HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Nous-Hermes-13B-SuperHOT-8K-fp16

TheBloke/Nous-Hermes-13B-SuperHOT-8K-fp16

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
—
provider
TheBloke
license
other
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
75
likes
4
created
—
last modified
2023-07-02T20:34:48+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Nous-Hermes-13B-SuperHOT-8K-fp16
tags
transformerspytorchllamatext-generationcustom_codelicense:othertext-generation-inferenceregion:us

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
PIQAknowledge79.65medium| piqa | 0 | acc | 0.7965 | ± | 0.0094 |
BoolQknowledge79.48medium| boolq | 1 | acc | 0.7948 | ± | 0.0071 |
WinoGrandeknowledge71.9medium| winogrande | 0 | acc | 0.7190 | ± | 0.0126 |
HellaSwagknowledge61.43medium| hellaswag | 0 | acc | 0.6143 | ± | 0.0049 |
ARC-Challengeknowledge49.15_challengemedium| arc_challenge | 0 | acc | 0.4915 | ± | 0.0146 |
OpenBookQAknowledge35.6medium| openbookqa | 0 | acc | 0.3560 | ± | 0.0214 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.