gliclass-small-v1.0 by Knowledgator Engineering: Open Model

Runs On

What it takes to serve gliclass-small-v1.0 (144M 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	0.3 GB	0.3 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
8-bit	0.1 GB	0.2 GB	1x MI300X (192 GB) Vultr	$1.85	1x H100 $1.99 · 1x MI325X $2.00
4-bit	0.1 GB	0.1 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 Knowledgator Engineering, published under apache-2.0, revision 21edefaf7951.

This is an efficient zero-shot classifier inspired by GLiNER work. It demonstrates the same performance as a cross-encoder while being more compute-efficient because classification is done at a single forward path. It can be used for topic classification, sentiment analysis and as a reranker in RAG pipelines. The model was trained on synthetic data and can be used in commercial applications. First of all, you need to install GLiClass library: Than you need to initialize a model and a pipeline: Below, you can see the F1 score on several text classification datasets. All tested models were not fine-tuned on those datasets and were tested in a zero-shot setting. Below you can find a comparison…

Read Knowledgator Engineering's full model card

GLiClass: Generalist and Lightweight Model for Sequence Classification

This is an efficient zero-shot classifier inspired by GLiNER work. It demonstrates the same performance as a cross-encoder while being more compute-efficient because classification is done at a single forward path.

It can be used for topic classification, sentiment analysis and as a reranker in RAG pipelines.

The model was trained on synthetic data and can be used in commercial applications.

How to use:

First of all, you need to install GLiClass library:

pip install gliclass

Than you need to initialize a model and a pipeline:

from gliclass import GLiClassModel, ZeroShotClassificationPipeline
from transformers import AutoTokenizer

model = GLiClassModel.from_pretrained("knowledgator/gliclass-small-v1.0")
tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-small-v1.0")

pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')

text = "One day I will see the world!"
labels = ["travel", "dreams", "sport", "science", "politics"]
results = pipeline(text, labels, threshold=0.5)[0] #because we have one text

for result in results:
 print(result["label"], "=>", result["score"])

Benchmarks:

Below, you can see the F1 score on several text classification datasets. All tested models were not fine-tuned on those datasets and were tested in a zero-shot setting. | Model | IMDB | AG_NEWS | Emotions | |-----------------------------|------|---------|----------| | gliclass-large-v1.0 (438 M) | 0.9404 | 0.7516 | 0.4874 | | gliclass-base-v1.0 (186 M) | 0.8650 | 0.6837 | 0.4749 | | gliclass-small-v1.0 (144 M) | 0.8650 | 0.6805 | 0.4664 | | Bart-large-mnli (407 M) | 0.89 | 0.6887 | 0.3765 | | Deberta-base-v3 (184 M) | 0.85 | 0.6455 | 0.5095 | | Comprehendo (184M) | 0.90 | 0.7982 | 0.5660 | | SetFit BAAI/bge-small-en-v1.5 (33.4M) | 0.86 | 0.5636 | 0.5754 |

Below you can find a comparison with other GLiClass models: | Dataset | gliclass-small-v1.0-lw | gliclass-base-v1.0-lw | gliclass-large-v1.0-lw | gliclass-small-v1.0 | gliclass-base-v1.0 | gliclass-large-v1.0 | |----------------------|-----------------------|-----------------------|-----------------------|---------------------|---------------------|---------------------| | CR | 0.8886 | 0.9097 | 0.9226 | 0.8824 | 0.8942 | 0.9219 | | sst2 | 0.8392 | 0.8987 | 0.9247 | 0.8518 | 0.8979 | 0.9269 | | sst5 | 0.2865 | 0.3779 | 0.2891 | 0.2424 | 0.2789 | 0.3900 | | 20_news_groups | 0.4572 | 0.3953 | 0.4083 | 0.3366 | 0.3576 | 0.3863 | | spam | 0.5118 | 0.5126 | 0.3642 | 0.4089 | 0.4938 | 0.3661 | | rotten_tomatoes | 0.8015 | 0.8429 | 0.8807 | 0.7987 | 0.8508 | 0.8808 | | massive | 0.3180 | 0.4635 | 0.5606 | 0.2546 | 0.1893 | 0.4376 | | banking | 0.1768 | 0.4396 | 0.3317 | 0.1374 | 0.2077 | 0.2847 | | yahoo_topics | 0.4686 | 0.4784 | 0.4760 | 0.4477 | 0.4516 | 0.4921 | | financial_phrasebank | 0.8665 | 0.8880 | 0.9044 | 0.8901 | 0.8955 | 0.8735 | | imdb | 0.9048 | 0.9351 | 0.9429 | 0.8982 | 0.9238 | 0.9333 | | ag_news | 0.7252 | 0.6985 | 0.7559 | 0.7242 | 0.6848 | 0.7503 | | dair_emotion | 0.4012 | 0.3516 | 0.3951 | 0.3450 | 0.2357 | 0.4013 | | capsotu | 0.3794 | 0.4643 | 0.4749 | 0.3432 | 0.4375 | 0.4644 | |Average:|0.5732|0.6183|0.6165|0.5401|0.5571|0.6078|

