metadata
license: apache-2.0
library_name: transformers
tags:
- merge
pipeline_tag: text-generation
model-index:
- name: TheTop-5x7B-Instruct-S5-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: 72.53
name: normalized accuracy
source:
url: >-
https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S5-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: 88.71
name: normalized accuracy
source:
url: >-
https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S5-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: 65.01
name: accuracy
source:
url: >-
https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S5-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: 67.58
source:
url: >-
https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S5-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: 86.19
name: accuracy
source:
url: >-
https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S5-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: 70.81
name: accuracy
source:
url: >-
https://huggingface.co./spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-S5-v0.1
name: Open LLM Leaderboard
Merge of top 7B models and the SLERP of other 7B models
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": 0.6564118716978186,
"acc_stderr": 0.03200912848183244,
"acc_norm": 0.6553902167958241,
"acc_norm_stderr": 0.03268788255929441,
"mc1": 0.5312117503059975,
"mc1_stderr": 0.01746936487457752,
"mc2": 0.6758096547963126,
"mc2_stderr": 0.015381620483561457
},
"harness|arc:challenge|25": {
"acc": 0.6919795221843004,
"acc_stderr": 0.013491429517292038,
"acc_norm": 0.7252559726962458,
"acc_norm_stderr": 0.013044617212771227
},
"harness|hellaswag|10": {
"acc": 0.7234614618601872,
"acc_stderr": 0.004463721071319078,
"acc_norm": 0.8870742879904402,
"acc_norm_stderr": 0.0031585512705264054
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.33,
"acc_stderr": 0.047258156262526045,
"acc_norm": 0.33,
"acc_norm_stderr": 0.047258156262526045
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6518518518518519,
"acc_stderr": 0.041153246103369526,
"acc_norm": 0.6518518518518519,
"acc_norm_stderr": 0.041153246103369526
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.7039473684210527,
"acc_stderr": 0.03715062154998904,
"acc_norm": 0.7039473684210527,
"acc_norm_stderr": 0.03715062154998904
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.65,
"acc_stderr": 0.0479372485441102,
"acc_norm": 0.65,
"acc_norm_stderr": 0.0479372485441102
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.6943396226415094,
"acc_stderr": 0.028353298073322663,
"acc_norm": 0.6943396226415094,
"acc_norm_stderr": 0.028353298073322663
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7708333333333334,
"acc_stderr": 0.03514697467862388,
"acc_norm": 0.7708333333333334,
"acc_norm_stderr": 0.03514697467862388
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.49,
"acc_stderr": 0.05024183937956912,
"acc_norm": 0.49,
"acc_norm_stderr": 0.05024183937956912
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.52,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.52,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.28,
"acc_stderr": 0.04512608598542126,
"acc_norm": 0.28,
"acc_norm_stderr": 0.04512608598542126
},
"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": 0.38235294117647056,
"acc_stderr": 0.04835503696107224,
"acc_norm": 0.38235294117647056,
"acc_norm_stderr": 0.04835503696107224
},
"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": 0.5957446808510638,
"acc_stderr": 0.03208115750788684,
"acc_norm": 0.5957446808510638,
"acc_norm_stderr": 0.03208115750788684
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5087719298245614,
"acc_stderr": 0.04702880432049615,
"acc_norm": 0.5087719298245614,
"acc_norm_stderr": 0.04702880432049615
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5724137931034483,
"acc_stderr": 0.04122737111370332,
"acc_norm": 0.5724137931034483,
"acc_norm_stderr": 0.04122737111370332
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.4312169312169312,
"acc_stderr": 0.025506481698138208,
"acc_norm": 0.4312169312169312,
"acc_norm_stderr": 0.025506481698138208
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.5,
"acc_stderr": 0.04472135954999579,
"acc_norm": 0.5,
"acc_norm_stderr": 0.04472135954999579
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.37,
"acc_stderr": 0.04852365870939099,
"acc_norm": 0.37,
"acc_norm_stderr": 0.04852365870939099
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7903225806451613,
"acc_stderr": 0.023157879349083525,
"acc_norm": 0.7903225806451613,
"acc_norm_stderr": 0.023157879349083525
},
"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": 0.66,
"acc_stderr": 0.04760952285695237,
"acc_norm": 0.66,
"acc_norm_stderr": 0.04760952285695237
},
"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": 0.7878787878787878,
"acc_stderr": 0.029126522834586818,
"acc_norm": 0.7878787878787878,
"acc_norm_stderr": 0.029126522834586818
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.9067357512953368,
"acc_stderr": 0.020986854593289733,
"acc_norm": 0.9067357512953368,
"acc_norm_stderr": 0.020986854593289733
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6641025641025641,
"acc_stderr": 0.023946724741563976,
"acc_norm": 0.6641025641025641,
"acc_norm_stderr": 0.023946724741563976
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.3592592592592593,
"acc_stderr": 0.02925290592725197,
