Hugging Face's logo

neuralmagic
/
Llama-2-7b-pruned50-retrained

Text Generation
Transformers
Safetensors
llama
sparse
Inference Endpoints
text-generation-inference
9 papers
Model card Files Community
1
mgoin commited on
Commit
0dd18e2
•
1 Parent(s): bd8474e

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. arc_challenge_25shot_bs16_bf16.json +25 -0
  2. config.json +25 -0
  3. gsm8k_5shot_bs16_bf16.json +23 -0
  4. hellaswag_10shot_bs16_bf16.json +25 -0
  5. humaneval_fp16.json +47 -0
  6. mmlu_5shot_bs4_bf16.json +417 -0
  7. model-00001-of-00006.safetensors +3 -0
  8. model-00002-of-00006.safetensors +3 -0
  9. model-00003-of-00006.safetensors +3 -0
  10. model-00004-of-00006.safetensors +3 -0
  11. model-00005-of-00006.safetensors +3 -0
  12. model-00006-of-00006.safetensors +3 -0
  13. model.safetensors.index.json +330 -0
  14. special_tokens_map.json +23 -0
  15. tokenizer.json +0 -0
  16. tokenizer.model +3 -0
  17. tokenizer_config.json +41 -0
  18. truthfulqa_mc_0shot_bs16_bf16.json +25 -0
  19. 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": 0.4616040955631399,
5
+ "acc_stderr": 0.014568245550296363,
6
+ "acc_norm": 0.49829351535836175,
7
+ "acc_norm_stderr": 0.014611305705056987
8
+ }
9
+ },
10
+ "versions": {
11
+ "arc_challenge": 0
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint,dtype=bfloat16",
16
+ "num_fewshot": 25,
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
+ }
config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "attention_bias": false,
3
+ "attention_dropout": 0.0,
4
+ "bos_token_id": 1,
5
+ "eos_token_id": 2,
6
+ "hidden_act": "silu",
7
+ "hidden_size": 4096,
8
+ "initializer_range": 0.02,
9
+ "intermediate_size": 11008,
10
+ "max_position_embeddings": 4096,
11
+ "model_type": "llama",
12
+ "num_attention_heads": 32,
13
+ "num_hidden_layers": 32,
14
+ "num_key_value_heads": 32,
15
+ "pretraining_tp": 1,
16
+ "rms_norm_eps": 1e-05,
17
+ "rope_scaling": null,
18
+ "rope_theta": 10000.0,
19
+ "tie_word_embeddings": false,
20
+ "tokenizer_class": "LlamaTokenizerFast",
21
+ "transformers_version": "4.37.2",
22
+ "use_cache": true,
23
+ "vocab_size": 32000,
24
+ "torch_dtype": "bfloat16"
25
+ }
gsm8k_5shot_bs16_bf16.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "gsm8k": {
4
+ "acc": 0.09173616376042457,
5
+ "acc_stderr": 0.007950942148339354
6
+ }
7
+ },
8
+ "versions": {
9
+ "gsm8k": 0
10
+ },
11
+ "config": {
12
+ "model": "sparseml",
13
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint,dtype=bfloat16",
14
+ "num_fewshot": 5,
15
+ "batch_size": "16",
16
+ "batch_sizes": [],
17
+ "device": "cuda:4",
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": 0.5711013742282414,
5
+ "acc_stderr": 0.0049390730147549425,
6
+ "acc_norm": 0.7646883091017725,
7
+ "acc_norm_stderr": 0.00423326537156471
8
+ }
9
+ },
10
+ "versions": {
11
+ "hellaswag": 0
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint,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
+ }
humaneval_fp16.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "humaneval": {
3
+ "pass@1": 0.14682926829268292,
4
+ "pass@10": 0.1950433350182723
5
+ },
6
+ "config": {
7
+ "prefix": "",
8
+ "do_sample": true,
9
+ "temperature": 0.2,
10
+ "top_k": 0,
11
+ "top_p": 0.95,
12
+ "n_samples": 50,
13
+ "eos": "<|endoftext|>",
14
+ "seed": 0,
15
+ "model": "/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint/",
16
+ "modeltype": "causal",
17
+ "peft_model": null,
18
+ "revision": null,
19
+ "use_auth_token": false,
20
+ "trust_remote_code": false,
21
+ "tasks": "humaneval",
22
+ "instruction_tokens": null,
23
+ "batch_size": 32,
24
+ "max_length_generation": 512,
25
+ "precision": "fp16",
26
+ "load_in_8bit": false,
27
+ "load_in_4bit": false,
28
+ "left_padding": false,
29
+ "limit": null,
30
+ "limit_start": 0,
31
+ "save_every_k_tasks": -1,
32
+ "postprocess": true,
33
+ "allow_code_execution": true,
34
+ "generation_only": false,
35
+ "load_generations_path": null,
36
+ "load_data_path": null,
37
+ "metric_output_path": "/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint//humaneval_fp16.json",
38
+ "save_generations": true,
39
+ "load_generations_intermediate_paths": null,
40
+ "save_generations_path": "generations.json",
41
+ "save_references": false,
42
+ "save_references_path": "references.json",
43
+ "prompt": "prompt",
44
+ "max_memory_per_gpu": "auto",
45
+ "check_references": false
46
+ }
47
+ }
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": 0.4666666666666667,
11
+ "acc_stderr": 0.043097329010363554,
12
+ "acc_norm": 0.4666666666666667,
13
+ "acc_norm_stderr": 0.043097329010363554
14
+ },
15
+ "hendrycksTest-astronomy": {
16
+ "acc": 0.42105263157894735,
17
+ "acc_stderr": 0.040179012759817494,
18
+ "acc_norm": 0.42105263157894735,
19
+ "acc_norm_stderr": 0.040179012759817494
20
+ },
21
+ "hendrycksTest-business_ethics": {
22
+ "acc": 0.46,
23
+ "acc_stderr": 0.05009082659620332,
24
+ "acc_norm": 0.46,
25
+ "acc_norm_stderr": 0.05009082659620332
26
+ },
27
+ "hendrycksTest-clinical_knowledge": {
28
+ "acc": 0.39245283018867927,
29
+ "acc_stderr": 0.030052580579557845,
30
+ "acc_norm": 0.39245283018867927,
31
+ "acc_norm_stderr": 0.030052580579557845
32
+ },
33
+ "hendrycksTest-college_biology": {
34
+ "acc": 0.3888888888888889,
35
+ "acc_stderr": 0.04076663253918567,
36
