Hugging Face's logo

neuralmagic
/
Llama-2-7b-ultrachat200k-pruned_70

Text Generation
Transformers
Safetensors
llama
sparse
chat
conversational
Inference Endpoints
text-generation-inference
9 papers
Model card Files Community
1
mgoin commited on
Commit
1b44e4b
•
1 Parent(s): b2bdd28

Upload folder using huggingface_hub

Browse files
Files changed (16) hide show
  1. arc_challenge_25shot_bs16_bf16.json +25 -0
  2. config.json +28 -0
  3. generation_config.json +6 -0
  4. gsm8k_5shot_bs16_bf16.json +23 -0
  5. hellaswag_10shot_bs16_bf16.json +25 -0
  6. mmlu_5shot_bs4_bf16.json +417 -0
  7. pytorch_model-00001-of-00003.bin +3 -0
  8. pytorch_model-00002-of-00003.bin +3 -0
  9. pytorch_model-00003-of-00003.bin +3 -0
  10. pytorch_model.bin.index.json +298 -0
  11. special_tokens_map.json +23 -0
  12. tokenizer.json +0 -0
  13. tokenizer.model +3 -0
  14. tokenizer_config.json +41 -0
  15. truthfulqa_mc_0shot_bs16_bf16.json +25 -0
  16. winogrande_5shot_bs16_bf16.json +23 -0
arc_challenge_25shot_bs16_bf16.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "arc_challenge": {
4
+ "acc": 0.4232081911262799,
5
+ "acc_stderr": 0.014438036220848027,
6
+ "acc_norm": 0.45307167235494883,
7
+ "acc_norm_stderr": 0.01454689205200563
8
+ }
9
+ },
10
+ "versions": {
11
+ "arc_challenge": 0
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
16
+ "num_fewshot": 25,
17
+ "batch_size": "16",
18
+ "batch_sizes": [],
19
+ "device": "cuda:1",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 11008,
13
+ "max_position_embeddings": 4096,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 32,
18
+ "pretraining_tp": 1,
19
+ "rms_norm_eps": 1e-05,
20
+ "rope_scaling": null,
21
+ "rope_theta": 10000.0,
22
+ "tie_word_embeddings": false,
23
+ "tokenizer_class": "LlamaTokenizerFast",
24
+ "torch_dtype": "float32",
25
+ "transformers_version": "1.7.0.20240309",
26
+ "use_cache": true,
27
+ "vocab_size": 32000
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "1.7.0.20240309"
6
+ }
gsm8k_5shot_bs16_bf16.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "gsm8k": {
4
+ "acc": 0.047763457164518575,
5
+ "acc_stderr": 0.005874387536229333
6
+ }
7
+ },
8
+ "versions": {
9
+ "gsm8k": 0
10
+ },
11
+ "config": {
12
+ "model": "sparseml",
13
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
14
+ "num_fewshot": 5,
15
+ "batch_size": "16",
16
+ "batch_sizes": [],
17
+ "device": "cuda:6",
18
+ "no_cache": true,
19
+ "limit": null,
20
+ "bootstrap_iters": 100000,
21
+ "description_dict": {}
22
+ }
23
+ }
hellaswag_10shot_bs16_bf16.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hellaswag": {
4
+ "acc": 0.5220075682135032,
5
+ "acc_stderr": 0.004984945635998312,
6
+ "acc_norm": 0.6885082652857997,
7
+ "acc_norm_stderr": 0.004621568125102052
8
+ }
9
+ },
10
+ "versions": {
11
+ "hellaswag": 0
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
16
+ "num_fewshot": 10,
17
+ "batch_size": "16",
18
+ "batch_sizes": [],
19
+ "device": "cuda:3",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
mmlu_5shot_bs4_bf16.json ADDED
@@ -0,0 +1,417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hendrycksTest-abstract_algebra": {
4
+ "acc": 0.32,
5
+ "acc_stderr": 0.046882617226215034,
6
+ "acc_norm": 0.32,
7
+ "acc_norm_stderr": 0.046882617226215034
8
+ },
9
+ "hendrycksTest-anatomy": {
10
+ "acc": 0.32592592592592595,
11
+ "acc_stderr": 0.040491220417025055,
12
+ "acc_norm": 0.32592592592592595,
13
+ "acc_norm_stderr": 0.040491220417025055
14
+ },
15
+ "hendrycksTest-astronomy": {
16
+ "acc": 0.23026315789473684,
17
+ "acc_stderr": 0.03426059424403165,
18
+ "acc_norm": 0.23026315789473684,
19
+ "acc_norm_stderr": 0.03426059424403165
20
+ },
21
+ "hendrycksTest-business_ethics": {
22
+ "acc": 0.3,
23
+ "acc_stderr": 0.046056618647183814,
24
+ "acc_norm": 0.3,
25
+ "acc_norm_stderr": 0.046056618647183814
26
+ },
27
+ "hendrycksTest-clinical_knowledge": {
28
+ "acc": 0.3584905660377358,
29
+ "acc_stderr": 0.02951470358398177,
30
+ "acc_norm": 0.3584905660377358,
31
+ "acc_norm_stderr": 0.02951470358398177
32
+ },
33
+ "hendrycksTest-college_biology": {
34
+ "acc": 0.2916666666666667,
35
+ "acc_stderr": 0.038009680605548594,
36
+ "acc_norm": 0.2916666666666667,
37
+ "acc_norm_stderr": 0.038009680605548594
38
+ },
39
+ "hendrycksTest-college_chemistry": {
40
+ "acc": 0.21,
41
+ "acc_stderr": 0.040936018074033256,
42
+ "acc_norm": 0.21,
43
+ "acc_norm_stderr": 0.040936018074033256
44
+ },
45
+ "hendrycksTest-college_computer_science": {
46
+ "acc": 0.21,
47
+ "acc_stderr": 0.040936018074033256,
48
+ "acc_norm": 0.21,
49
+ "acc_norm_stderr": 0.040936018074033256
50
+ },
51
+ "hendrycksTest-college_mathematics": {
52
+ "acc": 0.23,
53
+ "acc_stderr": 0.04229525846816506,
54
+ "acc_norm": 0.23,
55
+ "acc_norm_stderr": 0.04229525846816506
56
+ },
57
+ "hendrycksTest-college_medicine": {
58
+ "acc": 0.2832369942196532,
59
+ "acc_stderr": 0.034355680560478746,
60
+ "acc_norm": 0.2832369942196532,
61
+ "acc_norm_stderr": 0.034355680560478746
62
+ },
63
+ "hendrycksTest-college_physics": {
64
+ "acc": 0.21568627450980393,
65
+ "acc_stderr": 0.04092563958237655,
66
+ "acc_norm": 0.21568627450980393,
