515 lines
17 KiB
Markdown
515 lines
17 KiB
Markdown
---
|
|
license: apache-2.0
|
|
library_name: transformers
|
|
tags:
|
|
- merge
|
|
pipeline_tag: text-generation
|
|
model-index:
|
|
- name: TheTop-5x7B-Instruct-S2-v0.1
|
|
results:
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: AI2 Reasoning Challenge (25-Shot)
|
|
type: ai2_arc
|
|
config: ARC-Challenge
|
|
split: test
|
|
args:
|
|
num_few_shot: 25
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 69.45
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: HellaSwag (10-Shot)
|
|
type: hellaswag
|
|
split: validation
|
|
args:
|
|
num_few_shot: 10
|
|
metrics:
|
|
- type: acc_norm
|
|
value: 87.15
|
|
name: normalized accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: MMLU (5-Shot)
|
|
type: cais/mmlu
|
|
config: all
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 64.98
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: TruthfulQA (0-shot)
|
|
type: truthful_qa
|
|
config: multiple_choice
|
|
split: validation
|
|
args:
|
|
num_few_shot: 0
|
|
metrics:
|
|
- type: mc2
|
|
value: 62.18
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: Winogrande (5-shot)
|
|
type: winogrande
|
|
config: winogrande_xl
|
|
split: validation
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 79.64
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
name: Open LLM Leaderboard
|
|
- task:
|
|
type: text-generation
|
|
name: Text Generation
|
|
dataset:
|
|
name: GSM8k (5-shot)
|
|
type: gsm8k
|
|
config: main
|
|
split: test
|
|
args:
|
|
num_few_shot: 5
|
|
metrics:
|
|
- type: acc
|
|
value: 72.02
|
|
name: accuracy
|
|
source:
|
|
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
name: Open LLM Leaderboard
|
|
---
|
|
|
|
# MaziyarPanahi/TheTop-5x7B-Instruct-S2-v0.1
|
|
|
|
Merge of top 7B models with SLERP method.
|
|
|
|
> mergekit is a toolkit for merging pre-trained language models. mergekit uses an out-of-core approach to perform unreasonably elaborate merges in resource-constrained situations. Merges can be run entirely on CPU or accelerated with as little as 8 GB of VRAM. Many merging algorithms are supported, with more coming as they catch my attention.
|
|
>
|
|
> ## Eval
|
|
> ```python
|
|
> {
|
|
"all": {
|
|
"acc": 0.6545868511485138,
|
|
"acc_stderr": 0.031980293841566164,
|
|
"acc_norm": 0.6542757501692061,
|
|
"acc_norm_stderr": 0.03263807517879597,
|
|
"mc1": 0.45165238678090575,
|
|
"mc1_stderr": 0.017421480300277643,
|
|
"mc2": 0.6217500644350165,
|
|
"mc2_stderr": 0.015583825644663436
|
|
},
|
|
"harness|arc:challenge|25": {
|
|
"acc": 0.6723549488054608,
|
|
"acc_stderr": 0.01371584794071934,
|
|
"acc_norm": 0.6945392491467577,
|
|
"acc_norm_stderr": 0.01346008047800251
|
|
},
|
|
"harness|hellaswag|10": {
|
|
"acc": 0.7046405098585939,
|
|
"acc_stderr": 0.0045527183605131,
|
|
"acc_norm": 0.871539533957379,
|
|
"acc_norm_stderr": 0.0033391798350182853
|
|
},
|
|
"harness|hendrycksTest-abstract_algebra|5": {
|
|
"acc": 0.37,
|
|
"acc_stderr": 0.048523658709391,
|
|
"acc_norm": 0.37,
|
|
