6 projects
thinkpack
A framework for training, parsing, and evaluating explicit reasoning models — focused on reasoning collapse.
llm-codegen-research
Useful classes and methods for researching code-generation by LLMs.
libhallubench
Library Hallucinations Adversarial Benchmark — evaluate LLM code generation for hallucinated libraries.
github-issue-prompter
Use AI to find GitHub issue's that you can work on (even if the issue's appear active)!
jldc
Simplify using JSONLines files alongside dataclasses.
sonora
A WSGI and ASGI compatible grpc-web implementation.
