llama2-7B-layla-GGUF

Home/Models/TheBloke/llama2-7B-layla-GGUF

TheBloke/llama2-7B-layla-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: —
root model: l3utterfly/llama2-7b-layla
provider: TheBloke
license: llama2
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 164
likes: 2
created: —
last modified: 2023-11-20T02:41:29+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/llama2-7B-layla-GGUF
tags: transformersggufllamaenbase_model:l3utterfly/llama2-7b-laylabase_model:quantized:l3utterfly/llama2-7b-laylalicense:llama2region:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	79.34	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 79.34 \|`
WinoGrande	knowledge	74.11	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 74.11 \|`
MMLU	knowledge	49.7	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 49.7 \|`
TruthfulQA	safety	46.5	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 46.5 \|`
GSM8K	math	8.49	GSM8K (5-shot)	medium	`\| GSM8K (5-shot) \| 8.49 \|`
DROP	reasoning	6.57	DROP (3-shot)	medium	`\| DROP (3-shot) \| 6.57 \|`

none scraped.