🚀 Useful tools
A high-performance, zero-overhead, extensible Python compiler with built-in NumPy support
🐙 Guides, papers, lecture, notebooks and resources for prompt engineering
Cramming the training of a (BERT-type) language model into limited compute.
Dataframes powered by a multithreaded, vectorized query engine, written in Rust
📦 🔥 Python project management. Manage packages: convert between formats, lock, install, resolve, isolate, test, build graph, show outdated, audit. Manage venvs, build package, bump version.
Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"
A playbook for systematically maximizing the performance of deep learning models.
Visualize Your Ideas With Code
Large Language Model Text Generation Inference
Transformer related optimization, including BERT, GPT
Running large language models on a single GPU for throughput-oriented scenarios.
Prompt Engineering, Generative AI, and LLM Guide by Learn Prompting | Join our discord for the largest Prompt Engineering learning community
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
[ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters
Algorithms for explaining machine learning models
PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
High-performance In-browser LLM Inference Engine
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
Hackable and optimized Transformers building blocks, supporting a composable construction.
Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.
The official implementation of “Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training”
A guidance language for controlling large language models.
CLI platform to experiment with codegen. Precursor to: https://lovable.dev
AI tutor powered by Theory-of-Mind reasoning
Uni-Dock: a GPU-accelerated molecular docking program
Official code for "TOAST: Transfer Learning via Attention Steering"