omkarenator commited on
Commit
58d76d5
1 Parent(s): 9a2661d

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "workdir_7b/ckpt_353",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
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": 2048,
14
+ "max_sequence_length": 2048,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 32,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.35.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
eval_arc.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "arc_challenge": {
4
+ "acc": 0.39761092150170646,
5
+ "acc_stderr": 0.014301752223279536,
6
+ "acc_norm": 0.4129692832764505,
7
+ "acc_norm_stderr": 0.014388344935398326
8
+ }
9
+ },
10
+ "versions": {
11
+ "arc_challenge": 0
12
+ },
13
+ "config": {
14
+ "model": "hf-causal",
15
+ "model_args": "pretrained=./workdir_7b_16mix/ckpt_359",
16
+ "num_fewshot": 25,
17
+ "batch_size": "1",
18
+ "batch_sizes": [],
19
+ "device": null,
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
eval_hellaswag.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hellaswag": {
4
+ "acc": 0.5476000796654052,
5
+ "acc_stderr": 0.0049671185759052865,
6
+ "acc_norm": 0.7382991435968931,
7
+ "acc_norm_stderr": 0.004386622589119069
8
+ }
9
+ },
10
+ "versions": {
11
+ "hellaswag": 0
12
+ },
13
+ "config": {
14
+ "model": "hf-causal",
15
+ "model_args": "pretrained=./workdir_7b_16mix/ckpt_359",
16
+ "num_fewshot": 10,
17
+ "batch_size": "1",
18
+ "batch_sizes": [],
19
+ "device": null,
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
eval_mmlu.json ADDED
@@ -0,0 +1,417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hendrycksTest-abstract_algebra": {
4
+ "acc": 0.29,
5
+ "acc_stderr": 0.045604802157206845,
6
+ "acc_norm": 0.29,
7
+ "acc_norm_stderr": 0.045604802157206845
8
+ },
9
+ "hendrycksTest-anatomy": {
10
+ "acc": 0.26666666666666666,
11
+ "acc_stderr": 0.038201699145179055,
12
+ "acc_norm": 0.26666666666666666,
13
+ "acc_norm_stderr": 0.038201699145179055
14
+ },
15
+ "hendrycksTest-astronomy": {
16
+ "acc": 0.27631578947368424,
17
+ "acc_stderr": 0.03639057569952924,
18
+ "acc_norm": 0.27631578947368424,
19
+ "acc_norm_stderr": 0.03639057569952924
20
+ },
21
+ "hendrycksTest-business_ethics": {
22
+ "acc": 0.32,
23
+ "acc_stderr": 0.046882617226215034,
24
+ "acc_norm": 0.32,
25
+ "acc_norm_stderr": 0.046882617226215034
26
+ },
27
+ "hendrycksTest-clinical_knowledge": {
28
+ "acc": 0.26037735849056604,
29
+ "acc_stderr": 0.027008766090708104,
30
+ "acc_norm": 0.26037735849056604,
31
+ "acc_norm_stderr": 0.027008766090708104
32
+ },
33
+ "hendrycksTest-college_biology": {
34
+ "acc": 0.2986111111111111,
35
+ "acc_stderr": 0.03827052357950756,
36
+ "acc_norm": 0.2986111111111111,
37
+ "acc_norm_stderr": 0.03827052357950756
38
+ },
39
+ "hendrycksTest-college_chemistry": {
40
+ "acc": 0.22,
41
+ "acc_stderr": 0.0416333199893227,
42
+ "acc_norm": 0.22,
43
+ "acc_norm_stderr": 0.0416333199893227
44
+ },
45
+ "hendrycksTest-college_computer_science": {
46
+ "acc": 0.38,
47
+ "acc_stderr": 0.04878317312145631,
48
+ "acc_norm": 0.38,
49
+ "acc_norm_stderr": 0.04878317312145631
50
+ },
51
+ "hendrycksTest-college_mathematics": {
52
+ "acc": 0.26,
53
+ "acc_stderr": 0.04408440022768078,
54
+ "acc_norm": 0.26,
55
+ "acc_norm_stderr": 0.04408440022768078
56
+ },
57
+ "hendrycksTest-college_medicine": {
58
+ "acc": 0.2774566473988439,
59
+ "acc_stderr": 0.03414014007044036,
60
+ "acc_norm": 0.2774566473988439,
61
+ "acc_norm_stderr": 0.03414014007044036
62
+ },
63
+ "hendrycksTest-college_physics": {
64
+ "acc": 0.19607843137254902,
65
+ "acc_stderr": 0.03950581861179963,
66
+ "acc_norm": 0.19607843137254902,
67
+ "acc_norm_stderr": 0.03950581861179963
68
+ },
69
+ "hendrycksTest-computer_security": {
70
+ "acc": 0.38,
71
+ "acc_stderr": 0.04878317312145633,
72
+ "acc_norm": 0.38,
73
+ "acc_norm_stderr": 0.04878317312145633
74
+ },
75
+ "hendrycksTest-conceptual_physics": {
76
+ "acc": 0.23829787234042554,
77
+ "acc_stderr": 0.027851252973889778,
78
+ "acc_norm": 0.23829787234042554,
79
+ "acc_norm_stderr": 0.027851252973889778
80
+ },
81
+ "hendrycksTest-econometrics": {
82
+ "acc": 0.2807017543859649,
83
+ "acc_stderr": 0.042270544512322,
84
+ "acc_norm": 0.2807017543859649,
85
+ "acc_norm_stderr": 0.042270544512322
86
+ },
87
+ "hendrycksTest-electrical_engineering": {
88
+ "acc": 0.3103448275862069,
89
+ "acc_stderr": 0.03855289616378948,
90
+ "acc_norm": 0.3103448275862069,
91
+ "acc_norm_stderr": 0.03855289616378948
92
+ },
93
+ "hendrycksTest-elementary_mathematics": {
94
+ "acc": 0.2619047619047619,
95
+ "acc_stderr": 0.022644212615525214,
96
+ "acc_norm": 0.2619047619047619,
97
+ "acc_norm_stderr": 0.022644212615525214
98
+ },
99
+ "hendrycksTest-formal_logic": {
100
+ "acc": 0.29365079365079366,
101
+ "acc_stderr": 0.040735243221471276,
102
+ "acc_norm": 0.29365079365079366,
103
+ "acc_norm_stderr": 0.040735243221471276
104
+ },
105
+ "hendrycksTest-global_facts": {
106
+ "acc": 0.33,
107
+ "acc_stderr": 0.047258156262526045,
108
+ "acc_norm": 0.33,
109
+ "acc_norm_stderr": 0.047258156262526045
110
+ },
111
+ "hendrycksTest-high_school_biology": {
112
+ "acc": 0.24193548387096775,
113
+ "acc_stderr": 0.024362599693031086,
114
+ "acc_norm": 0.24193548387096775,
115
+ "acc_norm_stderr": 0.024362599693031086
116
+ },
117
+ "hendrycksTest-high_school_chemistry": {
118
+ "acc": 0.15763546798029557,
119
+ "acc_stderr": 0.025639014131172404,
120
+ "acc_norm": 0.15763546798029557,
121
+ "acc_norm_stderr": 0.025639014131172404
122
+ },
123
+ "hendrycksTest-high_school_computer_science": {
124
+ "acc": 0.28,
125
+ "acc_stderr": 0.045126085985421276,
126
+ "acc_norm": 0.28,
127
+ "acc_norm_stderr": 0.045126085985421276
128
+ },
129
+ "hendrycksTest-high_school_european_history": {
130
+ "acc": 0.2909090909090909,
131
+ "acc_stderr": 0.03546563019624335,
132
+ "acc_norm": 0.2909090909090909,
