🎨 NeMo Data Designer: A general library for generating high-quality synthetic data from scratch or based on seed data.

An Awesome list of curated DSPy resources.

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

SLiM: One-shot Quantized Sparse Plus Low-rank Approximation of LLMs (ICML 2025)

Use Hugging Face with JavaScript

Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Fast Semantic Text Deduplication

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

Lightweight Nearest Neighbors with Flexible Backends

Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

🪢 Langfuse Python SDK - Instrument your LLM app with decorators or low-level SDK and get detailed tracing/observability. Works with any LLM or framework

A collection of LogitsProcessors to customize and enhance LLM behavior for specific tasks.

Open-source AI cookbook

🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…

[NeurIPS 2023] ImageReward: Learning and Evaluating Human Preferences for Text-to-image Generation

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

A course on aligning smol models.

Public repo for HF blog posts

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.