# nli-deberta-v3-xsmall by Sentence Transformers - Cross-Encoders Source: https://savrn.com/models/nli-deberta-v3-xsmall Markdown alternate of the page above; the site index is https://savrn.com/llms.txt --- ## Runs On What it takes to serve nli-deberta-v3-xsmall (71M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them. | Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits | | --- | --- | --- | --- | --- | --- | | 16-bit | 0.1 GB | 0.2 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 8-bit | 0.1 GB | 0.1 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/mi325x) $2.00 | | 4-bit | 0.0 GB | 0.0 GB | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) (192 GB) Vultr | $1.85 | [1x H100](https://savrn.com/ai-index/pricing/gpus/h100) $1.99 · [1x MI325X](https://savrn.com/ai-index/pricing/gpus/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](https://savrn.com/ai-index/pricing/gpus), read Oct 24, 2026. [nli-deberta-v3-xsmall on every accelerator the SAVRN Index prices, at every precision](https://savrn.com/models/nli-deberta-v3-xsmall/gpus) ## Model Card By Sentence Transformers - Cross-Encoders, published under apache-2.0, revision a15087641532. ### Cross-Encoder for Natural Language Inference This model was trained using [SentenceTransformers](https://sbert.net) [Cross-Encoder](https://www.sbert.net/examples/applications/cross-encoder/README.html) class. This model is based on [microsoft/deberta-v3-xsmall](https://huggingface.co/microsoft/deberta-v3-xsmall) ### Training Data The model was trained on the [SNLI](https://nlp.stanford.edu/projects/snli/) and [MultiNLI](https://cims.nyu.edu/~sbowman/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: 91.64 - Accuracy on MNLI mismatched set: 87.77 For futher evaluation results, see [SBERT.net - Pretrained Cross-Encoder](https://www.sbert.net/docs/pretrained_cross-encoders.html#nli). ### Usage Pre-trained models can be used like this: ``` from sentence_transformers import CrossEncoder model = CrossEncoder('cross-encoder/nli-deberta-v3-xsmall') 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): [Read the full model card (254 words)](https://savrn.com/models/nli-deberta-v3-xsmall/card) ## Configuration Architecture DebertaV2ForSequenceClassification Context length (tokens) 512 Layers 12 Hidden size 384 Feed-forward size 1,536 Attention heads 6 Vocabulary size 128,100 Stored precision float32 Model type deberta-v2 ## Identity and Version Repository cross-encoder/nli-deberta-v3-xsmall Publisher Sentence Transformers - Cross-Encoders Task Zero-shot classification Modality Text Library sentence-transformers Parameters 71M parameters Languages en Revision a150876415327c80daeff35ca6f68f5ed8cf5c24 First published 2022-03-02 Last updated 2025-04-11 ## Files and Weights 20 files, 2.3 GB in total. The weights are 11 files totalling 2.3 GB in bin, onnx, safetensors. Weights11 files · 2.3 GB Configuration3 files · 1.4 KB Tokenizer2 files · 8.7 MB Documentation1 file · 2.9 KB Other2 files · 2.5 MB Repository1 file · 1.2 KB Every file | File | Type | Size | SHA-256 | | --- | --- | --- | --- | | model.safetensors | Weights | 283.4 MB | 4e4fc4977f8d | | onnx/model.onnx | Weights | 284.2 MB | 7105da41f625 | | onnx/model_O1.onnx | Weights | 302.0 MB | 67028fcdb307 | | onnx/model_O2.onnx | Weights | 301.9 MB | 41f436714a71 | | onnx/model_O3.onnx | Weights | 301.9 MB | e9c42b3c2931 | | onnx/model_O4.onnx | Weights | 151.3 MB | 7f3e118f3394 | | onnx/model_qint8_arm64.onnx | Weights | 87.4 MB | ef41fe8474f6 | | onnx/model_qint8_avx512.onnx | Weights | 87.4 MB | ef41fe8474f6 | | onnx/model_qint8_avx512_vnni.onnx | Weights | 87.4 MB | ef41fe8474f6 | | onnx/model_quint8_avx2.onnx | Weights | 87.4 MB | 21b14751a955 | | pytorch_model.bin | Weights | 283.4 MB | 7bfaa3c5238c | | added_tokens.json | Configuration | 26 B | — | | config.json | Configuration | 1.1 KB | — | | special_tokens_map.json | Configuration | 301 B | — | | README.md | Documentation | 2.9 KB | — | | CESoftmaxAccuracyEvaluator_AllNLI-dev_results.csv | Other | 681 B | — | | spm.model | Other | 2.5 MB | c679fbf93643 | | .gitattributes | Repository | 1.2 KB | — | | tokenizer.json | Tokenizer | 8.7 MB | — | | tokenizer_config.json | Tokenizer | 1.3 KB | — | ## License and Download License apache-2.0 Access Open weights, no gate Download size 2.3 GB [Download from Sentence Transformers - Cross-Encoders](https://huggingface.co/cross-encoder/nli-deberta-v3-xsmall) Released by Sentence Transformers - Cross-Encoders through its official repository on Hugging Face. [Read the license](https://www.apache.org/licenses/LICENSE-2.0). ## Built From - Derived from microsoft/deberta-v3-xsmall - Quantized from microsoft/deberta-v3-xsmall - Trained on (disclosed) nyu-mll/multi_nli - Trained on (disclosed) [stanfordnlp/snli](https://savrn.com/datasets/snli) ## Memory Requirements | Precision | Weights in memory | | --- | --- | | As published | 2.3 GB | | 16-bit | 0.1 GB | | 8-bit | 0.1 GB | | 4-bit | 0.0 GB | Weights only, from the published parameter count; the key-value cache and runtime add to this. ## Built on This Model - Quantized from[nli-deberta-v3-xsmall](https://savrn.com/models/nli-deberta-v3-xsmall-2) - Derived from[nli-deberta-v3-xsmall](https://savrn.com/models/nli-deberta-v3-xsmall-2) ## Questions About nli-deberta-v3-xsmall ### How much GPU memory does nli-deberta-v3-xsmall need? About 0.2 GB at 16-bit and 0 GB at 4-bit: the weights (71M parameters) plus a working margin. A long context needs more. ### What is the cheapest GPU to run nli-deberta-v3-xsmall 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 nli-deberta-v3-xsmall commercially? Yes. nli-deberta-v3-xsmall is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors. ### What is nli-deberta-v3-xsmall's context length? 512 tokens, from the maximum position embeddings in its published configuration. ## Similar Models Model · Zero-shot classification ### [DeBERTa-v3-xsmall-mnli-fever-anli-ling-binary](https://savrn.com/models/deberta-v3-xsmall-mnli-fever-anli-ling-binary) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) This model was trained on 782 357 hypothesis-premise pairs from 4 NLI datasets: MultiNLI, Fever-NLI, LingNLI and ANLI. Note that the model was trained on binary NLI to predict either "entailment" or "not-entailment". This is specifically designed for zero-shot classification, where the difference between "neutral" and "contradiction" is irrelevant. The base model is DeBERTa-v3-xsmall from Microsoft. The v3 variant of DeBERTa substantially outperforms previous versions of the model by including a different pre-training objective, see the DeBERTa-V3 paper. For highest performance (but less speed), I recommend using… Open weights mit 71M parameters 512 tokens transformers [View model](https://savrn.com/models/deberta-v3-xsmall-mnli-fever-anli-ling-binary) Model · Zero-shot classification ### [deberta-v3-xsmall-zeroshot-v1.1-all-33](https://savrn.com/models/deberta-v3-xsmall-zeroshot-v1-1-all-33) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) This model was fine-tuned using the same pipeline as described in the model card for MoritzLaurer/deberta-v3-large-zeroshot-v1.1-all-33 and in this paper. The foundation model is microsoft/deberta-v3-xsmall. The model only has 22 million backbone parameters and 128 million vocabulary parameters. The backbone parameters are the main parameters active during inference, providing a significant speedup over larger models. The model is 142 MB small. This model was trained to provide a small and highly efficient zeroshot option, especially for edge devices or in-browser use-cases with transformers.js. For usage instructions and other details refer to this model card… Open weights mit 71M parameters 512 tokens transformers [View