-
University of Illinois at Urbana–Champaign
- Urbana, Illinois
- https://xiaoyang-wang.github.io
Stars
RewardBench: the first evaluation tool for reward models.
DSPy: The framework for programming—not prompting—foundation models
Minimalistic large language model 3D-parallelism training
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
An Easy-to-use, Scalable and High-performance RLHF Framework (70B+ PPO Full Tuning & Iterative DPO & LoRA & Mixtral)
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.
pickleDB is an open source key-value store using Python's json module.
Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.
Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)
Robust recipes to align language models with human and AI preferences
Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Curated list of data science interview questions and answers
Machine Learning and Computer Vision Engineer - Technical Interview Questions
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
Development repository for the Triton language and compiler
[ICLR 2023 Spotlight] Code release for "Dirichlet-based Uncertainty Calibration for Active Domain Adaptation"