+ "acc_norm": 0.3888888888888889,
37
+ "acc_norm_stderr": 0.04076663253918567
38
+ },
39
+ "hendrycksTest-college_chemistry": {
40
+ "acc": 0.34,
41
+ "acc_stderr": 0.047609522856952344,
42
+ "acc_norm": 0.34,
43
+ "acc_norm_stderr": 0.047609522856952344
44
+ },
45
+ "hendrycksTest-college_computer_science": {
46
+ "acc": 0.4,
47
+ "acc_stderr": 0.049236596391733084,
48
+ "acc_norm": 0.4,
49
+ "acc_norm_stderr": 0.049236596391733084
50
+ },
51
+ "hendrycksTest-college_mathematics": {
52
+ "acc": 0.3,
53
+ "acc_stderr": 0.04605661864718381,
54
+ "acc_norm": 0.3,
55
+ "acc_norm_stderr": 0.04605661864718381
56
+ },
57
+ "hendrycksTest-college_medicine": {
58
+ "acc": 0.34104046242774566,
59
+ "acc_stderr": 0.036146654241808254,
60
+ "acc_norm": 0.34104046242774566,
61
+ "acc_norm_stderr": 0.036146654241808254
62
+ },
63
+ "hendrycksTest-college_physics": {
64
+ "acc": 0.19607843137254902,
65
+ "acc_stderr": 0.03950581861179964,
66
+ "acc_norm": 0.19607843137254902,
67
+ "acc_norm_stderr": 0.03950581861179964
68
+ },
69
+ "hendrycksTest-computer_security": {
70
+ "acc": 0.52,
71
+ "acc_stderr": 0.050211673156867795,
72
+ "acc_norm": 0.52,
73
+ "acc_norm_stderr": 0.050211673156867795
74
+ },
75
+ "hendrycksTest-conceptual_physics": {
76
+ "acc": 0.3872340425531915,
77
+ "acc_stderr": 0.03184389265339526,
78
+ "acc_norm": 0.3872340425531915,
79
+ "acc_norm_stderr": 0.03184389265339526
80
+ },
81
+ "hendrycksTest-econometrics": {
82
+ "acc": 0.2719298245614035,
83
+ "acc_stderr": 0.04185774424022056,
84
+ "acc_norm": 0.2719298245614035,
85
+ "acc_norm_stderr": 0.04185774424022056
86
+ },
87
+ "hendrycksTest-electrical_engineering": {
88
+ "acc": 0.4,
89
+ "acc_stderr": 0.040824829046386284,
90
+ "acc_norm": 0.4,
91
+ "acc_norm_stderr": 0.040824829046386284
92
+ },
93
+ "hendrycksTest-elementary_mathematics": {
94
+ "acc": 0.2671957671957672,
95
+ "acc_stderr": 0.022789673145776568,
96
+ "acc_norm": 0.2671957671957672,
97
+ "acc_norm_stderr": 0.022789673145776568
98
+ },
99
+ "hendrycksTest-formal_logic": {
100
+ "acc": 0.30158730158730157,
101
+ "acc_stderr": 0.04104947269903394,
102
+ "acc_norm": 0.30158730158730157,
103
+ "acc_norm_stderr": 0.04104947269903394
104
+ },
105
+ "hendrycksTest-global_facts": {
106
+ "acc": 0.27,
107
+ "acc_stderr": 0.044619604333847394,
108
+ "acc_norm": 0.27,
109
+ "acc_norm_stderr": 0.044619604333847394
110
+ },
111
+ "hendrycksTest-high_school_biology": {
112
+ "acc": 0.4290322580645161,
113
+ "acc_stderr": 0.02815603653823321,
114
+ "acc_norm": 0.4290322580645161,
115
+ "acc_norm_stderr": 0.02815603653823321
116
+ },
117
+ "hendrycksTest-high_school_chemistry": {
118
+ "acc": 0.28078817733990147,
119
+ "acc_stderr": 0.03161856335358608,
120
+ "acc_norm": 0.28078817733990147,
121
+ "acc_norm_stderr": 0.03161856335358608
122
+ },
123
+ "hendrycksTest-high_school_computer_science": {
124
+ "acc": 0.4,
125
+ "acc_stderr": 0.049236596391733084,
126
+ "acc_norm": 0.4,
127
+ "acc_norm_stderr": 0.049236596391733084
128
+ },
129
+ "hendrycksTest-high_school_european_history": {
130
+ "acc": 0.503030303030303,
131
+ "acc_stderr": 0.03904272341431857,
132
+ "acc_norm": 0.503030303030303,
133
+ "acc_norm_stderr": 0.03904272341431857
134
+ },
135
+ "hendrycksTest-high_school_geography": {
136
+ "acc": 0.43434343434343436,
137
+ "acc_stderr": 0.03531505879359183,
138
+ "acc_norm": 0.43434343434343436,
139
+ "acc_norm_stderr": 0.03531505879359183
140
+ },
141
+ "hendrycksTest-high_school_government_and_politics": {
142
+ "acc": 0.5958549222797928,
143
+ "acc_stderr": 0.0354150857888402,
144
+ "acc_norm": 0.5958549222797928,
145
+ "acc_norm_stderr": 0.0354150857888402
146
+ },
147
+ "hendrycksTest-high_school_macroeconomics": {
148
+ "acc": 0.3769230769230769,
149
+ "acc_stderr": 0.024570975364225995,
150
+ "acc_norm": 0.3769230769230769,
151
+ "acc_norm_stderr": 0.024570975364225995
152
+ },
153
+ "hendrycksTest-high_school_mathematics": {
154
+ "acc": 0.2740740740740741,
155
+ "acc_stderr": 0.027195934804085622,
156
+ "acc_norm": 0.2740740740740741,
157
+ "acc_norm_stderr": 0.027195934804085622
158
+ },
159
+ "hendrycksTest-high_school_microeconomics": {
160
+ "acc": 0.31932773109243695,
161
+ "acc_stderr": 0.0302839955258844,
162
+ "acc_norm": 0.31932773109243695,
163
+ "acc_norm_stderr": 0.0302839955258844
164
+ },
165
+ "hendrycksTest-high_school_physics": {
166
+ "acc": 0.2781456953642384,
167
+ "acc_stderr": 0.03658603262763743,
168
+ "acc_norm": 0.2781456953642384,
169
+ "acc_norm_stderr": 0.03658603262763743
170
+ },
171
+ "hendrycksTest-high_school_psychology": {
172
+ "acc": 0.5247706422018349,
173
+ "acc_stderr": 0.021410999753635914,
174
+ "acc_norm": 0.5247706422018349,
175
+ "acc_norm_stderr": 0.021410999753635914
176
+ },
177
+ "hendrycksTest-high_school_statistics": {
178
+ "acc": 0.3194444444444444,
179
+ "acc_stderr": 0.031798763421768524,
180
+ "acc_norm": 0.3194444444444444,
181
+ "acc_norm_stderr": 0.031798763421768524
182
+ },
183
+ "hendrycksTest-high_school_us_history": {
184
+ "acc": 0.44607843137254904,
185
+ "acc_stderr": 0.034888454513049734,
186
+ "acc_norm": 0.44607843137254904,
187
+ "acc_norm_stderr": 0.034888454513049734
188
+ },
189
+ "hendrycksTest-high_school_world_history": {
190
+ "acc": 0.5611814345991561,
191
+ "acc_stderr": 0.032302649315470375,
192
+ "acc_norm": 0.5611814345991561,
193
