mvakde / mdlARCLinks
Stupid test to check whether MDL principles improve ARC performance
☆77Updated this week
Alternatives and similar repositories for mdlARC
Users that are interested in mdlARC are comparing it to the libraries listed below
Sorting:
- an open source reproduction of NVIDIA's nGPT (Normalized Transformer with Representation Learning on the Hypersphere)☆109Updated 10 months ago
- Jax Codebase for Evolutionary Strategies at the Hyperscale☆216Updated last month
- ☆214Updated 3 weeks ago
- Build your own visual reasoning model☆417Updated last week
- Simple Transformer in Jax☆142Updated last year
- ☆134Updated last year
- ☆93Updated this week
- Gradient descent is cool and all, but what if we could delete it?☆106Updated 5 months ago
- ☆166Updated 5 months ago
- Our solution for the arc challenge 2024☆187Updated 7 months ago
- Getting crystal-like representations with harmonic loss☆195Updated 9 months ago
- rl from zero pretrain, can it be done? yes.☆286Updated 3 months ago
- Curated collection of community environments☆205Updated this week
- ☆67Updated 6 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆198Updated last year
- The history files when recording human interaction while solving ARC tasks☆117Updated this week
- Plotting (entropy, varentropy) for small LMs☆99Updated 8 months ago
- smolLM with Entropix sampler on pytorch☆149Updated last year
- Modular, scalable library to train ML models☆191Updated last week
- Bootstrapping ARC☆154Updated last year
- ☆115Updated 3 months ago
- Implementation of SOAR☆48Updated 4 months ago
- NanoGPT-speedrunning for the poor T4 enjoyers☆73Updated 9 months ago
- Simple & Scalable Pretraining for Neural Architecture Research☆306Updated last month
- MoE training for Me and You and maybe other people☆327Updated 3 weeks ago
- Code for ExploreTom☆90Updated 7 months ago
- PyTorch Code for Energy-Based Transformers paper -- generalizable reasoning and scalable learning☆577Updated 2 months ago
- look how they massacred my boy☆63Updated last year
- Attention Kernels for Symmetric Power Transformers☆128Updated 4 months ago
- Library for text-to-text regression, applicable to any input string representation and allows pretraining and fine-tuning over multiple r…☆312Updated last month