HF Model & Benchmark Matrix

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

Platypus-30B-SuperHOT-8K-fp16

TheBloke/Platypus-30B-SuperHOT-8K-fp16

kind
original
quant
bf16 (16-bit)
family
misc
modality
text-generation
root model
—
provider
TheBloke
license
other
language
—
context
8192
library
—
vRAM (GB)
—
size on disk
—
downloads
201
likes
2
created
—
last modified
2023-07-09T20:24:56+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Platypus-30B-SuperHOT-8K-fp16
tags
transformerspytorchllamatext-generationcustom_codearxiv:2302.13971license:othertext-generation-inferenceregion:us

Benchmark scores (3)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge84.3HellaSwag (10-shot)medium| HellaSwag (10-shot) | 84.3 |
MMLUknowledge64.2MMLU (5-shot)medium| MMLU (5-shot) | 64.2 |
TruthfulQAsafety45.8TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 45.8 |

Discussions (0)

none scraped.

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