"acc_norm_stderr": 0.048523658709391
|
|
},
|
|
"harness|hendrycksTest-anatomy|5": {
|
|
"acc": 0.6148148148148148,
|
|
"acc_stderr": 0.04203921040156279,
|
|
"acc_norm": 0.6148148148148148,
|
|
"acc_norm_stderr": 0.04203921040156279
|
|
},
|
|
"harness|hendrycksTest-astronomy|5": {
|
|
"acc": 0.6907894736842105,
|
|
"acc_stderr": 0.037610708698674805,
|
|
"acc_norm": 0.6907894736842105,
|
|
"acc_norm_stderr": 0.037610708698674805
|
|
},
|
|
"harness|hendrycksTest-business_ethics|5": {
|
|
"acc": 0.63,
|
|
"acc_stderr": 0.04852365870939099,
|
|
"acc_norm": 0.63,
|
|
"acc_norm_stderr": 0.04852365870939099
|
|
},
|
|
"harness|hendrycksTest-clinical_knowledge|5": {
|
|
"acc": 0.7132075471698113,
|
|
"acc_stderr": 0.02783491252754407,
|
|
"acc_norm": 0.7132075471698113,
|
|
"acc_norm_stderr": 0.02783491252754407
|
|
},
|
|
"harness|hendrycksTest-college_biology|5": {
|
|
"acc": 0.7638888888888888,
|
|
"acc_stderr": 0.03551446610810826,
|
|
"acc_norm": 0.7638888888888888,
|
|
"acc_norm_stderr": 0.03551446610810826
|
|
},
|
|
"harness|hendrycksTest-college_chemistry|5": {
|
|
"acc": 0.47,
|
|
"acc_stderr": 0.050161355804659205,
|
|
"acc_norm": 0.47,
|
|
"acc_norm_stderr": 0.050161355804659205
|
|
},
|
|
"harness|hendrycksTest-college_computer_science|5": {
|
|
"acc": 0.57,
|
|
"acc_stderr": 0.04975698519562428,
|
|
"acc_norm": 0.57,
|
|
"acc_norm_stderr": 0.04975698519562428
|
|
},
|
|
"harness|hendrycksTest-college_mathematics|5": {
|
|
"acc": 0.27,
|
|
"acc_stderr": 0.0446196043338474,
|
|
"acc_norm": 0.27,
|
|
"acc_norm_stderr": 0.0446196043338474
|
|
},
|
|
"harness|hendrycksTest-college_medicine|5": {
|
|
"acc": 0.6820809248554913,
|
|
"acc_stderr": 0.0355068398916558,
|
|
"acc_norm": 0.6820809248554913,
|
|
"acc_norm_stderr": 0.0355068398916558
|
|
},
|
|
"harness|hendrycksTest-college_physics|5": {
|
|
"acc": 0.4019607843137255,
|
|
"acc_stderr": 0.04878608714466996,
|
|
"acc_norm": 0.4019607843137255,
|
|
"acc_norm_stderr": 0.04878608714466996
|
|
},
|
|
"harness|hendrycksTest-computer_security|5": {
|
|
"acc": 0.77,
|
|
"acc_stderr": 0.04229525846816506,
|
|
"acc_norm": 0.77,
|
|
"acc_norm_stderr": 0.04229525846816506
|
|
},
|
|
"harness|hendrycksTest-conceptual_physics|5": {
|
|
"acc": 0.5829787234042553,
|
|
"acc_stderr": 0.03223276266711712,
|
|
"acc_norm": 0.5829787234042553,
|
|
"acc_norm_stderr": 0.03223276266711712
|
|
},
|
|
"harness|hendrycksTest-econometrics|5": {
|
|
"acc": 0.5175438596491229,
|
|
"acc_stderr": 0.04700708033551038,
|
|
"acc_norm": 0.5175438596491229,
|
|
"acc_norm_stderr": 0.04700708033551038
|
|
},
|
|
"harness|hendrycksTest-electrical_engineering|5": {
|
|
"acc": 0.5586206896551724,
|
|
"acc_stderr": 0.04137931034482757,
|
|
"acc_norm": 0.5586206896551724,
|
|
"acc_norm_stderr": 0.04137931034482757
|
|
},
|
|
"harness|hendrycksTest-elementary_mathematics|5": {
|
|
"acc": 0.41798941798941797,
|
|
"acc_stderr": 0.025402555503260912,
|
|
"acc_norm": 0.41798941798941797,
|
|
"acc_norm_stderr": 0.025402555503260912
|
|
},
|
|
"harness|hendrycksTest-formal_logic|5": {
|
|