133
+ "acc_norm_stderr": 0.03546563019624335
134
+ },
135
+ "hendrycksTest-high_school_geography": {
136
+ "acc": 0.2222222222222222,
137
+ "acc_stderr": 0.02962022787479047,
138
+ "acc_norm": 0.2222222222222222,
139
+ "acc_norm_stderr": 0.02962022787479047
140
+ },
141
+ "hendrycksTest-high_school_government_and_politics": {
142
+ "acc": 0.21243523316062177,
143
+ "acc_stderr": 0.029519282616817234,
144
+ "acc_norm": 0.21243523316062177,
145
+ "acc_norm_stderr": 0.029519282616817234
146
+ },
147
+ "hendrycksTest-high_school_macroeconomics": {
148
+ "acc": 0.24358974358974358,
149
+ "acc_stderr": 0.02176373368417393,
150
+ "acc_norm": 0.24358974358974358,
151
+ "acc_norm_stderr": 0.02176373368417393
152
+ },
153
+ "hendrycksTest-high_school_mathematics": {
154
+ "acc": 0.25555555555555554,
155
+ "acc_stderr": 0.02659393910184407,
156
+ "acc_norm": 0.25555555555555554,
157
+ "acc_norm_stderr": 0.02659393910184407
158
+ },
159
+ "hendrycksTest-high_school_microeconomics": {
160
+ "acc": 0.226890756302521,
161
+ "acc_stderr": 0.027205371538279496,
162
+ "acc_norm": 0.226890756302521,
163
+ "acc_norm_stderr": 0.027205371538279496
164
+ },
165
+ "hendrycksTest-high_school_physics": {
166
+ "acc": 0.2913907284768212,
167
+ "acc_stderr": 0.037101857261199946,
168
+ "acc_norm": 0.2913907284768212,
169
+ "acc_norm_stderr": 0.037101857261199946
170
+ },
171
+ "hendrycksTest-high_school_psychology": {
172
+ "acc": 0.22201834862385322,
173
+ "acc_stderr": 0.01781884956479661,
174
+ "acc_norm": 0.22201834862385322,
175
+ "acc_norm_stderr": 0.01781884956479661
176
+ },
177
+ "hendrycksTest-high_school_statistics": {
178
+ "acc": 0.2638888888888889,
179
+ "acc_stderr": 0.030058202704309846,
180
+ "acc_norm": 0.2638888888888889,
181
+ "acc_norm_stderr": 0.030058202704309846
182
+ },
183
+ "hendrycksTest-high_school_us_history": {
184
+ "acc": 0.29901960784313725,
185
+ "acc_stderr": 0.03213325717373616,
186
+ "acc_norm": 0.29901960784313725,
187
+ "acc_norm_stderr": 0.03213325717373616
188
+ },
189
+ "hendrycksTest-high_school_world_history": {
190
+ "acc": 0.29535864978902954,
191
+ "acc_stderr": 0.029696338713422886,
192
+ "acc_norm": 0.29535864978902954,
193
+ "acc_norm_stderr": 0.029696338713422886
194
+ },
195
+ "hendrycksTest-human_aging": {
196
+ "acc": 0.27802690582959644,
197
+ "acc_stderr": 0.030069584874494033,
198
+ "acc_norm": 0.27802690582959644,
199
+ "acc_norm_stderr": 0.030069584874494033
200
+ },
201
+ "hendrycksTest-human_sexuality": {
202
+ "acc": 0.29770992366412213,
203
+ "acc_stderr": 0.04010358942462203,
204
+ "acc_norm": 0.29770992366412213,
205
+ "acc_norm_stderr": 0.04010358942462203
206
+ },
207
+ "hendrycksTest-international_law": {
208
+ "acc": 0.2892561983471074,
209
+ "acc_stderr": 0.04139112727635464,
210
+ "acc_norm": 0.2892561983471074,
211
+ "acc_norm_stderr": 0.04139112727635464
212
+ },
213
+ "hendrycksTest-jurisprudence": {
214
+ "acc": 0.28703703703703703,
215
+ "acc_stderr": 0.043733130409147614,
216
+ "acc_norm": 0.28703703703703703,
217
+ "acc_norm_stderr": 0.043733130409147614
218
+ },
219
+ "hendrycksTest-logical_fallacies": {
220
+ "acc": 0.22699386503067484,
221
+ "acc_stderr": 0.032910995786157686,
222
+ "acc_norm": 0.22699386503067484,
223
+ "acc_norm_stderr": 0.032910995786157686
224
+ },
225
+ "hendrycksTest-machine_learning": {
226
+ "acc": 0.2767857142857143,
227
+ "acc_stderr": 0.04246624336697625,
228
+ "acc_norm": 0.2767857142857143,
229
+ "acc_norm_stderr": 0.04246624336697625
230
+ },
231
+ "hendrycksTest-management": {
232
+ "acc": 0.18446601941747573,
233
+ "acc_stderr": 0.03840423627288276,
234
+ "acc_norm": 0.18446601941747573,
235
+ "acc_norm_stderr": 0.03840423627288276
236
+ },
237
+ "hendrycksTest-marketing": {
238
+ "acc": 0.2948717948717949,
239
+ "acc_stderr": 0.029872577708891148,
240
+ "acc_norm": 0.2948717948717949,
241
+ "acc_norm_stderr": 0.029872577708891148
242
+ },
243
+ "hendrycksTest-medical_genetics": {
244
+ "acc": 0.37,
245
+ "acc_stderr": 0.04852365870939099,
246
+ "acc_norm": 0.37,
247
+ "acc_norm_stderr": 0.04852365870939099
248
+ },
249
+ "hendrycksTest-miscellaneous": {
250
+ "acc": 0.30779054916985954,
251
+ "acc_stderr": 0.016506045045155637,
252
+ "acc_norm": 0.30779054916985954,
253
+ "acc_norm_stderr": 0.016506045045155637
254
+ },
255
+ "hendrycksTest-moral_disputes": {
256
+ "acc": 0.30346820809248554,
257
+ "acc_stderr": 0.024752411960917202,
258
+ "acc_norm": 0.30346820809248554,
259
+ "acc_norm_stderr": 0.024752411960917202
260
+ },
261
+ "hendrycksTest-moral_scenarios": {
262
+ "acc": 0.24916201117318434,
263
+ "acc_stderr": 0.014465893829859923,
264
+ "acc_norm": 0.24916201117318434,
265
+ "acc_norm_stderr": 0.014465893829859923
266
+ },
267
+ "hendrycksTest-nutrition": {
268
+ "acc": 0.2549019607843137,
269
+ "acc_stderr": 0.02495418432487991,
270
+ "acc_norm": 0.2549019607843137,
271
+ "acc_norm_stderr": 0.02495418432487991
272
+ },
273
+ "hendrycksTest-philosophy": {
274
+ "acc": 0.34726688102893893,
275
+ "acc_stderr": 0.027040745502307336,
276
+ "acc_norm": 0.34726688102893893,
277
+ "acc_norm_stderr": 0.027040745502307336
278
+ },
279
+ "hendrycksTest-prehistory": {
280
+ "acc": 0.29012345679012347,
281
+ "acc_stderr": 0.025251173936495012,
282
+ "acc_norm": 0.29012345679012347,
283
+ "acc_norm_stderr": 0.025251173936495012
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": 0.2816166883963494,
293
+ "acc_stderr": 0.011487783272786696,
294
+ "acc_norm": 0.2816166883963494,
295
+ "acc_norm_stderr": 0.011487783272786696
296
+ },
297
+ "hendrycksTest-professional_medicine": {
298
+ "acc": 0.1948529411764706,
299
+ "acc_stderr": 0.024060599423487428,
300
+ "acc_norm": 0.1948529411764706,
301
+ "acc_norm_stderr": 0.024060599423487428
302
+ },
303
+ "hendrycksTest-professional_psychology": {
304
+ "acc": 0.30718954248366015,
305
+ "acc_stderr": 0.018663359671463653,
306
+ "acc_norm": 0.30718954248366015,
