young-geng / mintext
Minimal but scalable implementation of large language models in JAX
☆17Updated 3 weeks ago
Related projects: ⓘ
- ☆65Updated 2 months ago
- ☆48Updated 3 months ago
- ☆28Updated this week
- JAX reimplementation of the DeepMind paper "Genie: Generative Interactive Environments"☆27Updated last week
- ☆24Updated 2 weeks ago
- An Open-Ended Agentic Simulator☆17Updated last month
- JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)☆19Updated 3 months ago
- Implementation of Direct Preference Optimization☆16Updated last year
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆35Updated last month
- ☆23Updated 10 months ago
- ☆30Updated this week
- A simple library for scaling up JAX programs☆116Updated last month
- ☆14Updated last month
- Dateset Reset Policy Optimization☆27Updated 5 months ago
- ☆27Updated this week
- Rewarded soups official implementation☆43Updated 11 months ago
- Accelerated replay buffers in JAX☆39Updated 2 years ago
- ☆23Updated 4 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆73Updated 2 months ago
- ☆25Updated this week
- Building blocks for productive research☆44Updated last week
- ☆17Updated 3 months ago
- Open source code for paper "Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning" ICML 2023☆42Updated 4 months ago
- This is code for most of the experiments in the paper Understanding the Effects of RLHF on LLM Generalisation and Diversity☆35Updated 8 months ago
- A minimal home grid world environment to evaluate language understanding in interactive agents.☆19Updated last year
- If it quacks like a tensor...☆48Updated 7 months ago
- Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"☆84Updated 5 months ago
- Official codebase for "The Generalization Gap in Offline Reinforcement Learning" accepted to ICLR 2024☆26Updated last month
- ☆33Updated last year
- ☆42Updated 7 months ago