HF Model & Benchmark Matrix

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

supermario-v2-GGUF

TheBloke/supermario-v2-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
—
root model
janhq/supermario-v2
provider
TheBloke
license
apache-2.0
language
en
context
32768,
library
—
vRAM (GB)
—
size on disk
—
downloads
205
likes
5
created
—
last modified
2023-12-12T15:38:39+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/supermario-v2-GGUF
tags
transformersggufmistralenbase_model:jan-hq/supermario-v2base_model:quantized:jan-hq/supermario-v2license:apache-2.0region:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge86.51HellaSwag (10-shot)medium| HellaSwag (10-shot) | 86.51 |
WinoGrandeknowledge81.37Winogrande (5-shot)medium| Winogrande (5-shot) | 81.37 |
GSM8Kmath72.18GSM8K (5-shot)medium| GSM8K (5-shot) | 72.18 |
MMLUknowledge64.88MMLU (5-shot)medium| MMLU (5-shot) | 64.88 |
TruthfulQAsafety60.58TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 60.58 |

Discussions (0)

none scraped.

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