metadata
license: apache-2.0
library_name: transformers
tags:
- merge
pipeline_tag: text-generation
model-index:
- name: TheTop-5x7B-Instruct-P-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: 38.57
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-P-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: 51.54
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-P-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: 63.36
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-P-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: 50.07
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-P-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: 72.61
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-P-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: 0
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-P-v0.1
name: Open LLM Leaderboard
Merge of top 7B models with PASS 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
{
"all": {
"acc": 0.6152059168567449,
"acc_stderr": 0.031951119145286845,
"acc_norm": 0.6274010157580394,
"acc_norm_stderr": 0.032831804892806175,
"mc1": 0.25091799265605874,
"mc1_stderr": 0.015176985027707694,
"mc2": 0.5006656333594469,
"mc2_stderr": 0.01636490303268174
},
"harness|arc:challenge|25": {
"acc": 0.3447098976109215,
"acc_stderr": 0.013888816286782112,
"acc_norm": 0.3856655290102389,
"acc_norm_stderr": 0.01422425097325717
},
"harness|hellaswag|10": {
"acc": 0.34116709818761204,
"acc_stderr": 0.004731324409133264,
"acc_norm": 0.515435172276439,
"acc_norm_stderr": 0.004987403268345035
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.27,
"acc_stderr": 0.04461960433384741,
"acc_norm": 0.27,
"acc_norm_stderr": 0.04461960433384741
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.5703703703703704,
"acc_stderr": 0.042763494943765995,
"acc_norm": 0.5703703703703704,
"acc_norm_stderr": 0.042763494943765995
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.6842105263157895,
"acc_stderr": 0.0378272898086547,
"acc_norm": 0.6842105263157895,
"acc_norm_stderr": 0.0378272898086547
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.62,
"acc_stderr": 0.048783173121456316,
"acc_norm": 0.62,
"acc_norm_stderr": 0.048783173121456316
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7169811320754716,
"acc_stderr": 0.027724236492700918,
"acc_norm": 0.7169811320754716,
"acc_norm_stderr": 0.027724236492700918
},
"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": 0.45,
"acc_stderr": 0.05,
"acc_norm": 0.45,
"acc_norm_stderr": 0.05
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.46,
"acc_stderr": 0.05009082659620333,
"acc_norm": 0.46,
"acc_norm_stderr": 0.05009082659620333
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.32,
"acc_stderr": 0.04688261722621504,
"acc_norm": 0.32,
"acc_norm_stderr": 0.04688261722621504
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6358381502890174,
"acc_stderr": 0.03669072477416907,
"acc_norm": 0.6358381502890174,
"acc_norm_stderr": 0.03669072477416907
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.4019607843137255,
"acc_stderr": 0.048786087144669955,
"acc_norm": 0.4019607843137255,
"acc_norm_stderr": 0.048786087144669955
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.76,
"acc_stderr": 0.04292346959909283,
"acc_norm": 0.76,
"acc_norm_stderr": 0.04292346959909283
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5446808510638298,
"acc_stderr": 0.03255525359340355,
"acc_norm": 0.5446808510638298,
"acc_norm_stderr": 0.03255525359340355
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.4824561403508772,
"acc_stderr": 0.04700708033551038,
"acc_norm": 0.4824561403508772,
"acc_norm_stderr": 0.04700708033551038
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5172413793103449,
"acc_stderr": 0.04164188720169375,
"acc_norm": 0.5172413793103449,
"acc_norm_stderr": 0.04164188720169375
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42857142857142855,
"acc_stderr": 0.025487187147859372,
"acc_norm": 0.42857142857142855,
"acc_norm_stderr": 0.025487187147859372
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.3968253968253968,
"acc_stderr": 0.043758884927270605,
"acc_norm": 0.3968253968253968,
"acc_norm_stderr": 0.043758884927270605
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.34,
"acc_stderr": 0.04760952285695236,
"acc_norm": 0.34,
"acc_norm_stderr": 0.04760952285695236
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7741935483870968,
"acc_stderr": 0.023785577884181015,
"acc_norm": 0.7741935483870968,
"acc_norm_stderr": 0.023785577884181015
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5123152709359606,
"acc_stderr": 0.035169204442208966,
"acc_norm": 0.5123152709359606,
"acc_norm_stderr": 0.035169204442208966
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.66,
"acc_stderr": 0.04760952285695237,
"acc_norm": 0.66,
"acc_norm_stderr": 0.04760952285695237
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7636363636363637,
"acc_stderr": 0.03317505930009181,
"acc_norm": 0.7636363636363637,
"acc_norm_stderr": 0.03317505930009181
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.7373737373737373,
"acc_stderr": 0.03135305009533085,
"acc_norm": 0.7373737373737373,
"acc_norm_stderr": 0.03135305009533085
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.8808290155440415,
"acc_stderr": 0.023381935348121437,
"acc_norm": 0.8808290155440415,
"acc_norm_stderr": 0.023381935348121437
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.617948717948718,
"acc_stderr": 0.024635549163908237,
"acc_norm": 0.617948717948718,
"acc_norm_stderr": 0.024635549163908237
