No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from knowledgator/gliclass-multilang-ultra
All models by knowledgator →[Image blocked: image/png]
[Image blocked: Multilingual Quality vs Throughput]
GLiClass is an efficient zero-shot sequence classification model designed to achieve SoTA performance while being much faster than cross-encoders and LLMs, while preserving strong generalization capabilities.
The model supports text classification with any labels and can be used for the following tasks:
sentiment.positive, topic.product).See the GLiClass library README for full details on these features.
Natively trained on 20 languages. Labels and texts can be in different languages.
Same language (German):
Cross-lingual (French text, English labels):
Cross-lingual (Arabic text, English labels):
Cross-lingual (English text, Spanish labels):
Represent your premise as the text and the hypothesis as a label. The model works best with a single hypothesis at a time.
Score query–passage relevance by treating passages as texts and the query as the label:
Include the domain and rules as part of the text:
Summary across all evaluated multilingual-capable models (zero-shot, no fine-tuning). Speed averaged over all label counts and text lengths at batch_size=8 on NVIDIA RTX PRO 6000 Blackwell.
Multilingual avg F1 is the mean of 6 dataset-level scores (GermEval2017, MASSIVE, PolygloToxicityPrompts, SIB-200, TextDetox, TweetSentiment). Models without multilingual results (—) were only evaluated on English datasets.
F1 scores on zero-shot text classification (no fine-tuning on these datasets):
Table A: GLiClass Multilang (macro F1)
Table B: Baselines (macro F1)
Table C: GLiClass-V1 Multitask (macro F1)
Macro F1 averaged per dataset across all evaluated languages:
Per-language macro F1 (16-language fair comparison on massive + sib200):
[Image blocked: English Quality vs Throughput]
Throughput (samples/sec), batch_size=8, GPU: NVIDIA RTX PRO 6000 Blackwell. Averaged over text lengths (64 / 256 / 512 tokens).
NLI models (bge-m3, mDeBERTa) run one forward pass per label — throughput drops linearly with label count. GLiClass and GLiNER2 encode all labels in a single pass, so throughput stays nearly flat.
pip install gliclassfrom gliclass import GLiClassModel, ZeroShotClassificationPipelinefrom transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-multilang-ultra")tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-multilang-ultra")pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "NASA launched a new Mars rover to search for signs of ancient life."labels = ["space", "politics", "sports", "technology", "health"]
results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])from gliclass import GLiClassModel, ZeroShotClassificationPipelinefrom transformers import AutoTokenizer
model = GLiClassModel.from_pretrained("knowledgator/gliclass-multilang-ultra")tokenizer = AutoTokenizer.from_pretrained("knowledgator/gliclass-multilang-ultra")pipeline = ZeroShotClassificationPipeline(model, tokenizer, classification_type='multi-label', device='cuda:0')
text = "Die NASA hat einen neuen Mars-Rover gestartet, um nach Spuren alten Lebens zu suchen."labels = ["Weltraum", "Politik", "Sport", "Technologie", "Gesundheit"]results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])text = "Le gouvernement français a annoncé de nouvelles mesures économiques."labels = ["economy", "politics", "sports", "technology"]results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])text = "أطلقت ناسا مركبة جديدة للمريخ للبحث عن آثار الحياة القديمة."labels = ["space", "politics", "sports", "technology"]results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])text = "NASA launched a new Mars rover to search for signs of ancient life."labels = ["espacio", "política", "deportes", "tecnología", "salud"]results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])text = "NASA launched a new Mars rover to search for signs of ancient life."labels = ["space", "politics", "sports", "technology", "health"]
results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])hierarchical_labels = { "science": ["space", "biology", "physics"], "society": ["politics", "economics", "culture"]}
results = pipeline(text, hierarchical_labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])# e.g. science.space => 0.95text = "The food was excellent but the service was painfully slow."labels = ["positive", "negative", "neutral"]
results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])results = pipeline( text, labels, prompt="Classify the sentiment of this restaurant review:", threshold=0.5)[0]text = "Can you set an alarm for 7am tomorrow?"labels = ["set_alarm", "play_music", "get_weather", "send_message", "set_reminder"]
results = pipeline(text, labels, threshold=0.5)[0]for r in results: print(r["label"], "=>", r["score"])text = "The cat slept on the windowsill all afternoon."labels = ["The cat was awake and playing outside."]
results = pipeline(text, labels, threshold=0.0)[0]print(results)# Low score → contradictionquery = "How to train a neural network?"passages = [ "Backpropagation is the key algorithm for training deep neural networks.", "The stock market rallied on strong earnings reports.", "Gradient descent optimizes model weights during training.",]
for passage in passages: score = pipeline(passage, [query], threshold=0.0)[0][0]["score"] print(f"{score:.3f} {passage[:60]}")text = ( "Domain: e-commerce product reviews\n" "Rule: No promotion of illegal activity.\n" "Text: The software is okay, but search for 'productname_patch_v2.zip' " "to unlock all features for free.")labels = ["follows_guidelines", "violates_guidelines"]
results = pipeline(text, labels, threshold=0.0)[0]for r in results: print(r["label"], "=>", r["score"])@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}, }