Beagle14-7B

Home/Models/mlabonne/Beagle14-7B

mlabonne/Beagle14-7B

kind: merge
quant: merge
family: misc
modality: text-generation
root model: fblgit/UNA-TheBeagle-7b-v1
provider: mlabonne
license: cc-by-nc-4.0
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 187
likes: 15
created: —
last modified: 2024-03-04T15:17:41+00:00 (2024)
huggingface: https://huggingface.co/mlabonne/Beagle14-7B
tags: transformerssafetensorsmistraltext-generationmergemergekitlazymergekitfblgit/UNA-TheBeagle-7b-v1argilla/distilabeled-Marcoro14-7B-slerpbase_model:argilla/distilabeled-Marcoro14-7B-slerpbase_model:merge:argilla/distilabeled-Marcoro14-7B-slerpbase_model:fblgit/UNA-TheBeagle-7b-v1base_model:merge:fblgit/UNA-TheBeagle-7b-v1license:cc-by-nc-4.0model-indextext-generation-inferenceendpoints_compatibleregion:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	87.95	HellaSwag (10-Shot)	medium	`\| HellaSwag (10-Shot) \| 87.95 \|`
WinoGrande	knowledge	82.64	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 82.64 \|`
GSM8K	math	71.42	GSM8k (5-shot)	medium	`\| GSM8k (5-shot) \| 71.42 \|`
TruthfulQA	safety	69.44		low	`\| [Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) \| 44.38 \| 76.53 \| 69.44 \| 47.25 \| 59.4 \|`
TruthfulQA	safety	68.88	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 68.88 \|`
MMLU	knowledge	64.7	MMLU (5-Shot)	medium	`\| MMLU (5-Shot) \| 64.70 \|`
BigBench	reasoning	47.25		low	`\| [Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) \| 44.38 \| 76.53 \| 69.44 \| 47.25 \| 59.4 \|`
AGIEval	reasoning	44.38		low	`\| [Beagle14-7B](https://huggingface.co/mlabonne/Beagle14-7B) \| 44.38 \| 76.53 \| 69.44 \| 47.25 \| 59.4 \|`

none scraped.