HF Model & Benchmark Matrix

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

nemo-megatron-gpt-5B

nvidia/nemo-megatron-gpt-5B

kind
original
quant
bf16 (16-bit)
family
misc
modality
—
root model
nvidia/nemo-megatron-gpt-5B
provider
nvidia
license
cc-by-4.0
language
en
context
—
library
nemo
vRAM (GB)
—
size on disk
—
downloads
53
likes
22
created
—
last modified
2023-01-13T04:33:25+00:00 (2023)
huggingface
https://huggingface.co/nvidia/nemo-megatron-gpt-5B
tags
nemotext generationpytorchcausal-lmendataset:the_pilearxiv:1909.08053arxiv:2101.00027license:cc-by-4.0region:us

Benchmark scores (4)

benchmarkcategoryscorecontextconfevidence
PIQAknowledge74.92low| 0.3976 | 0.5566 | 0.5007 | 0.4171 | 0.6133 | 0.5812 | 0.6356 | 0.6298 | 0.7492 |
HellaSwagknowledge62.98low| 0.3976 | 0.5566 | 0.5007 | 0.4171 | 0.6133 | 0.5812 | 0.6356 | 0.6298 | 0.7492 |
WinoGrandeknowledge61.33low| 0.3976 | 0.5566 | 0.5007 | 0.4171 | 0.6133 | 0.5812 | 0.6356 | 0.6298 | 0.7492 |
ARC-Challengeknowledge39.76low| 0.3976 | 0.5566 | 0.5007 | 0.4171 | 0.6133 | 0.5812 | 0.6356 | 0.6298 | 0.7492 |

Discussions (0)

none scraped.

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