ORCA_LLaMA_70B_QLoRA-GGUF

Home/Models/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF

TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: —
root model: fangloveskari/ORCA_LLaMA_70B_QLoRA
provider: TheBloke
license: llama2
language: en
context: —
library: transformers
vRAM (GB): —
size on disk: —
downloads: 155
likes: 12
created: —
last modified: 2023-09-27T12:48:36+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/ORCA_LLaMA_70B_QLoRA-GGUF
tags: transformersggufllamaenarxiv:2308.07317arxiv:2306.02707base_model:fangloveskari/ORCA_LLaMA_70B_QLoRAbase_model:quantized:fangloveskari/ORCA_LLaMA_70B_QLoRAlicense:llama2region:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	87.74	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 87.74 \|`
MMLU	knowledge	70.23	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 70.23 \|`
TruthfulQA	safety	63.37	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 63.37 \|`

none scraped.