Starred repositories
Dream Recorder is an open-source venture by Modem. Developed in close collaboration with Mark Hinch (software & hardware), Ben Levinas and Joe Tsao (industrial design), and Alexis Jamet (illustrati…
Continuous Thought Machines, because thought takes time and reasoning is a process.
Drawing Bayesian networks, graphical models, tensors, technical frameworks, and illustrations in LaTeX.
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"
A PyTorch native platform for training generative AI models
Make Zotero effective for us LaTeX holdouts
Utilities intended for use with Llama models.
Collection of awesome parameter-efficient fine-tuning resources.
Train transformer language models with reinforcement learning.
[COLM 2024] LoraHub: Efficient Cross-Task Generalization via Dynamic LoRA Composition
Tools for merging pretrained large language models.
Data augmentation for NLP, presented at EMNLP 2019
An extremely fast Python package and project manager, written in Rust.
Simple language-driven navigation tasks for studying compositional learning
Codebase implementing LMs for learning the Dyck-(k,m) bounded hierarchical language
Code and data for "Superbizarre Is Not Superb: Derivational Morphology Improves BERT's Interpretation of Complex Words"
tiktoken is a fast BPE tokeniser for use with OpenAI's models.
Open Overleaf/ShareLaTex projects in vscode, with full collaboration support.