67
+ "acc_norm_stderr": 0.04092563958237655
68
+ },
69
+ "hendrycksTest-computer_security": {
70
+ "acc": 0.37,
71
+ "acc_stderr": 0.04852365870939099,
72
+ "acc_norm": 0.37,
73
+ "acc_norm_stderr": 0.04852365870939099
74
+ },
75
+ "hendrycksTest-conceptual_physics": {
76
+ "acc": 0.3574468085106383,
77
+ "acc_stderr": 0.03132941789476425,
78
+ "acc_norm": 0.3574468085106383,
79
+ "acc_norm_stderr": 0.03132941789476425
80
+ },
81
+ "hendrycksTest-econometrics": {
82
+ "acc": 0.24561403508771928,
83
+ "acc_stderr": 0.04049339297748142,
84
+ "acc_norm": 0.24561403508771928,
85
+ "acc_norm_stderr": 0.04049339297748142
86
+ },
87
+ "hendrycksTest-electrical_engineering": {
88
+ "acc": 0.2827586206896552,
89
+ "acc_stderr": 0.03752833958003337,
90
+ "acc_norm": 0.2827586206896552,
91
+ "acc_norm_stderr": 0.03752833958003337
92
+ },
93
+ "hendrycksTest-elementary_mathematics": {
94
+ "acc": 0.23809523809523808,
95
+ "acc_stderr": 0.021935878081184766,
96
+ "acc_norm": 0.23809523809523808,
97
+ "acc_norm_stderr": 0.021935878081184766
98
+ },
99
+ "hendrycksTest-formal_logic": {
100
+ "acc": 0.1984126984126984,
101
+ "acc_stderr": 0.035670166752768635,
102
+ "acc_norm": 0.1984126984126984,
103
+ "acc_norm_stderr": 0.035670166752768635
104
+ },
105
+ "hendrycksTest-global_facts": {
106
+ "acc": 0.34,
107
+ "acc_stderr": 0.04760952285695236,
108
+ "acc_norm": 0.34,
109
+ "acc_norm_stderr": 0.04760952285695236
110
+ },
111
+ "hendrycksTest-high_school_biology": {
112
+ "acc": 0.3225806451612903,
113
+ "acc_stderr": 0.02659308451657229,
114
+ "acc_norm": 0.3225806451612903,
115
+ "acc_norm_stderr": 0.02659308451657229
116
+ },
117
+ "hendrycksTest-high_school_chemistry": {
118
+ "acc": 0.2315270935960591,
119
+ "acc_stderr": 0.02967833314144444,
120
+ "acc_norm": 0.2315270935960591,
121
+ "acc_norm_stderr": 0.02967833314144444
122
+ },
123
+ "hendrycksTest-high_school_computer_science": {
124
+ "acc": 0.34,
125
+ "acc_stderr": 0.047609522856952365,
126
+ "acc_norm": 0.34,
127
+ "acc_norm_stderr": 0.047609522856952365
128
+ },
129
+ "hendrycksTest-high_school_european_history": {
130
+ "acc": 0.4,
131
+ "acc_stderr": 0.03825460278380026,
132
+ "acc_norm": 0.4,
133
+ "acc_norm_stderr": 0.03825460278380026
134
+ },
135
+ "hendrycksTest-high_school_geography": {
136
+ "acc": 0.3383838383838384,
137
+ "acc_stderr": 0.03371124142626303,
138
+ "acc_norm": 0.3383838383838384,
139
+ "acc_norm_stderr": 0.03371124142626303
140
+ },
141
+ "hendrycksTest-high_school_government_and_politics": {
142
+ "acc": 0.32642487046632124,
143
+ "acc_stderr": 0.033840286211432945,
144
+ "acc_norm": 0.32642487046632124,
145
+ "acc_norm_stderr": 0.033840286211432945
146
+ },
147
+ "hendrycksTest-high_school_macroeconomics": {
148
+ "acc": 0.2358974358974359,
149
+ "acc_stderr": 0.021525965407408726,
150
+ "acc_norm": 0.2358974358974359,
151
+ "acc_norm_stderr": 0.021525965407408726
152
+ },
153
+ "hendrycksTest-high_school_mathematics": {
154
+ "acc": 0.23703703703703705,
155
+ "acc_stderr": 0.025928876132766104,
156
+ "acc_norm": 0.23703703703703705,
157
+ "acc_norm_stderr": 0.025928876132766104
158
+ },
159
+ "hendrycksTest-high_school_microeconomics": {
160
+ "acc": 0.29411764705882354,
161
+ "acc_stderr": 0.02959732973097808,
162
+ "acc_norm": 0.29411764705882354,
163
+ "acc_norm_stderr": 0.02959732973097808
164
+ },
165
+ "hendrycksTest-high_school_physics": {
166
+ "acc": 0.2582781456953642,
167
+ "acc_stderr": 0.035737053147634576,
168
+ "acc_norm": 0.2582781456953642,
169
+ "acc_norm_stderr": 0.035737053147634576
170
+ },
171
+ "hendrycksTest-high_school_psychology": {
172
+ "acc": 0.3779816513761468,
173
+ "acc_stderr": 0.020789187066728117,
174
+ "acc_norm": 0.3779816513761468,
175
+ "acc_norm_stderr": 0.020789187066728117
176
+ },
177
+ "hendrycksTest-high_school_statistics": {
178
+ "acc": 0.1712962962962963,
179
+ "acc_stderr": 0.025695341643824674,
180
+ "acc_norm": 0.1712962962962963,
181
+ "acc_norm_stderr": 0.025695341643824674
182
+ },
183
+ "hendrycksTest-high_school_us_history": {
184
+ "acc": 0.3627450980392157,
185
+ "acc_stderr": 0.03374499356319355,
186
+ "acc_norm": 0.3627450980392157,
187
+ "acc_norm_stderr": 0.03374499356319355
188
+ },
189
+ "hendrycksTest-high_school_world_history": {
190
+ "acc": 0.47257383966244726,
191
+ "acc_stderr": 0.03249822718301303,
192
+ "acc_norm": 0.47257383966244726,
193
+ "acc_norm_stderr": 0.03249822718301303
194
+ },
195
+ "hendrycksTest-human_aging": {
196
+ "acc": 0.4080717488789238,
197
+ "acc_stderr": 0.03298574607842821,
198
+ "acc_norm": 0.4080717488789238,
199
+ "acc_norm_stderr": 0.03298574607842821
200
+ },
201
+ "hendrycksTest-human_sexuality": {
202
+ "acc": 0.3053435114503817,
203
+ "acc_stderr": 0.040393149787245626,
204
+ "acc_norm": 0.3053435114503817,
205
+ "acc_norm_stderr": 0.040393149787245626
206
+ },
207
+ "hendrycksTest-international_law": {
208
+ "acc": 0.5619834710743802,
209
+ "acc_stderr": 0.045291468044357915,
210
+ "acc_norm": 0.5619834710743802,
211
+ "acc_norm_stderr": 0.045291468044357915
212
+ },
213
+ "hendrycksTest-jurisprudence": {
214
+ "acc": 0.37037037037037035,
215
+ "acc_stderr": 0.04668408033024932,