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.2777777777777778,
"acc_stderr": 0.027309140588230203,
"acc_norm": 0.2777777777777778,
"acc_norm_stderr": 0.027309140588230203
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6512605042016807,
"acc_stderr": 0.030956636328566545,
"acc_norm": 0.6512605042016807,
"acc_norm_stderr": 0.030956636328566545
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.32450331125827814,
"acc_stderr": 0.038227469376587525,
"acc_norm": 0.32450331125827814,
"acc_norm_stderr": 0.038227469376587525
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8440366972477065,
"acc_stderr": 0.015555802713590158,
"acc_norm": 0.8440366972477065,
"acc_norm_stderr": 0.015555802713590158
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.4722222222222222,
"acc_stderr": 0.0340470532865388,
"acc_norm": 0.4722222222222222,
"acc_norm_stderr": 0.0340470532865388
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8431372549019608,
"acc_stderr": 0.025524722324553346,
"acc_norm": 0.8431372549019608,
"acc_norm_stderr": 0.025524722324553346
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.810126582278481,
"acc_stderr": 0.025530100460233497,
"acc_norm": 0.810126582278481,
"acc_norm_stderr": 0.025530100460233497
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.7174887892376681,
"acc_stderr": 0.03021683101150877,
"acc_norm": 0.7174887892376681,
"acc_norm_stderr": 0.03021683101150877
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7786259541984732,
"acc_stderr": 0.0364129708131373,
"acc_norm": 0.7786259541984732,
"acc_norm_stderr": 0.0364129708131373
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7768595041322314,
"acc_stderr": 0.03800754475228733,
"acc_norm": 0.7768595041322314,
"acc_norm_stderr": 0.03800754475228733
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.8148148148148148,
"acc_stderr": 0.03755265865037181,
"acc_norm": 0.8148148148148148,
"acc_norm_stderr": 0.03755265865037181
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7914110429447853,
"acc_stderr": 0.031921934489347235,
"acc_norm": 0.7914110429447853,
"acc_norm_stderr": 0.031921934489347235
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.5446428571428571,
"acc_stderr": 0.04726835553719097,
"acc_norm": 0.5446428571428571,
"acc_norm_stderr": 0.04726835553719097
},
"harness|hendrycksTest-management|5": {
"acc": 0.8349514563106796,
"acc_stderr": 0.036756688322331886,
"acc_norm": 0.8349514563106796,
"acc_norm_stderr": 0.036756688322331886
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8290598290598291,
"acc_stderr": 0.024662496845209804,
"acc_norm": 0.8290598290598291,
"acc_norm_stderr": 0.024662496845209804
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.69,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.69,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8250319284802043,
"acc_stderr": 0.013586619219903324,
"acc_norm": 0.8250319284802043,
"acc_norm_stderr": 0.013586619219903324
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7283236994219653,
"acc_stderr": 0.023948512905468348,
"acc_norm": 0.7283236994219653,
"acc_norm_stderr": 0.023948512905468348
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.36312849162011174,
"acc_stderr": 0.016083749986853704,
"acc_norm": 0.36312849162011174,
"acc_norm_stderr": 0.016083749986853704
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7450980392156863,
"acc_stderr": 0.02495418432487991,
"acc_norm": 0.7450980392156863,
"acc_norm_stderr": 0.02495418432487991
},
"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": 0.7530864197530864,
"acc_stderr": 0.023993501709042114,
"acc_norm": 0.7530864197530864,
"acc_norm_stderr": 0.023993501709042114
},
"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": 0.4367666232073012,
"acc_stderr": 0.01266770191960366,
"acc_norm": 0.4367666232073012,
"acc_norm_stderr": 0.01266770191960366
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6176470588235294,
"acc_stderr": 0.029520095697687765,
"acc_norm": 0.6176470588235294,
"acc_norm_stderr": 0.029520095697687765
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6699346405228758,
"acc_stderr": 0.019023726160724553,
"acc_norm": 0.6699346405228758,
"acc_norm_stderr": 0.019023726160724553
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6545454545454545,
"acc_stderr": 0.04554619617541054,
"acc_norm": 0.6545454545454545,
"acc_norm_stderr": 0.04554619617541054
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.726530612244898,
"acc_stderr": 0.028535560337128445,
"acc_norm": 0.726530612244898,
"acc_norm_stderr": 0.028535560337128445
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.845771144278607,
"acc_stderr": 0.025538433368578334,
"acc_norm": 0.845771144278607,
"acc_norm_stderr": 0.025538433368578334
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.85,
"acc_stderr": 0.03588702812826371,
"acc_norm": 0.85,
"acc_norm_stderr": 0.03588702812826371
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5542168674698795,
"acc_stderr": 0.03869543323472101,
"acc_norm": 0.5542168674698795,
"acc_norm_stderr": 0.03869543323472101
},
"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": 0.25091799265605874,
"mc1_stderr": 0.015176985027707694,
"mc2": 0.5006656333594469,
"mc2_stderr": 0.01636490303268174
},
"harness|winogrande|5": {
"acc": 0.7261247040252565,
"acc_stderr": 0.012533292732620296
},
"harness|gsm8k|5": {
"acc": 0.0,
"acc_stderr": 0.0
}
}
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 46.02 |
AI2 Reasoning Challenge (25-Shot) | 38.57 |
HellaSwag (10-Shot) | 51.54 |
MMLU (5-Shot) | 63.36 |
TruthfulQA (0-shot) | 50.07 |
Winogrande (5-shot) | 72.61 |
GSM8k (5-shot) | 0.00 |