Stars
Minimalist Hugo template for academic websites
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
Atom Agent, automate your workflows by talking to an AI — and let it remember, search, and handle tasks like a real assistant
Code for studying the super weight in LLM
The simplest, fastest repository for training/finetuning medium-sized GPTs.
An algorithm that approximates an orthogonal matrix with few-factor Givens factorization.
A community-maintained Python framework for creating mathematical animations.
Code accompanying the paper "Massive Activations in Large Language Models"
[ACL 2024] Official PyTorch implementation of "IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact"
Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in Pytorch
Repo for paper "Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration"
Vibe Coding free starter kit: https://vibe-codingschool.com/
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Supplementary material for the EMNLP 2024 paper "Conditional and Modal Reasoning in Large Language Models" by Wesley H. Holliday, Matthew Mandelkern, and Cedegao E. Zhang
JupyterLab for AI in Docker. Anaconda and PyTorch GPU supported.
AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning (ICLR 2023).
From Chain-of-Thought prompting to OpenAI o1 and DeepSeek-R1 🍓
Papers and resources on Controllable Generation using Diffusion Models, including ControlNet, DreamBooth, IP-Adapter.
An implementation of local windowed attention for language modeling
[ICLR 2024] Efficient Streaming Language Models with Attention Sinks
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining