mmlw retrieval roberta large v2 EU AI Act Compliance Profile

MMLW (muszę mieć lepszą wiadomość) are neural text encoders for Polish. The second version is based on the same foundational model (polish-roberta-large-v2), but the training process incorporated modern LLM-based English retrievers and rerankers, which led to improved results. This model is optimized for information retrieval tasks. It can transform queries and passages to 1024 dimensional vectors. The model was developed using a two-step procedure:

• In the first step, it was initialized with Polish RoBERTa checkpoint, and then trained with multilingual knowledge distillation method on a diverse corpus of 20 million Polish-English text pairs. We utilised stella_en_1.5B_v5 as the teacher models for distillation.
• The second step involved fine-tuning the model with contrastrive loss using a dataset consisting of over 4 million queries. Positive and negative passages for each query have been selected with the help of BAAI/bge-reranker-v2.5-gemma2-lightweight reranker.

Usage (Sentence-Transformers)

The model supports both information retrieval and semantic textual similarity. For retrieval, queries should be prefixed with "[query]: ". For symmetric tasks such as semantic similarity, both texts should be prefixed with "[sts]: ".

You can use the model like this with sentence-transformers:

from sentence_transformers import SentenceTransformer
from sentence_transformers.util import cos_sim

model = SentenceTransformer(
    "sdadas/mmlw-retrieval-roberta-large-v2",
    model_kwargs={"dtype": torch.bfloat16}
)

# Retrieval example
query_prefix = "[query]: "
queries = [query_prefix + "Jak dożyć 100 lat?"]
answers = [
    "Trzeba zdrowo się o

Your obligations as a mmlw retrieval roberta large v2 deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Languages

Library