.mlp.shared_experts*",
457
- "model.layers.68.self_attn*",
458
- "model.layers.69.mlp.shared_experts*",
459
- "model.layers.69.self_attn*",
460
- "model.layers.7.mlp.shared_experts*",
461
- "model.layers.7.self_attn*",
462
- "model.layers.70.mlp.shared_experts*",
463
- "model.layers.70.self_attn*",
464
- "model.layers.71.mlp.shared_experts*",
465
- "model.layers.71.self_attn*",
466
- "model.layers.72.mlp.shared_experts*",
467
- "model.layers.72.self_attn*",
468
- "model.layers.73.mlp.shared_experts*",
469
- "model.layers.73.self_attn*",
470
- "model.layers.74.mlp.shared_experts*",
471
- "model.layers.74.self_attn*",
472
- "model.layers.75.mlp.shared_experts*",
473
- "model.layers.75.self_attn*",
474
- "model.layers.76.mlp.shared_experts*",
475
- "model.layers.76.self_attn*",
476
- "model.layers.77.mlp.shared_experts*",
477
- "model.layers.77.self_attn*",
478
- "model.layers.8.mlp.shared_experts*",
479
- "model.layers.8.self_attn*",
480
- "model.layers.9.mlp.shared_experts*",
481
- "model.layers.9.self_attn*",
482
- "model.layers.78*"
483
- ],
484
- "quant_algo": "NVFP4",
485
- "kv_cache_scheme": {
486
- "dynamic": false,
487
- "num_bits": 8,
488
- "type": "float"
489
- },
490
- "producer": {
491
- "name": "modelopt",
492
- "version": "0.46.0.dev65+g977d34dc3"
493
- },
494
- "quant_method": "modelopt"
495
- }
496
- }