"acc": 0.47619047619047616,
|
|
"acc_stderr": 0.04467062628403273,
|
|
"acc_norm": 0.47619047619047616,
|
|
"acc_norm_stderr": 0.04467062628403273
|
|
},
|
|
"harness|hendrycksTest-global_facts|5": {
|
|
"acc": 0.34,
|
|
"acc_stderr": 0.04760952285695235,
|
|
"acc_norm": 0.34,
|
|
"acc_norm_stderr": 0.04760952285695235
|
|
},
|
|
"harness|hendrycksTest-high_school_biology|5": {
|
|
"acc": 0.7903225806451613,
|
|
"acc_stderr": 0.023157879349083522,
|
|
"acc_norm": 0.7903225806451613,
|
|
"acc_norm_stderr": 0.023157879349083522
|
|
},
|
|
"harness|hendrycksTest-high_school_chemistry|5": {
|
|
"acc": 0.4975369458128079,
|
|
"acc_stderr": 0.03517945038691063,
|
|
"acc_norm": 0.4975369458128079,
|
|
"acc_norm_stderr": 0.03517945038691063
|
|
},
|
|
"harness|hendrycksTest-high_school_computer_science|5": {
|
|
"acc": 0.68,
|
|
"acc_stderr": 0.04688261722621505,
|
|
"acc_norm": 0.68,
|
|
"acc_norm_stderr": 0.04688261722621505
|
|
},
|
|
"harness|hendrycksTest-high_school_european_history|5": {
|
|
"acc": 0.7696969696969697,
|
|
"acc_stderr": 0.0328766675860349,
|
|
"acc_norm": 0.7696969696969697,
|
|
"acc_norm_stderr": 0.0328766675860349
|
|
},
|
|
"harness|hendrycksTest-high_school_geography|5": {
|
|
"acc": 0.7828282828282829,
|
|
"acc_stderr": 0.029376616484945633,
|
|
"acc_norm": 0.7828282828282829,
|
|
"acc_norm_stderr": 0.029376616484945633
|
|
},
|
|
"harness|hendrycksTest-high_school_government_and_politics|5": {
|
|
"acc": 0.9015544041450777,
|
|
"acc_stderr": 0.021500249576033456,
|
|
"acc_norm": 0.9015544041450777,
|
|
"acc_norm_stderr": 0.021500249576033456
|
|
},
|
|
"harness|hendrycksTest-high_school_macroeconomics|5": {
|
|
"acc": 0.6717948717948717,
|
|
"acc_stderr": 0.023807633198657266,
|
|
"acc_norm": 0.6717948717948717,
|
|
"acc_norm_stderr": 0.023807633198657266
|
|
},
|
|
"harness|hendrycksTest-high_school_mathematics|5": {
|
|
"acc": 0.34444444444444444,
|
|
"acc_stderr": 0.02897264888484427,
|
|
"acc_norm": 0.34444444444444444,
|
|
"acc_norm_stderr": 0.02897264888484427
|
|
},
|
|
"harness|hendrycksTest-high_school_microeconomics|5": {
|
|
"acc": 0.6638655462184874,
|
|
"acc_stderr": 0.030684737115135363,
|
|
"acc_norm": 0.6638655462184874,
|
|
"acc_norm_stderr": 0.030684737115135363
|
|
},
|
|
"harness|hendrycksTest-high_school_physics|5": {
|
|
"acc": 0.304635761589404,
|
|
"acc_stderr": 0.03757949922943343,
|
|
"acc_norm": 0.304635761589404,
|
|
"acc_norm_stderr": 0.03757949922943343
|
|
},
|
|
"harness|hendrycksTest-high_school_psychology|5": {
|
|
"acc": 0.8458715596330275,
|
|
"acc_stderr": 0.015480826865374303,
|
|
"acc_norm": 0.8458715596330275,
|
|
"acc_norm_stderr": 0.015480826865374303
|
|
},
|
|
"harness|hendrycksTest-high_school_statistics|5": {
|
|
"acc": 0.5185185185185185,
|
|
"acc_stderr": 0.03407632093854051,
|
|
"acc_norm": 0.5185185185185185,
|
|
"acc_norm_stderr": 0.03407632093854051
|
|
},
|
|
"harness|hendrycksTest-high_school_us_history|5": {
|
|
"acc": 0.8382352941176471,
|
|
"acc_stderr": 0.025845017986926917,
|
|
"acc_norm": 0.8382352941176471,
|
|
