Darewin-7B-v2

Home/Models/mlabonne/Darewin-7B-v2

mlabonne/Darewin-7B-v2

kind: merge
quant: merge
family: misc
modality: text-generation
root model: OpenPipe/mistral-ft-optimized-1227
provider: mlabonne
license: apache-2.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 66
likes: 1
created: —
last modified: 2024-03-04T15:17:28+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/Darewin-7B-v2
tags: transformerssafetensorsmistraltext-generationmergemergekitlazymergekitconversationalbase_model:Intel/neural-chat-7b-v3-3base_model:merge:Intel/neural-chat-7b-v3-3base_model:Open-Orca/Mistral-7B-OpenOrcabase_model:merge:Open-Orca/Mistral-7B-OpenOrcabase_model:OpenPipe/mistral-ft-optimized-1227base_model:merge:OpenPipe/mistral-ft-optimized-1227base_model:dphn/dolphin-2.6-mistral-7b-dpo-laserbase_model:merge:dphn/dolphin-2.6-mistral-7b-dpo-laserbase_model:mlabonne/NeuralHermes-2.5-Mistral-7Bbase_model:merge:mlabonne/NeuralHermes-2.5-Mistral-7Bbase_model:openaccess-ai-collective/DPOpenHermes-7B-v2base_model:merge:openaccess-ai-collective/DPOpenHermes-7B-v2base_model:openchat/openchat-3.5-0106base_model:merge:openchat/openchat-3.5-0106license:apache-2.0model-index

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	78.28	HellaSwag (10-Shot)	medium	`\| HellaSwag (10-Shot) \| 78.28 \|`
WinoGrande	knowledge	73.95	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 73.95 \|`
MMLU	knowledge	53.01	MMLU (5-Shot)	medium	`\| MMLU (5-Shot) \| 53.01 \|`
TruthfulQA	safety	50.99	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 50.99 \|`
GSM8K	math	19.18	GSM8k (5-shot)	medium	`\| GSM8k (5-shot) \| 19.18 \|`

none scraped.