conflibertR
Inference and Fine-Tuning with 'ConfliBERT' Conflict Text Models
An interface to 'ConfliBERT', a pretrained language model for analyzing text about conflict and political violence (Hu et al. (2022) <doi:10.18653/v1/2022.naacl-main.400>). Provides functions for named entity recognition, binary and multilabel classification, and question answering, plus tools to fine-tune custom classifiers, compare several base model architectures, and run an interactive active-learning loop for efficiently labeling new data. Models are downloaded from 'Hugging Face' and run through the 'transformers' library for 'Python' via the 'reticulate' package.
Versions across snapshots
| Version | Repository | File | Size |
|---|---|---|---|
0.5.3 |
rolling linux/jammy R-4.5 | conflibertR_0.5.3.tar.gz |
480.7 KiB |
0.5.3 |
rolling linux/noble R-4.5 | conflibertR_0.5.3.tar.gz |
480.7 KiB |
0.5.3 |
rolling source/ R- | conflibertR_0.5.3.tar.gz |
339.3 KiB |
0.5.3 |
latest linux/jammy R-4.5 | conflibertR_0.5.3.tar.gz |
480.7 KiB |
0.5.3 |
latest linux/noble R-4.5 | conflibertR_0.5.3.tar.gz |
480.7 KiB |
0.5.3 |
latest source/ R- | conflibertR_0.5.3.tar.gz |
339.3 KiB |
0.5.3 |
2026-04-23 source/ R- | conflibertR_0.5.3.tar.gz |
0 B |
Dependencies (latest)
Imports
- cli
- reticulate (>= 1.34)
- tibble