Llama-2-13B-fp16

Home/Models/TheBloke/Llama-2-13B-fp16

TheBloke/Llama-2-13B-fp16

kind: original
quant: bf16 (16-bit)
family: llama
modality: text-generation
root model: —
provider: TheBloke
license: —
language: en
context: —
library: —
vRAM (GB): —
size on disk: —
downloads: 441
likes: 62
created: —
last modified: 2023-07-20T09:47:08+00:00 (2023)
huggingface: https://huggingface.co/TheBloke/Llama-2-13B-fp16
tags: transformerspytorchllamatext-generationfacebookmetallama-2entext-generation-inferenceregion:us

benchmark	category	score	conf	evidence
MMLU	knowledge	35.1	low	`\| Llama 1 \| 7B \| 14.1 \| 60.8 \| 46.2 \| 58.5 \| 6.95 \| 35.1 \| 30.3 \| 23.9 \|`
BBH	reasoning	30.3	low	`\| Llama 1 \| 7B \| 14.1 \| 60.8 \| 46.2 \| 58.5 \| 6.95 \| 35.1 \| 30.3 \| 23.9 \|`
AGIEval	reasoning	23.9	low	`\| Llama 1 \| 7B \| 14.1 \| 60.8 \| 46.2 \| 58.5 \| 6.95 \| 35.1 \| 30.3 \| 23.9 \|`
MATH	math	6.95	low	`\| Llama 1 \| 7B \| 14.1 \| 60.8 \| 46.2 \| 58.5 \| 6.95 \| 35.1 \| 30.3 \| 23.9 \|`

none scraped.