Here you can see how the performance of the model grows providing more examples: | Model | Num Examples | sst5 | spam | massive | banking | ag news | dair emotion | capsotu | Average | |-----------------------------|--------------|--------|---------|---------|---------|---------|--------------|---------|-------------| | gliclass-small-v1.0-lw | 0 | 0.2865 | 0.5118 | 0.318 | 0.1768 | 0.7252 | 0.4012 | 0.3794 | 0.3998428571| | gliclass-base-v1.0-lw | 0 | 0.3779 | 0.5126 | 0.4635 | 0.4396 | 0.6985 | 0.3516 | 0.4643 | 0.4725714286| | gliclass-large-v1.0-lw | 0 | 0.2891 | 0.3642 | 0.5606 | 0.3317 | 0.7559 | 0.3951 | 0.4749 | 0.4530714286| | gliclass-small-v1.0 | 0 | 0.2424 | 0.4089 | 0.2546 | 0.1374 | 0.7242 | 0.345 | 0.3432 | 0.3508142857| | gliclass-base-v1.0 | 0 | 0.2789 | 0.4938 | 0.1893 | 0.2077 | 0.6848 | 0.2357 | 0.4375 | 0.3611 | | gliclass-large-v1.0 | 0 | 0.39 | 0.3661 | 0.4376 | 0.2847 | 0.7503 | 0.4013 | 0.4644 | 0.4420571429| | gliclass-small-v1.0-lw | 8 | 0.2709 | 0.84026 | 0.62 | 0.6883 | 0.7786 | 0.449 | 0.4918 | 0.5912657143| | gliclass-base-v1.0-lw | 8 | 0.4275 | 0.8836 | 0.729 | 0.7667 | 0.7968 | 0.3866 | 0.4858 | 0.6394285714| | gliclass-large-v1.0-lw | 8 | 0.3345 | 0.8997 | 0.7658 | 0.848 | 0.84843 | 0.5219 | 0.508 | 0.67519 | | gliclass-small-v1.0 | 8 | 0.3042 | 0.5683 | 0.6332 | 0.7072 | 0.759 | 0.4509 | 0.4434 | 0.5523142857| | gliclass-base-v1.0 | 8 | 0.3387 | 0.7361 | 0.7059 | 0.7456 | 0.7896 | 0.4323 | 0.4802 | 0.6040571429| | gliclass-large-v1.0 | 8 | 0.4365 | 0.9018 | 0.77 | 0.8533 | 0.8509 | 0.5061 | 0.4935 | 0.6874428571|

Citation

@misc{stepanov2025gliclassgeneralistlightweightmodel,
      title={GLiClass: Generalist Lightweight Model for Sequence Classification Tasks}, 
      author={Ihor Stepanov and Mykhailo Shtopko and Dmytro Vodianytskyi and Oleksandr Lukashov and Alexander Yavorskyi and Mykyta Yaroshenko},
      year={2025},
      eprint={2508.07662},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2508.07662}, 
}

Configuration

Architecture: GLiClassModel
Hidden size: 768
Vocabulary size: 128,003
Stored precision: float32
Model type: GLiClass

Identity and Version

Repository: knowledgator/gliclass-small-v1.0
Publisher: Knowledgator Engineering
Task: Zero-shot classification
Modality: Text
Library: transformers
Parameters: 144M parameters
Languages: en
Revision: 21edefaf7951f68c68c505f9139ba536d3b448f7
First published: 2024-07-03
Last updated: 2025-08-12

Files and Weights

13 files, 1.3 GB in total. The weights are 4 files totalling 1.3 GB in bin, onnx, safetensors.

