Beyonder-4x7B-v2

Home/Models/mlabonne/Beyonder-4x7B-v2

Beyonder-4x7B-v2

mlabonne/Beyonder-4x7B-v2

kind: merge
quant: merge
family: misc
modality: text-generation
root model: mlabonne/Marcoro14-7B-slerp
provider: mlabonne
license: other
language: —
context: 8k
library: —
vRAM (GB): —
size on disk: —
downloads: 67
likes: 128
created: —
last modified: 2024-03-04T15:16:39+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/Beyonder-4x7B-v2
tags: transformerssafetensorsmixtraltext-generationmoemergemergekitMistralopenchat/openchat-3.5-1210beowolx/CodeNinja-1.0-OpenChat-7Bmaywell/PiVoT-0.1-Starling-LM-RPWizardLM/WizardMath-7B-V1.1conversationallicense:othermodel-indextext-generation-inferenceendpoints_compatibleregion:us

Benchmark scores (36)

benchmark	category	score	context	conf	evidence
BoolQ	knowledge	88.35		medium	`\| boolq \| 1 \| acc \| 88.35 \| ± \| 0.56 \|`
PIQA	knowledge	83.08		medium	`\| piqa \| 0 \| acc \| 83.08 \| ± \| 0.87 \|`
AGIEval	reasoning	79.13	_sat_en	medium	`\| agieval_sat_en \| 0 \| acc \| 79.13 \| ± \| 2.84 \|`
WinoGrande	knowledge	78.69		medium	`\| winogrande \| 0 \| acc \| 78.69 \| ± \| 1.15 \|`
BigBench	reasoning	77.35	_snarks	medium	`\| bigbench_snarks \| 0 \| multiple_choice_grade \| 77.35 \| ± \| 3.12 \|`
BigBench	reasoning	73.02	_sports_understanding	medium	`\| bigbench_sports_understanding \| 0 \| multiple_choice_grade \| 73.02 \| ± \| 1.41 \|`
BigBench	reasoning	69.75	_reasoning_about_colored_objects	medium	`\| bigbench_reasoning_about_colored_objects \| 0 \| multiple_choice_grade \| 69.75 \| ± \| 1.03 \|`
HellaSwag	knowledge	68.04		medium	`\| hellaswag \| 0 \| acc \| 68.04 \| ± \| 0.47 \|`
BigBench	reasoning	66.4	_date_understanding	medium	`\| bigbench_date_understanding \| 0 \| multiple_choice_grade \| 66.40 \| ± \| 2.46 \|`
AGIEval	reasoning	64.31	_lsat_rc	medium	`\| agieval_lsat_rc \| 0 \| acc \| 64.31 \| ± \| 2.93 \|`
ARC-Challenge	knowledge	61.86	_challenge	medium	`\| arc_challenge \| 0 \| acc \| 61.86 \| ± \| 1.42 \|`
BigBench	reasoning	58.95	_causal_judgement	medium	`\| bigbench_causal_judgement \| 0 \| multiple_choice_grade \| 58.95 \| ± \| 3.58 \|`
TruthfulQA	safety	55.37		low	`\| [NeuralHermes-2.5-Mistral-7B](https://huggingface.co/mlabonne/NeuralHermes-2.5-Mistral-7B) \| 43.67 \| 73.24 \| 55.37 \| 41.76 \| 53.51 \|`
BigBench	reasoning	55.36	_ruin_names	medium	`\| bigbench_ruin_names \| 0 \| multiple_choice_grade \| 55.36 \| ± \| 2.35 \|`
BigBench	reasoning	52.1	_navigate	medium	`\| bigbench_navigate \| 0 \| multiple_choice_grade \| 52.10 \| ± \| 1.58 \|`
BigBench	reasoning	52.0	_logical_deduction_three_objects	medium	`\| bigbench_logical_deduction_three_objects \| 0 \| multiple_choice_grade \| 52.00 \| ± \| 2.89 \|`
