This is your work, valued
Professional RL(VR) hyperparameter tuner
openchat. OpenChat: Advancing Open-source Language Models with Imperfect Data
5.5kopenchat-ui. An open source UI for OpenChat models
289multipack. Multipack distributed sampler for fast padding-free training of LLMs
207autonomous_driving_mpc. Model Predictive Controller for Autonomous Driving implemented using ROS and C++
104EvolvingConnectivity. Code for paper Evolving Connectivity for Spiking Neural Networks
22onerl. One RL Platform is all you need -- Event-driven fully distributed reinforcement learning framework
21mistral-tokenizer. JavaScript
20bf16_fused_adam. BFloat16 Fused Adam Operator for PyTorch
20RSP_JAX. [AAAI'25 Oral] Are Expressive Models Truly Necessary for Offline RL?
15carla_env. CARLA Sim2Real Environment
9transformers-pangu. Pangu-Alpha for Transformers
8Adams. Adams Optimizer for Stable and Scalable Training
8cutlass_grouped_gemm. PyTorch bindings for CUTLASS grouped GEMM.
7xrl-script. Efficient AutoRL script for any framework
6paper.io. Paper.io Server & Client Implementation
5adam-atan2. Fused Adam-atan2 implementation
5xrl-ppo. Automated & super fast PyTorch deep reinforcement learning platform for autonomous driving
5tea-dev. OneHoldsThree
4one-typecho. A Advanced PHP Blogging Platform. Fast & Powerful (Modified from Typecho)
4ijudge. Simple & Fast OI Judging Software
3transformers. 🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
3chain-of-thought-hub. Benchmarking large language models' complex reasoning ability with chain-of-thought prompting
2open_sharegpt. ShareGPT with Explore reopened
2mlc-llm. Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
2MBRL. Model-based Reinforcement Learning Framework
2CarZero. Reinforcement Learning Autonomous Driving with zero rules & prior
2brax. Massively parallel rigidbody physics simulation on accelerator hardware.
2CarZeroRecorder. Data recorder for offline RL
2d4rl. A benchmark for offline reinforcement learning.
2jax-docker. Dockerfile
1pytorch-docker. Dockerfile
1arc-agi-challenge-data.
1FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
1megablocks. Python
1