A modular implementation of PPO, and soon hopefully other algorithms.
structured outputs for llms
State-of-the-art NLP through transformer models in a modular design and consistent APIs.
Software Architecture for ML engineers
Training (hopefully) safe agents in gridworlds
Creating Artificial Life with Reinforcement Learning
A server for multilanguage, composable NLP API in Python
Configuration with Dataclasses+YAML+Argparse. Fork of Pyrallis
Reinforcement Learning in PyTorch
Official Python SDK for Kern AI refinery.
Pytest guide for unittest users
Robust policy search algorithms which train on model ensembles
Structured and typehinted GPT responses in Python
Conditional Transformer Language Model for Controllable Generation
My python journey
A lightweight evaluation suite tailored specifically for assessing Indic LLMs across a diverse ra...