README.md

---
pipeline_tag: sentence-similarity
tags:
- sentence-transformers
- feature-extraction
- sentence-similarity
- transformers
language: pl
license: gemma
widget:
- source_sentence: "zapytanie: Jak dożyć 100 lat?"
  sentences:
    - "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."

---

<h1 align="center">Stella-PL-retrieval</h1>

This is a text encoder based on [stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5) and further fine-tuned for Polish information retrieval tasks. 
- In the first step, we adapted the model for Polish with [multilingual knowledge distillation method](https://aclanthology.org/2020.emnlp-main.365/) using a diverse corpus of 20 million Polish-English text pairs. 
- The second step involved fine-tuning the model with contrastrive loss using a dataset consisting of 1.4 million queries. Positive and negative passages for each query have been selected with the help of [BAAI/bge-reranker-v2.5-gemma2-lightweight](https://huggingface.co/BAAI/bge-reranker-v2.5-gemma2-lightweight) reranker. The model was trained for three epochs with a batch size of 1024 queries. 

The encoder transforms texts to 1024 dimensional vectors. The model is optimized specifically for Polish information retrieval tasks. If you need a more versatile encoder, suitable for a wider range of tasks such as semantic similarity or clustering, you should probably use the distilled version from the first step: [sdadas/stella-pl](https://huggingface.co/sdadas/stella-pl).

## Usage (Sentence-Transformers)

The model utilizes the same prompts as the original [stella_en_1.5B_v5](https://huggingface.co/dunzhang/stella_en_1.5B_v5).

For retrieval, queries should be prefixed with **"Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: "**.

For symmetric tasks such as semantic similarity, both texts should be prefixed with **"Instruct: Retrieve semantically similar text.\nQuery: "**.

Please note that the model uses a custom implementation, so you should add `trust_remote_code=True` argument when loading it. 
It is also recommended to use Flash Attention 2, which can be enabled with `attn_implementation` argument. 
You can use the model like this with [sentence-transformers](https://www.SBERT.net):

```python
from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim

model = SentenceTransformer(
    "sdadas/stella-pl-retrieval",
    trust_remote_code=True,
    device="cuda",
    model_kwargs={"attn_implementation": "flash_attention_2", "trust_remote_code": True}
)
model.bfloat16()

# Retrieval example
query_prefix = "Instruct: Given a web search query, retrieve relevant passages that answer the query.\nQuery: "
queries = [query_prefix + "Jak dożyć 100 lat?"]
answers = [
    "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."
]
queries_emb = model.encode(queries, convert_to_tensor=True, show_progress_bar=False)
answers_emb = model.encode(answers, convert_to_tensor=True, show_progress_bar=False)
best_answer = cos_sim(queries_emb, answers_emb).argmax().item()
print(answers[best_answer])

# Semantic similarity example
sim_prefix = "Instruct: Retrieve semantically similar text.\nQuery: "
sentences = [
    sim_prefix + "Trzeba zdrowo się odżywiać i uprawiać sport.",
    sim_prefix + "Warto jest prowadzić zdrowy tryb życia, uwzględniający aktywność fizyczną i dietę.",
    sim_prefix + "One should eat healthy and engage in sports.",
    sim_prefix + "Zakupy potwierdzasz PINem, który bezpiecznie ustalisz podczas aktywacji."
]
emb = model.encode(sentences, convert_to_tensor=True, show_progress_bar=False)
print(cos_sim(emb, emb))

```

## Evaluation Results

The model achieves **NDCG@10** of **62.32** on the Polish Information Retrieval Benchmark. See [PIRB Leaderboard](https://huggingface.co/spaces/sdadas/pirb) for detailed results.

## Citation

```bibtex
@article{dadas2024pirb,
  title={{PIRB}: A Comprehensive Benchmark of Polish Dense and Hybrid Text Retrieval Methods}, 
  author={Sławomir Dadas and Michał Perełkiewicz and Rafał Poświata},
  year={2024},
  eprint={2402.13350},
  archivePrefix={arXiv},
  primaryClass={cs.CL}
}
```