HF Model & Benchmark Matrix

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

koOpenChat-sft-GGUF

TheBloke/koOpenChat-sft-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
—
root model
maywell/koOpenChat-sft
provider
TheBloke
license
cc-by-sa-4.0
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
60
likes
1
created
—
last modified
2023-11-23T15:48:39+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/koOpenChat-sft-GGUF
tags
transformersggufmistralbase_model:maywell/koOpenChat-sftbase_model:quantized:maywell/koOpenChat-sftlicense:cc-by-sa-4.0region:us

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge78.73HellaSwag (10-shot)medium| HellaSwag (10-shot) | 78.73 |
WinoGrandeknowledge76.4Winogrande (5-shot)medium| Winogrande (5-shot) | 76.4 |
MMLUknowledge61.32MMLU (5-shot)medium| MMLU (5-shot) | 61.32 |
TruthfulQAsafety51.24TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 51.24 |
GSM8Kmath24.18GSM8K (5-shot)medium| GSM8K (5-shot) | 24.18 |
DROPreasoning7.82DROP (3-shot)medium| DROP (3-shot) | 7.82 |

Discussions (0)

none scraped.

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