Weights4 files · 1.3 GB

Configuration4 files · 5.3 KB

Tokenizer2 files · 8.7 MB

Documentation1 file · 7.9 KB

Other1 file · 2.5 MB

Repository1 file · 1.5 KB

Every file

File	Type	Size	SHA-256
model.safetensors	Weights	574.4 MB	ed3d94af3541
onnx/model-int8-quantized.onnx	Weights	174.1 MB	825c1f9231ec
onnx/model.onnx	Weights	574.9 MB	01ed6e5f0c6e
training_args.bin	Weights	5.2 KB	d65c11a69b6b
added_tokens.json	Configuration	67 B	—
config.json	Configuration	3.2 KB	—
onnx/config.json	Configuration	1.0 KB	—
special_tokens_map.json	Configuration	970 B	—
README.md	Documentation	7.9 KB	—
spm.model	Other	2.5 MB	c679fbf93643
.gitattributes	Repository	1.5 KB	—
tokenizer.json	Tokenizer	8.6 MB	—
tokenizer_config.json	Tokenizer	1.6 KB	—

License and Download

License: apache-2.0
Access: Open weights, no gate
Download size: 1.3 GB

Download from Knowledgator Engineering

Released by Knowledgator Engineering through its official repository on Hugging Face. Read the license.

Built From

Described by arXiv:2508.07662
Trained on (disclosed) MoritzLaurer/synthetic_zeroshot_mixtral_v0.1

Memory Requirements

Precision	Weights in memory
As published	1.3 GB
16-bit	0.3 GB
8-bit	0.1 GB
4-bit	0.1 GB

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

Questions About gliclass-small-v1.0

How much GPU memory does gliclass-small-v1.0 need?

About 0.3 GB at 16-bit and 0.1 GB at 4-bit: the weights (144M parameters) plus a working margin. A long context needs more.

What is the cheapest GPU to run gliclass-small-v1.0 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 gliclass-small-v1.0 commercially?

Yes. gliclass-small-v1.0 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.

Similar Models

Model · Zero-shot classification

nli-deberta-v3-small

Sentence Transformers - Cross-Encoders

This model was trained using SentenceTransformers Cross-Encoder class. This model is based on microsoft/deberta-v3-small 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 142M parameters 512 tokens sentence-transformers

View model

Model · Zero-shot classification

deberta-small-long-nli

Tasksource

DeBERTa-v3-small with context length of 1680 tokens fine-tuned on tasksource for 250k steps. I oversampled long NLI tasks (ConTRoL, doc-nli). Training data include HelpSteer v1/v2, logical reasoning tasks (FOLIO, FOL-nli, LogicNLI...), OASST, hh/rlhf, linguistics oriented NLI tasks, tasksource-dpo, fact verification tasks. This model is suitable for long context NLI or as a backbone for reward models or classifiers fine-tuning. This checkpoint has strong zero-shot validation performance on many tasks (e.g. 70% on WNLI), and can be used for: - Zero-shot entailment-based classification for arbitrary labels [ZS]. - Natural language inference [NLI] - Further fine-tuning on a new task or…

Open weights apache-2.0 142M parameters 1,680 tokens transformers

View model

Model · Zero-shot classification

nli-deberta-base

Sentence Transformers - Cross-Encoders

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 139M parameters 512 tokens sentence-transformers

View model

Model · Zero-shot classification

ModernBERT-base-nli

Tasksource

ModernBERT multi-task fine-tuned on tasksource NLI tasks, including MNLI, ANLI, SICK, WANLI, doc-nli, LingNLI, FOLIO, FOL-NLI, LogicNLI, Label-NLI and all datasets in the below table). This is the equivalent of an "instruct" version. The model was trained for 200k steps on an Nvidia A30 GPU. It is very good at reasoning tasks (better than llama 3.1 8B Instruct on ANLI and FOLIO), long context reasoning, sentiment analysis and zero-shot classification with new labels. The following table shows model test accuracy. These are the scores for the same single transformer with different classification heads on top. Further gains can be obtained by fine-tuning on a single-task, e.g. SST, but it…

Open weights apache-2.0 150M parameters 2,048 tokens transformers

View model

Model · Zero-shot classification

nli-roberta-base

Sentence Transformers - Cross-Encoders

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 125M parameters 514 tokens sentence-transformers

View model

Model · Zero-shot classification

roberta-base-zeroshot-v2.0-c

Moritz Borrett-Laurer (formerly Laurer)

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 125M parameters 514 tokens transformers

View model