LLM training in simple, raw C/CUDA

Material for gpu-mode lectures

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Inspect: A framework for large language model evaluations

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

LLM101n: Let's build a Storyteller

Intelligent Go-Explore: Standing on the Shoulders of Giant Foundation Models

METR Task Standard

[ICLR 2024] SWE-Bench: Can Language Models Resolve Real-world Github Issues?

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

Machine Learning Engineering Open Book

The LLM Evaluation Framework

Efficient LLM inference on Slurm clusters using vLLM.

Toy autograd engine in OCaml with Apple Accelerate backend

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

Ongoing research training transformer models at scale

Universal LLM Deployment Engine with ML Compilation

Fast inference engine for Transformer models

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

What would you do with 1000 H100s...

[NeurIPS 2023] Official implementation of the paper "Segment Everything Everywhere All at Once"

[CVPR 2020 & 2021 & 2022 & 2023] Agriculture-Vision Dataset, Prize Challenge and Workshop: A joint effort with many great collaborators to bring Agriculture and Computer Vision/AI communities toget…

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Minimalistic large language model 3D-parallelism training

LLM finetuning in resource-constrained environments.

Refine high-quality datasets and visual AI models

GEO-Bench: Toward Foundation Models for Earth Monitoring