Hugging Face's logo

neuralmagic
/
Llama-2-7b-dolphin-open_platypus

Text Generation
Transformers
Safetensors
llama
instruct
text-generation-inference
Inference Endpoints
Model card Files Community
shubhrapandit commited on
Commit
9647286
•
1 Parent(s): 48a08c9

Convert model to BFloat16 and shard using SafeTensors

Browse files
Files changed (12) hide show
  1. arc_challenge.json +25 -0
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. gsm8k.json +23 -0
  5. hellaswag.json +25 -0
  6. mmlu.json +417 -0
  7. model-00001-of-00003.safetensors → model-00001-of-00002.safetensors +2 -2
  8. model-00002-of-00003.safetensors → model-00002-of-00002.safetensors +2 -2
  9. model-00003-of-00003.safetensors +0 -3
  10. model.safetensors.index.json +291 -291
  11. truthfulqa_mc.json +25 -0
  12. winogrande.json +23 -0
arc_challenge.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "arc_challenge": {
4
+ "acc": 0.5136518771331058,
5
+ "acc_stderr": 0.014605943429860947,
6
+ "acc_norm": 0.5409556313993175,
7
+ "acc_norm_stderr": 0.014562291073601229
8
+ }
9
+ },
10
+ "versions": {
11
+ "arc_challenge": 0
12
+ },
13
+ "config": {
14
+ "model": "hf",
15
+ "model_args": "pretrained=/cache/shubhra/models/llama2_denseft_playtpus_dolphin_LR1e-5_E2_noGC_LRScosine/combined/,trust_remote_code=True,dtype=bfloat16",
16
+ "num_fewshot": 25,
17
+ "batch_size": "32",
18
+ "batch_sizes": [],
19
+ "device": "cuda:0",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
config.json CHANGED
@@ -22,7 +22,7 @@
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
- "transformers_version": "4.40.0",
26
  "use_cache": true,
27
  "vocab_size": 32000
28
  }
 
22
  "rope_theta": 10000.0,
23
  "tie_word_embeddings": false,
24
  "torch_dtype": "bfloat16",
25
+ "transformers_version": "1.7.0.43401",
26
  "use_cache": true,
27
  "vocab_size": 32000
28
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.40.0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "1.7.0.43401"
6
  }
gsm8k.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "gsm8k": {
4
+ "acc": 0.1516300227445034,
5
+ "acc_stderr": 0.009879331091354313
6
+ }
7
+ },
8
+ "versions": {
9
+ "gsm8k": 0
10
+ },
11
+ "config": {
12
+ "model": "hf",
13
+ "model_args": "pretrained=/cache/shubhra/models/llama2_denseft_playtpus_dolphin_LR1e-5_E2_noGC_LRScosine/combined/,trust_remote_code=True,dtype=bfloat16",
14
+ "num_fewshot": 5,
15
+ "batch_size": "128",
16
+ "batch_sizes": [],
17
+ "device": "cuda:0",
18
+ "no_cache": true,
19
+ "limit": null,
20
+ "bootstrap_iters": 100000,
21
+ "description_dict": {}
22
+ }
23
+ }
hellaswag.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hellaswag": {
4
+ "acc": 0.5950009958175663,
5
+ "acc_stderr": 0.0048988860806879276,
6
+ "acc_norm": 0.793666600278829,
7
+ "acc_norm_stderr": 0.004038455815535897
8
+ }
9
+ },
10
+ "versions": {
11
+ "hellaswag": 0
12
+ },
13
+ "config": {
14
+ "model": "hf",
15
+ "model_args": "pretrained=/cache/shubhra/models/llama2_denseft_playtpus_dolphin_LR1e-5_E2_noGC_LRScosine/combined/,trust_remote_code=True,dtype=bfloat16",
16
+ "num_fewshot": 10,
17
+ "batch_size": "48",
18
+ "batch_sizes": [],
19
+ "device": "cuda:0",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
mmlu.json ADDED
@@ -0,0 +1,417 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "hendrycksTest-abstract_algebra": {
4
+ "acc": 0.34,
5
+ "acc_stderr": 0.047609522856952365,
6
+ "acc_norm": 0.34,
7
+ "acc_norm_stderr": 0.047609522856952365
8
+ },
9
+ "hendrycksTest-anatomy": {
10
+ "acc": 0.5037037037037037,
11
+ "acc_stderr": 0.04319223625811331,
12
+ "acc_norm": 0.5037037037037037,
13
+ "acc_norm_stderr": 0.04319223625811331
14
+ },
15
+ "hendrycksTest-astronomy": {
16
+ "acc": 0.4276315789473684,
17
+ "acc_stderr": 0.04026097083296558,
18
+ "acc_norm": 0.4276315789473684,
19
+ "acc_norm_stderr": 0.04026097083296558
20
+ },
21
+ "hendrycksTest-business_ethics": {
22
+ "acc": 0.54,
23
+ "acc_stderr": 0.05009082659620333,
24
+ "acc_norm": 0.54,
25
+ "acc_norm_stderr": 0.05009082659620333
26
+ },
27
+ "hendrycksTest-clinical_knowledge": {
28
+ "acc": 0.4679245283018868,
29
+ "acc_stderr": 0.030709486992556545,
30
+ "acc_norm": 0.4679245283018868,
31
+ "acc_norm_stderr": 0.030709486992556545
32
+ },
33
+ "hendrycksTest-college_biology": {
34
+ "acc": 0.5,
35
+ "acc_stderr": 0.04181210050035455,
36
+ "acc_norm": 0.5,
37
+ "acc_norm_stderr": 0.04181210050035455
38
+ },
39
+ "hendrycksTest-college_chemistry": {
40
+ "acc": 0.29,
41
+ "acc_stderr": 0.045604802157206845,
42
+ "acc_norm": 0.29,
43
+ "acc_norm_stderr": 0.045604802157206845
44
+ },
45
+ "hendrycksTest-college_computer_science": {
46
+ "acc": 0.4,
47
