Feature Extraction
Transformers
Safetensors
English
enoki-openie
openie
open-information-extraction
information-extraction
triplet-extraction
relation-extraction
modernbert
enoki
igl
custom_code
Instructions to use s-nlp/enoki-openie-encoder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use s-nlp/enoki-openie-encoder with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="s-nlp/enoki-openie-encoder", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("s-nlp/enoki-openie-encoder", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Add repository link and citation
Browse files
README.md
CHANGED
|
@@ -22,6 +22,8 @@ tags:
|
|
| 22 |
Enoki OpenIE Encoder is a ModernBERT-based Iterative Grid Labeling model for
|
| 23 |
extracting subject–relation–object triples from English sentences.
|
| 24 |
|
|
|
|
|
|
|
| 25 |
## Installation
|
| 26 |
|
| 27 |
```bash
|
|
@@ -90,3 +92,19 @@ python inference.py \
|
|
| 90 |
when a smaller, higher-precision result set is preferred.
|
| 91 |
- Loading requires `trust_remote_code=True` because the IGL architecture and
|
| 92 |
OpenIE decoder are custom Transformers code included in this repository.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
Enoki OpenIE Encoder is a ModernBERT-based Iterative Grid Labeling model for
|
| 23 |
extracting subject–relation–object triples from English sentences.
|
| 24 |
|
| 25 |
+
Source code: [s-nlp/Enoki](https://github.com/s-nlp/Enoki)
|
| 26 |
+
|
| 27 |
## Installation
|
| 28 |
|
| 29 |
```bash
|
|
|
|
| 92 |
when a smaller, higher-precision result set is preferred.
|
| 93 |
- Loading requires `trust_remote_code=True` because the IGL architecture and
|
| 94 |
OpenIE decoder are custom Transformers code included in this repository.
|
| 95 |
+
|
| 96 |
+
## Citation
|
| 97 |
+
|
| 98 |
+
If you use Enoki in your research, please cite:
|
| 99 |
+
|
| 100 |
+
```bibtex
|
| 101 |
+
@misc{rykov2026enokiefficientmultilevelhallucination,
|
| 102 |
+
title = {Enoki: Efficient Multi-Level Hallucination Detection},
|
| 103 |
+
author = {Elisei Rykov and Timur Ionov and Nikolay Ivanov and Maksim Savkin and Maksim Makarenko and Alexander Panchenko and Vasily Konovalov and Julia Belikova},
|
| 104 |
+
year = {2026},
|
| 105 |
+
eprint = {2609.00581},
|
| 106 |
+
archivePrefix = {arXiv},
|
| 107 |
+
primaryClass = {cs.CL},
|
| 108 |
+
url = {https://arxiv.org/abs/2609.00581},
|
| 109 |
+
}
|
| 110 |
+
```
|