Lists (2)
Stars
A Python library for interacting with AWS SageMaker AI deployments of the Isaacus API.
The code used to evaluate embedding models on the Massive Legal Embedding Benchmark (MLEB).
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
Unofficial faiss wheel builder for NVIDIA GPU
🚀 Efficient implementations of state-of-the-art linear attention models
PyTorch native quantization and sparsity for training and inference
Efficient Triton Kernels for LLM Training
This repository provides a clear, educational implementation of Byte Pair Encoding (BPE) tokenization in plain Python. The focus is on algorithmic understanding, not raw performance.
Fast bare-bones BPE for modern tokenizer training
(1) Courses on key machine learning and software engineering topics; (2) and a workflow for creating similar courses with LLMs in Cursor.
Python bindings for the PCRE2 library created by Philip Hazel
KL3M training data collection and preprocessing
A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.
Scripts for evaluating extractive question answering models on the LegalQAEval legal question answering benchmark.
A server-side JavaScript/TypeScript library for interacting with the Isaacus API, the world's first legal AI API.
A Python library for interacting with the Isaacus API, the world's first legal AI API.
The highest quality collection of up-to-date OpenAPI specifications for public APIs on the internet. This dataset also includes descriptions, categories, uptime metrics, and media assets for every …
A GitHub action to build Stainless SDKs.
Franken UI is an HTML-first UI component library built on UIkit 3 and extended with LitElement, inspired by shadcn/ui.
A simple zero-config tool to make locally trusted development certificates with any names you'd like.
The most advanced frontend drag & drop page builder. Create high-end, pixel perfect websites at record speeds. Any theme, any page, any design.
Get your documents ready for gen AI
A fast and lightweight Rust library for splitting text into semantically meaningful chunks.
The No-Hassle CMS for Static Sites Generators