The AI Code Editor

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

The code and data for "MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark" [NeurIPS 2024]

Aidan Bench attempts to measure <big_model_smell> in LLMs.

Orbax provides common checkpointing and persistence utilities for JAX users

Recipes to scale inference-time compute of open models

Large Context Attention

Tools for merging pretrained large language models.

Python logging made (stupidly) simple

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

A bibliography and survey of the papers surrounding o1

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

aider is AI pair programming in your terminal

Minimal transformer for arbtirary data (i.e. bio stuff!)

An extremely fast Python package and project manager, written in Rust.

A plotting tool that outputs Line Rider maps, so you can watch a man on a sled scoot down your loss curves. 🎿

Official inference repo for FLUX.1 models

A set of Python scripts that makes your experience on TPU better

TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.

Minimal but scalable implementation of large language models in JAX

Read Google Cloud Storage, Azure Blobs, and local paths with the same interface

Turn jitted jax functions back into python source code

SWE-bench [Multimodal]: Can Language Models Resolve Real-world Github Issues?

lightweight, standalone C++ inference engine for Google's Gemma models.