+ "acc_stderr": 0.04923659639173309,
48
+ "acc_norm": 0.4,
49
+ "acc_norm_stderr": 0.04923659639173309
50
+ },
51
+ "hendrycksTest-college_mathematics": {
52
+ "acc": 0.31,
53
+ "acc_stderr": 0.04648231987117316,
54
+ "acc_norm": 0.31,
55
+ "acc_norm_stderr": 0.04648231987117316
56
+ },
57
+ "hendrycksTest-college_medicine": {
58
+ "acc": 0.4393063583815029,
59
+ "acc_stderr": 0.03784271932887467,
60
+ "acc_norm": 0.4393063583815029,
61
+ "acc_norm_stderr": 0.03784271932887467
62
+ },
63
+ "hendrycksTest-college_physics": {
64
+ "acc": 0.20588235294117646,
65
+ "acc_stderr": 0.04023382273617747,
66
+ "acc_norm": 0.20588235294117646,
67
+ "acc_norm_stderr": 0.04023382273617747
68
+ },
69
+ "hendrycksTest-computer_security": {
70
+ "acc": 0.61,
71
+ "acc_stderr": 0.04902071300001975,
72
+ "acc_norm": 0.61,
73
+ "acc_norm_stderr": 0.04902071300001975
74
+ },
75
+ "hendrycksTest-conceptual_physics": {
76
+ "acc": 0.43829787234042555,
77
+ "acc_stderr": 0.03243618636108101,
78
+ "acc_norm": 0.43829787234042555,
79
+ "acc_norm_stderr": 0.03243618636108101
80
+ },
81
+ "hendrycksTest-econometrics": {
82
+ "acc": 0.2894736842105263,
83
+ "acc_stderr": 0.04266339443159393,
84
+ "acc_norm": 0.2894736842105263,
85
+ "acc_norm_stderr": 0.04266339443159393
86
+ },
87
+ "hendrycksTest-electrical_engineering": {
88
+ "acc": 0.46206896551724136,
89
+ "acc_stderr": 0.041546596717075474,
90
+ "acc_norm": 0.46206896551724136,
91
+ "acc_norm_stderr": 0.041546596717075474
92
+ },
93
+ "hendrycksTest-elementary_mathematics": {
94
+ "acc": 0.2962962962962963,
95
+ "acc_stderr": 0.023517294335963276,
96
+ "acc_norm": 0.2962962962962963,
97
+ "acc_norm_stderr": 0.023517294335963276
98
+ },
99
+ "hendrycksTest-formal_logic": {
100
+ "acc": 0.30952380952380953,
101
+ "acc_stderr": 0.04134913018303316,
102
+ "acc_norm": 0.30952380952380953,
103
+ "acc_norm_stderr": 0.04134913018303316
104
+ },
105
+ "hendrycksTest-global_facts": {
106
+ "acc": 0.38,
107
+ "acc_stderr": 0.048783173121456316,
108
+ "acc_norm": 0.38,
109
+ "acc_norm_stderr": 0.048783173121456316
110
+ },
111
+ "hendrycksTest-high_school_biology": {
112
+ "acc": 0.5419354838709678,
113
+ "acc_stderr": 0.028343787250540615,
114
+ "acc_norm": 0.5419354838709678,
115
+ "acc_norm_stderr": 0.028343787250540615
116
+ },
117
+ "hendrycksTest-high_school_chemistry": {
118
+ "acc": 0.3448275862068966,
119
+ "acc_stderr": 0.03344283744280458,
120
+ "acc_norm": 0.3448275862068966,
121
+ "acc_norm_stderr": 0.03344283744280458
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": 0.6363636363636364,
131
+ "acc_stderr": 0.03756335775187897,
132
+ "acc_norm": 0.6363636363636364,
133
+ "acc_norm_stderr": 0.03756335775187897
134
+ },
135
+ "hendrycksTest-high_school_geography": {
136
+ "acc": 0.5353535353535354,
137
+ "acc_stderr": 0.03553436368828061,
138
+ "acc_norm": 0.5353535353535354,
139
+ "acc_norm_stderr": 0.03553436368828061
140
+ },
141
+ "hendrycksTest-high_school_government_and_politics": {
142
+ "acc": 0.7150259067357513,
143
+ "acc_stderr": 0.032577140777096614,
144
+ "acc_norm": 0.7150259067357513,
145
+ "acc_norm_stderr": 0.032577140777096614
146
+ },
147
+ "hendrycksTest-high_school_macroeconomics": {
148
+ "acc": 0.4564102564102564,
149
+ "acc_stderr": 0.025254485424799602,
150
+ "acc_norm": 0.4564102564102564,
151
+ "acc_norm_stderr": 0.025254485424799602
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": 0.4495798319327731,
161
+ "acc_stderr": 0.03231293497137707,
162
+ "acc_norm": 0.4495798319327731,
163
+ "acc_norm_stderr": 0.03231293497137707
164
+ },
165
+ "hendrycksTest-high_school_physics": {
166
+ "acc": 0.2847682119205298,
167
+ "acc_stderr": 0.03684881521389023,
168
+ "acc_norm": 0.2847682119205298,
169
+ "acc_norm_stderr": 0.03684881521389023
170
+ },
171
+ "hendrycksTest-high_school_psychology": {
172
+ "acc": 0.655045871559633,
173
+ "acc_stderr": 0.020380605405066955,
174
+ "acc_norm": 0.655045871559633,
175
+ "acc_norm_stderr": 0.020380605405066955
176
+ },
177
+ "hendrycksTest-high_school_statistics": {
178
+ "acc": 0.32407407407407407,
179
+ "acc_stderr": 0.03191923445686185,
180
+ "acc_norm": 0.32407407407407407,
181
+ "acc_norm_stderr": 0.03191923445686185
182
+ },
183
+ "hendrycksTest-high_school_us_history": {
184
+ "acc": 0.6274509803921569,
185
+ "acc_stderr": 0.03393388584958406,
186
+ "acc_norm": 0.6274509803921569,
187
+ "acc_norm_stderr": 0.03393388584958406
188
+ },
189
+ "hendrycksTest-high_school_world_history": {
190
+ "acc": 0.6497890295358649,
191
+ "acc_stderr": 0.031052391937584346,
192
+ "acc_norm": 0.6497890295358649,
193
+ "acc_norm_stderr": 0.031052391937584346
194
+ },
195
+ "hendrycksTest-human_aging": {