+ "acc_norm_stderr": 0.032302649315470375
194
+ },
195
+ "hendrycksTest-human_aging": {
196
+ "acc": 0.43946188340807174,
197
+ "acc_stderr": 0.03331092511038179,
198
+ "acc_norm": 0.43946188340807174,
199
+ "acc_norm_stderr": 0.03331092511038179
200
+ },
201
+ "hendrycksTest-human_sexuality": {
202
+ "acc": 0.44274809160305345,
203
+ "acc_stderr": 0.04356447202665069,
204
+ "acc_norm": 0.44274809160305345,
205
+ "acc_norm_stderr": 0.04356447202665069
206
+ },
207
+ "hendrycksTest-international_law": {
208
+ "acc": 0.6115702479338843,
209
+ "acc_stderr": 0.04449270350068382,
210
+ "acc_norm": 0.6115702479338843,
211
+ "acc_norm_stderr": 0.04449270350068382
212
+ },
213
+ "hendrycksTest-jurisprudence": {
214
+ "acc": 0.4166666666666667,
215
+ "acc_stderr": 0.04766075165356461,
216
+ "acc_norm": 0.4166666666666667,
217
+ "acc_norm_stderr": 0.04766075165356461
218
+ },
219
+ "hendrycksTest-logical_fallacies": {
220
+ "acc": 0.4539877300613497,
221
+ "acc_stderr": 0.0391170190467718,
222
+ "acc_norm": 0.4539877300613497,
223
+ "acc_norm_stderr": 0.0391170190467718
224
+ },
225
+ "hendrycksTest-machine_learning": {
226
+ "acc": 0.32142857142857145,
227
+ "acc_stderr": 0.044328040552915185,
228
+ "acc_norm": 0.32142857142857145,
229
+ "acc_norm_stderr": 0.044328040552915185
230
+ },
231
+ "hendrycksTest-management": {
232
+ "acc": 0.36893203883495146,
233
+ "acc_stderr": 0.04777615181156739,
234
+ "acc_norm": 0.36893203883495146,
235
+ "acc_norm_stderr": 0.04777615181156739
236
+ },
237
+ "hendrycksTest-marketing": {
238
+ "acc": 0.5769230769230769,
239
+ "acc_stderr": 0.032366121762202014,
240
+ "acc_norm": 0.5769230769230769,
241
+ "acc_norm_stderr": 0.032366121762202014
242
+ },
243
+ "hendrycksTest-medical_genetics": {
244
+ "acc": 0.45,
245
+ "acc_stderr": 0.05,
246
+ "acc_norm": 0.45,
247
+ "acc_norm_stderr": 0.05
248
+ },
249
+ "hendrycksTest-miscellaneous": {
250
+ "acc": 0.5823754789272031,
251
+ "acc_stderr": 0.01763563732695151,
252
+ "acc_norm": 0.5823754789272031,
253
+ "acc_norm_stderr": 0.01763563732695151
254
+ },
255
+ "hendrycksTest-moral_disputes": {
256
+ "acc": 0.4653179190751445,
257
+ "acc_stderr": 0.02685425792825889,
258
+ "acc_norm": 0.4653179190751445,
259
+ "acc_norm_stderr": 0.02685425792825889
260
+ },
261
+ "hendrycksTest-moral_scenarios": {
262
+ "acc": 0.26145251396648045,
263
+ "acc_stderr": 0.014696599650364557,
264
+ "acc_norm": 0.26145251396648045,
265
+ "acc_norm_stderr": 0.014696599650364557
266
+ },
267
+ "hendrycksTest-nutrition": {
268
+ "acc": 0.4215686274509804,
269
+ "acc_stderr": 0.028275490156791434,
270
+ "acc_norm": 0.4215686274509804,
271
+ "acc_norm_stderr": 0.028275490156791434
272
+ },
273
+ "hendrycksTest-philosophy": {
274
+ "acc": 0.5176848874598071,
275
+ "acc_stderr": 0.02838032284907713,
276
+ "acc_norm": 0.5176848874598071,
277
+ "acc_norm_stderr": 0.02838032284907713
278
+ },
279
+ "hendrycksTest-prehistory": {
280
+ "acc": 0.4783950617283951,
281
+ "acc_stderr": 0.027794760105008746,
282
+ "acc_norm": 0.4783950617283951,
283
+ "acc_norm_stderr": 0.027794760105008746
284
+ },
285
+ "hendrycksTest-professional_accounting": {
286
+ "acc": 0.32269503546099293,
287
+ "acc_stderr": 0.02788913930053479,
288
+ "acc_norm": 0.32269503546099293,
289
+ "acc_norm_stderr": 0.02788913930053479
290
+ },
291
+ "hendrycksTest-professional_law": {
292
+ "acc": 0.3344198174706649,
293
+ "acc_stderr": 0.012049668983214934,
294
+ "acc_norm": 0.3344198174706649,
295
+ "acc_norm_stderr": 0.012049668983214934
296
+ },
297
+ "hendrycksTest-professional_medicine": {
298
+ "acc": 0.4522058823529412,
299
+ "acc_stderr": 0.03023375855159644,
300
+ "acc_norm": 0.4522058823529412,
301
+ "acc_norm_stderr": 0.03023375855159644
302
+ },
303
+ "hendrycksTest-professional_psychology": {
304
+ "acc": 0.41013071895424835,
305
+ "acc_stderr": 0.019898412717635917,
306
+ "acc_norm": 0.41013071895424835,
307
+ "acc_norm_stderr": 0.019898412717635917
308
+ },
309
+ "hendrycksTest-public_relations": {
310
+ "acc": 0.4636363636363636,
311
+ "acc_stderr": 0.047764491623961985,
312
+ "acc_norm": 0.4636363636363636,
313
+ "acc_norm_stderr": 0.047764491623961985
314
+ },
315
+ "hendrycksTest-security_studies": {
316
+ "acc": 0.42857142857142855,
317
+ "acc_stderr": 0.03168091161233882,
318
+ "acc_norm": 0.42857142857142855,
319
+ "acc_norm_stderr": 0.03168091161233882
320
+ },
321
+ "hendrycksTest-sociology": {
322
+ "acc": 0.5024875621890548,
323
+ "acc_stderr": 0.03535490150137289,
324
+ "acc_norm": 0.5024875621890548,
325
+ "acc_norm_stderr": 0.03535490150137289
326
+ },
327
+ "hendrycksTest-us_foreign_policy": {
328
+ "acc": 0.6,
329
+ "acc_stderr": 0.04923659639173309,
330
+ "acc_norm": 0.6,
331
+ "acc_norm_stderr": 0.04923659639173309
332
+ },
333
+ "hendrycksTest-virology": {
334
+ "acc": 0.40963855421686746,
335
+ "acc_stderr": 0.03828401115079023,
336
+ "acc_norm": 0.40963855421686746,
337
+ "acc_norm_stderr": 0.03828401115079023
338
+ },
339
+ "hendrycksTest-world_religions": {
340
+ "acc": 0.6198830409356725,
341
+ "acc_stderr": 0.037229657413855394,
342
+ "acc_norm": 0.6198830409356725,
343
+ "acc_norm_stderr": 0.037229657413855394
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_sparse50_45B_retrained/checkpoint,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
+ }