model](https://savrn.com/models/deberta-v3-xsmall-zeroshot-v1-1-all-33) Model · Zero-shot classification ### [distilbert-base-uncased-mnli](https://savrn.com/models/distilbert-base-uncased-mnli) [Typeform](https://savrn.com/model-publishers/typeform) This is the uncased DistilBERT model fine-tuned on Multi-Genre Natural Language Inference (MNLI) dataset for the zero-shot classification task. This model can be used for text classification tasks. CONTENT WARNING: Readers should be aware this section contains content that is disturbing, offensive, and can propagate historical and current stereotypes. Significant research has explored bias and fairness issues with language models (see, e.g., Sheng et al. (2021) and Bender et al. (2021)). This model of DistilBERT-uncased is pretrained on the Multi-Genre Natural Language Inference (MultiNLI) corpus. It is a crowd-sourced collection of 433k sentence pairs annotated with textual entailment… Open weights 67M parameters 512 tokens transformers [View model](https://savrn.com/models/distilbert-base-uncased-mnli) Model · Zero-shot classification ### [nli-MiniLM2-L6-H768](https://savrn.com/models/nli-minilm2-l6-h768) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained using SentenceTransformers Cross-Encoder class. 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 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 82M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/nli-minilm2-l6-h768) Model · Zero-shot classification ### [nli-distilroberta-base](https://savrn.com/models/nli-distilroberta-base) [Sentence Transformers - Cross-Encoders](https://savrn.com/model-publishers/cross-encoder) This model was trained using SentenceTransformers Cross-Encoder class. 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 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 82M parameters 514 tokens sentence-transformers [View model](https://savrn.com/models/nli-distilroberta-base) Model · Zero-shot classification ### [multilingual-MiniLMv2-L6-mnli-xnli](https://savrn.com/models/multilingual-minilmv2-l6-mnli-xnli) [Moritz Borrett-Laurer (formerly Laurer)](https://savrn.com/model-publishers/moritzlaurer) multilingual - zero-shot-classification - text-classification - nli - pytorch - accuracy - multinli - xnli pipelinetag: zero-shot-classification candidatelabels: "politics, economy, entertainment, environment" This multilingual model can perform natural language inference (NLI) on 100+ languages and is therefore also suitable for multilingual zero-shot classification. The underlying multilingual-MiniLM-L6 model was created by Microsoft and was distilled from XLM-RoBERTa-large (see details in the original paper and newer information in this repo). The model was then fine-tuned on the XNLI dataset, which contains hypothesis-premise pairs from 15 languages, as well as the English MNLI dataset.… Open weights mit 107M parameters 514 tokens transformers [View model](https://savrn.com/models/multilingual-minilmv2-l6-mnli-xnli) ## Sentence Transformers - Cross-Encoders [All models and datasets](https://savrn.com/model-publishers/cross-encoder) ## Versions - [a15087641532](https://savrn.com/models/nli-deberta-v3-xsmall/versions/a15087641532) · current 2026-09-18 ## Explore More - [All zero-shot classification models](https://savrn.com/models/tasks/zero-shot-classification) - [All models under apache-2.0](https://savrn.com/models/licenses/apache-2-0) - [Model comparisons](https://savrn.com/models/comparisons) - [The model directory](https://savrn.com/models) - [Open model prices by host](https://savrn.com/ai-index/pricing/open-models) ## Source - Repository metadata, read 2026-10-20. - [Sentence Transformers - Cross-Encoders website](https://sbert.net/) - [Hugging Face record](https://huggingface.co/cross-encoder/nli-deberta-v3-xsmall) - [How the hub is built](https://savrn.com/model-hub/methodology)