Hugging Face's logo

nvidia
/
GLM-5.1-NVFP4

Text Generation
Safetensors
Model Optimizer
glm_moe_dsa
nvidia
ModelOpt
quantized
4-bit precision
FP4
fp4
conversational
8-bit precision
modelopt
Model card Files
xet
 Community
4
frida-a commited on
Commit
25630d0
·
verified ·
1 Parent(s): 8bcf48f

Add files using upload-large-folder tool

Browse files
Files changed (45) hide show
  1. .gitattributes +1 -0
  2. config.json +399 -398
  3. config.json.bak +402 -0
  4. hf_quant_config.json +166 -165
  5. hf_quant_config.json.bak +167 -0
  6. model-00001-of-00049.safetensors +3 -0
  7. model-00002-of-00049.safetensors +3 -0
  8. model-00003-of-00049.safetensors +3 -0
  9. model-00004-of-00049.safetensors +3 -0
  10. model-00005-of-00049.safetensors +3 -0
  11. model-00006-of-00049.safetensors +3 -0
  12. model-00007-of-00049.safetensors +3 -0
  13. model-00008-of-00049.safetensors +3 -0
  14. model-00010-of-00049.safetensors +3 -0
  15. model-00011-of-00049.safetensors +3 -0
  16. model-00012-of-00049.safetensors +3 -0
  17. model-00014-of-00049.safetensors +3 -0
  18. model-00015-of-00049.safetensors +3 -0
  19. model-00016-of-00049.safetensors +3 -0
  20. model-00018-of-00049.safetensors +3 -0
  21. model-00019-of-00049.safetensors +3 -0
  22. model-00021-of-00049.safetensors +3 -0
  23. model-00023-of-00049.safetensors +3 -0
  24. model-00027-of-00049.safetensors +3 -0
  25. model-00028-of-00049.safetensors +3 -0
  26. model-00029-of-00049.safetensors +3 -0
  27. model-00030-of-00049.safetensors +3 -0
  28. model-00031-of-00049.safetensors +3 -0
  29. model-00032-of-00049.safetensors +3 -0
  30. model-00033-of-00049.safetensors +3 -0
  31. model-00034-of-00049.safetensors +3 -0
  32. model-00035-of-00049.safetensors +3 -0
  33. model-00036-of-00049.safetensors +3 -0
  34. model-00038-of-00049.safetensors +3 -0
  35. model-00041-of-00049.safetensors +3 -0
  36. model-00042-of-00049.safetensors +3 -0
  37. model-00043-of-00049.safetensors +3 -0
  38. model-00044-of-00049.safetensors +3 -0
  39. model-00045-of-00049.safetensors +3 -0
  40. model-00046-of-00049.safetensors +3 -0
  41. model-00047-of-00049.safetensors +3 -0
  42. model-00048-of-00049.safetensors +3 -0
  43. model-00049-of-00049.safetensors +3 -0
  44. model.safetensors.index.json +2 -2
  45. model.safetensors.index.json.bak +3 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  model.safetensors.index.json filter=lfs diff=lfs merge=lfs -text
38
+ model.safetensors.index.json.bak filter=lfs diff=lfs merge=lfs -text
config.json CHANGED
@@ -1,402 +1,403 @@
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
- "hidden_act": "silu",
17
- "hidden_size": 6144,
18
- "index_head_dim": 128,
19
- "index_n_heads": 32,
20
- "index_topk": 2048,
21
- "indexer_rope_interleave": true,
22
- "indexer_types": [
23
- "full",
24
- "full",
25
- "full",
26
- "full",
27
- "full",
28
- "full",
29
- "full",
30
- "full",
31
- "full",
32
- "full",
33
- "full",
34
- "full",
35
- "full",
36
- "full",
37
- "full",
38
- "full",
39
- "full",
40
- "full",
41
- "full",
42
- "full",
43
- "full",
44
- "full",
45
- "full",
46
- "full",
47
- "full",
48
- "full",
49
- "full",
50
- "full",
51
- "full",
52
- "full",
53
- "full",
54
- "full",
55
- "full",
56
- "full",
57
- "full",
58
- "full",
59
- "full",
60
- "full",
61
- "full",
62
- "full",
63
- "full",
64
- "full",
65
- "full",
66
- "full",
67
- "full",
68
- "full",
69
- "full",
70
- "full",
71
- "full",
72
- "full",
73
- "full",
74
- "full",
75
- "full",
76
- "full",
77
- "full",
78
- "full",
79
- "full",
80
- "full",
81
- "full",
82
- "full",
83
- "full",
84
- "full",
85
- "full",
86
- "full",
87
- "full",
88
- "full",
89
- "full",
90
- "full",
91
- "full",
92
- "full",
93
- "full",
94
- "full",
95
- "full",
96
- "full",
97
- "full",
98
- "full",
99
- "full",
100
- "full"
101
- ],
102
- "initializer_range": 0.02,
103
- "intermediate_size": 12288,
104
- "kv_lora_rank": 512,
105
- "max_position_embeddings": 202752,
106
- "mlp_layer_types": [
107
- "dense",
108
- "dense",
109
- "dense",
110
- "sparse",
111
- "sparse",
112
- "sparse",
113
- "sparse",
114
- "sparse",
115
- "sparse",
116
- "sparse",
117
- "sparse",
118
- "sparse",
119
- "sparse",
120
- "sparse",
121
- "sparse",
122
- "sparse",
123
- "sparse",
124
- "sparse",
125
- "sparse",
126
- "sparse",
127
- "sparse",
128
- "sparse",
129
- "sparse",
130
- "sparse",
131
- "sparse",
132
- "sparse",
133
- "sparse",
134
- "sparse",
135
- "sparse",
136
- "sparse",
137
- "sparse",
138
- "sparse",
139
- "sparse",
140
- "sparse",
141
- "sparse",
142
- "sparse",
143
- "sparse",
144
- "sparse",
145
- "sparse",
146
- "sparse",
147
- "sparse",
148
- "sparse",
149
- "sparse",
150
- "sparse",
151
- "sparse",
152
- "sparse",
153
- "sparse",
154
- "sparse",
155
- "sparse",
156
- "sparse",
157
- "sparse",
158
- "sparse",
159
- "sparse",
160
- "sparse",
161
- "sparse",
162
- "sparse",
163
- "sparse",
164
- "sparse",
165
- "sparse",
166
- "sparse",
167
- "sparse",
168
- "sparse",
169
- "sparse",
170
- "sparse",
171
- "sparse",
172
- "sparse",
173
- "sparse",
174
- "sparse",
175
- "sparse",
176
- "sparse",
177
- "sparse",
178
- "sparse",
179
- "sparse",
180
- "sparse",
181
- "sparse",
182
- "sparse",
183
- "sparse",
184
- "sparse"
185
- ],
186
- "model_type": "glm_moe_dsa",
187
- "moe_intermediate_size": 2048,
188
- "moe_layer_freq": 1,
189
- "n_group": 1,
190
- "n_routed_experts": 256,
191
- "n_shared_experts": 1,
192
- "norm_topk_prob": true,
193
- "num_attention_heads": 64,
194
- "num_experts_per_tok": 8,
195
- "num_hidden_layers": 78,
196
- "num_key_value_heads": 64,
197
- "num_nextn_predict_layers": 1,
198
- "pad_token_id": 154820,
199
- "pretraining_tp": 1,
200
- "q_lora_rank": 2048,
201
- "qk_head_dim": 256,
202
- "qk_nope_head_dim": 192,
203
- "qk_rope_head_dim": 64,
204
- "rms_norm_eps": 1e-05,
205
- "rope_interleave": true,
206
- "rope_parameters": {
207
- "rope_theta": 1000000,
208
- "rope_type": "default"
209
- },
210
- "routed_scaling_factor": 2.5,
211
- "scoring_func": "sigmoid",
212
- "tie_word_embeddings": false,
213
- "topk_group": 1,
214
- "topk_method": "noaux_tc",
215
- "transformers_version": "5.8.0",
216
- "use_cache": true,
217
- "v_head_dim": 256,
218
- "vocab_size": 154880,
219
- "quantization_config": {
220
- "config_groups": {
221
- "group_0": {
222
- "input_activations": {
223
- "dynamic": false,
224
- "num_bits": 4,
225
- "type": "float",
226
- "group_size": 16
227
- },
228
- "weights": {
229
- "dynamic": false,
230
- "num_bits": 4,
231
- "type": "float",
232
- "group_size": 16
233
- },
234
- "targets": [
235
- "Linear"
236
- ]
237
- }
238
  },
239
- "ignore": [
240
- "lm_head",
241
- "model.layers.0*",
242
- "model.layers.1.*",
243
- "model.layers.10.mlp.shared_experts*",
244
- "model.layers.10.self_attn*",
245
- "model.layers.11.mlp.shared_experts*",
246
- "model.layers.11.self_attn*",
247
- "model.layers.12.mlp.shared_experts*",
248
- "model.layers.12.self_attn*",
249
- "model.layers.13.mlp.shared_experts*",
250
- "model.layers.13.self_attn*",
251
- "model.layers.14.mlp.shared_experts*",
252
- "model.layers.14.self_attn*",
253
- "model.layers.15.mlp.shared_experts*",
254
- "model.layers.15.self_attn*",
255
- "model.layers.16.mlp.shared_experts*",
256
- "model.layers.16.self_attn*",
257
- "model.layers.17.mlp.shared_experts*",
258
- "model.layers.17.self_attn*",
259
- "model.layers.18.mlp.shared_experts*",
260
- "model.layers.18.self_attn*",
261
- "model.layers.19.mlp.shared_experts*",
262
- "model.layers.19.self_attn*",
263
- "model.layers.2.*",
264
- "model.layers.20.mlp.shared_experts*",
265
- "model.layers.20.self_attn*",
266
- "model.layers.21.mlp.shared_experts*",
267
- "model.layers.21.self_attn*",
268
- "model.layers.22.mlp.shared_experts*",
269
- "model.layers.22.self_attn*",
270
- "model.layers.23.mlp.shared_experts*",
271
- "model.layers.23.self_attn*",
272
- "model.layers.24.mlp.shared_experts*",
273
- "model.layers.24.self_attn*",
274
- "model.layers.25.mlp.shared_experts*",
275
- "model.layers.25.self_attn*",
276
- "model.layers.26.mlp.shared_experts*",
277
- "model.layers.26.self_attn*",
278
- "model.layers.27.mlp.shared_experts*",
279
- "model.layers.27.self_attn*",
280
- "model.layers.28.mlp.shared_experts*",
281
- "model.layers.28.self_attn*",
282
- "model.layers.29.mlp.shared_experts*",
283
- "model.layers.29.self_attn*",
284
- "model.layers.3.mlp.shared_experts*",
285
- "model.layers.3.self_attn*",
286
- "model.layers.30.mlp.shared_experts*",
287
- "model.layers.30.self_attn*",
288
- "model.layers.31.mlp.shared_experts*",
289
- "model.layers.31.self_attn*",
290
- "model.layers.32.mlp.shared_experts*",
291
- "model.layers.32.self_attn*",
292
- "model.layers.33.mlp.shared_experts*",
293
- "model.layers.33.self_attn*",
294
- "model.layers.34.mlp.shared_experts*",
295
- "model.layers.34.self_attn*",
296
- "model.layers.35.mlp.shared_experts*",
297
- "model.layers.35.self_attn*",
298
- "model.layers.36.mlp.shared_experts*",
299
- "model.layers.36.self_attn*",
300
- "model.layers.37.mlp.shared_experts*",
301
- "model.layers.37.self_attn*",
302
- "model.layers.38.mlp.shared_experts*",
303
- "model.layers.38.self_attn*",
304
- "model.layers.39.mlp.shared_experts*",
305
- "model.layers.39.self_attn*",
306
- "model.layers.4.mlp.shared_experts*",
307
- "model.layers.4.self_attn*",
308
- "model.layers.40.mlp.shared_experts*",
309
- "model.layers.40.self_attn*",
310
- "model.layers.41.mlp.shared_experts*",
311
- "model.layers.41.self_attn*",
312
- "model.layers.42.mlp.shared_experts*",
313
- "model.layers.42.self_attn*",
314
- "model.layers.43.mlp.shared_experts*",
315
- "model.layers.43.self_attn*",
316
- "model.layers.44.mlp.shared_experts*",
317
- "model.layers.44.self_attn*",
318
- "model.layers.45.mlp.shared_experts*",
319
- "model.layers.45.self_attn*",
320
- "model.layers.46.mlp.shared_experts*",
321
- "model.layers.46.self_attn*",
322
- "model.layers.47.mlp.shared_experts*",
323
- "model.layers.47.self_attn*",
324
- "model.layers.48.mlp.shared_experts*",
325
- "model.layers.48.self_attn*",
326
- "model.layers.49.mlp.shared_experts*",
327
- "model.layers.49.self_attn*",
328
- "model.layers.5.mlp.shared_experts*",
329
- "model.layers.5.self_attn*",
330
- "model.layers.50.mlp.shared_experts*",
331
- "model.layers.50.self_attn*",
332
- "model.layers.51.mlp.shared_experts*",
333
- "model.layers.51.self_attn*",
334
- "model.layers.52.mlp.shared_experts*",
335
- "model.layers.52.self_attn*",
336
- "model.layers.53.mlp.shared_experts*",
337
- "model.layers.53.self_attn*",
338
- "model.layers.54.mlp.shared_experts*",
339
- "model.layers.54.self_attn*",
340
- "model.layers.55.mlp.shared_experts*",
341
- "model.layers.55.self_attn*",
342
- "model.layers.56.mlp.shared_experts*",
343
- "model.layers.56.self_attn*",
344
- "model.layers.57.mlp.shared_experts*",
345
- "model.layers.57.self_attn*",
346
- "model.layers.58.mlp.shared_experts*",
347
- "model.layers.58.self_attn*",
348
- "model.layers.59.mlp.shared_experts*",
349
- "model.layers.59.self_attn*",
350
- "model.layers.6.mlp.shared_experts*",
351
- "model.layers.6.self_attn*",
352
- "model.layers.60.mlp.shared_experts*",
353
- "model.layers.60.self_attn*",
354
- "model.layers.61.mlp.shared_experts*",
355
- "model.layers.61.self_attn*",
356
- "model.layers.62.mlp.shared_experts*",
357
- "model.layers.62.self_attn*",
358
- "model.layers.63.mlp.shared_experts*",
359
- "model.layers.63.self_attn*",
360
- "model.layers.64.mlp.shared_experts*",
361
- "model.layers.64.self_attn*",
362
- "model.layers.65.mlp.shared_experts*",
363
- "model.layers.65.self_attn*",
364
- "model.layers.66.mlp.shared_experts*",
365
- "model.layers.66.self_attn*",
366
- "model.layers.67.mlp.shared_experts*",
367
- "model.layers.67.self_attn*",
368
- "model.layers.68.mlp.shared_experts*",
369
- "model.layers.68.self_attn*",
370
- "model.layers.69.mlp.shared_experts*",
371
- "model.layers.69.self_attn*",
372
- "model.layers.7.mlp.shared_experts*",
373
- "model.layers.7.self_attn*",
374
- "model.layers.70.mlp.shared_experts*",
375
- "model.layers.70.self_attn*",
376
- "model.layers.71.mlp.shared_experts*",
377
- "model.layers.71.self_attn*",
378
- "model.layers.72.mlp.shared_experts*",
379
- "model.layers.72.self_attn*",
380
- "model.layers.73.mlp.shared_experts*",
381
- "model.layers.73.self_attn*",
382
- "model.layers.74.mlp.shared_experts*",
383
- "model.layers.74.self_attn*",
384
- "model.layers.75.mlp.shared_experts*",
385
- "model.layers.75.self_attn*",
386
- "model.layers.76.mlp.shared_experts*",
387
- "model.layers.76.self_attn*",
388
- "model.layers.77.mlp.shared_experts*",
389
- "model.layers.77.self_attn*",
390
- "model.layers.8.mlp.shared_experts*",
391
- "model.layers.8.self_attn*",
392
- "model.layers.9.mlp.shared_experts*",
393
- "model.layers.9.self_attn*"
394
- ],
395
- "quant_algo": "NVFP4",
396
- "producer": {
397
- "name": "modelopt",
398
- "version": "0.45.0.dev44+gc273ddb8a.d20260509"
399
  },
400
- "quant_method": "modelopt"
401
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
402
  }
 
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
+ "hidden_act": "silu",
17
+ "hidden_size": 6144,
18
+ "index_head_dim": 128,
19
+ "index_n_heads": 32,
20
+ "index_topk": 2048,
21
+ "indexer_rope_interleave": true,
22
+ "indexer_types": [
23
+ "full",
24
+ "full",
25
+ "full",
26
+ "full",
27
+ "full",
28
+ "full",
29
+ "full",
30
+ "full",
31
+ "full",
32
+ "full",
33
+ "full",
34
+ "full",
35
+ "full",
36
+ "full",
37
+ "full",
38
+ "full",
39
+ "full",
40
+ "full",
41
+ "full",
42
+ "full",
43
+ "full",
44
+ "full",
45
+ "full",
46
+ "full",
47
+ "full",
48
+ "full",
49
+ "full",
50
+ "full",
51
+ "full",
52
+ "full",
53
+ "full",
54
+ "full",
55
+ "full",
56
+ "full",
57
+ "full",
58
+ "full",
59
+ "full",
60
+ "full",
61
+ "full",
62
+ "full",
63
+ "full",
64
+ "full",
65
+ "full",
66
+ "full",
67
+ "full",
68
+ "full",
69
+ "full",
70
+ "full",
71
+ "full",
72
+ "full",
73
+ "full",
74
+ "full",
75
+ "full",
76
+ "full",
77
+ "full",
78
+ "full",
79
+ "full",
80
+ "full",
81
+ "full",
82
+ "full",
83
+ "full",
84
+ "full",
85
+ "full",
86
+ "full",
87
+ "full",
88
+ "full",
89
+ "full",
90
+ "full",
91
+ "full",
92
+ "full",
93
+ "full",
94
+ "full",
95
+ "full",
96
+ "full",
97
+ "full",
98
+ "full",
99
+ "full",
100
+ "full"
101
+ ],
102
+ "initializer_range": 0.02,
103
+ "intermediate_size": 12288,
104
+ "kv_lora_rank": 512,
105
+ "max_position_embeddings": 202752,
106
+ "mlp_layer_types": [
107
+ "dense",
108
+ "dense",
109
+ "dense",
110
+ "sparse",
111
+ "sparse",
112
+ "sparse",
113
+ "sparse",
114
+ "sparse",
115
+ "sparse",
116
+ "sparse",
117
+ "sparse",
118
+ "sparse",
119
+ "sparse",
120
+ "sparse",
121
+ "sparse",
122
+ "sparse",
123
+ "sparse",
124
+ "sparse",
125
+ "sparse",
126
+ "sparse",
127
+ "sparse",
128
+ "sparse",
129
+ "sparse",
