avnishn

ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

llm.c

LLM training in simple, raw C/CUDA

mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

llama-dl

High-speed download of LLaMA, Facebook's 65B parameter GPT model

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

garage

A toolkit for reproducible reinforcement learning research.

Metaworld

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

deep_learning_curriculum

Language model alignment-focused deep learning curriculum

ray-llm

RayLLM - LLMs on Ray

rliable

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

llmperf

LLMPerf is a library for validating and benchmarking LLMs

machine-learning-specialization-andrew-ng

A collection of notes and implementations of machine learning algorithms from Andrew Ng's machine learning specialization.

mtrl

Multi Task RL Baselines

EasyReinforcementLearning

EasyRL: An easy-to-use and comprehensive reinforcement learning package.

MirageStock

Open-Source Implementations of Multi-Modal Diffusion Models Optimized for Highest Quality and Ease of Use

hash-hop

Long context evaluation for large language models

minimal-stable-PPO

A minimal and stable PPO.

raylab

Reinforcement learning algorithms in RLlib

sapg

Code for SAPG: Split and Aggregate Policy Gradients (ICML 2024)

Betha

language-world

soccerprojects

My adventures exploring soccer data analysis

hebi