HF Model & Benchmark Matrix

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

Synatra-V0.1-7B-Instruct-GGUF

TheBloke/Synatra-V0.1-7B-Instruct-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
text-generation
root model
maywell/Synatra-V0.1-7B-Instruct
provider
TheBloke
license
cc-by-nc-4.0
language
ko
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
640
likes
1
created
—
last modified
2023-11-23T17:45:05+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Synatra-V0.1-7B-Instruct-GGUF
tags
transformersggufmistraltext-generationkobase_model:maywell/Synatra-V0.1-7B-Instructbase_model:quantized:maywell/Synatra-V0.1-7B-Instructlicense:cc-by-nc-4.0region:us

Benchmark scores (6)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge76.63HellaSwag (10-shot)medium| HellaSwag (10-shot) | 76.63 |
WinoGrandeknowledge72.77Winogrande (5-shot)medium| Winogrande (5-shot) | 72.77 |
TruthfulQAsafety55.76TruthfulQA (0-shot)medium| TruthfulQA (0-shot) | 55.76 |
MMLUknowledge55.29MMLU (5-shot)medium| MMLU (5-shot) | 55.29 |
DROPreasoning39.63DROP (3-shot)medium| DROP (3-shot) | 39.63 |
GSM8Kmath19.41GSM8K (5-shot)medium| GSM8K (5-shot) | 19.41 |

Discussions (0)

none scraped.

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