130
+ "sparse",
131
+ "sparse",
132
+ "sparse",
133
+ "sparse",
134
+ "sparse",
135
+ "sparse",
136
+ "sparse",
137
+ "sparse",
138
+ "sparse",
139
+ "sparse",
140
+ "sparse",
141
+ "sparse",
142
+ "sparse",
143
+ "sparse",
144
+ "sparse",
145
+ "sparse",
146
+ "sparse",
147
+ "sparse",
148
+ "sparse",
149
+ "sparse",
150
+ "sparse",
151
+ "sparse",
152
+ "sparse",
153
+ "sparse",
154
+ "sparse",
155
+ "sparse",
156
+ "sparse",
157
+ "sparse",
158
+ "sparse",
159
+ "sparse",
160
+ "sparse",
161
+ "sparse",
162
+ "sparse",
163
+ "sparse",
164
+ "sparse",
165
+ "sparse",
166
+ "sparse",
167
+ "sparse",
168
+ "sparse",
169
+ "sparse",
170
+ "sparse",
171
+ "sparse",
172
+ "sparse",
173
+ "sparse",
174
+ "sparse",
175
+ "sparse",
176
+ "sparse",
177
+ "sparse",
178
+ "sparse",
179
+ "sparse",
180
+ "sparse",
181
+ "sparse",
182
+ "sparse",
183
+ "sparse",
184
+ "sparse"
185
+ ],
186
+ "model_type": "glm_moe_dsa",
187
+ "moe_intermediate_size": 2048,
188
+ "moe_layer_freq": 1,
189
+ "n_group": 1,
190
+ "n_routed_experts": 256,
191
+ "n_shared_experts": 1,
192
+ "norm_topk_prob": true,
193
+ "num_attention_heads": 64,
194
+ "num_experts_per_tok": 8,
195
+ "num_hidden_layers": 78,
196
+ "num_key_value_heads": 64,
197
+ "num_nextn_predict_layers": 1,
198
+ "pad_token_id": 154820,
199
+ "pretraining_tp": 1,
200
+ "q_lora_rank": 2048,
201
+ "qk_head_dim": 256,
202
+ "qk_nope_head_dim": 192,
203
+ "qk_rope_head_dim": 64,
204
+ "rms_norm_eps": 1e-05,
205
+ "rope_interleave": true,
206
+ "rope_parameters": {
207
+ "rope_theta": 1000000,
208
+ "rope_type": "default"
209
+ },
210
+ "routed_scaling_factor": 2.5,
211
+ "scoring_func": "sigmoid",
212
+ "tie_word_embeddings": false,
213
+ "topk_group": 1,
214
+ "topk_method": "noaux_tc",
215
+ "transformers_version": "5.8.0",
216
+ "use_cache": true,
217
+ "v_head_dim": 256,
218
+ "vocab_size": 154880,
219
+ "quantization_config": {
220
+ "config_groups": {
221
+ "group_0": {
222
+ "input_activations": {
223
+ "dynamic": false,
224
+ "num_bits": 4,
225
+ "type": "float",
226
+ "group_size": 16
 
 
 
 
 
 
 
 
 
 
 
227
  },
228
+ "weights": {
229
+ "dynamic": false,
230
+ "num_bits": 4,
231
+ "type": "float",
232
+ "group_size": 16
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
233
  },
234
+ "targets": [
235
+ "Linear"
236
+ ]
237
+ }
238
+ },
239
+ "ignore": [
240
+ "lm_head",
241
+ "model.layers.0*",
242
+ "model.layers.1.*",
243
+ "model.layers.10.mlp.shared_experts*",
244
+ "model.layers.10.self_attn*",
245
+ "model.layers.11.mlp.shared_experts*",
246
+ "model.layers.11.self_attn*",
247
+ "model.layers.12.mlp.shared_experts*",
248
+ "model.layers.12.self_attn*",
249
+ "model.layers.13.mlp.shared_experts*",
250
+ "model.layers.13.self_attn*",
251
+ "model.layers.14.mlp.shared_experts*",
252
+ "model.layers.14.self_attn*",
253
+ "model.layers.15.mlp.shared_experts*",
254
+ "model.layers.15.self_attn*",
255
+ "model.layers.16.mlp.shared_experts*",
256
+ "model.layers.16.self_attn*",
257
+ "model.layers.17.mlp.shared_experts*",
258
+ "model.layers.17.self_attn*",
259
+ "model.layers.18.mlp.shared_experts*",
260
+ "model.layers.18.self_attn*",
261
+ "model.layers.19.mlp.shared_experts*",
262
+ "model.layers.19.self_attn*",
263
+ "model.layers.2.*",
264
+ "model.layers.20.mlp.shared_experts*",
265
+ "model.layers.20.self_attn*",
266
+ "model.layers.21.mlp.shared_experts*",
267
+ "model.layers.21.self_attn*",
268
+ "model.layers.22.mlp.shared_experts*",
269
+ "model.layers.22.self_attn*",
270
+ "model.layers.23.mlp.shared_experts*",
271
+ "model.layers.23.self_attn*",
272
+ "model.layers.24.mlp.shared_experts*",
273
+ "model.layers.24.self_attn*",
274
+ "model.layers.25.mlp.shared_experts*",
275
+ "model.layers.25.self_attn*",
276
+ "model.layers.26.mlp.shared_experts*",
277
+ "model.layers.26.self_attn*",
278
+ "model.layers.27.mlp.shared_experts*",
279
+ "model.layers.27.self_attn*",
280
+ "model.layers.28.mlp.shared_experts*",
281
+ "model.layers.28.self_attn*",
282
+ "model.layers.29.mlp.shared_experts*",
283
+ "model.layers.29.self_attn*",
284
+ "model.layers.3.mlp.shared_experts*",
285
+ "model.layers.3.self_attn*",
286
+ "model.layers.30.mlp.shared_experts*",
287
+ "model.layers.30.self_attn*",
288
+ "model.layers.31.mlp.shared_experts*",
289
+ "model.layers.31.self_attn*",
290
+ "model.layers.32.mlp.shared_experts*",
291
+ "model.layers.32.self_attn*",
292
+ "model.layers.33.mlp.shared_experts*",
293
+ "model.layers.33.self_attn*",
294
+ "model.layers.34.mlp.shared_experts*",
295
+ "model.layers.34.self_attn*",
296
+ "model.layers.35.mlp.shared_experts*",
297
+ "model.layers.35.self_attn*",
298
+ "model.layers.36.mlp.shared_experts*",
299
+ "model.layers.36.self_attn*",
300
+ "model.layers.37.mlp.shared_experts*",
301
+ "model.layers.37.self_attn*",
302
+ "model.layers.38.mlp.shared_experts*",
303
+ "model.layers.38.self_attn*",
304
+ "model.layers.39.mlp.shared_experts*",
305
+ "model.layers.39.self_attn*",
306
+ "model.layers.4.mlp.shared_experts*",
307
+ "model.layers.4.self_attn*",
308
+ "model.layers.40.mlp.shared_experts*",
309
+ "model.layers.40.self_attn*",
310
+ "model.layers.41.mlp.shared_experts*",
311
+ "model.layers.41.self_attn*",
312
+ "model.layers.42.mlp.shared_experts*",
313
+ "model.layers.42.self_attn*",
314
+ "model.layers.43.mlp.shared_experts*",
315
+ "model.layers.43.self_attn*",
316
+ "model.layers.44.mlp.shared_experts*",
317
+ "model.layers.44.self_attn*",
318
+ "model.layers.45.mlp.shared_experts*",
319
+ "model.layers.45.self_attn*",
320
+ "model.layers.46.mlp.shared_experts*",
321
+ "model.layers.46.self_attn*",
322
+ "model.layers.47.mlp.shared_experts*",
323
+ "model.layers.47.self_attn*",
324
+ "model.layers.48.mlp.shared_experts*",
325
+ "model.layers.48.self_attn*",
326
+ "model.layers.49.mlp.shared_experts*",
327
+ "model.layers.49.self_attn*",
328
+ "model.layers.5.mlp.shared_experts*",
329
+ "model.layers.5.self_attn*",
330
+ "model.layers.50.mlp.shared_experts*",
331
+ "model.layers.50.self_attn*",
332
+ "model.layers.51.mlp.shared_experts*",
333
+ "model.layers.51.self_attn*",
334
+ "model.layers.52.mlp.shared_experts*",
335
+ "model.layers.52.self_attn*",
336
+ "model.layers.53.mlp.shared_experts*",
337
+ "model.layers.53.self_attn*",
338
+ "model.layers.54.mlp.shared_experts*",
339
+ "model.layers.54.self_attn*",
340
+ "model.layers.55.mlp.shared_experts*",
341
+ "model.layers.55.self_attn*",
342
+ "model.layers.56.mlp.shared_experts*",
343
+ "model.layers.56.self_attn*",
344
+ "model.layers.57.mlp.shared_experts*",
345
+ "model.layers.57.self_attn*",
346
+ "model.layers.58.mlp.shared_experts*",
347
+ "model.layers.58.self_attn*",
348
+ "model.layers.59.mlp.shared_experts*",
349
+ "model.layers.59.self_attn*",
350
+ "model.layers.6.mlp.shared_experts*",
351
+ "model.layers.6.self_attn*",
352
+ "model.layers.60.mlp.shared_experts*",
353
+ "model.layers.60.self_attn*",
354
+ "model.layers.61.mlp.shared_experts*",
355
+ "model.layers.61.self_attn*",
356
+ "model.layers.62.mlp.shared_experts*",
357
+ "model.layers.62.self_attn*",
358
+ "model.layers.63.mlp.shared_experts*",
359
+ "model.layers.63.self_attn*",
360
+ "model.layers.64.mlp.shared_experts*",
361
+ "model.layers.64.self_attn*",
362
+ "model.layers.65.mlp.shared_experts*",
363
+ "model.layers.65.self_attn*",
364
+ "model.layers.66.mlp.shared_experts*",
365
+ "model.layers.66.self_attn*",
366
+ "model.layers.67.mlp.shared_experts*",