"acc_norm_stderr": 0.025845017986926917
|
|
},
|
|
"harness|hendrycksTest-high_school_world_history|5": {
|
|
"acc": 0.810126582278481,
|
|
"acc_stderr": 0.02553010046023349,
|
|
"acc_norm": 0.810126582278481,
|
|
"acc_norm_stderr": 0.02553010046023349
|
|
},
|
|
"harness|hendrycksTest-human_aging|5": {
|
|
"acc": 0.6905829596412556,
|
|
"acc_stderr": 0.03102441174057221,
|
|
"acc_norm": 0.6905829596412556,
|
|
"acc_norm_stderr": 0.03102441174057221
|
|
},
|
|
"harness|hendrycksTest-human_sexuality|5": {
|
|
"acc": 0.7786259541984732,
|
|
"acc_stderr": 0.036412970813137296,
|
|
"acc_norm": 0.7786259541984732,
|
|
"acc_norm_stderr": 0.036412970813137296
|
|
},
|
|
"harness|hendrycksTest-international_law|5": {
|
|
"acc": 0.8099173553719008,
|
|
"acc_stderr": 0.03581796951709282,
|
|
"acc_norm": 0.8099173553719008,
|
|
"acc_norm_stderr": 0.03581796951709282
|
|
},
|
|
"harness|hendrycksTest-jurisprudence|5": {
|
|
"acc": 0.7685185185185185,
|
|
"acc_stderr": 0.04077494709252627,
|
|
"acc_norm": 0.7685185185185185,
|
|
"acc_norm_stderr": 0.04077494709252627
|
|
},
|
|
"harness|hendrycksTest-logical_fallacies|5": {
|
|
"acc": 0.7607361963190185,
|
|
"acc_stderr": 0.0335195387952127,
|
|
"acc_norm": 0.7607361963190185,
|
|
"acc_norm_stderr": 0.0335195387952127
|
|
},
|
|
"harness|hendrycksTest-machine_learning|5": {
|
|
"acc": 0.45535714285714285,
|
|
"acc_stderr": 0.047268355537191,
|
|
"acc_norm": 0.45535714285714285,
|
|
"acc_norm_stderr": 0.047268355537191
|
|
},
|
|
"harness|hendrycksTest-management|5": {
|
|
"acc": 0.8058252427184466,
|
|
"acc_stderr": 0.03916667762822584,
|
|
"acc_norm": 0.8058252427184466,
|
|
"acc_norm_stderr": 0.03916667762822584
|
|
},
|
|
"harness|hendrycksTest-marketing|5": {
|
|
"acc": 0.8675213675213675,
|
|
"acc_stderr": 0.022209309073165612,
|
|
"acc_norm": 0.8675213675213675,
|
|
"acc_norm_stderr": 0.022209309073165612
|
|
},
|
|
"harness|hendrycksTest-medical_genetics|5": {
|
|
"acc": 0.71,
|
|
"acc_stderr": 0.045604802157206845,
|
|
"acc_norm": 0.71,
|
|
"acc_norm_stderr": 0.045604802157206845
|
|
},
|
|
"harness|hendrycksTest-miscellaneous|5": {
|
|
"acc": 0.8352490421455939,
|
|
"acc_stderr": 0.013265346261323788,
|
|
"acc_norm": 0.8352490421455939,
|
|
"acc_norm_stderr": 0.013265346261323788
|
|
},
|
|
"harness|hendrycksTest-moral_disputes|5": {
|
|
"acc": 0.7543352601156069,
|
|
"acc_stderr": 0.023176298203992005,
|
|
"acc_norm": 0.7543352601156069,
|
|
"acc_norm_stderr": 0.023176298203992005
|
|
},
|
|
"harness|hendrycksTest-moral_scenarios|5": {
|
|
"acc": 0.4547486033519553,
|
|
"acc_stderr": 0.016653875777524006,
|
|
"acc_norm": 0.4547486033519553,
|
|
"acc_norm_stderr": 0.016653875777524006
|
|
},
|
|
"harness|hendrycksTest-nutrition|5": {
|
|
"acc": 0.7483660130718954,
|
|
"acc_stderr": 0.0248480182638752,
|
|
"acc_norm": 0.7483660130718954,
|
|
"acc_norm_stderr": 0.0248480182638752
|
|
},
|
|
"harness|hendrycksTest-philosophy|5": {
|
|
"acc": 0.7202572347266881,
|
|
"acc_stderr": 0.02549425935069491,
|
|
"acc_norm": 0.7202572347266881,
|
|
"acc_norm_stderr": 0.02549425935069491
