Task
Sentence Similarity
M
sdadas/mmlw-roberta-large
Sentence Similarity·sdadas· 262.5K· 14
MMLW (muszę mieć lepszą wiadomość) are neural text encoders for Polish. This is a distilled model that can be used to generate embeddings applicable to many tasks such as semantic similarity, clustering, information retrieval. The model can also serve as a base for further fine-tuning. It transforms texts to 1024 dimensional vectors. The model was initialized with Polish RoBERTa checkpoint, and
# pull & run locally
pip install mlforge-sdk && mlforge pull sdadas/mmlw-roberta-large
pip install mlforge-sdk && mlforge pull sdadas/mmlw-roberta-large
Model details
Provider
sdadas
Framework
sentence-transformers
Parameters
435.0M
Size
3.2 GB
License
apache-2.0
Downloads
262.5K
Likes
14
Updated
2026-02-12
About sdadas/mmlw-roberta-large
MMLW (muszę mieć lepszą wiadomość) are neural text encoders for Polish. This is a distilled model that can be used to generate embeddings applicable to many tasks such as semantic similarity, clustering, information retrieval. The model can also serve as a base for further fine-tuning. It transforms texts to 1024 dimensional vectors. The model was initialized with Polish RoBERTa checkpoint, and then trained with multilingual knowledge distillation method on a diverse corpus of 60 million Polish-English text pairs. We utilised English FlagEmbeddings (BGE) as teacher models for distillation.
Related Sentence Similarity
A
sentence-transformers/all-MiniLM-L6-v2
255.4M 5.0K
🤗 HF
P
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
50.8M 1.3K
🤗 HF
A
sentence-transformers/all-mpnet-base-v2
33.9M 1.3K
🤗 HF
B
BAAI/bge-m3
31.1M 3.1K
🤗 HF
N
nomic-ai/nomic-embed-text-v1.5
18.3M 856
🤗 HF
M
intfloat/multilingual-e5-small
10.0M 344
🤗 HF