SAVRN
Search Contact SAVRN

Open-weight model · Zero-shot classification

DeBERTa-v3-large-mnli-fever-anli-ling-wanli

by Moritz Borrett-Laurer (formerly Laurer) MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli

This model was fine-tuned on the MultiNLI, Fever-NLI, Adversarial-NLI (ANLI), LingNLI and WANLI datasets, which comprise 885 242 NLI hypothesis-premise pairs.

Parameters435M
Context512
Weights4.1 GB
Licensemit
AccessOpen weights
Monthly Downloads179.1k

Runs On

What it takes to serve DeBERTa-v3-large-mnli-fever-anli-ling-wanli (435M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.

PrecisionWeightsMemory neededCheapest setupPer hourAlso fits
16-bit 0.9 GB 1.0 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
8-bit 0.4 GB 0.5 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00
4-bit 0.2 GB 0.3 GB 1x MI300X (192 GB)
Vultr		 $1.85 1x H100 $1.99 · 1x MI325X $2.00

Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.

Model Card

By Moritz Borrett-Laurer (formerly Laurer), published under mit, revision b3546ea6b034.

Model description

This model was fine-tuned on the MultiNLI, Fever-NLI, Adversarial-NLI (ANLI), LingNLI and WANLI datasets, which comprise 885 242 NLI hypothesis-premise pairs. This model is the best performing NLI model on the Hugging Face Hub as of 06.06.22 and can be used for zero-shot classification. It significantly outperforms all other large models on the ANLI benchmark.

The foundation model is DeBERTa-v3-large from Microsoft. DeBERTa-v3 combines several recent innovations compared to classical Masked Language Models like BERT, RoBERTa etc., see the paper

How to use the model

Simple zero-shot classification pipeline
from transformers import pipeline
classifier = pipeline("zero-shot-classification", model="MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli")
sequence_to_classify = "Angela Merkel is a politician in Germany and leader of the CDU"
candidate_labels = ["politics", "economy", "entertainment", "environment"]
output = classifier(sequence_to_classify, candidate_labels, multi_label=False)
print(output)
NLI use-case

Read the full model card (599 words)

Configuration

Architecture
DebertaV2ForSequenceClassification
Context length (tokens)
512
Layers
24
Hidden size
1,024
Feed-forward size
4,096
Attention heads
16
Vocabulary size
128,100
Stored precision
float16
Model type
deberta-v2

Identity and Version

Repository
MoritzLaurer/DeBERTa-v3-large-mnli-fever-anli-ling-wanli
Publisher
Moritz Borrett-Laurer (formerly Laurer)
Task
Zero-shot classification
Modality
Text
Library
transformers
Parameters
435M parameters
Languages
en
Revision
b3546ea6b0346eb6f8d5d68b13c7dc6d0376b3d7
First published
2022-06-06
Last updated
2024-04-11

Files and Weights

12 files, 4.1 GB in total. The weights are 4 files totalling 4.1 GB in bin, onnx, safetensors.

Weights4 files · 4.1 GB
Configuration3 files · 1.2 KB
Tokenizer2 files · 8.6 MB
Documentation1 file · 7.6 KB
Other1 file · 2.5 MB
Repository1 file · 1.2 KB
Every file
FileTypeSizeSHA-256
model.safetensorsWeights870.2 MB c03cd208bf92
onnx/model.onnxWeights1.7 GB 9f304954c0c3
onnx/model_quantized.onnxWeights642.6 MB 2eb57451c9d9
pytorch_model.binWeights870.3 MB 37a7caf315cf
added_tokens.jsonConfiguration18 B —
config.jsonConfiguration1.1 KB —
special_tokens_map.jsonConfiguration156 B —
README.mdDocumentation7.6 KB —
spm.modelOther2.5 MB c679fbf93643
.gitattributesRepository1.2 KB —
tokenizer.jsonTokenizer8.6 MB —
tokenizer_config.jsonTokenizer395 B —

License and Download

License
mit
Access
Open weights, no gate
Download size
4.1 GB
Download from Moritz Borrett-Laurer (formerly Laurer)

Released by Moritz Borrett-Laurer (formerly Laurer) through its official repository on Hugging Face. Read the license.

Built From

  • Described by arXiv:2104.07179
  • Described by arXiv:2111.09543
  • Trained on (disclosed) alisawuffles/WANLI
  • Trained on (disclosed) facebook/anli
  • Trained on (disclosed) fever
  • Trained on (disclosed) lingnli
  • Trained on (disclosed) multi_nli

Evaluations

Each result is shown as reported, with the conditions its reporter stated. None is a SAVRN measurement. A comparison lines two results up only when their configuration, unit and setup are all stated and identical.

