Stars
KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems
A bibliography and survey of the papers surrounding o1
Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.
DSPy: The framework for programming—not prompting—language models
Embedding Recycling for Language models
Source codes for the paper "Examining the Ordering of Rhetorical Strategies in Persuasive Requests"
Python toolbox to evaluate graph vulnerability and robustness (CIKM 2021)
Visualization Tool for Mapping Out Researchers using Natural Language Processing