Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

QAmeleon introduces synthetic multilingual QA data using PaLM, a 540B large language model. This dataset was generated by prompt tuning PaLM with only five examples per language. We use the synthet…

llama2.c but in Julia

High performance, self-hosted, newsletter and mailing list manager with a modern dashboard. Single binary app.

Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.

Given a humerus 3D mesh, extract a custom 3D implant shape.

Gzip and nearest neighbors for text classification

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

Code for Implement DNS in a Weekend

Large Language-and-Vision Assistant built towards multimodal GPT-4 level capabilities.

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

8-bit CUDA functions for PyTorch

Official Code for DragGAN (SIGGRAPH 2023)

Notebooks for Large Language Models (LLMs) Specialization

AI companions with memory: a lightweight stack to create and host your own AI companions

📋 A list of open LLMs available for commercial use.

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

CodeGen is an open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.

Open source Medium alternative

eBPF-based Networking, Security, and Observability

The fastai book, published as Jupyter Notebooks

Hackable implementation of state-of-the-art open-source LLMs based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.…

A web app for ranking computer science departments according to their research output in selective venues, and for finding active faculty across a wide range of areas.

Home of CodeT5: Open Code LLMs for Code Understanding and Generation

Port of OpenAI's Whisper model in C/C++

Modin: Scale your Pandas workflows by changing a single line of code

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.