HF Model & Benchmark Matrix

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

deberta-v3-large

microsoft/deberta-v3-large

kind
original
quant
bf16 (16-bit)
family
misc
modality
fill-mask
root model
microsoft/deberta-v3-large
provider
microsoft
license
mit
language
—
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
2,411,420
likes
284
created
—
last modified
2023-03-19T06:24:32+00:00 (2023)
huggingface
https://huggingface.co/microsoft/deberta-v3-large
tags
transformerspytorchtfdeberta-v2debertadeberta-v3fill-maskenarxiv:2006.03654arxiv:2111.09543license:mitendpoints_compatibleregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (16)

titleauthorstatuscommentstype
TemporalMesh Transformer: 29.4 PPL at 48% compute — beats Mamba, new open-source architecturevigneshwar234open0disc
VORTEXRAG: 7-Layer RAG — Eliminates Semantic Drift & Context Poisoning (EM 74.8, +13.6 vs Naive RAG)vigneshwar234closed0disc
Add link to Neuron-optimized versionbadaouiopen0disc
Adding `safetensors` variant of this modelSFconvertbotopen0disc
Update README.mdjackkolbopen0disc
Adding ONNX file of this modelksamlopen0disc
Added license based on tagiamankitopen0disc
tensorflow version does not work.ali-hooshmandopen0disc
Tokenizer and model vocab size differentabpani1994open0disc
Unable to load vocabulary from fileIgorShopen0disc
Bizzare responsesumarbutleropen0disc
[AUTOMATED] Model Memory Requirementsmodel-sizer-botopen0disc
Adding `safetensors` variant of this modelSFconvertbotopen0disc
Case?malikarumiopen0disc
Add task to enable widgetlewtunmerged0disc
Is the config.json correct?LeoWu2021closed0disc
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.