MaziyarPanahi's picture
Adding Evaluation Results (#2)
7b965c8 verified
---
license: apache-2.0
library_name: transformers
tags:
- merge
pipeline_tag: text-generation
model-index:
- name: TheTop-5x7B-Instruct-D-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: 71.76
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-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: 88.21
name: normalized accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-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: 64.86
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-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: 66.32
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-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: 84.37
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-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: 71.72
name: accuracy
source:
url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=MaziyarPanahi/TheTop-5x7B-Instruct-D-v0.1
name: Open LLM Leaderboard
---
Merge of top 7B models with DARE 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": 0.6547370286177235,
"acc_stderr": 0.03204709242170183,
"acc_norm": 0.6537337854798912,
"acc_norm_stderr": 0.03272317883588649,
"mc1": 0.5189718482252142,
"mc1_stderr": 0.01749089640576236,
"mc2": 0.6631825155680797,
"mc2_stderr": 0.01527641053841743
},
"harness|arc:challenge|25": {
"acc": 0.6953924914675768,
"acc_stderr": 0.013449522109932485,
"acc_norm": 0.7175767918088737,
"acc_norm_stderr": 0.013155456884097225
},
"harness|hellaswag|10": {
"acc": 0.7120095598486357,
"acc_stderr": 0.004519011688417168,
"acc_norm": 0.8820952001593309,
"acc_norm_stderr": 0.003218362717491129
},
"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": 0.6296296296296297,
"acc_stderr": 0.041716541613545426,
"acc_norm": 0.6296296296296297,
"acc_norm_stderr": 0.041716541613545426
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.7105263157894737,
"acc_stderr": 0.03690677986137283,
"acc_norm": 0.7105263157894737,
"acc_norm_stderr": 0.03690677986137283
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.64,
"acc_stderr": 0.04824181513244218,
"acc_norm": 0.64,
"acc_norm_stderr": 0.04824181513244218
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.7056603773584905,
"acc_stderr": 0.02804918631569525,
"acc_norm": 0.7056603773584905,
"acc_norm_stderr": 0.02804918631569525
},
"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": 0.48,
"acc_stderr": 0.050211673156867795,
"acc_norm": 0.48,
"acc_norm_stderr": 0.050211673156867795
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620333,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620333
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.31,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.31,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.6705202312138728,
"acc_stderr": 0.03583901754736411,
"acc_norm": 0.6705202312138728,
"acc_norm_stderr": 0.03583901754736411
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.4215686274509804,
"acc_stderr": 0.04913595201274498,
"acc_norm": 0.4215686274509804,
"acc_norm_stderr": 0.04913595201274498
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.78,
"acc_stderr": 0.04163331998932263,
"acc_norm": 0.78,
"acc_norm_stderr": 0.04163331998932263
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5787234042553191,
"acc_stderr": 0.03227834510146268,
"acc_norm": 0.5787234042553191,
"acc_norm_stderr": 0.03227834510146268
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5,
"acc_stderr": 0.047036043419179864,
"acc_norm": 0.5,
"acc_norm_stderr": 0.047036043419179864
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5586206896551724,
"acc_stderr": 0.04137931034482758,
"acc_norm": 0.5586206896551724,
"acc_norm_stderr": 0.04137931034482758
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.42857142857142855,
"acc_stderr": 0.02548718714785938,
"acc_norm": 0.42857142857142855,
"acc_norm_stderr": 0.02548718714785938
},
"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": 0.33,
"acc_stderr": 0.04725815626252604,
"acc_norm": 0.33,
"acc_norm_stderr": 0.04725815626252604
},
"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": 0.4876847290640394,
"acc_stderr": 0.035169204442208966,
"acc_norm": 0.4876847290640394,
"acc_norm_stderr": 0.035169204442208966
},
"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": 0.7878787878787878,
"acc_stderr": 0.03192271569548301,
"acc_norm": 0.7878787878787878,
"acc_norm_stderr": 0.03192271569548301
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.797979797979798,
"acc_stderr": 0.02860620428922987,
"acc_norm": 0.797979797979798,
"acc_norm_stderr": 0.02860620428922987
},
"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": 0.6666666666666666,
"acc_stderr": 0.023901157979402538,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.023901157979402538
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.35185185185185186,