216
+ "acc_norm": 0.37037037037037035,
217
+ "acc_norm_stderr": 0.04668408033024932
218
+ },
219
+ "hendrycksTest-logical_fallacies": {
220
+ "acc": 0.38650306748466257,
221
+ "acc_stderr": 0.038258255488486076,
222
+ "acc_norm": 0.38650306748466257,
223
+ "acc_norm_stderr": 0.038258255488486076
224
+ },
225
+ "hendrycksTest-machine_learning": {
226
+ "acc": 0.3482142857142857,
227
+ "acc_stderr": 0.04521829902833585,
228
+ "acc_norm": 0.3482142857142857,
229
+ "acc_norm_stderr": 0.04521829902833585
230
+ },
231
+ "hendrycksTest-management": {
232
+ "acc": 0.3300970873786408,
233
+ "acc_stderr": 0.0465614711001235,
234
+ "acc_norm": 0.3300970873786408,
235
+ "acc_norm_stderr": 0.0465614711001235
236
+ },
237
+ "hendrycksTest-marketing": {
238
+ "acc": 0.47435897435897434,
239
+ "acc_stderr": 0.03271298896811159,
240
+ "acc_norm": 0.47435897435897434,
241
+ "acc_norm_stderr": 0.03271298896811159
242
+ },
243
+ "hendrycksTest-medical_genetics": {
244
+ "acc": 0.35,
245
+ "acc_stderr": 0.047937248544110196,
246
+ "acc_norm": 0.35,
247
+ "acc_norm_stderr": 0.047937248544110196
248
+ },
249
+ "hendrycksTest-miscellaneous": {
250
+ "acc": 0.47126436781609193,
251
+ "acc_stderr": 0.01785041079438017,
252
+ "acc_norm": 0.47126436781609193,
253
+ "acc_norm_stderr": 0.01785041079438017
254
+ },
255
+ "hendrycksTest-moral_disputes": {
256
+ "acc": 0.315028901734104,
257
+ "acc_stderr": 0.025009313790069727,
258
+ "acc_norm": 0.315028901734104,
259
+ "acc_norm_stderr": 0.025009313790069727
260
+ },
261
+ "hendrycksTest-moral_scenarios": {
262
+ "acc": 0.23798882681564246,
263
+ "acc_stderr": 0.014242630070574915,
264
+ "acc_norm": 0.23798882681564246,
265
+ "acc_norm_stderr": 0.014242630070574915
266
+ },
267
+ "hendrycksTest-nutrition": {
268
+ "acc": 0.369281045751634,
269
+ "acc_stderr": 0.027634176689602653,
270
+ "acc_norm": 0.369281045751634,
271
+ "acc_norm_stderr": 0.027634176689602653
272
+ },
273
+ "hendrycksTest-philosophy": {
274
+ "acc": 0.3633440514469453,
275
+ "acc_stderr": 0.027316847674192717,
276
+ "acc_norm": 0.3633440514469453,
277
+ "acc_norm_stderr": 0.027316847674192717
278
+ },
279
+ "hendrycksTest-prehistory": {
280
+ "acc": 0.36419753086419754,
281
+ "acc_stderr": 0.02677492989972233,
282
+ "acc_norm": 0.36419753086419754,
283
+ "acc_norm_stderr": 0.02677492989972233
284
+ },
285
+ "hendrycksTest-professional_accounting": {
286
+ "acc": 0.30141843971631205,
287
+ "acc_stderr": 0.02737412888263115,
288
+ "acc_norm": 0.30141843971631205,
289
+ "acc_norm_stderr": 0.02737412888263115
290
+ },
291
+ "hendrycksTest-professional_law": {
292
+ "acc": 0.3044328552803129,
293
+ "acc_stderr": 0.011752877592597575,
294
+ "acc_norm": 0.3044328552803129,
295
+ "acc_norm_stderr": 0.011752877592597575
296
+ },
297
+ "hendrycksTest-professional_medicine": {
298
+ "acc": 0.2426470588235294,
299
+ "acc_stderr": 0.026040662474201264,
300
+ "acc_norm": 0.2426470588235294,
301
+ "acc_norm_stderr": 0.026040662474201264
302
+ },
303
+ "hendrycksTest-professional_psychology": {
304
+ "acc": 0.3104575163398693,
305
+ "acc_stderr": 0.018718067052623227,
306
+ "acc_norm": 0.3104575163398693,
307
+ "acc_norm_stderr": 0.018718067052623227
308
+ },
309
+ "hendrycksTest-public_relations": {
310
+ "acc": 0.38181818181818183,
311
+ "acc_stderr": 0.04653429807913508,
312
+ "acc_norm": 0.38181818181818183,
313
+ "acc_norm_stderr": 0.04653429807913508
314
+ },
315
+ "hendrycksTest-security_studies": {
316
+ "acc": 0.3020408163265306,
317
+ "acc_stderr": 0.029393609319879818,
318
+ "acc_norm": 0.3020408163265306,
319
+ "acc_norm_stderr": 0.029393609319879818
320
+ },
321
+ "hendrycksTest-sociology": {
322
+ "acc": 0.4079601990049751,
323
+ "acc_stderr": 0.034751163651940926,
324
+ "acc_norm": 0.4079601990049751,
325
+ "acc_norm_stderr": 0.034751163651940926
326
+ },
327
+ "hendrycksTest-us_foreign_policy": {
328
+ "acc": 0.41,
329
+ "acc_stderr": 0.04943110704237102,
330
+ "acc_norm": 0.41,
331
+ "acc_norm_stderr": 0.04943110704237102
332
+ },
333
+ "hendrycksTest-virology": {
334
+ "acc": 0.4036144578313253,
335
+ "acc_stderr": 0.038194861407583984,
336
+ "acc_norm": 0.4036144578313253,
337
+ "acc_norm_stderr": 0.038194861407583984
338
+ },
339
+ "hendrycksTest-world_religions": {
340
+ "acc": 0.40350877192982454,
341
+ "acc_stderr": 0.03762738699917056,
342
+ "acc_norm": 0.40350877192982454,
343
+ "acc_norm_stderr": 0.03762738699917056
344
+ }
345
+ },
346
+ "versions": {
347
+ "hendrycksTest-abstract_algebra": 1,
348
+ "hendrycksTest-anatomy": 1,
349
+ "hendrycksTest-astronomy": 1,
350
+ "hendrycksTest-business_ethics": 1,
351
+ "hendrycksTest-clinical_knowledge": 1,
352
+ "hendrycksTest-college_biology": 1,
353
+ "hendrycksTest-college_chemistry": 1,
354
+ "hendrycksTest-college_computer_science": 1,
355
+ "hendrycksTest-college_mathematics": 1,
356
+ "hendrycksTest-college_medicine": 1,
357
+ "hendrycksTest-college_physics": 1,
358
+ "hendrycksTest-computer_security": 1,
359
+ "hendrycksTest-conceptual_physics": 1,
360
+ "hendrycksTest-econometrics": 1,
361
+ "hendrycksTest-electrical_engineering": 1,
362
+ "hendrycksTest-elementary_mathematics": 1,
363
