HF Model & Benchmark Matrix

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

Synatra-7B-v0.3-RP-GGUF

TheBloke/Synatra-7B-v0.3-RP-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
text-generation
root model
maywell/Synatra-7B-v0.3-RP
provider
TheBloke
license
cc-by-nc-4.0
language
ko
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
691
likes
15
created
—
last modified
2023-11-23T16:46:40+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Synatra-7B-v0.3-RP-GGUF
tags
transformersggufmistraltext-generationkobase_model:maywell/Synatra-7B-v0.3-RPbase_model:quantized:maywell/Synatra-7B-v0.3-RPlicense:cc-by-nc-4.0region:usconversational

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge82.29HellaSwag (10-shot)medium| HellaSwag (10-shot) | 82.29 |
WinoGrandeknowledge76.48Winogrande (5-shot)medium| Winogrande (5-shot) | 76.48 |
MMLUknowledge60.8MMLU (5-shot)medium| MMLU (5-shot) | 60.8 |
TruthfulQAsafety52.64TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 52.64 |
DROPreasoning46.06DROP (3-shot)medium| DROP (3-shot) | 46.06 |
GSM8Kmath21.15GSM8K (5-shot)medium| GSM8K (5-shot) | 21.15 |

Discussions (0)

none scraped.

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