p-doom / jasmineLinks
A simple, performant and scalable JAX-based world modeling codebase
☆70Updated this week
Alternatives and similar repositories for jasmine
Users that are interested in jasmine are comparing it to the libraries listed below
Sorting:
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆105Updated 11 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆131Updated last year
- ☆115Updated 2 months ago
- Minimal but scalable implementation of large language models in JAX☆35Updated last month
- 📄Small Batch Size Training for Language Models☆43Updated last week
- JAX implementation of VQVAE/VQGAN autoencoders (+FSQ)☆34Updated last year
- ☆31Updated 9 months ago
- ☆44Updated last month
- ☆101Updated last week
- Synchronized Curriculum Learning for RL Agents☆111Updated this week
- Implementation of PSGD optimizer in JAX☆34Updated 7 months ago
- A simple library for scaling up JAX programs☆143Updated 9 months ago
- Efficient baselines for autocurricula in JAX.☆194Updated last year
- Train vision models using JAX and 🤗 transformers☆98Updated this week
- ☆87Updated last year
- TPU pod commander is a package for managing and launching jobs on Google Cloud TPU pods.☆20Updated last year
- OMNI-EPIC: Open-endedness via Models of human Notions of Interestingness with Environments Programmed in Code (ICLR 2025).☆67Updated 8 months ago
- ☆53Updated last year
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning - - — ICLR 2025☆78Updated 6 months ago
- Focused on fast experimentation and simplicity☆76Updated 8 months ago
- Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models☆63Updated 6 months ago
- GPT implementation in Flax☆18Updated 3 years ago
- Code for the paper "Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making"☆27Updated last year
- OMNI: Open-endedness via Models of human Notions of Interestingness☆55Updated 7 months ago
- JAX Implementation of Black Forest Labs' Flux.1 family of models☆35Updated 2 weeks ago
- A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks☆35Updated 9 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆93Updated 5 months ago
- Unofficial but Efficient Implementation of "Mamba: Linear-Time Sequence Modeling with Selective State Spaces" in JAX☆87Updated last year
- Code for the paper "Function-Space Learning Rates"☆23Updated 2 months ago
- ☆13Updated last year