irregular-rhomboid / EAI-Math-Reading-GroupLinks
Resources from the EleutherAI Math Reading Group
β54Updated 10 months ago
Alternatives and similar repositories for EAI-Math-Reading-Group
Users that are interested in EAI-Math-Reading-Group are comparing it to the libraries listed below
Sorting:
- π§ Starter templates for doing interpretability researchβ76Updated 2 years ago
- An interactive exploration of Transformer programming.β271Updated 2 years ago
- Neural Networks and the Chomsky Hierarchyβ213Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paperβ132Updated 3 years ago
- Erasing concepts from neural representations with provable guaranteesβ242Updated 11 months ago
- A puzzle to learn about promptingβ135Updated 2 years ago
- git extension for {collaborative, communal, continual} model developmentβ217Updated last year
- Code associated to papers on superposition (in ML interpretability)β35Updated 3 years ago
- β167Updated 2 years ago
- Train very large language models in Jax.β210Updated 2 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.β181Updated 6 months ago
- β287Updated last year
- LoRA for arbitrary JAX models and functionsβ143Updated last year
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"β81Updated 3 years ago
- Functional local implementations of main model parallelism approachesβ95Updated 2 years ago
- JAX implementation of the Llama 2 modelβ215Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic taskβ198Updated 2 years ago
- Tools for working with the Abstraction & Reasoning Corpusβ213Updated 4 months ago
- Understand and test language model architectures on synthetic tasks.β248Updated 3 months ago
- HomebrewNLP in JAX flavour for maintable TPU-Trainingβ51Updated last year
- Extract full next-token probabilities via language model APIsβ248Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)β198Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)β189Updated 3 years ago
- Puzzles for exploring transformersβ382Updated 2 years ago
- See the issue board for the current status of active and prospective projects!β65Updated 3 years ago
- β63Updated 3 years ago
- Large scale 4D parallelism pre-training for π€ transformers in Mixture of Experts *(still work in progress)*β86Updated 2 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.β216Updated 3 weeks ago
- Tools for studying developmental interpretability in neural networks.β122Updated 2 weeks ago
- Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inferenceβ¦β216Updated 7 months ago