Sentence Similarity
sentence-transformers
Safetensors
Transformers
Polish
modernbert
feature-extraction
text-embeddings-inference
Instructions to use OPI-PIB/PolDense-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use OPI-PIB/PolDense-1B with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("OPI-PIB/PolDense-1B") sentences = [ "zapytanie: Jak dożyć 100 lat?", "Trzeba zdrowo się odżywiać i uprawiać sport.", "Trzeba pić alkohol, imprezować i jeździć szybkimi autami.", "Gdy trwała kampania politycy zapewniali, że rozprawią się z zakazem niedzielnego handlu." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [4, 4] - Transformers
How to use OPI-PIB/PolDense-1B with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("OPI-PIB/PolDense-1B") model = AutoModel.from_pretrained("OPI-PIB/PolDense-1B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -98,4 +98,18 @@ vllm serve OPI-PIB/PolDense-1B --dtype bfloat16 --runner pooling --convert embed
|
|
| 98 |
|
| 99 |
The research was supported by the project <strong>Large Language Models for the European Union (LLMs4EU)</strong>. This project is co-funded by the Digital Europe Programme under Grant Agreement 101198470.
|
| 100 |
|
| 101 |
-
The research was supported [in part] by project “<strong>Cloud Artificial Intelligence Service Engineering (CAISE)</strong> platform to create universal and smart services for various application areas”, No. KPOD.05.10-IW.10-0005/24, as part of the European IPCEI-CIS program, financed by NRRP (National Recovery and Resilience Plan) funds. Computations were carried out using the computers of <strong>Centre of Informatics Tricity Academic Supercomputer & Network at Gdansk University of Technology</strong>.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
|
| 99 |
The research was supported by the project <strong>Large Language Models for the European Union (LLMs4EU)</strong>. This project is co-funded by the Digital Europe Programme under Grant Agreement 101198470.
|
| 100 |
|
| 101 |
+
The research was supported [in part] by project “<strong>Cloud Artificial Intelligence Service Engineering (CAISE)</strong> platform to create universal and smart services for various application areas”, No. KPOD.05.10-IW.10-0005/24, as part of the European IPCEI-CIS program, financed by NRRP (National Recovery and Resilience Plan) funds. Computations were carried out using the computers of <strong>Centre of Informatics Tricity Academic Supercomputer & Network at Gdansk University of Technology</strong>.
|
| 102 |
+
|
| 103 |
+
## Citation
|
| 104 |
+
|
| 105 |
+
```bibtex
|
| 106 |
+
@misc{dadas2026parameterefficientretrieverspolisheuropean,
|
| 107 |
+
title={Parameter-Efficient Retrievers for Polish and European Languages},
|
| 108 |
+
author={Sławomir Dadas and Rafał Poświata and Małgorzata Grębowiec and Michał Perełkiewicz},
|
| 109 |
+
year={2026},
|
| 110 |
+
eprint={2609.12913},
|
| 111 |
+
archivePrefix={arXiv},
|
| 112 |
+
primaryClass={cs.CL},
|
| 113 |
+
url={https://arxiv.org/abs/2609.12913}
|
| 114 |
+
}
|
| 115 |
+
```
|