irregular-rhomboid / EAI-Math-Reading-GroupLinks
Resources from the EleutherAI Math Reading Group
โ54Updated 7 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:
- ๐ง Starter templates for doing interpretability researchโ74Updated 2 years ago
- unofficial re-implementation of "Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets"โ79Updated 3 years ago
- An interactive exploration of Transformer programming.โ269Updated last year
- โ166Updated 2 years ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.โ164Updated 3 months ago
- Neural Networks and the Chomsky Hierarchyโ209Updated last year
- Understand and test language model architectures on synthetic tasks.โ229Updated last week
- Erasing concepts from neural representations with provable guaranteesโ236Updated 8 months ago
- A puzzle to learn about promptingโ135Updated 2 years ago
- โ89Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paperโ129Updated 3 years ago
- git extension for {collaborative, communal, continual} model developmentโ216Updated 10 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)โ193Updated last year
- Large scale 4D parallelism pre-training for ๐ค transformers in Mixture of Experts *(still work in progress)*โ87Updated last year
- Emergent world representations: Exploring a sequence model trained on a synthetic taskโ191Updated 2 years ago
- A MAD laboratory to improve AI architecture designs ๐งชโ129Updated 9 months ago
- Train very large language models in Jax.โ209Updated last year
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT trainingโ132Updated last year
- ๐งฑ Modula software packageโ277Updated last month
- LoRA for arbitrary JAX models and functionsโ142Updated last year
- โ281Updated last year
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizationsโ199Updated 3 years ago
- โ276Updated last year
- Implementation of the specific Transformer architecture from PaLM - Scaling Language Modeling with Pathways - in Jax (Equinox framework)โ189Updated 3 years ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.โ209Updated last week
- NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Dayโ257Updated last year
- Code associated to papers on superposition (in ML interpretability)โ33Updated 3 years ago
- nanoGPT-like codebase for LLM trainingโ107Updated 4 months ago
- โ21Updated last year
- Extract full next-token probabilities via language model APIsโ248Updated last year