307
+ "acc_norm_stderr": 0.018663359671463653
308
+ },
309
+ "hendrycksTest-public_relations": {
310
+ "acc": 0.2727272727272727,
311
+ "acc_stderr": 0.04265792110940588,
312
+ "acc_norm": 0.2727272727272727,
313
+ "acc_norm_stderr": 0.04265792110940588
314
+ },
315
+ "hendrycksTest-security_studies": {
316
+ "acc": 0.2,
317
+ "acc_stderr": 0.025607375986579153,
318
+ "acc_norm": 0.2,
319
+ "acc_norm_stderr": 0.025607375986579153
320
+ },
321
+ "hendrycksTest-sociology": {
322
+ "acc": 0.24875621890547264,
323
+ "acc_stderr": 0.030567675938916707,
324
+ "acc_norm": 0.24875621890547264,
325
+ "acc_norm_stderr": 0.030567675938916707
326
+ },
327
+ "hendrycksTest-us_foreign_policy": {
328
+ "acc": 0.32,
329
+ "acc_stderr": 0.04688261722621504,
330
+ "acc_norm": 0.32,
331
+ "acc_norm_stderr": 0.04688261722621504
332
+ },
333
+ "hendrycksTest-virology": {
334
+ "acc": 0.2710843373493976,
335
+ "acc_stderr": 0.03460579907553027,
336
+ "acc_norm": 0.2710843373493976,
337
+ "acc_norm_stderr": 0.03460579907553027
338
+ },
339
+ "hendrycksTest-world_religions": {
340
+ "acc": 0.3742690058479532,
341
+ "acc_stderr": 0.03711601185389481,
342
+ "acc_norm": 0.3742690058479532,
343
+ "acc_norm_stderr": 0.03711601185389481
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": "hf-causal",
407
+ "model_args": "pretrained=./workdir_7b_16mix/ckpt_359",
408
+ "num_fewshot": 5,
409
+ "batch_size": "1",
410
+ "batch_sizes": [],
411
+ "device": null,
412
+ "no_cache": true,
413
+ "limit": null,
414
+ "bootstrap_iters": 100000,
415
+ "description_dict": {}
416
+ }
417
+ }
eval_truthfulqa.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "truthfulqa_mc": {
4
+ "mc1": 0.2141982864137087,
5
+ "mc1_stderr": 0.014362148155690462,
6
+ "mc2": 0.3359467406926554,
7
+ "mc2_stderr": 0.013120875222733098
8
+ }
9
+ },
10
+ "versions": {
11
+ "truthfulqa_mc": 1
12
+ },
13
+ "config": {
14
+ "model": "hf-causal",
15
+ "model_args": "pretrained=./workdir_7b_16mix/ckpt_359",
16
+ "num_fewshot": 0,
17
+ "batch_size": "1",
18
+ "batch_sizes": [],
19
+ "device": null,
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.35.2"
7
+ }
pytorch_model-00001-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc640b954d07c1a3bb13e4fb8355129d64bb2805b0625c9b800fde564e3f7692
3
+ size 4840412662
pytorch_model-00002-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fec9598a92027235d8183356862d15e34abd9902512ea96a40d24e0e96eaf71
3
+ size 4857224198
pytorch_model-00003-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2c13ac3d6938541d7fe0c9a6a9000881b5903b88a0fc85d6bd1a5d8c22d4041
3
+ size 4857224262
pytorch_model-00004-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba59353ca8e4389a412cb21f2674de8aa5fee22cccfbba6e80a21daf745fe71d
3
+ size 4857224262
pytorch_model-00005-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd152ca6875f5d20a7ab2a1c10d0d7e729059f91deb10eb82cf046c8aa03aa57
3
+ size 4857224262
pytorch_model-00006-of-00006.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:067d28cad8953be2bc2fd5032a1c14d570a145033fb5767d8ddc4d9af6767350
3
+ size 2684479760
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,330 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 26953670656
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "pytorch_model-00006-of-00006.bin",
7
+ "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin",
8
+ "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
9
+ "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
10
+ "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
11
+ "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
12
+ "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
13
+ "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
14
+ "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
15
+ "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
16
+ "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
17
+ "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
18
+ "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
19
+ "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
20
+ "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
21
+ "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
22
+ "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
23
+ "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
24
+ "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
25
+ "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
26
+ "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
27
+ "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
28
+ "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
29
+ "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
30
+ "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
31
+ "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
32
+ "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
33
+ "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
34
+ "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
35
+ "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
36
+ "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
37
+ "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
38
+ "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
39
+ "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
40
+ "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
41
+ "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
42
+ "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
43
+ "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
44
+ "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
45
+ "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
46
+ "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
47
+ "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
48
+ "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
49
+ "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
