F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912974586773504 |
|---|---|
| author | Zhang, Ziyin Liao, Zihan Yu, Hang Di, Peng Wang, Rui |
| author_facet | Zhang, Ziyin Liao, Zihan Yu, Hang Di, Peng Wang, Rui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19223 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World Zhang, Ziyin Liao, Zihan Yu, Hang Di, Peng Wang, Rui Computation and Language Artificial Intelligence 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. |
| title | F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.19223 |