HF Model & Benchmark Matrix

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

Synthia-70B-GGUF

TheBloke/Synthia-70B-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
text-generation
root model
migtissera/Synthia-70B
provider
TheBloke
license
llama2
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
87
likes
7
created
—
last modified
2023-09-27T12:46:22+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Synthia-70B-GGUF
tags
transformersggufllamatext-generationenarxiv:2306.02707arxiv:2302.13971base_model:migtissera/Synthia-70Bbase_model:quantized:migtissera/Synthia-70Blicense:llama2region:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge87.11**medium| *hellaswag* | acc_norm | 0.8711 |
ARC-Challengeknowledge69.45*_challenge*medium| *arc_challenge* | acc_norm | 0.6945 |
MMLUknowledge68.91**medium| *mmlu* | acc_norm | 0.6891 |
TruthfulQAsafety59.79*_mc*medium| *truthfulqa_mc* | mc2 | 0.5979 |

Discussions (0)

none scraped.

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