50
+ "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
51
+ "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
52
+ "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
53
+ "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
54
+ "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
55
+ "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
56
+ "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
57
+ "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
58
+ "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
59
+ "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
60
+ "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
61
+ "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
62
+ "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
63
+ "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
64
+ "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
65
+ "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
66
+ "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
67
+ "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
68
+ "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
69
+ "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
70
+ "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
71
+ "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
72
+ "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
73
+ "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
74
+ "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
75
+ "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
76
+ "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
77
+ "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
78
+ "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
79
+ "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
80
+ "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
81
+ "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
82
+ "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
83
+ "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
84
+ "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
85
+ "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
86
+ "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
87
+ "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
88
+ "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00006.bin",
89
+ "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin",
90
+ "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin",
91
+ "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin",
92
+ "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin",
93
+ "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
94
+ "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
95
+ "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
96
+ "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
97
+ "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
98
+ "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
99
+ "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
100
+ "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
101
+ "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
102
+ "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
103
+ "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin",
104
+ "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin",
105
+ "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin",
106
+ "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00006.bin",
107
+ "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin",
108
+ "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
109
+ "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
110
+ "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
111
+ "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
112
+ "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
113
+ "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
114
+ "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
115
+ "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
116
+ "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
117
+ "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
118
+ "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
119
+ "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
120
+ "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
121
+ "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
122
+ "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
123
+ "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
124
+ "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
125
+ "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
126
+ "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
127
+ "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
128
+ "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
129
+ "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
130
+ "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
131
+ "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
132
+ "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
133
+ "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
134
+ "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
135
+ "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
136
+ "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
137
+ "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
138
+ "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
139
+ "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
140
+ "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
141
+ "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
142
+ "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
143
+ "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
144
+ "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
145
+ "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
146