+ "hendrycksTest-formal_logic": 1,
364
+ "hendrycksTest-global_facts": 1,
365
+ "hendrycksTest-high_school_biology": 1,
366
+ "hendrycksTest-high_school_chemistry": 1,
367
+ "hendrycksTest-high_school_computer_science": 1,
368
+ "hendrycksTest-high_school_european_history": 1,
369
+ "hendrycksTest-high_school_geography": 1,
370
+ "hendrycksTest-high_school_government_and_politics": 1,
371
+ "hendrycksTest-high_school_macroeconomics": 1,
372
+ "hendrycksTest-high_school_mathematics": 1,
373
+ "hendrycksTest-high_school_microeconomics": 1,
374
+ "hendrycksTest-high_school_physics": 1,
375
+ "hendrycksTest-high_school_psychology": 1,
376
+ "hendrycksTest-high_school_statistics": 1,
377
+ "hendrycksTest-high_school_us_history": 1,
378
+ "hendrycksTest-high_school_world_history": 1,
379
+ "hendrycksTest-human_aging": 1,
380
+ "hendrycksTest-human_sexuality": 1,
381
+ "hendrycksTest-international_law": 1,
382
+ "hendrycksTest-jurisprudence": 1,
383
+ "hendrycksTest-logical_fallacies": 1,
384
+ "hendrycksTest-machine_learning": 1,
385
+ "hendrycksTest-management": 1,
386
+ "hendrycksTest-marketing": 1,
387
+ "hendrycksTest-medical_genetics": 1,
388
+ "hendrycksTest-miscellaneous": 1,
389
+ "hendrycksTest-moral_disputes": 1,
390
+ "hendrycksTest-moral_scenarios": 1,
391
+ "hendrycksTest-nutrition": 1,
392
+ "hendrycksTest-philosophy": 1,
393
+ "hendrycksTest-prehistory": 1,
394
+ "hendrycksTest-professional_accounting": 1,
395
+ "hendrycksTest-professional_law": 1,
396
+ "hendrycksTest-professional_medicine": 1,
397
+ "hendrycksTest-professional_psychology": 1,
398
+ "hendrycksTest-public_relations": 1,
399
+ "hendrycksTest-security_studies": 1,
400
+ "hendrycksTest-sociology": 1,
401
+ "hendrycksTest-us_foreign_policy": 1,
402
+ "hendrycksTest-virology": 1,
403
+ "hendrycksTest-world_religions": 1
404
+ },
405
+ "config": {
406
+ "model": "sparseml",
407
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
408
+ "num_fewshot": 5,
409
+ "batch_size": "4",
410
+ "batch_sizes": [],
411
+ "device": "cuda:7",
412
+ "no_cache": true,
413
+ "limit": null,
414
+ "bootstrap_iters": 100000,
415
+ "description_dict": {}
416
+ }
417
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db10a283fa0ce643dbf8e820a17d7a32161cb48bbf050fd91681c1c4e377e360
3
+ size 9877982873
pytorch_model-00002-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e00b0b63a2192c38b3243abdaa3cb3e59122657d4ae7575d719ea722bd44a5c3
3
+ size 9894794253
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638a4b6a16dfd8ecefb2247877a4a4470b1b4d5954f7d54a6bd883b3b84be97d
3
+ size 7180986412
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953662464
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00003-of-00003.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00003.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
16
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
17
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
18
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
19
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
20
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
21
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
22
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
23
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
24
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
25
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
26
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
27
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
28
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
29
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
30
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
31
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
32
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
33
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
34
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
35
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
36
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
37
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
38
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
39
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
40
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
41
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
42
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
43
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
44
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
45
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
46
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
47
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
48
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
49
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
50
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
51
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
52
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
53
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
54
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
55
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
56
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
