OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF

Home/Models/TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF

TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF

kind: gguf
quant: gguf (2-bit)
family: misc
modality: —
root model: Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerp
provider: TheBloke
license: apache-2.0
language: —
context: 32768,
library: —
vRAM (GB): —
size on disk: —
downloads: 869
likes: 30
created: —
last modified: 2023-12-11T11:48:42+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/OpenHermes-2.5-neural-chat-v3-3-Slerp-GGUF
tags: transformersggufmistralbase_model:Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerpbase_model:quantized:Weyaxi/OpenHermes-2.5-neural-chat-v3-3-Slerplicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	86.2	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 86.2 \|`
WinoGrande	knowledge	79.16	Winogrande (5-shot)	medium	`\| Winogrande (5-shot) \| 79.16 \|`
GSM8K	math	67.78	GSM8K (5-shot)	medium	`\| GSM8K (5-shot) \| 67.78 \|`
MMLU	knowledge	64.26	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 64.26 \|`
TruthfulQA	safety	62.78	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 62.78 \|`

none scraped.