ironbar / arc24
Create an AI capable of solving reasoning tasks it has never seen before
☆16Updated last week
Related projects ⓘ
Alternatives and complementary repositories for arc24
- Our solution for the arc challenge 2024☆32Updated last week
- Collection of autoregressive model implementation☆67Updated this week
- Multiple datasets for ARC (Abstraction and Reasoning Corpus)☆39Updated last week
- ☆10Updated last week
- Muon optimizer for neural networks: >30% extra sample efficiency, <3% wallclock overhead☆113Updated this week
- An introduction to LLM Sampling☆64Updated 2 weeks ago
- Textbook on reinforcement learning from human feedback☆76Updated 3 weeks ago
- Evaluation of neuro-symbolic engines☆33Updated 3 months ago
- ☆43Updated 2 months ago
- A python framework to streamline your ARC challenge solutions. From graphical displays to optimized Kaggle submissions☆11Updated last month
- ☆35Updated 2 weeks ago
- PyTorch Implementation of the paper "Towards Learning Abductive Reasoning using VSA Distributed Representations".☆12Updated 3 months ago
- A set of Python scripts that makes your experience on TPU better☆40Updated 4 months ago
- ☆15Updated last month
- Code for NeurIPS LLM Efficiency Challenge☆54Updated 7 months ago
- Bootstrapping ARC☆65Updated this week
- ☆36Updated this week
- ☆115Updated 3 weeks ago
- code for training & evaluating Contextual Document Embedding models☆117Updated last week
- ☆76Updated 7 months ago
- Explorations into the proposal from the paper "Grokfast, Accelerated Grokking by Amplifying Slow Gradients"☆85Updated 2 months ago
- ☆53Updated 10 months ago
- Fast, Modern, Memory Efficient, and Low Precision PyTorch Optimizers☆58Updated 4 months ago
- ARC gym: a data generation framework for the Abstraction & Reasoning Corpus☆17Updated last month
- Draw more samples☆179Updated 4 months ago
- ☆27Updated 4 months ago
- Jax like function transformation engine but micro, microjax☆26Updated 3 weeks ago
- ☆41Updated 2 weeks ago
- Large scale 4D parallelism pre-training for 🤗 transformers in Mixture of Experts *(still work in progress)*☆80Updated 11 months ago
- Normalized Transformer (nGPT)☆66Updated this week