model-00001-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d49d816e2995332d3b00ad7afec6f3ec9ce70a7427387435894d366ad75cc766
3
+ size 4840431640
model-00002-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4896b7ef48c217dd5abed345d44b703265eb4fb497d70845acd6432f1c8d13e9
3
+ size 4857209080
model-00003-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f065272668fbe741826e9e0d2200f7280b9a5dca5427151206e537e9b8a52dc
3
+ size 4857209144
model-00004-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41fa92f1c8fa1216cea2ac062077e1541b33504d108f8ca50e95249515680d06
3
+ size 4857209144
model-00005-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4bf14637086dbb6ce3c1d00c909518646d3866aed1d12e765680ca4bef803ce
3
+ size 4857209144
model-00006-of-00006.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7200524ec5670e6bf8a1df13c1b987898a45fd4bae7a88b72a8203498c497780
3
+ size 2684439864
model.safetensors.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953670656
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
7
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
8
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
9
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
10
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
11
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
12
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
13
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
14
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
15
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
16
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
17
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
18
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
19
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
20
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
21
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
22
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
24
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
25
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
26
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
27
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
28
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
29
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
30
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
31
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
32
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
33
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
34
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
35
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
36
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
37
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
38
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
39
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
40
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
41
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
42
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
43
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
44
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
45
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
46
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
47
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
48
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
49
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
50
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
51
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
52
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
53
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
54
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
55
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
56
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
57
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
58
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
59
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
60
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
61
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "model-00001-of-00006.safetensors",
62
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00006.safetensors",
63
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
64
+ "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
65
+ "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
66
+ "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
67
+ "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
68
+ "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
69
+ "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
70
+ "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
71
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
72
+ "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
73
+ "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
74
+ "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
75
+ "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
76
+ "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
77
+ "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
78
+ "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
79
+ "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
80
+ "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
81
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
82
