amjadmajid / BabyTorch
BabyTorch is a minimalist deep-learning framework with a similar API to PyTorch. This minimalist design encourages learners explore and understand the underlying algorithms and mechanics of deep learning processes. It is design such that when learners are ready to switch to PyTorch they only need to remove the word `baby`.
☆27Updated 8 months ago
Alternatives and similar repositories for BabyTorch:
Users that are interested in BabyTorch are comparing it to the libraries listed below
- fast + parallel AlphaZero in JAX☆90Updated 3 weeks ago
- A set of Python scripts that makes your experience on TPU better☆44Updated 6 months ago
- Cost aware hyperparameter tuning algorithm☆138Updated 6 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆43Updated last month
- ☆201Updated 6 months ago
- ☆146Updated last month
- Minimal but scalable implementation of large language models in JAX☆28Updated 2 months ago
- Efficient World Models with Context-Aware Tokenization. ICML 2024☆89Updated 3 months ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆81Updated last year
- List of companies/universities lab that might offers Internships in the Reinforcement Learning field☆23Updated 8 months ago
- Our solution for the arc challenge 2024☆84Updated last month
- Accelerated minigrid environments with JAX☆127Updated 5 months ago
- Simple single-file baselines for Q-Learning in pure-GPU setting☆133Updated last month
- ☆71Updated 2 months ago
- Implementation of Soft Actor Critic and some of its improvements in Pytorch☆51Updated 3 weeks ago
- Implementation of Diffusion Transformer (DiT) in JAX☆261Updated 7 months ago
- WIP☆92Updated 5 months ago
- Gradient Boosting Reinforcement Learning (GBRL)☆95Updated last month
- supporting pytorch FSDP for optimizers☆75Updated last month
- 🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX☆51Updated last year
- Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new…☆119Updated 5 months ago
- A Gymnasium-based Environment of the Abstraction and Reasoning Corpus (ARC)☆62Updated 4 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆121Updated 9 months ago
- A simple library for scaling up JAX programs☆129Updated 2 months ago
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning☆60Updated 5 months ago
- ☆177Updated last month
- Solve puzzles. Learn CUDA.☆61Updated last year
- ☆413Updated 3 months ago
- seqax = sequence modeling + JAX☆136Updated 6 months ago
- JAX implementation of RL algorithms and vectorized environments☆38Updated last year