OmniBeagle-7B

Home/Models/mlabonne/OmniBeagle-7B

mlabonne/OmniBeagle-7B

kind: merge
quant: merge
family: misc
modality: text-generation
root model: shadowml/BeagleSempra-7B
provider: mlabonne
license: cc-by-nc-4.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 78
likes: 21
created: —
last modified: 2024-03-04T15:15:00+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/OmniBeagle-7B
tags: transformerssafetensorsmistraltext-generationmergemergekitlazymergekitbase_model:shadowml/BeagSake-7Bbase_model:merge:shadowml/BeagSake-7Bbase_model:shadowml/BeagleSempra-7Bbase_model:merge:shadowml/BeagleSempra-7Bbase_model:shadowml/WestBeagle-7Bbase_model:merge:shadowml/WestBeagle-7Blicense:cc-by-nc-4.0model-indextext-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	88.93	HellaSwag (10-Shot)	medium	`\| HellaSwag (10-Shot) \| 88.93 \|`
WinoGrande	knowledge	83.11	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 83.11 \|`
TruthfulQA	safety	74.45	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 74.45 \|`
GSM8K	math	70.05	GSM8k (5-shot)	medium	`\| GSM8k (5-shot) \| 70.05 \|`
MMLU	knowledge	64.8	MMLU (5-Shot)	medium	`\| MMLU (5-Shot) \| 64.80 \|`

none scraped.