tech-srl / RASP-exps
Code for running the transformers in the ICML 2021 paper "Thinking Like Transformers"
☆16Updated 3 years ago
Related projects: ⓘ
- Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"☆58Updated 2 years ago
- Language-annotated Abstraction and Reasoning Corpus☆76Updated last year
- ☆44Updated 2 years ago
- My writings about ARC (Abstraction and Reasoning Corpus)☆55Updated 3 weeks ago
- One stop shop for all things carp☆58Updated 2 years ago
- Implementing RASP transformer programming language https://arxiv.org/pdf/2106.06981.pdf.☆42Updated 3 years ago
- Serialize JAX, Flax, Haiku, or Objax model params with 🤗`safetensors`☆41Updated 3 months ago
- A dataset of alignment research and code to reproduce it☆68Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆88Updated 2 years ago
- A programming language for formal/informal computation.☆39Updated 3 months ago
- Materials for ConceptARC paper☆71Updated 4 months ago
- ☆38Updated last year
- Mechanistic Interpretability for Transformer Models☆48Updated 2 years ago
- ☆56Updated 2 years ago
- Resources from the EleutherAI Math Reading Group☆50Updated 2 months ago
- Latent Diffusion Language Models☆66Updated last year
- Swarm training framework using Haiku + JAX + Ray for layer parallel transformer language models on unreliable, heterogeneous nodes☆236Updated last year
- An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"☆279Updated this week
- See the issue board for the current status of active and prospective projects!☆65Updated 2 years ago
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)☆184Updated 2 years ago
- Automatically take good care of your preemptible TPUs☆28Updated last year
- Reverse Engineering the Abstraction and Reasoning Corpus☆130Updated last month
- Official repository for the paper "A Modern Self-Referential Weight Matrix That Learns to Modify Itself" (ICML 2022 & NeurIPS 2021 Deep R…☆168Updated 9 months ago
- RWKV model implementation☆38Updated last year
- ☆23Updated last year
- A case study of efficient training of large language models using commodity hardware.☆68Updated 2 years ago
- minGPT in JAX☆45Updated 2 years ago
- Probabilistic LLM evaluations. [CogSci2023; ACL2023]☆72Updated last month
- ☆85Updated this week
- Utilities for the HuggingFace transformers library☆55Updated last year