irregular-rhomboid / EAI-Math-Reading-GroupLinks
Resources from the EleutherAI Math Reading Group
☆54Updated 8 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:
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"☆79Updated 3 years ago
- A puzzle to learn about prompting☆134Updated 2 years ago
- 🧠 Starter templates for doing interpretability research☆75Updated 2 years ago
- An interactive exploration of Transformer programming.☆271Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆239Updated 9 months ago
- git extension for {collaborative, communal, continual} model development☆215Updated last year
- ☆166Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆130Updated 3 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆172Updated 4 months ago
- Functional local implementations of main model parallelism approaches☆96Updated 2 years ago
- Neural Networks and the Chomsky Hierarchy☆211Updated last year
- ☆285Updated last year
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- Puzzles for exploring transformers☆376Updated 2 years ago
- ☆91Updated last year
- Train very large language models in Jax.☆210Updated 2 years ago
- ☆457Updated last year
- Extract full next-token probabilities via language model APIs☆247Updated last year
- LoRA for arbitrary JAX models and functions☆142Updated last year
- A library to create and manage configuration files, especially for machine learning projects.☆80Updated 3 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- ☆281Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆212Updated this week
- Understand and test language model architectures on synthetic tasks.☆238Updated last month
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆132Updated last year
- Utilities for the HuggingFace transformers library☆72Updated 2 years ago
- A MAD laboratory to improve AI architecture designs 🧪☆133Updated 10 months ago
- nanoGPT-like codebase for LLM training☆109Updated last week
- we got you bro☆36Updated last year
- Mechanistic Interpretability for Transformer Models☆53Updated 3 years ago