HF Model & Benchmark Matrix

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

orca_mini_v3_70B-GPTQ

TheBloke/orca_mini_v3_70B-GPTQ

kind
gptq
quant
gptq
family
misc
modality
text-generation
root model
psmathur/orca_mini_v3_70b
provider
TheBloke
license
other
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
60
likes
13
created
—
last modified
2023-09-27T12:45:50+00:00 (2023)
huggingface
https://huggingface.co/TheBloke/orca_mini_v3_70B-GPTQ
tags
transformerssafetensorsllamatext-generationendataset:psmathur/orca_mini_v1_datasetdataset:ehartford/dolphinarxiv:2306.02707base_model:pankajmathur/orca_mini_v3_70bbase_model:quantized:pankajmathur/orca_mini_v3_70blicense:othertext-generation-inference4-bitgptqregion:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge87.79**medium| *hellaswag* | acc_norm | 0.8779 | 0.0032 |
ARC-Challengeknowledge70.98*_challenge*medium| *arc_challenge* | acc_norm | 0.7098 | 0.0132 |
MMLUknowledge69.04**medium| *mmlu* | acc_norm | 0.6904 | 0.0351 |
TruthfulQAsafety61.96*_mc*medium| *truthfulqa_mc* | mc2 | 0.6196 | 0.0151 |

Discussions (0)

none scraped.

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