+ "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
83
+ "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
84
+ "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
85
+ "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
86
+ "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
87
+ "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
88
+ "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
89
+ "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
90
+ "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
91
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
92
+ "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
93
+ "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
94
+ "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
95
+ "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
96
+ "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
97
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
98
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
99
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
100
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
101
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
102
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
103
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
104
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
105
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
106
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
107
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
108
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
109
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
110
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
111
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
112
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
113
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
114
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
115
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
116
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
117
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
118
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
119
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
120
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
121
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "model-00002-of-00006.safetensors",
122
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
123
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
124
+ "model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
125
+ "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
126
+ "model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
127
+ "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
128
+ "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
129
+ "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
130
+ "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
131
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
132
+ "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
133
+ "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
134
+ "model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
135
+ "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
136
+ "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
137
+ "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
138
+ "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
139
+ "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
140
+ "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
141
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
142
+ "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
143
+ "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
144
+ "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
145
+ "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
146
+ "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
147
+ "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
148
+ "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
149
+ "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
150
+ "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
151
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
152
+ "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
153
+ "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
154
+ "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
155
+ "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
156
+ "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
157
+ "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
158
+ "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
159
+ "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
160
+ "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
161
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
162
+ "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
163
+ "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
164
+ "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
165
+ "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
166
+ "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
167
+ "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
168
+ "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
169
+ "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
170
+ "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