367
+ "model.layers.67.self_attn*",
368
+ "model.layers.68.mlp.shared_experts*",
369
+ "model.layers.68.self_attn*",
370
+ "model.layers.69.mlp.shared_experts*",
371
+ "model.layers.69.self_attn*",
372
+ "model.layers.7.mlp.shared_experts*",
373
+ "model.layers.7.self_attn*",
374
+ "model.layers.70.mlp.shared_experts*",
375
+ "model.layers.70.self_attn*",
376
+ "model.layers.71.mlp.shared_experts*",
377
+ "model.layers.71.self_attn*",
378
+ "model.layers.72.mlp.shared_experts*",
379
+ "model.layers.72.self_attn*",
380
+ "model.layers.73.mlp.shared_experts*",
381
+ "model.layers.73.self_attn*",
382
+ "model.layers.74.mlp.shared_experts*",
383
+ "model.layers.74.self_attn*",
384
+ "model.layers.75.mlp.shared_experts*",
385
+ "model.layers.75.self_attn*",
386
+ "model.layers.76.mlp.shared_experts*",
387
+ "model.layers.76.self_attn*",
388
+ "model.layers.77.mlp.shared_experts*",
389
+ "model.layers.77.self_attn*",
390
+ "model.layers.78*",
391
+ "model.layers.8.mlp.shared_experts*",
392
+ "model.layers.8.self_attn*",
393
+ "model.layers.9.mlp.shared_experts*",
394
+ "model.layers.9.self_attn*"
395
+ ],
396
+ "quant_algo": "NVFP4",
397
+ "producer": {
398
+ "name": "modelopt",
399
+ "version": "0.45.0.dev44+gc273ddb8a.d20260509"
400
+ },
401
+ "quant_method": "modelopt"
402
+ }
403
  }
config.json.bak ADDED
@@ -0,0 +1,402 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "hidden_act": "silu",
17
+ "hidden_size": 6144,
18
+ "index_head_dim": 128,
19
+ "index_n_heads": 32,
20
+ "index_topk": 2048,
21
+ "indexer_rope_interleave": true,
22
+ "indexer_types": [
23
+ "full",
24
+ "full",
25
+ "full",
26
+ "full",
27
+ "full",
28
+ "full",
29
+ "full",
30
+ "full",
31
+ "full",
32
+ "full",
33
+ "full",
34
+ "full",
35
+ "full",
36
+ "full",
37
+ "full",
38
+ "full",
39
+ "full",
40
+ "full",
41
+ "full",
42
+ "full",
43
+ "full",
44
+ "full",
45
+ "full",
46
+ "full",
47
+ "full",
48
+ "full",
49
+ "full",
50
+ "full",
51
+ "full",
52
+ "full",
53
+ "full",
54
+ "full",
55
+ "full",
56
+ "full",
57
+ "full",
58
+ "full",
59
+ "full",
60
+ "full",
61
+ "full",
62
+ "full",
63
+ "full",
64
+ "full",
65
+ "full",
66
+ "full",
67
+ "full",
68
+ "full",
69
+ "full",
70
+ "full",
71
+ "full",
72
+ "full",
73
+ "full",
74
+ "full",
75
+ "full",
76
+ "full",
77
+ "full",
78
+ "full",
79
+ "full",
80
+ "full",
81
+ "full",
82
+ "full",
83
+ "full",
84
+ "full",
85
+ "full",
86
+ "full",
87
+ "full",
88
+ "full",
89
+ "full",
90
+ "full",
91
+ "full",
92
+ "full",
93
+ "full",
94
+ "full",
95
+ "full",
96
+ "full",
97
+ "full",
98
+ "full",
99
+ "full",
100
+ "full"
101
+ ],
102
+ "initializer_range": 0.02,
103
+ "intermediate_size": 12288,
104
+ "kv_lora_rank": 512,
105
+ "max_position_embeddings": 202752,
106
+ "mlp_layer_types": [
107
+ "dense",
108
+ "dense",
109
+ "dense",
110
+ "sparse",
111
+ "sparse",
112
+ "sparse",
113
+ "sparse",
114
+ "sparse",
115
+ "sparse",
116
+ "sparse",
117
+ "sparse",
118
+ "sparse",
119
+ "sparse",
120
+ "sparse",
121
+ "sparse",
122
+ "sparse",
123
+ "sparse",
124
+ "sparse",
125
+ "sparse",
126
+ "sparse",
127
+ "sparse",
128
+ "sparse",
129
+ "sparse",
130
+ "sparse",
131
+ "sparse",
132
+ "sparse",
133
+ "sparse",
134
+ "sparse",
135
+ "sparse",
136
+ "sparse",
137
+ "sparse",
138
+ "sparse",
139
+ "sparse",
140
+ "sparse",
141
+ "sparse",
142
+ "sparse",
143
+ "sparse",
144
+ "sparse",
145
+ "sparse",
146
+ "sparse",
147
+ "sparse",
148
+ "sparse",
149
+ "sparse",
150
+ "sparse",
151
+ "sparse",
152
+ "sparse",
153
+ "sparse",
154
+ "sparse",
155
+ "sparse",
156
+ "sparse",
157
+ "sparse",
158
+ "sparse",
159
+ "sparse",
160
+ "sparse",
161
+ "sparse",
162
+ "sparse",
163
+ "sparse",
164
+ "sparse",
165
+ "sparse",
166
+ "sparse",
167
+ "sparse",
168
+ "sparse",
169
+ "sparse",
170
+ "sparse",
171
+ "sparse",
172
+ "sparse",
173
+ "sparse",
174
+ "sparse",
175
+ "sparse",
176
+ "sparse",
177
+ "sparse",
178
+ "sparse",
179
+ "sparse",
180
+ "sparse",
181
+ "sparse",
182
+ "sparse",
183
+ "sparse",
184
+ "sparse"
185
+ ],
186
+ "model_type": "glm_moe_dsa",
187
+ "moe_intermediate_size": 2048,
188
+ "moe_layer_freq": 1,
189
+ "n_group": 1,
190
+ "n_routed_experts": 256,
191
+ "n_shared_experts": 1,
192
+ "norm_topk_prob": true,
193
+ "num_attention_heads": 64,
194
+ "num_experts_per_tok": 8,
195
+ "num_hidden_layers": 78,
196
+ "num_key_value_heads": 64,
197
+ "num_nextn_predict_layers": 1,
198
+ "pad_token_id": 154820,
199
+ "pretraining_tp": 1,
200
+ "q_lora_rank": 2048,
201
+ "qk_head_dim": 256,
202
+ "qk_nope_head_dim": 192,
203
+ "qk_rope_head_dim": 64,
204
+ "rms_norm_eps": 1e-05,
205
+ "rope_interleave": true,
206
+ "rope_parameters": {
207
+ "rope_theta": 1000000,
208
+ "rope_type": "default"
209
+ },
210
+ "routed_scaling_factor": 2.5,
211
+ "scoring_func": "sigmoid",
212
+ "tie_word_embeddings": false,
213
+ "topk_group": 1,
214
+ "topk_method": "noaux_tc",
215
+ "transformers_version": "5.8.0",
216
+ "use_cache": true,
217
+ "v_head_dim": 256,
218
+ "vocab_size": 154880,
219
+ "quantization_config": {
220
+ "config_groups": {
221
+ "group_0": {
222
+ "input_activations": {
223
+ "dynamic": false,
224
+ "num_bits": 4,
225
+ "type": "float",
226
+ "group_size": 16
227
+ },
228
+ "weights": {
229
+ "dynamic": false,
230
+ "num_bits": 4,
231
+ "type": "float",
232
+ "group_size": 16
233
+ },
234
+ "targets": [
235
+ "Linear"
236
+ ]
237
+ }
238
+ },
239
+ "ignore": [
240
+ "lm_head",
241
+ "model.layers.0*",
242
+ "model.layers.1.*",
243
+ "model.layers.10.mlp.shared_experts*",
244
+ "model.layers.10.self_attn*",
245
+ "model.layers.11.mlp.shared_experts*",
246
+ "model.layers.11.self_attn*",
247
+ "model.layers.12.mlp.shared_experts*",
248
+ "model.layers.12.self_attn*",
249
+ "model.layers.13.mlp.shared_experts*",
250
+ "model.layers.13.self_attn*",
251
+ "model.layers.14.mlp.shared_experts*",
252
+ "model.layers.14.self_attn*",
253
+ "model.layers.15.mlp.shared_experts*",
254
+ "model.layers.15.self_attn*",
255
+ "model.layers.16.mlp.shared_experts*",
256
+ "model.layers.16.self_attn*",
257
+ "model.layers.17.mlp.shared_experts*",
258
+ "model.layers.17.self_attn*",
259
+ "model.layers.18.mlp.shared_experts*",
260
+ "model.layers.18.self_attn*",
261
+ "model.layers.19.mlp.shared_experts*",
262
+ "model.layers.19.self_attn*",
263
+ "model.layers.2.*",
264
+ "model.layers.20.mlp.shared_experts*",
265
+ "model.layers.20.self_attn*",
266
+ "model.layers.21.mlp.shared_experts*",
267
+ "model.layers.21.self_attn*",
268
+ "model.layers.22.mlp.shared_experts*",
269
+ "model.layers.22.self_attn*",
270
+ "model.layers.23.mlp.shared_experts*",
271
+ "model.layers.23.self_attn*",
272
+ "model.layers.24.mlp.shared_experts*",
273
+ "model.layers.24.self_attn*",
274
+ "model.layers.25.mlp.shared_experts*",
275
+ "model.layers.25.self_attn*",
276
+ "model.layers.26.mlp.shared_experts*",
277
+ "model.layers.26.self_attn*",
278
+ "model.layers.27.mlp.shared_experts*",
279
+ "model.layers.27.self_attn*",
280
+ "model.layers.28.mlp.shared_experts*",
281
+ "model.layers.28.self_attn*",
282
+ "model.layers.29.mlp.shared_experts*",
283
+ "model.layers.29.self_attn*",
284
+ "model.layers.3.mlp.shared_experts*",
285
+ "model.layers.3.self_attn*",
286
+ "model.layers.30.mlp.shared_experts*",
287
+ "model.layers.30.self_attn*",
288
+ "model.layers.31.mlp.shared_experts*",
289
+ "model.layers.31.self_attn*",
290
+ "model.layers.32.mlp.shared_experts*",