57
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
58
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
59
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
60
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
61
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
62
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
63
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
64
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
65
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
66
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
67
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
68
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
69
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
70
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
71
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
72
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
73
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
74
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
75
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
76
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
77
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
78
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
79
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
80
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
81
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
82
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
83
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
84
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
85
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
86
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
87
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
88
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
89
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
90
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
91
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
92
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
93
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
94
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
95
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
96
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
97
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
98
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
99
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
100
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
101
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
102
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
103
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
104
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
105
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
106
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
107
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
108
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
109
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
110
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
111
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
112
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
113
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
114
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
115
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
116
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
117
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
118
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
119
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
120
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
121
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
122
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
123
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
124
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
125
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
126
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
127
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
128
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
129
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
130
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
131
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
132
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
133
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
134
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
135
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
136
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
137
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
138
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
139
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
140
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
141
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
142
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
143
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00003.bin",
144
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00003.bin",
145
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
146
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
147
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00003.bin",
148
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
149
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
150
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
151
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
152
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
153
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
154
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00003.bin",
155
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00003.bin",
156
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
157
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00003.bin",
158
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00003.bin",
159
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00003.bin",
160
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00003.bin",
161
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
162
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
163
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
164
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
165
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
166
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
167
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
168
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
169
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
170
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
171
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
172
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
173
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
174
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
175
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
176
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
177
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
178
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
179
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
180
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
181
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
182
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
183
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
184
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
185
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
186
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
187
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
188
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
189
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
190
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
191
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
192
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
193
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
194
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
195
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
196
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
197
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
198
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
199
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
200
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
201
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
202
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
203
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
204
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
205
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
206
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
207
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
208
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
209
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
210
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
211
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
212
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
213
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
214
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
215
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
216
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
217
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
218
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
219
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
220
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
221
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
222
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
223
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
224
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
225
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
226
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
227
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
228
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
229
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
230
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
231
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
232
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
233