+ "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
147
+ "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
148
+ "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
149
+ "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
150
+ "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
151
+ "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
152
+ "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
153
+ "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
154
+ "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
155
+ "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
156
+ "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
157
+ "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
158
+ "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00006.bin",
159
+ "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin",
160
+ "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin",
161
+ "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin",
162
+ "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin",
163
+ "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
164
+ "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
165
+ "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
166
+ "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
167
+ "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
168
+ "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
169
+ "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
170
+ "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
171
+ "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
172
+ "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
173
+ "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin",
174
+ "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin",
175
+ "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin",
176
+ "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00006.bin",
177
+ "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin",
178
+ "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
179
+ "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
180
+ "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
181
+ "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
182
+ "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
183
+ "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
184
+ "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
185
+ "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
186
+ "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
187
+ "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
188
+ "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
189
+ "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
190
+ "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
191
+ "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
192
+ "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
193
+ "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
194
+ "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
195
+ "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
196
+ "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
197
+ "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
198
+ "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
199
+ "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
200
+ "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
201
+ "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
202
+ "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
203
+ "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
204
+ "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
205
+ "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
206
+ "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
207
+ "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
208
+ "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
209
+ "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
210
+ "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
211
+ "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
212
+ "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
213
+ "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
214
+ "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
215
+ "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
216
+ "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
217
+ "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
218
+ "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00006.bin",
219
+ "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin",
220
+ "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin",
221
+ "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin",
222
+ "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin",
223
+ "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
224
+ "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
225
+ "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
226
+ "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
227
+ "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
228
+ "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
229
+ "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
230
+ "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
231
+ "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
232
+ "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
233
+ "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin",
234
+ "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin",
235
+ "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin",
236
+ "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00006.bin",
237
+ "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin",
238
+ "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
239
+ "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
240
+ "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