171
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
172
+ "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
173
+ "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
174
+ "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
175
+ "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
176
+ "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
177
+ "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
178
+ "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
179
+ "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
180
+ "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
181
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "model-00003-of-00006.safetensors",
182
+ "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
183
+ "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
184
+ "model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
185
+ "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
186
+ "model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
187
+ "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
188
+ "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
189
+ "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
190
+ "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
191
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
192
+ "model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
193
+ "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
194
+ "model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
195
+ "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
196
+ "model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
197
+ "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
198
+ "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
199
+ "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
200
+ "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
201
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
202
+ "model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
203
+ "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
204
+ "model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
205
+ "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
206
+ "model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
207
+ "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
208
+ "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
209
+ "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
210
+ "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
211
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
212
+ "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
213
+ "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
214
+ "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
215
+ "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
216
+ "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
217
+ "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
218
+ "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
219
+ "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
220
+ "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
221
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
222
+ "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
223
+ "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
224
+ "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
225
+ "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
226
+ "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
227
+ "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
228
+ "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
229
+ "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
230
+ "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
231
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
232
+ "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
233
+ "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
234
+ "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
235
+ "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
236
+ "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
237
+ "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
238
+ "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
239
+ "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
240
+ "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
241
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "model-00004-of-00006.safetensors",
242
+ "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
243
+ "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
244
+ "model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
245
+ "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
246
+ "model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
247
+ "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
248
+ "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
249
+ "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
250
+ "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
251
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
252
+ "model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
253
+ "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
254
+ "model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
255
+ "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
256
