HF Model & Benchmark Matrix

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

Seraph-7B-GGUF

TheBloke/Seraph-7B-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
—
root model
Weyaxi/Seraph-7B
provider
TheBloke
license
cc-by-nc-4.0
language
—
context
32768,
library
—
vRAM (GB)
—
size on disk
—
downloads
299
likes
4
created
—
last modified
2023-12-12T11:04:41+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Seraph-7B-GGUF
tags
transformersggufmistralbase_model:Weyaxi/Seraph-7Bbase_model:quantized:Weyaxi/Seraph-7Blicense:cc-by-nc-4.0region:us

Benchmark scores (5)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge86.22HellaSwag (10-shot)medium| HellaSwag (10-shot) | 86.22 |
WinoGrandeknowledge80.66Winogrande (5-shot)medium| Winogrande (5-shot) | 80.66 |
GSM8Kmath71.87GSM8K (5-shot)medium| GSM8K (5-shot) | 71.87 |
MMLUknowledge65.07MMLU (5-shot)medium| MMLU (5-shot) | 65.07 |
TruthfulQAsafety59.49TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 59.49 |

Discussions (0)

none scraped.

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