F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Abstract
F2LLM-v2 is a multilingual embedding model family trained on 60 million samples across 200+ languages, achieving superior performance through LLM-based training, matryoshka learning, pruning, and distillation techniques.
We present F2LLM-v2, a new family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a newly curated composite of 60 million publicly available high-quality data samples, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages. By integrating a two-stage LLM-based embedding training pipeline with matryoshka learning, model pruning, and knowledge distillation techniques, we present models that are far more efficient than previous LLM-based embedding models while retaining competitive performances. Extensive evaluations confirm that F2LLM-v2-14B ranks first on 11 MTEB benchmarks, while the smaller models in the family also set a new state of the art for resource-constrained applications. To facilitate open-source embedding model research, we release all models, data, code, and intermediate checkpoints.
Community
F2LLM-v2 is a family of general-purpose, multilingual embedding models in 8 distinct sizes ranging from 80M to 14B. Trained on a curated composite of 60 million publicly available high-quality data, F2LLM-v2 supports more than 200 languages, with a particular emphasis on previously underserved mid- and low-resource languages. F2LLM-v2-14B ranks 1st on 11 MTEB benchmarks: European, Scandinavian, German, French, Polish, Dutch, Indic, Japanese, Persian, Vietnamese, and Code.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- jina-embeddings-v5-text: Task-Targeted Embedding Distillation (2026)
- Diffusion-Pretrained Dense and Contextual Embeddings (2026)
- Nemotron ColEmbed V2: Top-Performing Late Interaction embedding models for Visual Document Retrieval (2026)
- MrBERT: Modern Multilingual Encoders via Vocabulary, Domain, and Dimensional Adaptation (2026)
- LLM2Vec-Gen: Generative Embeddings from Large Language Models (2026)
- Learning Retrieval Models with Sparse Autoencoders (2026)
- Bootstrapping Embeddings for Low Resource Languages (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Models citing this paper 17
Browse 17 models citing this paperDatasets citing this paper 1
Spaces citing this paper 0
No Space linking this paper