+ "model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
257
+ "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
258
+ "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
259
+ "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
260
+ "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
261
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
262
+ "model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
263
+ "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
264
+ "model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
265
+ "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
266
+ "model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
267
+ "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
268
+ "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
269
+ "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
270
+ "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
271
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
272
+ "model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
273
+ "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
274
+ "model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
275
+ "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
276
+ "model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
277
+ "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
278
+ "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
279
+ "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
280
+ "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
281
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
282
+ "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
283
+ "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
284
+ "model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
285
+ "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
286
+ "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
287
+ "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
288
+ "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
289
+ "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
290
+ "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
291
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
292
+ "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
293
+ "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
294
+ "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
295
+ "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
296
+ "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
297
+ "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
298
+ "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
299
+ "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
300
+ "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
301
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "model-00005-of-00006.safetensors",
302
+ "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
303
+ "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
304
+ "model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
305
+ "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
306
+ "model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
307
+ "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
308
+ "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
309
+ "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
310
+ "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
311
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
312
+ "model.layers.30.input_layernorm.weight": "model-00006-of-00006.safetensors",
313
+ "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
314
+ "model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
315
+ "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
316
+ "model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
317
+ "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
318
+ "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
319
+ "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
320
+ "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
321
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "model-00006-of-00006.safetensors",
322
+ "model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
323
+ "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
324
+ "model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
325
+ "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
326
+ "model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
327
+ "model.norm.weight": "model-00006-of-00006.safetensors",
328
+ "lm_head.weight": "model-00006-of-00006.safetensors"
329
+ }
330
+ }
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": 0.23745410036719705,
5
+ "mc1_stderr": 0.014896277441041843,
6
+ "mc2": 0.3767993171277586,
7
+ "mc2_stderr": 0.013650568183578926
8
+ }
9
+ },
10
+ "versions": {
11
+ "truthfulqa_mc": 1
12
+ },
13
+ "config": {
14
+ "model": "sparseml",
15
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint,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": 0.7205998421468035,
5
+ "acc_stderr": 0.012610826539404676
6
+ }
7
+ },
8
+ "versions": {
9
+ "winogrande": 0
10
+ },
11
+ "config": {
12
+ "model": "sparseml",
13
+ "model_args": "pretrained=/network/alexandre/research/cerebras/llama2_7B_sparse50_45B_retrained/checkpoint,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
+ }