Model Card for quinex-quantity-v0-82M
quinex-quantity-v0-82M is based on ClimateBERT (distilroberta-base-climate-f), which is a DistilRoBERTa-based, encoder-only transformer model that was trained on climate-related scientific abstracts, news, and company reports. We further fine-tuned this model to identify quantities (i.e., a number and, if applicable, a unit) in text. For more details, please refer to our paper "Quinex: Quantitative Information Extraction from Text using Open and Lightweight LLMs" (published soon).
Uses
This model is intended for detecting quantity mentions in text using sequence labeling. Please note that quantity modifiers (e.g., 'approximately', 'about', 'more than', 'not', etc.) are not considered part of quantity spans in this work.
Example output
| Token | NER tag |
|---|---|
| The | O |
| hydroelectric | O |
| complex | O |
| has | O |
| a | O |
| capacity | O |
| of | O |
| approximately | O |
| 2,500 | B-Quantity |
| megawatts | I-Quantity |
| and | O |
| produces | O |
| about | O |
| 4.9 | B-Quantity |
| terawatt | I-Quantity |
| - | I-Quantity |
| hours | I-Quantity |
| yearly | O |
| ( | O |
| see | O |
| Figure | O |
| 2 | O |
| ) | O |
| . | O |
Model details
- Base Model: distilroberta-base-climate-f
- Tokenizer: distilroberta-base-climate-f
- Parameters: 82M
Fine-tuning data
The model was first fine-tuned on non-curated examples from a filtered variant of Wiki-Quantities and subsequently on a combination of datasets for quantity span identification, including:
- Wiki-Quantities (small variant, curated examples only)
- SOFC-Exp (relabeled)
- Grobid-quantities (relabeled)
- MeasEval (relabeled)
- Custom quinex data
Evaluation results
Evaluation results on the test set as described in the paper:
| F1 | Precision | Recall | Accuracy |
|---|---|---|---|
| 94.56 | 93.92 | 95.21 | 99.15 |
Note that here we report the scores of this specific checkpoint, which slightly differ from the scores averaged over multiple seeds reported in the paper.
Also, note that these scores do not account for alternative correct answers (e.g., '1.2 kW and 1.4 kW' could be labeled as a list or individually) or debatable cases (e.g., whether 'bi-layer' or 'quartet' should be considered a quantity). Counting these as correct results in higher scores.
For better performance, refer to the larger quinex-quantity-v0-124M variant.
Citation
If you use this model in your research, please cite the following paper:
@article{quinex2025,
title = {{Quinex: Quantitative Information Extraction from Text using Open and Lightweight LLMs}},
author = {Göpfert, Jan and Kuckertz, Patrick and Müller, Gian and Lütz, Luna and Körner, Celine and Khuat, Hang and Stolten, Detlef and Weinand, Jann M.},
month = okt,
year = {2025},
}
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2
- Datasets 2.16.1
- Tokenizers 0.15.0