BigBench	reasoning	52.0	_tracking_shuffled_objects_three_objects	medium	`\| bigbench_tracking_shuffled_objects_three_objects \| 0 \| multiple_choice_grade \| 52.00 \| ± \| 2.89 \|`
AGIEval	reasoning	51.57	_lsat_lr	medium	`\| agieval_lsat_lr \| 0 \| acc \| 51.57 \| ± \| 2.22 \|`
BigBench	reasoning	48.84	_disambiguation_qa	medium	`\| bigbench_disambiguation_qa \| 0 \| multiple_choice_grade \| 48.84 \| ± \| 3.12 \|`
BigBench	reasoning	46.8	_temporal_sequences	medium	`\| bigbench_temporal_sequences \| 0 \| multiple_choice_grade \| 46.80 \| ± \| 1.58 \|`
BigBench	reasoning	46.4		low	`\| [Beyonder-4x7B-v2](https://huggingface.co/shadowml/Beyonder-4x7B-v2) \| 45.29 \| 75.95 \| <u>60.86</u> \| 46.4 \| 57.13 \|`
AGIEval	reasoning	45.29		low	`\| [Beyonder-4x7B-v2](https://huggingface.co/shadowml/Beyonder-4x7B-v2) \| 45.29 \| 75.95 \| <u>60.86</u> \| 46.4 \| 57.13 \|`
TruthfulQA	safety	44.55	_mc	medium	`\| truthfulqa_mc \| 1 \| mc1 \| 44.55 \| ± \| 1.74 \|`
BigBench	reasoning	44.4	_movie_recommendation	medium	`\| bigbench_movie_recommendation \| 0 \| multiple_choice_grade \| 44.40 \| ± \| 2.22 \|`
AGIEval	reasoning	43.2	_sat_en_without_passage	medium	`\| agieval_sat_en_without_passage \| 0 \| acc \| 43.20 \| ± \| 3.46 \|`
AGIEval	reasoning	41.47	_logiqa_en	medium	`\| agieval_logiqa_en \| 0 \| acc \| 41.47 \| ± \| 1.93 \|`
OpenBookQA	knowledge	37.8		medium	`\| openbookqa \| 0 \| acc \| 37.80 \| ± \| 2.17 \|`
AGIEval	reasoning	34.55	_sat_math	medium	`\| agieval_sat_math \| 0 \| acc \| 34.55 \| ± \| 3.21 \|`
BigBench	reasoning	30.4	_logical_deduction_five_objects	medium	`\| bigbench_logical_deduction_five_objects \| 0 \| multiple_choice_grade \| 30.40 \| ± \| 2.06 \|`
BigBench	reasoning	23.65	_salient_translation_error_detection	medium	`\| bigbench_salient_translation_error_detection \| 0 \| multiple_choice_grade \| 23.65 \| ± \| 1.35 \|`
AGIEval	reasoning	23.62	_aqua_rat	medium	`\| agieval_aqua_rat \| 0 \| acc \| 23.62 \| ± \| 2.67 \|`
AGIEval	reasoning	23.04	_lsat_ar	medium	`\| agieval_lsat_ar \| 0 \| acc \| 23.04 \| ± \| 2.78 \|`
BigBench	reasoning	22.56	_geometric_shapes	medium	`\| bigbench_geometric_shapes \| 0 \| multiple_choice_grade \| 22.56 \| ± \| 2.21 \|`
BigBench	reasoning	22.08	_tracking_shuffled_objects_five_objects	medium	`\| bigbench_tracking_shuffled_objects_five_objects \| 0 \| multiple_choice_grade \| 22.08 \| ± \| 1.17 \|`
BigBench	reasoning	20.57	_logical_deduction_seven_objects	medium	`\| bigbench_logical_deduction_seven_objects \| 0 \| multiple_choice_grade \| 20.57 \| ± \| 1.53 \|`
BigBench	reasoning	19.03	_tracking_shuffled_objects_seven_objects	medium	`\| bigbench_tracking_shuffled_objects_seven_objects \| 0 \| multiple_choice_grade \| 19.03 \| ± \| 0.94 \|`

Discussions (0)

none scraped.