291
+ "model.layers.32.self_attn*",
292
+ "model.layers.33.mlp.shared_experts*",
293
+ "model.layers.33.self_attn*",
294
+ "model.layers.34.mlp.shared_experts*",
295
+ "model.layers.34.self_attn*",
296
+ "model.layers.35.mlp.shared_experts*",
297
+ "model.layers.35.self_attn*",
298
+ "model.layers.36.mlp.shared_experts*",
299
+ "model.layers.36.self_attn*",
300
+ "model.layers.37.mlp.shared_experts*",
301
+ "model.layers.37.self_attn*",
302
+ "model.layers.38.mlp.shared_experts*",
303
+ "model.layers.38.self_attn*",
304
+ "model.layers.39.mlp.shared_experts*",
305
+ "model.layers.39.self_attn*",
306
+ "model.layers.4.mlp.shared_experts*",
307
+ "model.layers.4.self_attn*",
308
+ "model.layers.40.mlp.shared_experts*",
309
+ "model.layers.40.self_attn*",
310
+ "model.layers.41.mlp.shared_experts*",
311
+ "model.layers.41.self_attn*",
312
+ "model.layers.42.mlp.shared_experts*",
313
+ "model.layers.42.self_attn*",
314
+ "model.layers.43.mlp.shared_experts*",
315
+ "model.layers.43.self_attn*",
316
+ "model.layers.44.mlp.shared_experts*",
317
+ "model.layers.44.self_attn*",
318
+ "model.layers.45.mlp.shared_experts*",
319
+ "model.layers.45.self_attn*",
320
+ "model.layers.46.mlp.shared_experts*",
321
+ "model.layers.46.self_attn*",
322
+ "model.layers.47.mlp.shared_experts*",
323
+ "model.layers.47.self_attn*",
324
+ "model.layers.48.mlp.shared_experts*",
325
+ "model.layers.48.self_attn*",
326
+ "model.layers.49.mlp.shared_experts*",
327
+ "model.layers.49.self_attn*",
328
+ "model.layers.5.mlp.shared_experts*",
329
+ "model.layers.5.self_attn*",
330
+ "model.layers.50.mlp.shared_experts*",
331
+ "model.layers.50.self_attn*",
332
+ "model.layers.51.mlp.shared_experts*",
333
+ "model.layers.51.self_attn*",
334
+ "model.layers.52.mlp.shared_experts*",
335
+ "model.layers.52.self_attn*",
336
+ "model.layers.53.mlp.shared_experts*",
337
+ "model.layers.53.self_attn*",
338
+ "model.layers.54.mlp.shared_experts*",
339
+ "model.layers.54.self_attn*",
340
+ "model.layers.55.mlp.shared_experts*",
341
+ "model.layers.55.self_attn*",
342
+ "model.layers.56.mlp.shared_experts*",
343
+ "model.layers.56.self_attn*",
344
+ "model.layers.57.mlp.shared_experts*",
345
+ "model.layers.57.self_attn*",
346
+ "model.layers.58.mlp.shared_experts*",
347
+ "model.layers.58.self_attn*",
348
+ "model.layers.59.mlp.shared_experts*",
349
+ "model.layers.59.self_attn*",
350
+ "model.layers.6.mlp.shared_experts*",
351
+ "model.layers.6.self_attn*",
352
+ "model.layers.60.mlp.shared_experts*",
353
+ "model.layers.60.self_attn*",
354
+ "model.layers.61.mlp.shared_experts*",
355
+ "model.layers.61.self_attn*",
356
+ "model.layers.62.mlp.shared_experts*",
357
+ "model.layers.62.self_attn*",
358
+ "model.layers.63.mlp.shared_experts*",
359
+ "model.layers.63.self_attn*",
360
+ "model.layers.64.mlp.shared_experts*",
361
+ "model.layers.64.self_attn*",
362
+ "model.layers.65.mlp.shared_experts*",
363
+ "model.layers.65.self_attn*",
364
+ "model.layers.66.mlp.shared_experts*",
365
+ "model.layers.66.self_attn*",
366
+ "model.layers.67.mlp.shared_experts*",
367
+ "model.layers.67.self_attn*",
368
+ "model.layers.68.mlp.shared_experts*",
369
+ "model.layers.68.self_attn*",
370
+ "model.layers.69.mlp.shared_experts*",
371
+ "model.layers.69.self_attn*",
372
+ "model.layers.7.mlp.shared_experts*",
373
+ "model.layers.7.self_attn*",
374
+ "model.layers.70.mlp.shared_experts*",
375
+ "model.layers.70.self_attn*",
376
+ "model.layers.71.mlp.shared_experts*",
377
+ "model.layers.71.self_attn*",
378
+ "model.layers.72.mlp.shared_experts*",
379
+ "model.layers.72.self_attn*",
380
+ "model.layers.73.mlp.shared_experts*",
381
+ "model.layers.73.self_attn*",
382
+ "model.layers.74.mlp.shared_experts*",
383
+ "model.layers.74.self_attn*",
384
+ "model.layers.75.mlp.shared_experts*",
385
+ "model.layers.75.self_attn*",
386
+ "model.layers.76.mlp.shared_experts*",
387
+ "model.layers.76.self_attn*",
388
+ "model.layers.77.mlp.shared_experts*",
389
+ "model.layers.77.self_attn*",
390
+ "model.layers.8.mlp.shared_experts*",
391
+ "model.layers.8.self_attn*",
392
+ "model.layers.9.mlp.shared_experts*",
393
+ "model.layers.9.self_attn*"
394
+ ],
395
+ "quant_algo": "NVFP4",
396
+ "producer": {
397
+ "name": "modelopt",
398
+ "version": "0.45.0.dev44+gc273ddb8a.d20260509"
399
+ },
400
+ "quant_method": "modelopt"
401
+ }
402
+ }
hf_quant_config.json CHANGED
@@ -1,167 +1,168 @@
1
  {
2
- "producer": {
3
- "name": "modelopt",
4
- "version": "0.45.0.dev44+gc273ddb8a.d20260509"
5
- },
6
- "quantization": {
7
- "quant_algo": "NVFP4",
8
- "kv_cache_quant_algo": null,
9
- "group_size": 16,
10
- "exclude_modules": [
11
- "lm_head",
12
- "model.layers.0*",
13
- "model.layers.1.*",
14
- "model.layers.10.mlp.shared_experts*",
15
- "model.layers.10.self_attn*",
16
- "model.layers.11.mlp.shared_experts*",
17
- "model.layers.11.self_attn*",
18
- "model.layers.12.mlp.shared_experts*",
19
- "model.layers.12.self_attn*",
20
- "model.layers.13.mlp.shared_experts*",
21
- "model.layers.13.self_attn*",
22
- "model.layers.14.mlp.shared_experts*",
23
- "model.layers.14.self_attn*",
24
- "model.layers.15.mlp.shared_experts*",
25
- "model.layers.15.self_attn*",
26
- "model.layers.16.mlp.shared_experts*",
27
- "model.layers.16.self_attn*",
28
- "model.layers.17.mlp.shared_experts*",
29
- "model.layers.17.self_attn*",
30
- "model.layers.18.mlp.shared_experts*",
31
- "model.layers.18.self_attn*",
32
- "model.layers.19.mlp.shared_experts*",
33
- "model.layers.19.self_attn*",
34
- "model.layers.2.*",
35
- "model.layers.20.mlp.shared_experts*",
36
- "model.layers.20.self_attn*",
37
- "model.layers.21.mlp.shared_experts*",
38
- "model.layers.21.self_attn*",
39
- "model.layers.22.mlp.shared_experts*",
40
- "model.layers.22.self_attn*",
41
- "model.layers.23.mlp.shared_experts*",
42
- "model.layers.23.self_attn*",
43
- "model.layers.24.mlp.shared_experts*",
44
- "model.layers.24.self_attn*",
45
- "model.layers.25.mlp.shared_experts*",
46
- "model.layers.25.self_attn*",
47
- "model.layers.26.mlp.shared_experts*",
48
- "model.layers.26.self_attn*",
49
- "model.layers.27.mlp.shared_experts*",
50
- "model.layers.27.self_attn*",
51
- "model.layers.28.mlp.shared_experts*",
52
- "model.layers.28.self_attn*",
53
- "model.layers.29.mlp.shared_experts*",
54
- "model.layers.29.self_attn*",
55
- "model.layers.3.mlp.shared_experts*",
56
- "model.layers.3.self_attn*",
57
- "model.layers.30.mlp.shared_experts*",
58
- "model.layers.30.self_attn*",
59
- "model.layers.31.mlp.shared_experts*",
60
- "model.layers.31.self_attn*",
61
- "model.layers.32.mlp.shared_experts*",
62
- "model.layers.32.self_attn*",
63
- "model.layers.33.mlp.shared_experts*",
64
- "model.layers.33.self_attn*",
65
- "model.layers.34.mlp.shared_experts*",
66
- "model.layers.34.self_attn*",
67
- "model.layers.35.mlp.shared_experts*",
68
- "model.layers.35.self_attn*",
69
- "model.layers.36.mlp.shared_experts*",
70
- "model.layers.36.self_attn*",
71
- "model.layers.37.mlp.shared_experts*",
72
- "model.layers.37.self_attn*",
73
- "model.layers.38.mlp.shared_experts*",
74
- "model.layers.38.self_attn*",
75
- "model.layers.39.mlp.shared_experts*",
76
- "model.layers.39.self_attn*",
77
- "model.layers.4.mlp.shared_experts*",
78
- "model.layers.4.self_attn*",
79
- "model.layers.40.mlp.shared_experts*",
80
- "model.layers.40.self_attn*",
81
- "model.layers.41.mlp.shared_experts*",
82
- "model.layers.41.self_attn*",