196
+ "acc": 0.547085201793722,
197
+ "acc_stderr": 0.033408675019233246,
198
+ "acc_norm": 0.547085201793722,
199
+ "acc_norm_stderr": 0.033408675019233246
200
+ },
201
+ "hendrycksTest-human_sexuality": {
202
+ "acc": 0.5648854961832062,
203
+ "acc_stderr": 0.04348208051644858,
204
+ "acc_norm": 0.5648854961832062,
205
+ "acc_norm_stderr": 0.04348208051644858
206
+ },
207
+ "hendrycksTest-international_law": {
208
+ "acc": 0.6363636363636364,
209
+ "acc_stderr": 0.043913262867240704,
210
+ "acc_norm": 0.6363636363636364,
211
+ "acc_norm_stderr": 0.043913262867240704
212
+ },
213
+ "hendrycksTest-jurisprudence": {
214
+ "acc": 0.5555555555555556,
215
+ "acc_stderr": 0.04803752235190193,
216
+ "acc_norm": 0.5555555555555556,
217
+ "acc_norm_stderr": 0.04803752235190193
218
+ },
219
+ "hendrycksTest-logical_fallacies": {
220
+ "acc": 0.49693251533742333,
221
+ "acc_stderr": 0.03928297078179663,
222
+ "acc_norm": 0.49693251533742333,
223
+ "acc_norm_stderr": 0.03928297078179663
224
+ },
225
+ "hendrycksTest-machine_learning": {
226
+ "acc": 0.39285714285714285,
227
+ "acc_stderr": 0.04635550135609976,
228
+ "acc_norm": 0.39285714285714285,
229
+ "acc_norm_stderr": 0.04635550135609976
230
+ },
231
+ "hendrycksTest-management": {
232
+ "acc": 0.5728155339805825,
233
+ "acc_stderr": 0.048979577377811674,
234
+ "acc_norm": 0.5728155339805825,
235
+ "acc_norm_stderr": 0.048979577377811674
236
+ },
237
+ "hendrycksTest-marketing": {
238
+ "acc": 0.6965811965811965,
239
+ "acc_stderr": 0.030118210106942638,
240
+ "acc_norm": 0.6965811965811965,
241
+ "acc_norm_stderr": 0.030118210106942638
242
+ },
243
+ "hendrycksTest-medical_genetics": {
244
+ "acc": 0.53,
245
+ "acc_stderr": 0.05016135580465919,
246
+ "acc_norm": 0.53,
247
+ "acc_norm_stderr": 0.05016135580465919
248
+ },
249
+ "hendrycksTest-miscellaneous": {
250
+ "acc": 0.6602809706257982,
251
+ "acc_stderr": 0.016936394114301635,
252
+ "acc_norm": 0.6602809706257982,
253
+ "acc_norm_stderr": 0.016936394114301635
254
+ },
255
+ "hendrycksTest-moral_disputes": {
256
+ "acc": 0.5317919075144508,
257
+ "acc_stderr": 0.026864624366756643,
258
+ "acc_norm": 0.5317919075144508,
259
+ "acc_norm_stderr": 0.026864624366756643
260
+ },
261
+ "hendrycksTest-moral_scenarios": {
262
+ "acc": 0.24581005586592178,
263
+ "acc_stderr": 0.014400296429225627,
264
+ "acc_norm": 0.24581005586592178,
265
+ "acc_norm_stderr": 0.014400296429225627
266
+ },
267
+ "hendrycksTest-nutrition": {
268
+ "acc": 0.5163398692810458,
269
+ "acc_stderr": 0.02861462475280544,
270
+ "acc_norm": 0.5163398692810458,
271
+ "acc_norm_stderr": 0.02861462475280544
272
+ },
273
+ "hendrycksTest-philosophy": {
274
+ "acc": 0.6012861736334405,
275
+ "acc_stderr": 0.027809322585774496,
276
+ "acc_norm": 0.6012861736334405,
277
+ "acc_norm_stderr": 0.027809322585774496
278
+ },
279
+ "hendrycksTest-prehistory": {
280
+ "acc": 0.5185185185185185,
281
+ "acc_stderr": 0.02780165621232366,
282
+ "acc_norm": 0.5185185185185185,
283
+ "acc_norm_stderr": 0.02780165621232366
284
+ },
285
+ "hendrycksTest-professional_accounting": {
286
+ "acc": 0.3723404255319149,
287
+ "acc_stderr": 0.028838921471251458,
288
+ "acc_norm": 0.3723404255319149,
289
+ "acc_norm_stderr": 0.028838921471251458
290
+ },
291
+ "hendrycksTest-professional_law": {
292
+ "acc": 0.3683181225554107,
293
+ "acc_stderr": 0.012319403369564637,
294
+ "acc_norm": 0.3683181225554107,
295
+ "acc_norm_stderr": 0.012319403369564637
296
+ },
297
+ "hendrycksTest-professional_medicine": {
298
+ "acc": 0.5330882352941176,
299
+ "acc_stderr": 0.030306257722468317,
300
+ "acc_norm": 0.5330882352941176,
301
+ "acc_norm_stderr": 0.030306257722468317
302
+ },
303
+ "hendrycksTest-professional_psychology": {
304
+ "acc": 0.46405228758169936,
305
+ "acc_stderr": 0.020175488765484036,
306
+ "acc_norm": 0.46405228758169936,
307
+ "acc_norm_stderr": 0.020175488765484036
308
+ },
309
+ "hendrycksTest-public_relations": {
310
+ "acc": 0.5545454545454546,
311
+ "acc_stderr": 0.047605488214603246,
312
+ "acc_norm": 0.5545454545454546,
313
+ "acc_norm_stderr": 0.047605488214603246
314
+ },
315
+ "hendrycksTest-security_studies": {
316
+ "acc": 0.4897959183673469,
317
+ "acc_stderr": 0.03200255347893782,
318
+ "acc_norm": 0.4897959183673469,
319
+ "acc_norm_stderr": 0.03200255347893782
320
+ },
321
+ "hendrycksTest-sociology": {
322
+ "acc": 0.6417910447761194,
323
+ "acc_stderr": 0.03390393042268814,
324
+ "acc_norm": 0.6417910447761194,
325
+ "acc_norm_stderr": 0.03390393042268814
326
+ },
327
+ "hendrycksTest-us_foreign_policy": {
328
+ "acc": 0.65,
329
+ "acc_stderr": 0.047937248544110196,
330
+ "acc_norm": 0.65,
331
+ "acc_norm_stderr": 0.047937248544110196