"acc_norm": 0.3592592592592593,
"acc_norm_stderr": 0.02925290592725197
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6764705882352942,
"acc_stderr": 0.03038835355188679,
"acc_norm": 0.6764705882352942,
"acc_norm_stderr": 0.03038835355188679
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.36423841059602646,
"acc_stderr": 0.03929111781242742,
"acc_norm": 0.36423841059602646,
"acc_norm_stderr": 0.03929111781242742
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.8385321100917431,
"acc_stderr": 0.015776239256163224,
"acc_norm": 0.8385321100917431,
"acc_norm_stderr": 0.015776239256163224
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5138888888888888,
"acc_stderr": 0.03408655867977749,
"acc_norm": 0.5138888888888888,
"acc_norm_stderr": 0.03408655867977749
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8529411764705882,
"acc_stderr": 0.024857478080250447,
"acc_norm": 0.8529411764705882,
"acc_norm_stderr": 0.024857478080250447
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.8143459915611815,
"acc_stderr": 0.025310495376944856,
"acc_norm": 0.8143459915611815,
"acc_norm_stderr": 0.025310495376944856
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6816143497757847,
"acc_stderr": 0.03126580522513713,
"acc_norm": 0.6816143497757847,
"acc_norm_stderr": 0.03126580522513713
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.816793893129771,
"acc_stderr": 0.03392770926494733,
"acc_norm": 0.816793893129771,
"acc_norm_stderr": 0.03392770926494733
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7933884297520661,
"acc_stderr": 0.03695980128098824,
"acc_norm": 0.7933884297520661,
"acc_norm_stderr": 0.03695980128098824
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.7870370370370371,
"acc_stderr": 0.0395783547198098,
"acc_norm": 0.7870370370370371,
"acc_norm_stderr": 0.0395783547198098
},
"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": 0.48214285714285715,
"acc_stderr": 0.047427623612430116,
"acc_norm": 0.48214285714285715,
"acc_norm_stderr": 0.047427623612430116
},
"harness|hendrycksTest-management|5": {
"acc": 0.7864077669902912,
"acc_stderr": 0.040580420156460344,
"acc_norm": 0.7864077669902912,
"acc_norm_stderr": 0.040580420156460344
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8760683760683761,
"acc_stderr": 0.021586494001281365,
"acc_norm": 0.8760683760683761,
"acc_norm_stderr": 0.021586494001281365
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.72,
"acc_stderr": 0.04512608598542128,
"acc_norm": 0.72,
"acc_norm_stderr": 0.04512608598542128
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8250319284802043,
"acc_stderr": 0.013586619219903341,
"acc_norm": 0.8250319284802043,
"acc_norm_stderr": 0.013586619219903341
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7456647398843931,
"acc_stderr": 0.02344582627654554,
"acc_norm": 0.7456647398843931,
"acc_norm_stderr": 0.02344582627654554
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.45251396648044695,
"acc_stderr": 0.016646914804438778,
"acc_norm": 0.45251396648044695,
"acc_norm_stderr": 0.016646914804438778
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7254901960784313,
"acc_stderr": 0.02555316999182652,
"acc_norm": 0.7254901960784313,
"acc_norm_stderr": 0.02555316999182652
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.707395498392283,
"acc_stderr": 0.02583989833487798,
"acc_norm": 0.707395498392283,
"acc_norm_stderr": 0.02583989833487798
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7561728395061729,
"acc_stderr": 0.02389187954195961,
"acc_norm": 0.7561728395061729,
"acc_norm_stderr": 0.02389187954195961
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.4645390070921986,
"acc_stderr": 0.029752389657427047,
"acc_norm": 0.4645390070921986,
"acc_norm_stderr": 0.029752389657427047
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.47327249022164275,
"acc_stderr": 0.01275197796767601,
"acc_norm": 0.47327249022164275,
"acc_norm_stderr": 0.01275197796767601
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6838235294117647,
"acc_stderr": 0.02824568739146292,
"acc_norm": 0.6838235294117647,
"acc_norm_stderr": 0.02824568739146292
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6715686274509803,
"acc_stderr": 0.018999707383162673,
"acc_norm": 0.6715686274509803,
"acc_norm_stderr": 0.018999707383162673
},
"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": 0.7306122448979592,
"acc_stderr": 0.02840125202902294,
"acc_norm": 0.7306122448979592,
"acc_norm_stderr": 0.02840125202902294
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.8208955223880597,
"acc_stderr": 0.027113286753111837,
"acc_norm": 0.8208955223880597,
"acc_norm_stderr": 0.027113286753111837
},
"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": 0.038695433234721015,
"acc_norm": 0.5542168674698795,
"acc_norm_stderr": 0.038695433234721015
},
"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": 0.5312117503059975,
"mc1_stderr": 0.01746936487457752,
"mc2": 0.6758096547963126,
"mc2_stderr": 0.015381620483561457
},
"harness|winogrande|5": {
"acc": 0.861878453038674,
"acc_stderr": 0.00969698839367458
},
"harness|gsm8k|5": {
"acc": 0.7081122062168309,
"acc_stderr": 0.012522795894420867
}
}
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 75.14 |
| AI2 Reasoning Challenge (25-Shot) | 72.53 |
| HellaSwag (10-Shot) | 88.71 |
| MMLU (5-Shot) | 65.01 |
| TruthfulQA (0-shot) | 67.58 |
| Winogrande (5-shot) | 86.19 |
| GSM8k (5-shot) | 70.81 |