83
- "model.layers.42.mlp.shared_experts*",
84
- "model.layers.42.self_attn*",
85
- "model.layers.43.mlp.shared_experts*",
86
- "model.layers.43.self_attn*",
87
- "model.layers.44.mlp.shared_experts*",
88
- "model.layers.44.self_attn*",
89
- "model.layers.45.mlp.shared_experts*",
90
- "model.layers.45.self_attn*",
91
- "model.layers.46.mlp.shared_experts*",
92
- "model.layers.46.self_attn*",
93
- "model.layers.47.mlp.shared_experts*",
94
- "model.layers.47.self_attn*",
95
- "model.layers.48.mlp.shared_experts*",
96
- "model.layers.48.self_attn*",
97
- "model.layers.49.mlp.shared_experts*",
98
- "model.layers.49.self_attn*",
99
- "model.layers.5.mlp.shared_experts*",
100
- "model.layers.5.self_attn*",
101
- "model.layers.50.mlp.shared_experts*",
102
- "model.layers.50.self_attn*",
103
- "model.layers.51.mlp.shared_experts*",
104
- "model.layers.51.self_attn*",
105
- "model.layers.52.mlp.shared_experts*",
106
- "model.layers.52.self_attn*",
107
- "model.layers.53.mlp.shared_experts*",
108
- "model.layers.53.self_attn*",
109
- "model.layers.54.mlp.shared_experts*",
110
- "model.layers.54.self_attn*",
111
- "model.layers.55.mlp.shared_experts*",
112
- "model.layers.55.self_attn*",
113
- "model.layers.56.mlp.shared_experts*",
114
- "model.layers.56.self_attn*",
115
- "model.layers.57.mlp.shared_experts*",
116
- "model.layers.57.self_attn*",
117
- "model.layers.58.mlp.shared_experts*",
118
- "model.layers.58.self_attn*",
119
- "model.layers.59.mlp.shared_experts*",
120
- "model.layers.59.self_attn*",
121
- "model.layers.6.mlp.shared_experts*",
122
- "model.layers.6.self_attn*",
123
- "model.layers.60.mlp.shared_experts*",
124
- "model.layers.60.self_attn*",
125
- "model.layers.61.mlp.shared_experts*",
126
- "model.layers.61.self_attn*",
127
- "model.layers.62.mlp.shared_experts*",
128
- "model.layers.62.self_attn*",
129
- "model.layers.63.mlp.shared_experts*",
130
- "model.layers.63.self_attn*",
131
- "model.layers.64.mlp.shared_experts*",
132
- "model.layers.64.self_attn*",
133
- "model.layers.65.mlp.shared_experts*",
134
- "model.layers.65.self_attn*",
135
- "model.layers.66.mlp.shared_experts*",
136
- "model.layers.66.self_attn*",
137
- "model.layers.67.mlp.shared_experts*",
138
- "model.layers.67.self_attn*",
139
- "model.layers.68.mlp.shared_experts*",
140
- "model.layers.68.self_attn*",
141
- "model.layers.69.mlp.shared_experts*",
142
- "model.layers.69.self_attn*",
143
- "model.layers.7.mlp.shared_experts*",
144
- "model.layers.7.self_attn*",
145
- "model.layers.70.mlp.shared_experts*",
146
- "model.layers.70.self_attn*",
147
- "model.layers.71.mlp.shared_experts*",
148
- "model.layers.71.self_attn*",
149
- "model.layers.72.mlp.shared_experts*",
150
- "model.layers.72.self_attn*",
151
- "model.layers.73.mlp.shared_experts*",
152
- "model.layers.73.self_attn*",
153
- "model.layers.74.mlp.shared_experts*",
154
- "model.layers.74.self_attn*",
155
- "model.layers.75.mlp.shared_experts*",
156
- "model.layers.75.self_attn*",
157
- "model.layers.76.mlp.shared_experts*",
158
- "model.layers.76.self_attn*",
159
- "model.layers.77.mlp.shared_experts*",
160
- "model.layers.77.self_attn*",
161
- "model.layers.8.mlp.shared_experts*",
162
- "model.layers.8.self_attn*",
163
- "model.layers.9.mlp.shared_experts*",
164
- "model.layers.9.self_attn*"
165
- ]
166
- }
 
167
  }
 
1
  {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.45.0.dev44+gc273ddb8a.d20260509"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": null,
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "model.layers.0*",
13
+ "model.layers.1.*",
14
+ "model.layers.10.mlp.shared_experts*",
15
+ "model.layers.10.self_attn*",
16
+ "model.layers.11.mlp.shared_experts*",
17
+ "model.layers.11.self_attn*",
18
+ "model.layers.12.mlp.shared_experts*",
19
+ "model.layers.12.self_attn*",
20
+ "model.layers.13.mlp.shared_experts*",
21
+ "model.layers.13.self_attn*",
22
+ "model.layers.14.mlp.shared_experts*",
23
+ "model.layers.14.self_attn*",
24
+ "model.layers.15.mlp.shared_experts*",
25
+ "model.layers.15.self_attn*",
26
+ "model.layers.16.mlp.shared_experts*",
27
+ "model.layers.16.self_attn*",
28
+ "model.layers.17.mlp.shared_experts*",
29
+ "model.layers.17.self_attn*",
30
+ "model.layers.18.mlp.shared_experts*",
31
+ "model.layers.18.self_attn*",
32
+ "model.layers.19.mlp.shared_experts*",
33
+ "model.layers.19.self_attn*",
34
+ "model.layers.2.*",
35
+ "model.layers.20.mlp.shared_experts*",
36
+ "model.layers.20.self_attn*",
37
+ "model.layers.21.mlp.shared_experts*",
38
+ "model.layers.21.self_attn*",
39
+ "model.layers.22.mlp.shared_experts*",
40
+ "model.layers.22.self_attn*",
41
+ "model.layers.23.mlp.shared_experts*",
42
+ "model.layers.23.self_attn*",
43
+ "model.layers.24.mlp.shared_experts*",
44
+ "model.layers.24.self_attn*",
45
+ "model.layers.25.mlp.shared_experts*",
46
+ "model.layers.25.self_attn*",
47
+ "model.layers.26.mlp.shared_experts*",
48
+ "model.layers.26.self_attn*",
49
+ "model.layers.27.mlp.shared_experts*",
50
+ "model.layers.27.self_attn*",
51
+ "model.layers.28.mlp.shared_experts*",
52
+ "model.layers.28.self_attn*",
53
+ "model.layers.29.mlp.shared_experts*",
54
+ "model.layers.29.self_attn*",
55
+ "model.layers.3.mlp.shared_experts*",
56
+ "model.layers.3.self_attn*",
57
+ "model.layers.30.mlp.shared_experts*",
58
+ "model.layers.30.self_attn*",
59
+ "model.layers.31.mlp.shared_experts*",
60
+ "model.layers.31.self_attn*",
61
+ "model.layers.32.mlp.shared_experts*",
62
+ "model.layers.32.self_attn*",
63
+ "model.layers.33.mlp.shared_experts*",
64
+ "model.layers.33.self_attn*",
65
+ "model.layers.34.mlp.shared_experts*",
66
+ "model.layers.34.self_attn*",
67
+ "model.layers.35.mlp.shared_experts*",
68
+ "model.layers.35.self_attn*",
69
+ "model.layers.36.mlp.shared_experts*",
70
+ "model.layers.36.self_attn*",
71
+ "model.layers.37.mlp.shared_experts*",
72
+ "model.layers.37.self_attn*",
73
+ "model.layers.38.mlp.shared_experts*",
74
+ "model.layers.38.self_attn*",
75
+ "model.layers.39.mlp.shared_experts*",
76
+ "model.layers.39.self_attn*",
77
+ "model.layers.4.mlp.shared_experts*",
78
+ "model.layers.4.self_attn*",
79
+ "model.layers.40.mlp.shared_experts*",
80
+ "model.layers.40.self_attn*",
81
+ "model.layers.41.mlp.shared_experts*",
82
+ "model.layers.41.self_attn*",
83
+ "model.layers.42.mlp.shared_experts*",
84
+ "model.layers.42.self_attn*",
85
+ "model.layers.43.mlp.shared_experts*",
86
+ "model.layers.43.self_attn*",
87
+ "model.layers.44.mlp.shared_experts*",
88
+ "model.layers.44.self_attn*",
89
+ "model.layers.45.mlp.shared_experts*",
90
+ "model.layers.45.self_attn*",
91
+ "model.layers.46.mlp.shared_experts*",
92
+ "model.layers.46.self_attn*",
93
+ "model.layers.47.mlp.shared_experts*",
94
+ "model.layers.47.self_attn*",
95
+ "model.layers.48.mlp.shared_experts*",
96
+ "model.layers.48.self_attn*",
97
+ "model.layers.49.mlp.shared_experts*",
98
+ "model.layers.49.self_attn*",
99
+ "model.layers.5.mlp.shared_experts*",
100
+ "model.layers.5.self_attn*",
101
+ "model.layers.50.mlp.shared_experts*",
102
+ "model.layers.50.self_attn*",
103
+ "model.layers.51.mlp.shared_experts*",
104
+ "model.layers.51.self_attn*",
105
+ "model.layers.52.mlp.shared_experts*",
106
+ "model.layers.52.self_attn*",
107
+ "model.layers.53.mlp.shared_experts*",
108
+ "model.layers.53.self_attn*",
109
+ "model.layers.54.mlp.shared_experts*",
110
+ "model.layers.54.self_attn*",
111