332
+ },
333
+ "hendrycksTest-virology": {
334
+ "acc": 0.39759036144578314,
335
+ "acc_stderr": 0.038099730845402184,
336
+ "acc_norm": 0.39759036144578314,
337
+ "acc_norm_stderr": 0.038099730845402184
338
+ },
339
+ "hendrycksTest-world_religions": {
340
+ "acc": 0.7134502923976608,
341
+ "acc_stderr": 0.03467826685703826,
342
+ "acc_norm": 0.7134502923976608,
343
+ "acc_norm_stderr": 0.03467826685703826
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",
407
+ "model_args": "pretrained=/cache/shubhra/models/llama2_denseft_playtpus_dolphin_LR1e-5_E2_noGC_LRScosine/combined/,trust_remote_code=True,dtype=bfloat16",
408
+ "num_fewshot": 5,
409
+ "batch_size": "16",
410
+ "batch_sizes": [],
411
+ "device": "cuda:0",
412
+ "no_cache": true,
413
+ "limit": null,
414
+ "bootstrap_iters": 100000,
415
+ "description_dict": {}
416
+ }
417
+ }
model-00001-of-00003.safetensors → model-00001-of-00002.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2a666fb314273e1d1d1d611352533488e2514441ddda7d30e34c0d05efe8949
3
- size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcc8fc90cc6d1156c0e6c6f20493031e6ad8c7312e76d5b6a736ff1d73d93dd
3
+ size 9976570520
model-00002-of-00003.safetensors → model-00002-of-00002.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1f6e841bd270ebd278153aa166eb0ff4ce505b2bb1d00fd70db0cde31ff39d6
3
- size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f07a69d6ca04193259443522cd7e2b44558af94c191f3a91f2073729ddfc262e
3
+ size 3500294544
model-00003-of-00003.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1611ff41be15845d4f7e18cc7cdfd8a80e74a540176daa7506a8b70f9d554d84
3
- size 3590488816
 
 
 
 
model.safetensors.index.json CHANGED
@@ -3,296 +3,296 @@
3
  "total_size": 13476831232
4
  },
5
  "weight_map": {
6
- "lm_head.weight": "model-00003-of-00003.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
- "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
- "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
- "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
36
- "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
37
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
- "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
39
- "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
40
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
- "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
- "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
- "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
47
- "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
48
- "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
- "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
50
- "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
51
- "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
52
- "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
53
- "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
- "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
- "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
- "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
- "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
- "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
- "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
- "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
- "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
- "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
- "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
- "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
- "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
- "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
- "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
- "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
- "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
- "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
- "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
- "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
- "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
- "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
- "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
- "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
- "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
- "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
- "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
- "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
- "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
- "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
- "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
