LogiTorch is a PyTorch-based library designed for logical reasoning on natural language, featuring various textual logical reasoning datasets and implementations of logical reasoning neural architectures. It offers a simple and clean API for use with PyTorch Lightning. Installation is straightforward via pip, with examples provided for training, testing, and using pre-configured pipelines. The library supports numerous datasets such as AR-LSAT, ConTRoL, LogiQA, and models including RuleTaker, ProofWriter, and BERTNOT. Users are encouraged to cite both LogiTorch and the original data sources when publishing results. The project recognizes partial funding by ANR-20-CHIA-0012-01 ("NoRDF").
• textual logical reasoning datasets
• pre-configured training pipelines
• installation via pip
• implementations of logical reasoning neural architectures
• simple and clean api for pytorch lightning
• supports various models
Average Rating: 0.0
5 Stars:
0 Ratings
4 Stars:
0 Ratings
3 Stars:
0 Ratings
2 Stars:
0 Ratings
1 Star:
0 Ratings
No ratings available.
Create spooky beats online with this unique musical game featuring character-based sound mixing.
View Details