|
|
},
|
|
"harness|hendrycksTest-prehistory|5": {
|
|
"acc": 0.7592592592592593,
|
|
"acc_stderr": 0.02378858355165854,
|
|
"acc_norm": 0.7592592592592593,
|
|
"acc_norm_stderr": 0.02378858355165854
|
|
},
|
|
"harness|hendrycksTest-professional_accounting|5": {
|
|
"acc": 0.4787234042553192,
|
|
"acc_stderr": 0.029800481645628693,
|
|
"acc_norm": 0.4787234042553192,
|
|
"acc_norm_stderr": 0.029800481645628693
|
|
},
|
|
"harness|hendrycksTest-professional_law|5": {
|
|
"acc": 0.4745762711864407,
|
|
"acc_stderr": 0.012753716929101008,
|
|
"acc_norm": 0.4745762711864407,
|
|
"acc_norm_stderr": 0.012753716929101008
|
|
},
|
|
"harness|hendrycksTest-professional_medicine|5": {
|
|
"acc": 0.7095588235294118,
|
|
"acc_stderr": 0.027576468622740536,
|
|
"acc_norm": 0.7095588235294118,
|
|
"acc_norm_stderr": 0.027576468622740536
|
|
},
|
|
"harness|hendrycksTest-professional_psychology|5": {
|
|
"acc": 0.6928104575163399,
|
|
"acc_stderr": 0.01866335967146367,
|
|
"acc_norm": 0.6928104575163399,
|
|
"acc_norm_stderr": 0.01866335967146367
|
|
},
|
|
"harness|hendrycksTest-public_relations|5": {
|
|
"acc": 0.6727272727272727,
|
|
"acc_stderr": 0.0449429086625209,
|
|
"acc_norm": 0.6727272727272727,
|
|
"acc_norm_stderr": 0.0449429086625209
|
|
},
|
|
"harness|hendrycksTest-security_studies|5": {
|
|
"acc": 0.7387755102040816,
|
|
"acc_stderr": 0.02812342933514278,
|
|
"acc_norm": 0.7387755102040816,
|
|
"acc_norm_stderr": 0.02812342933514278
|
|
},
|
|
"harness|hendrycksTest-sociology|5": {
|
|
"acc": 0.845771144278607,
|
|
"acc_stderr": 0.025538433368578337,
|
|
"acc_norm": 0.845771144278607,
|
|
"acc_norm_stderr": 0.025538433368578337
|
|
},
|
|
"harness|hendrycksTest-us_foreign_policy|5": {
|
|
"acc": 0.86,
|
|
"acc_stderr": 0.0348735088019777,
|
|
"acc_norm": 0.86,
|
|
"acc_norm_stderr": 0.0348735088019777
|
|
},
|
|
"harness|hendrycksTest-virology|5": {
|
|
"acc": 0.5481927710843374,
|
|
"acc_stderr": 0.03874371556587953,
|
|
"acc_norm": 0.5481927710843374,
|
|
"acc_norm_stderr": 0.03874371556587953
|
|
},
|
|
"harness|hendrycksTest-world_religions|5": {
|
|
"acc": 0.8362573099415205,
|
|
"acc_stderr": 0.028380919596145866,
|
|
"acc_norm": 0.8362573099415205,
|
|
"acc_norm_stderr": 0.028380919596145866
|
|
},
|
|
"harness|truthfulqa:mc|0": {
|
|
"mc1": 0.45165238678090575,
|
|
"mc1_stderr": 0.017421480300277643,
|
|
"mc2": 0.6217500644350165,
|
|
"mc2_stderr": 0.015583825644663436
|
|
},
|
|
"harness|winogrande|5": {
|
|
"acc": 0.7963693764798737,
|
|
"acc_stderr": 0.011317798781626913
|
|
},
|
|
"harness|gsm8k|5": {
|
|
"acc": 0.7202426080363912,
|
|
"acc_stderr": 0.01236438401673532
|
|
}
|
|
}
|
|
```
|
|
|
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__TheTop-5x7B-Instruct-S2-v0.1)
|
|
|
|
| Metric |Value|
|
|
|---------------------------------|----:|
|
|
|Avg. |72.57|
|
|
|AI2 Reasoning Challenge (25-Shot)|69.45|
|
|
|HellaSwag (10-Shot) |87.15|
|
|
|MMLU (5-Shot) |64.98|
|
|
|TruthfulQA (0-shot) |62.18|
|
|
|Winogrande (5-shot) |79.64|
|
|
|GSM8k (5-shot) |72.02|
|
|
|