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00003.bin",
234
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00003.bin",
235
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00003.bin",
236
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00003.bin",
237
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00003.bin",
238
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00003.bin",
239
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00003.bin",
240
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00003.bin",
241
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00003.bin",
242
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
243
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
244
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
245
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
246
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
247
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
248
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
249
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
250
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
251
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
252
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
253
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
254
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
255
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
256
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
257
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
258
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
259
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
260
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
261
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
262
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
263
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
264
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
265
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
266
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
267
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
268
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
269
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
270
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
271
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
272
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
273
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
274
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
275
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
276
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
277
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
278
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
279
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
280
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
281
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
282
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
283
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
284
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
285
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
286
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
287
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00003.bin",
288
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00003.bin",
289
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00003.bin",
290
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00003.bin",
291
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00003.bin",
292
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00003.bin",
293
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00003.bin",
294
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00003.bin",
295
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00003.bin",
296
+ "model.norm.weight": "pytorch_model-00003-of-00003.bin"
297
+ }
298
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": null,
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
truthfulqa_mc_0shot_bs16_bf16.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "truthfulqa_mc": {
4
+ "mc1": 0.2521419828641371,
5
+ "mc1_stderr": 0.01520152224629996,
6
+ "mc2": 0.3954683484720209,
7
+ "mc2_stderr": 0.014883378073318826
8
+ }
9
+ },
10
+ "versions": {
11
+ "truthfulqa_mc": 1
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
16
+ "num_fewshot": 0,
17
+ "batch_size": "16",
18
+ "batch_sizes": [],
19
+ "device": "cuda:4",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
winogrande_5shot_bs16_bf16.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "winogrande": {
4
+ "acc": 0.6511444356748224,
5
+ "acc_stderr": 0.013395059320137332
6
+ }
7
+ },
8
+ "versions": {
9
+ "winogrande": 0
10
+ },
11
+ "config": {
12
+ "model": "sparseml",
13
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse70_retrained/ultrachat200k/llama2_7B_sparse70_LR3e-4_GC2_E2/training,dtype=bfloat16",
14
+ "num_fewshot": 5,
15
+ "batch_size": "16",
16
+ "batch_sizes": [],
17
+ "device": "cuda:2",
18
+ "no_cache": true,
19
+ "limit": null,
20
+ "bootstrap_iters": 100000,
21
+ "description_dict": {}
22
+ }
23
+ }