Downloads · 30 days
0
yeseul0-0/docred-stage2-atlop-fine-tuning-v2
docred-stage2-atlop-fine-tuning-v2 is a machine learning model from yeseul0-0. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Evaluation was conducted on the DocRED dev set.
Downloads · 30 days
0
Access
Public
Updated Apr 10, 2026
Repo size
1.8 GB
Likes
0
Public
Click a slice to open those files.
.pt1.8 GB · 100%
From the Hugging Face model README
Evaluation was conducted on the DocRED dev set.
Micro F1: 60.71%
Ign F1: 58.58%
Evidence F1: 43.09%
The model achieves a Micro F1 of 60.71% on the DocRED dev set, showing solid document-level relation extraction performance under a multi-label setting.
The Ign F1 of 58.58% indicates that the model maintains reasonable generalization even when excluding overlapping relational facts seen in training.
The Evidence F1 of 43.09% suggests that the evidence prediction module provides meaningful sentence-level grounding, although evidence selection remains more challenging than relation prediction itself.
This project is built upon several open-source works:
This model is trained and evaluated on the DocRED dataset.
DocRED is intended for research use. Users should separately review the dataset’s original terms and conditions before any redistribution or commercial use.
This repository is intended for:
It is not guaranteed for production use without additional validation.