"acc_stderr": 0.029116617606083008,
"acc_norm": 0.35185185185185186,
"acc_norm_stderr": 0.029116617606083008
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6722689075630253,
"acc_stderr": 0.03048991141767323,
"acc_norm": 0.6722689075630253,
"acc_norm_stderr": 0.03048991141767323
},
"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": 0.8440366972477065,
"acc_stderr": 0.015555802713590167,
"acc_norm": 0.8440366972477065,
"acc_norm_stderr": 0.015555802713590167
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5092592592592593,
"acc_stderr": 0.034093869469927006,
"acc_norm": 0.5092592592592593,
"acc_norm_stderr": 0.034093869469927006
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8333333333333334,
"acc_stderr": 0.026156867523931045,
"acc_norm": 0.8333333333333334,
"acc_norm_stderr": 0.026156867523931045
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.7848101265822784,
"acc_stderr": 0.02675082699467618,
"acc_norm": 0.7848101265822784,
"acc_norm_stderr": 0.02675082699467618
},
"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": 0.03641297081313729,
"acc_norm": 0.7786259541984732,
"acc_norm_stderr": 0.03641297081313729
},
"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": 0.7730061349693251,
"acc_stderr": 0.03291099578615769,
"acc_norm": 0.7730061349693251,
"acc_norm_stderr": 0.03291099578615769
},
"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": 0.7766990291262136,
"acc_stderr": 0.04123553189891431,
"acc_norm": 0.7766990291262136,
"acc_norm_stderr": 0.04123553189891431
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8760683760683761,
"acc_stderr": 0.021586494001281376,
"acc_norm": 0.8760683760683761,
"acc_norm_stderr": 0.021586494001281376
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.72,
"acc_stderr": 0.045126085985421276,
"acc_norm": 0.72,
"acc_norm_stderr": 0.045126085985421276
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8275862068965517,
"acc_stderr": 0.013507943909371798,
"acc_norm": 0.8275862068965517,
"acc_norm_stderr": 0.013507943909371798
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.7427745664739884,
"acc_stderr": 0.02353292543104429,
"acc_norm": 0.7427745664739884,
"acc_norm_stderr": 0.02353292543104429
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.4312849162011173,
"acc_stderr": 0.016563829399047707,
"acc_norm": 0.4312849162011173,
"acc_norm_stderr": 0.016563829399047707
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7320261437908496,
"acc_stderr": 0.025360603796242557,
"acc_norm": 0.7320261437908496,
"acc_norm_stderr": 0.025360603796242557
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7170418006430869,
"acc_stderr": 0.02558306248998481,
"acc_norm": 0.7170418006430869,
"acc_norm_stderr": 0.02558306248998481
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7438271604938271,
"acc_stderr": 0.024288533637726095,
"acc_norm": 0.7438271604938271,
"acc_norm_stderr": 0.024288533637726095
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.46808510638297873,
"acc_stderr": 0.029766675075873866,
"acc_norm": 0.46808510638297873,
"acc_norm_stderr": 0.029766675075873866
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.4726205997392438,
"acc_stderr": 0.012751075788015055,
"acc_norm": 0.4726205997392438,
"acc_norm_stderr": 0.012751075788015055
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6801470588235294,
"acc_stderr": 0.02833295951403121,
"acc_norm": 0.6801470588235294,
"acc_norm_stderr": 0.02833295951403121
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6748366013071896,
"acc_stderr": 0.018950886770806315,
"acc_norm": 0.6748366013071896,
"acc_norm_stderr": 0.018950886770806315
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6909090909090909,
"acc_stderr": 0.044262946482000985,
"acc_norm": 0.6909090909090909,
"acc_norm_stderr": 0.044262946482000985
},
"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": 0.835820895522388,
"acc_stderr": 0.026193923544454115,
"acc_norm": 0.835820895522388,
"acc_norm_stderr": 0.026193923544454115
},
"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": 0.5602409638554217,
"acc_stderr": 0.03864139923699122,
"acc_norm": 0.5602409638554217,
"acc_norm_stderr": 0.03864139923699122
},
"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": 0.5189718482252142,
"mc1_stderr": 0.01749089640576236,
"mc2": 0.6631825155680797,
"mc2_stderr": 0.01527641053841743
},
"harness|winogrande|5": {
"acc": 0.8437253354380426,
"acc_stderr": 0.01020535179187352
},
"harness|gsm8k|5": {
"acc": 0.7172100075815011,
"acc_stderr": 0.012405020417873619
}
}
```
# [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-D-v0.1)
| Metric |Value|
|---------------------------------|----:|
|Avg. |74.54|
|AI2 Reasoning Challenge (25-Shot)|71.76|
|HellaSwag (10-Shot) |88.21|
|MMLU (5-Shot) |64.86|
|TruthfulQA (0-shot) |66.32|
|Winogrande (5-shot) |84.37|
|GSM8k (5-shot) |71.72|