rgreenblatt / arc_draw_more_samples_pub
Draw more samples
☆185Updated 7 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
- Bootstrapping ARC☆94Updated 2 months ago
- The history files when recording human interaction while solving ARC tasks☆96Updated this week
- Reverse Engineering the Abstraction and Reasoning Corpus☆219Updated 3 months ago
- Domain Specific Language for the Abstraction and Reasoning Corpus☆233Updated 3 months ago
- ☆82Updated 3 weeks ago
- ☆98Updated last month
- ☆54Updated 3 weeks ago
- ☆25Updated 9 months ago
- METR Task Standard☆137Updated 3 weeks ago
- Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"☆285Updated 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…☆163Updated this week
- Repository for the paper Stream of Search: Learning to Search in Language☆125Updated 5 months ago
- Extract full next-token probabilities via language model APIs☆229Updated 11 months ago
- Simple Transformer in Jax☆130Updated 7 months ago
- ☆117Updated last week
- smolLM with Entropix sampler on pytorch☆148Updated 2 months ago
- My writings about ARC (Abstraction and Reasoning Corpus)☆64Updated 2 weeks ago
- Long context evaluation for large language models☆198Updated this week
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆176Updated last month
- OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.☆158Updated 2 weeks ago
- Sparse autoencoders☆414Updated last week
- Mechanistic Interpretability Visualizations using React☆223Updated last month
- ☆249Updated 6 months ago
- Materials for ConceptARC paper☆85Updated 2 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆183Updated 8 months ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆75Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆177Updated last month
- Our solution for the arc challenge 2024☆89Updated last month
- ☆92Updated last year