+ "model.layers.55.mlp.shared_experts*",
112
+ "model.layers.55.self_attn*",
113
+ "model.layers.56.mlp.shared_experts*",
114
+ "model.layers.56.self_attn*",
115
+ "model.layers.57.mlp.shared_experts*",
116
+ "model.layers.57.self_attn*",
117
+ "model.layers.58.mlp.shared_experts*",
118
+ "model.layers.58.self_attn*",
119
+ "model.layers.59.mlp.shared_experts*",
120
+ "model.layers.59.self_attn*",
121
+ "model.layers.6.mlp.shared_experts*",
122
+ "model.layers.6.self_attn*",
123
+ "model.layers.60.mlp.shared_experts*",
124
+ "model.layers.60.self_attn*",
125
+ "model.layers.61.mlp.shared_experts*",
126
+ "model.layers.61.self_attn*",
127
+ "model.layers.62.mlp.shared_experts*",
128
+ "model.layers.62.self_attn*",
129
+ "model.layers.63.mlp.shared_experts*",
130
+ "model.layers.63.self_attn*",
131
+ "model.layers.64.mlp.shared_experts*",
132
+ "model.layers.64.self_attn*",
133
+ "model.layers.65.mlp.shared_experts*",
134
+ "model.layers.65.self_attn*",
135
+ "model.layers.66.mlp.shared_experts*",
136
+ "model.layers.66.self_attn*",
137
+ "model.layers.67.mlp.shared_experts*",
138
+ "model.layers.67.self_attn*",
139
+ "model.layers.68.mlp.shared_experts*",
140
+ "model.layers.68.self_attn*",
141
+ "model.layers.69.mlp.shared_experts*",
142
+ "model.layers.69.self_attn*",
143
+ "model.layers.7.mlp.shared_experts*",
144
+ "model.layers.7.self_attn*",
145
+ "model.layers.70.mlp.shared_experts*",
146
+ "model.layers.70.self_attn*",
147
+ "model.layers.71.mlp.shared_experts*",
148
+ "model.layers.71.self_attn*",
149
+ "model.layers.72.mlp.shared_experts*",
150
+ "model.layers.72.self_attn*",
151
+ "model.layers.73.mlp.shared_experts*",
152
+ "model.layers.73.self_attn*",
153
+ "model.layers.74.mlp.shared_experts*",
154
+ "model.layers.74.self_attn*",
155
+ "model.layers.75.mlp.shared_experts*",
156
+ "model.layers.75.self_attn*",
157
+ "model.layers.76.mlp.shared_experts*",
158
+ "model.layers.76.self_attn*",
159
+ "model.layers.77.mlp.shared_experts*",
160
+ "model.layers.77.self_attn*",
161
+ "model.layers.78*",
162
+ "model.layers.8.mlp.shared_experts*",
163
+ "model.layers.8.self_attn*",
164
+ "model.layers.9.mlp.shared_experts*",
165
+ "model.layers.9.self_attn*"
166
+ ]
167
+ }
168
  }
hf_quant_config.json.bak ADDED
@@ -0,0 +1,167 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "producer": {
3
+ "name": "modelopt",
4
+ "version": "0.45.0.dev44+gc273ddb8a.d20260509"
5
+ },
6
+ "quantization": {
7
+ "quant_algo": "NVFP4",
8
+ "kv_cache_quant_algo": null,
9
+ "group_size": 16,
10
+ "exclude_modules": [
11
+ "lm_head",
12
+ "model.layers.0*",
13
+ "model.layers.1.*",
14
+ "model.layers.10.mlp.shared_experts*",
15
+ "model.layers.10.self_attn*",
16
+ "model.layers.11.mlp.shared_experts*",
17
+ "model.layers.11.self_attn*",
18
+ "model.layers.12.mlp.shared_experts*",
19
+ "model.layers.12.self_attn*",
20
+ "model.layers.13.mlp.shared_experts*",
21
+ "model.layers.13.self_attn*",
22
+ "model.layers.14.mlp.shared_experts*",
23
+ "model.layers.14.self_attn*",
24
+ "model.layers.15.mlp.shared_experts*",
25
+ "model.layers.15.self_attn*",
26
+ "model.layers.16.mlp.shared_experts*",
27
+ "model.layers.16.self_attn*",
28
+ "model.layers.17.mlp.shared_experts*",
29
+ "model.layers.17.self_attn*",
30
+ "model.layers.18.mlp.shared_experts*",
31
+ "model.layers.18.self_attn*",
32
+ "model.layers.19.mlp.shared_experts*",
33
+ "model.layers.19.self_attn*",
34
+ "model.layers.2.*",
35
+ "model.layers.20.mlp.shared_experts*",
36
+ "model.layers.20.self_attn*",
37
+ "model.layers.21.mlp.shared_experts*",
38
+ "model.layers.21.self_attn*",
39
+ "model.layers.22.mlp.shared_experts*",
40
+ "model.layers.22.self_attn*",
41
+ "model.layers.23.mlp.shared_experts*",
42
+ "model.layers.23.self_attn*",
43
+ "model.layers.24.mlp.shared_experts*",
44
+ "model.layers.24.self_attn*",
45
+ "model.layers.25.mlp.shared_experts*",
46
+ "model.layers.25.self_attn*",
47
+ "model.layers.26.mlp.shared_experts*",
48
+ "model.layers.26.self_attn*",
49
+ "model.layers.27.mlp.shared_experts*",
50
+ "model.layers.27.self_attn*",
51
+ "model.layers.28.mlp.shared_experts*",
52
+ "model.layers.28.self_attn*",
53
+ "model.layers.29.mlp.shared_experts*",
54
+ "model.layers.29.self_attn*",
55
+ "model.layers.3.mlp.shared_experts*",
56
+ "model.layers.3.self_attn*",
57
+ "model.layers.30.mlp.shared_experts*",
58
+ "model.layers.30.self_attn*",
59
+ "model.layers.31.mlp.shared_experts*",
60
+ "model.layers.31.self_attn*",
61
+ "model.layers.32.mlp.shared_experts*",
62
+ "model.layers.32.self_attn*",
63
+ "model.layers.33.mlp.shared_experts*",
64
+ "model.layers.33.self_attn*",
65
+ "model.layers.34.mlp.shared_experts*",
66
+ "model.layers.34.self_attn*",
67
+ "model.layers.35.mlp.shared_experts*",
68
+ "model.layers.35.self_attn*",
69
+ "model.layers.36.mlp.shared_experts*",
70
+ "model.layers.36.self_attn*",
71
+ "model.layers.37.mlp.shared_experts*",
72
+ "model.layers.37.self_attn*",
73
+ "model.layers.38.mlp.shared_experts*",
74
+ "model.layers.38.self_attn*",
75
+ "model.layers.39.mlp.shared_experts*",
76
+ "model.layers.39.self_attn*",
77
+ "model.layers.4.mlp.shared_experts*",
78
+ "model.layers.4.self_attn*",
79
+ "model.layers.40.mlp.shared_experts*",
80
+ "model.layers.40.self_attn*",
81
+ "model.layers.41.mlp.shared_experts*",
82
+ "model.layers.41.self_attn*",
83
+ "model.layers.42.mlp.shared_experts*",
84
+ "model.layers.42.self_attn*",
85
+ "model.layers.43.mlp.shared_experts*",
86
+ "model.layers.43.self_attn*",
87
+ "model.layers.44.mlp.shared_experts*",
88
+ "model.layers.44.self_attn*",
89
+ "model.layers.45.mlp.shared_experts*",
90
+ "model.layers.45.self_attn*",
91
+ "model.layers.46.mlp.shared_experts*",
92
+ "model.layers.46.self_attn*",
93
+ "model.layers.47.mlp.shared_experts*",
94
+ "model.layers.47.self_attn*",
95
+ "model.layers.48.mlp.shared_experts*",
96
+ "model.layers.48.self_attn*",
97
+ "model.layers.49.mlp.shared_experts*",
98
+ "model.layers.49.self_attn*",
99
+ "model.layers.5.mlp.shared_experts*",
100
+ "model.layers.5.self_attn*",
101
+ "model.layers.50.mlp.shared_experts*",
102
+ "model.layers.50.self_attn*",
103
+ "model.layers.51.mlp.shared_experts*",
104
+ "model.layers.51.self_attn*",
105
+ "model.layers.52.mlp.shared_experts*",
106
+ "model.layers.52.self_attn*",
107
+ "model.layers.53.mlp.shared_experts*",
108
+ "model.layers.53.self_attn*",
109
+ "model.layers.54.mlp.shared_experts*",
110
+ "model.layers.54.self_attn*",
111
+ "model.layers.55.mlp.shared_experts*",
112
+ "model.layers.55.self_attn*",
113
+ "model.layers.56.mlp.shared_experts*",
114
+ "model.layers.56.self_attn*",
115
+ "model.layers.57.mlp.shared_experts*",
116
+ "model.layers.57.self_attn*",
117
+ "model.layers.58.mlp.shared_experts*",
118
+ "model.layers.58.self_attn*",
119
+ "model.layers.59.mlp.shared_experts*",
120
+ "model.layers.59.self_attn*",
121
+ "model.layers.6.mlp.shared_experts*",
122
+ "model.layers.6.self_attn*",
123
+ "model.layers.60.mlp.shared_experts*",
124
+ "model.layers.60.self_attn*",
125
+ "model.layers.61.mlp.shared_experts*",
126
+ "model.layers.61.self_attn*",
127
+ "model.layers.62.mlp.shared_experts*",
128
+ "model.layers.62.self_attn*",
129
+ "model.layers.63.mlp.shared_experts*",
130
+ "model.layers.63.self_attn*",
131
+ "model.layers.64.mlp.shared_experts*",
132
+ "model.layers.64.self_attn*",
133
+ "model.layers.65.mlp.shared_experts*",
134
+ "model.layers.65.self_attn*",
135