241
+ "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
242
+ "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
243
+ "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
244
+ "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
245
+ "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
246
+ "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
247
+ "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
248
+ "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
249
+ "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
250
+ "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
251
+ "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
252
+ "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
253
+ "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
254
+ "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
255
+ "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
256
+ "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
257
+ "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
258
+ "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00006.bin",
259
+ "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin",
260
+ "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin",
261
+ "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin",
262
+ "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin",
263
+ "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin",
264
+ "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin",
265
+ "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin",
266
+ "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00006.bin",
267
+ "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin",
268
+ "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin",
269
+ "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin",
270
+ "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin",
271
+ "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin",
272
+ "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin",
273
+ "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
274
+ "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
275
+ "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
276
+ "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
277
+ "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
278
+ "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
279
+ "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
280
+ "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
281
+ "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
282
+ "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
283
+ "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin",
284
+ "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin",
285
+ "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin",
286
+ "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00006.bin",
287
+ "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin",
288
+ "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
289
+ "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
290
+ "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
291
+ "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
292
+ "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
293
+ "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
294
+ "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
295
+ "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
296
+ "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
297
+ "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
298
+ "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
299
+ "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
300
+ "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
301
+ "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
302
+ "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
303
+ "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
304
+ "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
305
+ "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
306
+ "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
307
+ "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
308
+ "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
309
+ "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
310
+ "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
311
+ "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
312
+ "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
313
+ "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
314
+ "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
315
+ "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
316
+ "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
317
+ "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
318
+ "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin",
319
+ "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin",
320
+ "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin",
321
+ "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin",
322
+ "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin",
323
+ "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin",
324
+ "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin",
325
+ "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin",
326
+ "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00006.bin",
327
+ "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin",
328
+ "model.norm.weight": "pytorch_model-00006-of-00006.bin"
329
+ }
330
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
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 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "model_max_length": 2048,
32
+ "pad_token": null,
33
+ "sp_model_kwargs": {},
34
+ "tokenizer_class": "LlamaTokenizer",
35
+ "unk_token": "<unk>",
36
+ "use_default_system_prompt": false
37
+ }