Name: nli deberta v3 base
Author: cross-encoder

Overview

The NLI DeBERTa-v3-base is a high-performance cross-encoder optimized for Natural Language Inference tasks. Unlike standard bi-encoders, it processes sentence pairs simultaneously, allowing for deeper interaction between text segments to determine if a premise entails or contradicts a hypothesis. For developers, this makes it an ideal choice for building high-precision verification systems, automated FAQ matching, or filtering noise in RAG pipelines where semantic accuracy outweighs raw throughput. It leverages the DeBERTa-v3 architecture's improved disentangled attention and ELECTRA-style pre-training, offering significantly better performance-per-parameter than original BERT or RoBERTa models. Integration is straightforward via the Hugging Face Transformers library, fitting easily into existing Python-based NLP stacks.

Highlights

Superior precision in entailment and contradiction detection
Cross-encoder architecture for deeper semantic analysis
Optimized performance over standard BERT-base models
Ideal for RAG verification and fact-checking workflows
Apache-2.0 licensed for flexible commercial integration

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("cross-encoder/nli-deberta-v3-base")
tokenizer = AutoTokenizer.from_pretrained("cross-encoder/nli-deberta-v3-base")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download cross-encoder/nli-deberta-v3-base

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download cross-encoder/nli-deberta-v3-base config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('cross-encoder/nli-deberta-v3-base')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/cross-encoder/nli-deberta-v3-base

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/cross-encoder/nli-deberta-v3-base

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('cross-encoder/nli-deberta-v3-base')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-v3-base')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model cross-encoder/nli-deberta-v3-base

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model cross-encoder/nli-deberta-v3-base README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('cross-encoder/nli-deberta-v3-base')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/cross-encoder/nli-deberta-v3-base.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/cross-encoder/nli-deberta-v3-base.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'cross-encoder/nli-deberta-v3-base')

Full Documentation

来源: HuggingFace

---
language: en
pipeline_tag: zero-shot-classification
tags:

transformers

datasets:

nyu-mll/multi_nli

stanfordnlp/snli

metrics:

accuracy

license: apache-2.0
base_model:

microsoft/deberta-v3-base

library_name: sentence-transformers
---

Cross-Encoder for Natural Language Inference

This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-base

Training Data

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.

Performance

Accuracy on SNLI-test dataset: 92.38

Accuracy on MNLI mismatched set: 90.04

For futher evaluation results, see SBERT.net - Pretrained Cross-Encoder.

Usage

Pre-trained models can be used like this:

python

from sentence_transformers import CrossEncoder
model = CrossEncoder('cross-encoder/nli-deberta-v3-base')
scores = model.predict([('A man is eating pizza', 'A man eats something'), ('A black race car starts up in front of a crowd of people.', 'A man is driving down a lonely road.')])
#Convert scores to labels
label_mapping = ['contradiction', 'entailment', 'neutral']
labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]

Usage with Transformers AutoModel

You can use the model also directly with Transformers library (without SentenceTransformers library):

python

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
model = AutoModelForSequenceClassification.from_pretrained('cross-encoder/nli-deberta-v3-base')
tokenizer = AutoTokenizer.from_pretrained('cross-encoder/nli-deberta-v3-base')
features = tokenizer(['A man is eating pizza', 'A black race car starts up in front of a crowd of people.'], ['A man eats something', 'A man is driving down a lonely road.'],  padding=True, truncation=True, return_tensors="pt")
model.eval()
with torch.no_grad():
    scores = model(**features).logits
    label_mapping = ['contradiction', 'entailment', 'neutral']
    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
    print(labels)

Zero-Shot Classification

This model can also be used for zero-shot-classification:

python

from transformers import pipeline
classifier = pipeline("zero-shot-classification", model='cross-encoder/nli-deberta-v3-base')
sent = "Apple just announced the newest iPhone X"
candidate_labels = ["technology", "sports", "politics"]
res = classifier(sent, candidate_labels)
print(res)