+ "model.layers.66.mlp.shared_experts*",
136
+ "model.layers.66.self_attn*",
137
+ "model.layers.67.mlp.shared_experts*",
138
+ "model.layers.67.self_attn*",
139
+ "model.layers.68.mlp.shared_experts*",
140
+ "model.layers.68.self_attn*",
141
+ "model.layers.69.mlp.shared_experts*",
142
+ "model.layers.69.self_attn*",
143
+ "model.layers.7.mlp.shared_experts*",
144
+ "model.layers.7.self_attn*",
145
+ "model.layers.70.mlp.shared_experts*",
146
+ "model.layers.70.self_attn*",
147
+ "model.layers.71.mlp.shared_experts*",
148
+ "model.layers.71.self_attn*",
149
+ "model.layers.72.mlp.shared_experts*",
150
+ "model.layers.72.self_attn*",
151
+ "model.layers.73.mlp.shared_experts*",
152
+ "model.layers.73.self_attn*",
153
+ "model.layers.74.mlp.shared_experts*",
154
+ "model.layers.74.self_attn*",
155
+ "model.layers.75.mlp.shared_experts*",
156
+ "model.layers.75.self_attn*",
157
+ "model.layers.76.mlp.shared_experts*",
158
+ "model.layers.76.self_attn*",
159
+ "model.layers.77.mlp.shared_experts*",
160
+ "model.layers.77.self_attn*",
161
+ "model.layers.8.mlp.shared_experts*",
162
+ "model.layers.8.self_attn*",
163
+ "model.layers.9.mlp.shared_experts*",
164
+ "model.layers.9.self_attn*"
165
+ ]
166
+ }
167
+ }
model-00001-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b308a5f4e235ca979ed55a9d04246828d70bb5d1b7d8f6ae06fca76e9ff9852
3
+ size 9994445096
model-00002-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c04b6f42af59e3079eb4cbff0c1e29a6bc99a329421f9df26691a94607f0f1
3
+ size 10000173680
model-00003-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916825f855f959eebcd26cce4b092c3aedbc6d72759c6bc8175c0e09ea4359fb
3
+ size 10000173248
model-00004-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01f3ab46fd77768ab9e1fb5e9fd07dc512c24d41b9f52407b27c12ce4ec216f0
3
+ size 10000173744
model-00005-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be72b5db9fb5e8c0bbae35e2ad33cc0371859523ff27d9cd1848e2b3a42ddf4
3
+ size 9997417040
model-00006-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0ecf2992985b423f7a27bda78b920463ade2f9d6a55f334f35dc338497e349
3
+ size 10000178448
model-00007-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05a59d35a9d206e4c620ca39f0cb106d8e187538731082e1f0a6a8191a0ba6cd
3
+ size 10000178672
model-00008-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d4d6006655c3686be039267c7c2d4697352d84eca0e9a8d07eb42195a7d92cf
3
+ size 9997420960
model-00010-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a392b350bdb50a167d5ab53837aa479f1480b068942a1b285efd4b56fe079865
3
+ size 10000178464
model-00011-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5e4c6baf48da4eb731c49dd0094d38f5401452cedcc580019f5ef2af7276c5
3
+ size 9992458640
model-00012-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffc9d67ffc0c288b0f31c76edf36b3d3a011364b9c7367aa2673639d82e0d497
3
+ size 9998062264
model-00014-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb566b59272d413a83cf54f839fea75a6fabafec5c8124bd6615ac3ce6061bdb
3
+ size 10000178872
model-00015-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3db02c0d381364e408c94173c17bef531c81e19285835f1bf6d04b9d759032e
3
+ size 9997420752
model-00016-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80745abab4ec4da3759762140be1b2ab5973f84ba9095ade02c7cf03f59ba4bd
3
+ size 10000178464
model-00018-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcaefca8fbb5670052e1854a2dd64d39cee860bfe0126e9a2fe7ffe53bc087aa
3
+ size 9997421136
model-00019-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39c0cbde14edf84b41e66d7ad561cfe795b9176b15550c70aaa63e8371dc0fc5
3
+ size 10000178848
model-00021-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:045ee0c7947a31bacedec03d520ac5f42eb6500b739105d311ee6b1532ff5d44
3
+ size 10000178984
model-00023-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2067fa0c29a3882fc0b5b7ef7c74847dac0c55554529e9871377aa21d93c75e
3
+ size 10000178448
model-00027-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af58bb2a9caec711592af4cc6c6315eb6118e9d0bfbd60dcd531b35ac1dd291
3
+ size 10000178464
model-00028-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:634c6fd49ecc03d53b3d2b824c36d419bac4770f7f9809ff03cad1d4217a8e7b
3
+ size 9952615376
model-00029-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4377e5c69de696407a5214d4729b5fe95ea0648c92072de87462d3c263c19091
3
+ size 9995435208
model-00030-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aff393e8e22f76922de446fdd02c7b98b1d86bc3aa5ac9ac1a3f98dedefbf6b
3
+ size 10000178456
model-00031-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43da3079e18393d129e48b3010773aec8e66c13221429ce6fba3e95b2886134e
3
+ size 10000178912
model-00032-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:636e0d90e6bfbceabe4e0492367f2ac42051bb22c751b807ddbc89f012e2b5b6
3
+ size 9997420696
model-00033-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5088cacb3ce1ff16797a6a812d89c820b74741e4e7db2ab84bfedcc25bd7daf8
3
+ size 10000178448
model-00034-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5789392d340621cb0ffbccec89db8705e2566232b67994ea2d641b09b705265f
3
+ size 10000178552
model-00035-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:703fd9a8c4ca7808d4a921e699918ee7e9582fcb566981462b94c5f3b3b26a6d
3
+ size 9997421080
model-00036-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2a6f8e65e9aea11ff429909f08e339e0810df7e5fd3856c202e3a9c8f5215f
3
+ size 10000178792
model-00038-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:440475bcaec6a16a2fd2716726f5c5a4b857ada4ccd68b135c1d8b4d46054d5c
3
+ size 9995591328
model-00041-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f65116d4949ef34c6bc106e0547e1e2719a8c65c5f04c472d9debcb692b2dc
3
+ size 10000178760
model-00042-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65a54d32bfa45e54588d74a027118a68ff5c522006b3b51b2b6dc1a3eeeb9995
3
+ size 9997420856
model-00043-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01c5d275ae93da06ee97a28ab91fe245193ceadcc397795c6df831917c493e03
3
+ size 10000178584
model-00044-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2d9f25f86d7b7dddae264bad40327ef70365c8f4e2581101b816322f7e9ac0
3
+ size 10000178456
model-00045-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c887d5e75a5e4fcba9e4a1ed2310e4ec599d318783a53212b5d99a2a5738bc8
3
+ size 6080226488
model-00046-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca007d4dee75241b953ce996fd5f1ec909ef0b4fd3d61bc989d17865b0a8d8a6
3
+ size 5360383880
model-00047-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97688c5ecb245fb16224367f4c5f02fcb836f862429499d757f5d480b4d257d
3
+ size 5360347344
model-00048-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2693423b13074e283c23ddc384c24adbfd95a44e8040a3e72ef1c27fa0bda91a
3
+ size 5360347248
model-00049-of-00049.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8106dd9b4f26611fe6c5e1468d7c247f00dcdf026533b309602205882abd3a39
3
+ size 3824862424
model.safetensors.index.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59bc81fea793850940f43c3ee89aa883a3a71adbfb3d19c97ac7046f0733c5da
3
- size 22148477
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:268d86637a153c0c289e271c6baa6357d97e84fd7a5112313048b6c6ac1f3547
3
+ size 22220282
model.safetensors.index.json.bak ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59bc81fea793850940f43c3ee89aa883a3a71adbfb3d19c97ac7046f0733c5da
3
+ size 22148477