rgreenblatt / arc_draw_more_samples_pub
Draw more samples
☆186Updated 8 months ago
Alternatives and similar repositories for arc_draw_more_samples_pub:
Users that are interested in arc_draw_more_samples_pub are comparing it to the libraries listed below
- Reverse Engineering the Abstraction and Reasoning Corpus☆233Updated last week
- Domain Specific Language for the Abstraction and Reasoning Corpus☆237Updated 4 months ago
- Bootstrapping ARC☆102Updated 3 months ago
- The history files when recording human interaction while solving ARC tasks☆97Updated last week
- Extract full next-token probabilities via language model APIs☆231Updated last year
- ☆100Updated 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…☆165Updated this week
- Repository for the paper Stream of Search: Learning to Search in Language☆138Updated last month
- Simple Transformer in Jax☆136Updated 8 months ago
- Our solution for the arc challenge 2024☆105Updated this week
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆295Updated 3 months ago
- ☆122Updated 2 weeks ago
- ☆60Updated last month
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆186Updated 9 months ago
- ☆84Updated last month
- Mechanistic Interpretability Visualizations using React☆235Updated 2 months ago
- Sparsify transformers with SAEs and transcoders☆476Updated this week
- Long context evaluation for large language models☆200Updated last week
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆99Updated 3 months ago
- METR Task Standard☆142Updated last month
- Materials for ConceptARC paper☆88Updated 3 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆183Updated 3 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆183Updated 2 months ago
- My writings about ARC (Abstraction and Reasoning Corpus)☆68Updated this week
- A library for making RepE control vectors☆552Updated last month
- Multiple datasets for ARC (Abstraction and Reasoning Corpus)☆51Updated last week
- Latent Program Network (from the "Searching Latent Program Spaces" paper)☆61Updated 3 months ago
- Comprehensive analysis of difference in performance of QLora, Lora, and Full Finetunes.☆82Updated last year
- A puzzle to learn about prompting☆124Updated last year