Mistral-7B-OpenOrca-GGUF

Home/Models/TheBloke/Mistral-7B-OpenOrca-GGUF

TheBloke/Mistral-7B-OpenOrca-GGUF

kind: gguf
quant: gguf (2-bit)
family: mistral
modality: text-generation
root model: Open-Orca/Mistral-7B-OpenOrca
provider: TheBloke
license: apache-2.0
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 3,564
likes: 243
created: —
last modified: 2023-10-02T23:16:16+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Mistral-7B-OpenOrca-GGUF
tags: transformersggufmistraltext-generationendataset:Open-Orca/OpenOrcaarxiv:2306.02707arxiv:2301.13688base_model:Open-Orca/Mistral-7B-OpenOrcabase_model:quantized:Open-Orca/Mistral-7B-OpenOrcalicense:apache-2.0region:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	83.79	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 83.79 \|`
MMLU	knowledge	61.73	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 61.73 \|`
TruthfulQA	safety	52.24	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 52.24 \|`

none scraped.