Monarch-7B

Home/Models/mlabonne/Monarch-7B

mlabonne/Monarch-7B

kind: merge
quant: merge
family: misc
modality: text-generation
root model: mlabonne/OmniTruthyBeagle-7B-v0
provider: mlabonne
license: cc-by-nc-4.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 122
likes: 11
created: —
last modified: 2024-03-04T15:18:10+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/Monarch-7B
tags: transformerssafetensorsmistraltext-generationmergemergekitlazymergekitbase_model:mlabonne/NeuBeagle-7Bbase_model:merge:mlabonne/NeuBeagle-7Bbase_model:mlabonne/NeuralOmniBeagle-7Bbase_model:merge:mlabonne/NeuralOmniBeagle-7Bbase_model:mlabonne/OmniTruthyBeagle-7B-v0base_model:merge:mlabonne/OmniTruthyBeagle-7B-v0license:cc-by-nc-4.0model-indextext-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	89.03	HellaSwag (10-Shot)	medium	`\| HellaSwag (10-Shot) \| 89.03 \|`
WinoGrande	knowledge	84.61	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 84.61 \|`
TruthfulQA	safety	78.04		low	`\| [Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B) [📄](https://gist.github.com/mlabonne/0b8d057c5ece41e0290580a108c7a093) \| 62.68 \| 45.48 \| 77.07 \| *78.04`
TruthfulQA	safety	77.35	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 77.35 \|`
GSM8K	math	69.07	GSM8k (5-shot)	medium	`\| GSM8k (5-shot) \| 69.07 \|`
MMLU	knowledge	64.41	MMLU (5-Shot)	medium	`\| MMLU (5-Shot) \| 64.41 \|`
BigBench	reasoning	50.14		low	`\| [Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B) [📄](https://gist.github.com/mlabonne/0b8d057c5ece41e0290580a108c7a093) \| 62.68 \| 45.48 \| 77.07 \| *78.04`
AGIEval	reasoning	45.48		low	`\| [Monarch-7B](https://huggingface.co/mlabonne/Monarch-7B) [📄](https://gist.github.com/mlabonne/0b8d057c5ece41e0290580a108c7a093) \| 62.68 \| 45.48 \| 77.07 \| *78.04`

none scraped.