zhixuan-lin

zhixuan-lin's Stars

• OpenNLPLab/HGRN

  [NeurIPS 2023 spotlight] Official implementation of HGRN in our NeurIPS 2023 paper - Hierarchically Gated Recurrent Neural Network for Sequence Modeling

  Language:Python614

• corl-team/xland-minigrid

  JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️

  Language:Python19415

• NicolasZucchet/Online-learning-LR-dependencies

  Implementation of the "Online learning of long-range dependencies" paper, NeurIPS 2023

  Language:Python111

• BartoszJarocki/cv

  Print-friendly, minimalist CV page

  Language:TypeScript8.9k970

• instadeepai/flashbax

  ⚡ Flashbax: Accelerated Replay Buffers in JAX

  Language:Python20410

• johnma2006/mamba-minimal

  Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

  Language:Python2.6k190

• practical-tutorials/project-based-learning

  Curated list of project-based tutorials

  202k26.4k

• hristo-vrigazov/mmap.ninja

  Memory mapped numpy arrays of varying shapes

  Language:Python28311

• jurgisp/pydreamer

  PyTorch implementation of DreamerV2 model-based RL algorithm

  Language:Python20847

• state-spaces/mamba

  Mamba SSM architecture

  Language:Python13k1.1k

• brett-daley/trajectory-aware-etraces

  ICML 2023: Trajectory-Aware Eligibility Traces for Off-Policy Reinforcement Learning. https://arxiv.org/abs/2301.11321

  Language:Python1

• facebookresearch/motif

  Intrinsic Motivation from Artificial Intelligence Feedback

  Language:Python11814

• NM512/dreamerv3-torch

  Implementation of Dreamer v3 in pytorch.

  Language:Python40892

• stas00/ml-engineering

  Machine Learning Engineering Open Book

  Language:Python11.5k697

• karpathy/nn-zero-to-hero

  Neural Networks: Zero to Hero

  Language:Jupyter Notebook11.8k1.5k

• UT-Austin-RPL/amago

  a simple and scalable agent for training adaptive policies with sequence-based RL

  Language:Python884

• 01-ai/Yi

  A series of large language models trained from scratch by developers @01-ai

  Language:Jupyter Notebook7.7k475

• luchris429/popjaxrl

  Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]

  Language:Python8412

• state-spaces/s4

  Structured state space sequence models

  Language:Jupyter Notebook2.4k292

• lindermanlab/S5

  Language:Python25644

• vwxyzjn/cleanba

  CleanRL's implementation of DeepMind's Podracer Sebulba Architecture for Distributed DRL

  Language:Python10511

• eureka-research/Eureka

  Official Repository for "Eureka: Human-Level Reward Design via Coding Large Language Models" (ICLR 2024)

  Language:Jupyter Notebook2.8k255

• cpacker/MemGPT

  Letta (fka MemGPT) is a framework for creating stateful LLM services.

  Language:Python12k1.3k

• bstadie/krazyworld

  krazy grid world

  Language:Python243

• PWhiddy/PokemonRedExperiments

  Playing Pokemon Red with Reinforcement Learning

  Language:Jupyter Notebook6.9k633

• NicolasZucchet/minimal-LRU

  Non official implementation of the Linear Recurrent Unit (LRU, Orvieto et al. 2023)

  Language:Python484

• BlinkDL/RWKV-LM

  RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

  Language:Python12.6k859

• Hannibal046/RWKV-howto

  possibly useful materials for learning RWKV language model.

  252

• RulinShao/LightSeq

  Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

  Language:Python1959

• luchris429/purejaxrl

  Really Fast End-to-End Jax RL Implementations

  Language:Python70060