BenchmarkConditionsResultReported byRevisionDate
ANLI-all Task Natural Language InferenceMetric accuracyComparison conditions not established 0,702 MoritzLaurer
Publisher reported		 Evaluated revision not stated —
ANLI-r3 Task Natural Language InferenceMetric accuracyComparison conditions not established 0,64 MoritzLaurer
Publisher reported		 Evaluated revision not stated —
LingNLI Task Natural Language InferenceMetric accuracyComparison conditions not established 0,87 MoritzLaurer
Publisher reported		 Evaluated revision not stated —
MultiNLI-matched Task Natural Language InferenceMetric accuracyComparison conditions not established 0,912 MoritzLaurer
Publisher reported		 Evaluated revision not stated —
MultiNLI-mismatched Task Natural Language InferenceMetric accuracyComparison conditions not established 0,908 MoritzLaurer
Publisher reported		 Evaluated revision not stated —
WANLI Task Natural Language InferenceMetric accuracyComparison conditions not established 0,77 MoritzLaurer
Publisher reported		 Evaluated revision not stated —

Memory Requirements

PrecisionWeights in memory
As published4.1 GB
16-bit0.9 GB
8-bit0.4 GB
4-bit0.2 GB

Weights only, from the published parameter count; the key-value cache and runtime add to this.

Compare DeBERTa-v3-large-mnli-fever-anli-ling-wanli

Questions About DeBERTa-v3-large-mnli-fever-anli-ling-wanli

How much GPU memory does DeBERTa-v3-large-mnli-fever-anli-ling-wanli need?

About 1 GB at 16-bit and 0.3 GB at 4-bit: the weights (435M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run DeBERTa-v3-large-mnli-fever-anli-ling-wanli on?

At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.

Can I use DeBERTa-v3-large-mnli-fever-anli-ling-wanli commercially?

Yes. DeBERTa-v3-large-mnli-fever-anli-ling-wanli is released under MIT License. The MIT License is a short permissive license. It permits commercial use, modification and redistribution, provided the copyright notice and permission notice are included.

What is DeBERTa-v3-large-mnli-fever-anli-ling-wanli's context length?

512 tokens, from the maximum position embeddings in its published configuration.

Similar Models

This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-large The model was trained on the SNLI and MultiNLI datasets. For a given sentence pair, it will output three scores corresponding to the labels: contradiction, entailment, neutral. For futher evaluation results, see SBERT.net - Pretrained Cross-Encoder. Pre-trained models can be used like this: You can use the model also directly with Transformers library (without SentenceTransformers library): This model can also be used for zero-shot-classification

Open weights apache-2.0 435M parameters 512 tokens sentence-transformers
View model

Model · Zero-shot classification

deberta-v3-large-tasksource-nli

Damien Sileo

DeBERTa-v3-large fine-tuned with multi-task learning on 600 tasks of the tasksource collection You can further fine-tune this model to use it for any classification or multiple-choice task. This checkpoint has strong zero-shot validation performance on many tasks (e.g. 77% on WNLI). The untuned model CLS embedding also has strong linear probing performance (90% on MNLI), due to the multitask training. This is the shared model with the MNLI classifier on top. Its encoder was trained on many datasets including bigbench, Anthropic rlhf, anli... alongside many NLI and classification tasks with a SequenceClassification heads while using only one shared encoder. Each task had a specific CLS…

Open weights apache-2.0 435M parameters 512 tokens transformers
View model

Models in this series are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can do classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in my Zeroshot Classifier Collection. The main update of this zeroshot-v2.0 series of models is that several models are trained on fully commercially-friendly data for users with strict license requirements. These models can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is…

Open weights mit 435M parameters 512 tokens transformers
View model

The model is designed for zero-shot classification with the Hugging Face pipeline. The model should be substantially better at zero-shot classification than my other zero-shot models on the The model can do one universal task: determine whether a hypothesis is true or nottrue given a text (also called entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is so universal that any classification task can be reformulated into the task. The model was trained on a mixture of 27 tasks and 310 classes that have been reformatted into this universal format. 1. 26 classification tasks with ~400k texts: 'amazonpolarity', 'imdb', 'appreviews'…

Open weights mit 435M parameters 512 tokens transformers
View model

The model is designed for zero-shot classification with the Hugging Face pipeline. The model can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is so universal that any classification task can be reformulated into this task. A detailed description of how the model was trained and how it can be used is available in this paper. The model was trained on a mixture of 33 datasets and 387 classes that have been reformatted into this universal format. 1. Five NLI datasets with ~885k texts: "mnli", "anli", "fever", "wanli"…

Open weights mit 435M parameters 512 tokens transformers
View model

Models in this series are designed for efficient zeroshot classification with the Hugging Face pipeline. These models can do classification without training data and run on both GPUs and CPUs. An overview of the latest zeroshot classifiers is available in my Zeroshot Classifier Collection. The main update of this zeroshot-v2.0 series of models is that several models are trained on fully commercially-friendly data for users with strict license requirements. These models can do one universal classification task: determine whether a hypothesis is "true" or "not true" given a text (entailment vs. notentailment). This task format is based on the Natural Language Inference task (NLI). The task is…

Open weights mit 435M parameters 512 tokens transformers
View model