- "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
- "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
- "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
- "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
- "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
- "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
- "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
- "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
- "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
- "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
- "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
- "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
- "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
- "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
- "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
- "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
- "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
- "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
- "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
- "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
- "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
- "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
- "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
- "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
- "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
- "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
- "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
- "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
- "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
- "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
- "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
- "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
- "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
- "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
- "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
- "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
- "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
- "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
- "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
- "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
- "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
- "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
- "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
- "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
- "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
- "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
- "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
- "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
- "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
- "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
153
- "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
154
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
- "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
157
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
- "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
162
- "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
163
- "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
164
- "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
165
- "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
166
- "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
167
- "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
168
- "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
169
- "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
170
- "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
171
- "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
172
- "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
173
- "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
174
- "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
175
- "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
176
- "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
177
- "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
178
- "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
179
- "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
180
- "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
181
- "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
182
- "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
183
- "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
184
- "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
185
- "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
186
- "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
187
- "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
188
- "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
- "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
- "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
- "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
- "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
- "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
194
- "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
- "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
196
- "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
197
- "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
- "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
- "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
- "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
- "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
- "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
- "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
- "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
- "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
- "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
- "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
- "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
- "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
- "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
- "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
- "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
- "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
- "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
- "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
- "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
- "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
- "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
- "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
- "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
- "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
- "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
- "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
- "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
- "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
- "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
- "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
- "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
- "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
- "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
- "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
- "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
- "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
- "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
- "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
- "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
- "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
- "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
- "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
- "model.norm.weight": "model-00003-of-00003.safetensors"
297
  }
298
  }
 
3
  "total_size": 13476831232
4
  },
5
  "weight_map": {
6
+ "lm_head.weight": "model-00002-of-00002.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
296
+ "model.norm.weight": "model-00002-of-00002.safetensors"
297
  }
298
  }
truthfulqa_mc.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "truthfulqa_mc": {
4
+ "mc1": 0.2802937576499388,
5
+ "mc1_stderr": 0.015723139524608763,
6
+ "mc2": 0.4267590294350202,
7
+ "mc2_stderr": 0.014157890438760036
8
+ }
9
+ },
10
+ "versions": {
11
+ "truthfulqa_mc": 1
12
+ },
13
+ "config": {
14
+ "model": "hf",
15
+ "model_args": "pretrained=/cache/shubhra/models/llama2_denseft_playtpus_dolphin_LR1e-5_E2_noGC_LRScosine/combined/,trust_remote_code=True,dtype=bfloat16",
16
+ "num_fewshot": 0,
17
+ "batch_size": "128",
18
+ "batch_sizes": [],
19
+ "device": "cuda:0",
20
+ "no_cache": true,
21
+ "limit": null,
22
+ "bootstrap_iters": 100000,
23
+ "description_dict": {}
24
+ }
25
+ }
winogrande.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "results": {
3
+ "winogrande": {
4
+ "acc": 0.744277821625888,
5
+ "acc_stderr": 0.012261253845440474
6
+ }
7
+ },
8
+ "versions": {
9
+ "winogrande": 0
10
+ },
11
+ "config": {
12
+ "model": "hf",
13
+ "model_args": "pretrained=/cache/shubhra/models/llama2_denseft_playtpus_dolphin_LR1e-5_E2_noGC_LRScosine/combined/,trust_remote_code=True,dtype=bfloat16",
14
+ "num_fewshot": 5,
15
+ "batch_size": "128",
16
+ "batch_sizes": [],
17
+ "device": "cuda:0",
18
+ "no_cache": true,
19
+ "limit": null,
20
+ "bootstrap_iters": 100000,
21
+ "description_dict": {}
22
+ }
23
+ }