Llama2-chat-AYB-13B-GGUF

Home/Models/TheBloke/Llama2-chat-AYB-13B-GGUF

TheBloke/Llama2-chat-AYB-13B-GGUF

kind: gguf
quant: gguf (2-bit)
family: llama
modality: —
root model: posicube/Llama2-chat-AYB-13B
provider: TheBloke
license: llama2
language: —
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 204
likes: 5
created: —
last modified: 2023-10-08T17:42:25+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Llama2-chat-AYB-13B-GGUF
tags: transformersggufllamaarxiv:2306.02707base_model:posicube/Llama2-chat-AYB-13Bbase_model:quantized:posicube/Llama2-chat-AYB-13Blicense:llama2region:us

benchmark	category	score	context	conf	evidence
HellaSwag	knowledge	84.79	HellaSwag (10-shot)	medium	`\| HellaSwag (10-shot) \| 84.79 \| 84.87 \|`
MMLU	knowledge	59.34	MMLU (5-shot)	medium	`\| MMLU (5-shot) \| 59.34 \| 59.59 \|`
TruthfulQA	safety	55.62	TruthfulQA (0-shot)	medium	`\| TruthfulQA (0-shot) \| 55.62 \| 55.22 \|`

none scraped.