HF Model & Benchmark Matrix

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

Synthia-70B-v1.1-GGUF

TheBloke/Synthia-70B-v1.1-GGUF

kind
gguf
quant
gguf (2-bit)
family
misc
modality
text-generation
root model
migtissera/Synthia-70B-v1.1
provider
TheBloke
license
llama2
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
138
likes
3
created
—
last modified
2023-09-27T12:46:56+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/Synthia-70B-v1.1-GGUF
tags
transformersggufllamatext-generationenarxiv:2306.02707arxiv:2302.13971base_model:migtissera/Synthia-70B-v1.1base_model:quantized:migtissera/Synthia-70B-v1.1license:llama2region:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge87.12**medium| *hellaswag* | acc_norm | 87.12 |
MMLUknowledge70.34**medium| *mmlu* | acc_norm | 70.34 |
ARC-Challengeknowledge70.05*_challenge*medium| *arc_challenge* | acc_norm | 70.05 |
TruthfulQAsafety57.84*_mc*medium| *truthfulqa_mc* | mc2 | 57.84 |

Discussions (0)

none scraped.

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