HF Model & Benchmark Matrix

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

mdeberta-v3-base

microsoft/mdeberta-v3-base

kind
original
quant
bf16 (16-bit)
family
misc
modality
fill-mask
root model
microsoft/mdeberta-v3-base
provider
microsoft
license
mit
language
multilingual, en, ar, bg, de, el, es, fr, hi, ru, sw, th
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
3,139,676
likes
231
created
—
last modified
2023-04-06T05:32:33+00:00 (2023)
huggingface
https://huggingface.co/microsoft/mdeberta-v3-base
tags
transformerspytorchtfdeberta-v2debertadeberta-v3mdebertafill-maskmultilingualenarbgdeelesfrhiruswthtrurvizh

Benchmark scores (0)

no scores extracted for this variant.

Discussions (6)

titleauthorstatuscommentstype
TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecturevigneshwar234open0disc
Adding `safetensors` variant of this modelSFconvertbotopen0disc
Generator Modelprajwal967closed0disc
Large Multilingual Modelstevenhillisopen0disc
Add task tag to enable widgetlewtunmerged0disc
Add language tagslbourdoismerged0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.