F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Ziyin, Liao, Zihan, Yu, Hang, Di, Peng, Wang, Rui
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911189223604224
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 introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cost, model size, and embedding performance. On the MTEB English leaderboard, F2LLM-4B ranks 2nd among models with approximately 4B parameters and 7th overall, while F2LLM-1.7B ranks 1st among models in the 1B-2B size range. To facilitate future research in the field, we release the models, training dataset, and code, positioning F2LLM as a strong, reproducible, and budget-friendly baseline for future works.
format Preprint
id arxiv_https___arxiv_org_abs_2510_02294
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
Zhang, Ziyin
Liao, Zihan
Yu, Hang
Di, Peng
Wang, Rui
Computation and Language
Artificial Intelligence
We introduce F2LLM - Foundation to Feature Large Language Models, a suite of state-of-the-art embedding models in three sizes: 0.6B, 1.7B, and 4B. Unlike previous top-ranking embedding models that require massive contrastive pretraining, sophisticated training pipelines, and costly synthetic training data, F2LLM is directly finetuned from foundation models on 6 million query-document-negative tuples curated from open-source, non-synthetic datasets, striking a strong balance between training cost, model size, and embedding performance. On the MTEB English leaderboard, F2LLM-4B ranks 2nd among models with approximately 4B parameters and 7th overall, while F2LLM-1.7B ranks 1st among models in the 1B-2B size range. To facilitate future research in the field, we release the models, training dataset, and code, positioning F2LLM as a strong, reproducible, and budget-friendly baseline for future works.
title F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.02294