neoneye / ARC-Interactive-History-DatasetLinks
The history files when recording human interaction while solving ARC tasks
☆116Updated this week
Alternatives and similar repositories for ARC-Interactive-History-Dataset
Users that are interested in ARC-Interactive-History-Dataset are comparing it to the libraries listed below
Sorting:
- Draw more samples☆194Updated last year
- My writings about ARC (Abstraction and Reasoning Corpus)☆84Updated last month
- Simple Transformer in Jax☆139Updated last year
- Tools for working with the Abstraction & Reasoning Corpus☆208Updated last month
- Domain Specific Language for the Abstraction and Reasoning Corpus☆299Updated 11 months ago
- Reverse Engineering the Abstraction and Reasoning Corpus☆306Updated 7 months ago
- ☆124Updated 9 months ago
- Reasoning Computers. Lambda Calculus, Fully Differentiable. Also Neural Stacks, Queues, Arrays, Lists, Trees, and Latches.☆274Updated 11 months ago
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆98Updated last week
- Code for 1st place solution to Kaggle's Abstraction and Reasoning Challenge☆161Updated 2 months ago
- MiniHF is an inference, human preference data collection, and fine-tuning tool for local language models. It is intended to help the user…☆181Updated 2 months ago
- ☆142Updated last month
- Materials for ConceptARC paper☆103Updated 11 months ago
- A puzzle to learn about prompting☆135Updated 2 years ago
- ☆104Updated 2 weeks ago
- Learning Universal Predictors☆79Updated last year
- Our solution for the arc challenge 2024☆179Updated 3 months ago
- An interactive exploration of Transformer programming.☆269Updated last year
- Aidan Bench attempts to measure <big_model_smell> in LLMs.☆312Updated 3 months ago
- ☆188Updated last month
- Code for the Fractured Entangled Representation Hypothesis position paper!☆199Updated 4 months ago
- ☆123Updated last year
- ☆97Updated 2 months ago
- Plotting (entropy, varentropy) for small LMs☆98Updated 4 months ago
- Minimalistic, extremely fast, and hackable researcher's toolbench for GPT models in 307 lines of code. Reaches <3.8 validation loss on wi…☆348Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- smol models are fun too☆93Updated 10 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.☆173Updated 2 years ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆213Updated 10 months ago