Stars
Apache Hamilton helps data scientists and engineers define testable, modular, self-documenting dataflows, that encode lineage/tracing and metadata. Runs and scales everywhere python does.
Simple Workflow Framework - Hamilton + Task Queue (RQ or APScheduler) = FlowerPower
geonamescache - a Python library for quick access to a subset of GeoNames data.
ETL, Analytics, Versioning for Unstructured Data
DSPy: The framework for programming—not prompting—language models
📁 Generate pixel-perfect macOS folder icons in the native style. (Now with support for macOS 26 Tahoe!)
Open Machine Learning course
[ICLR2024 spotlight] OmniQuant is a simple and powerful quantization technique for LLMs.
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.