Stars
The fastest way to create an HTML app
Training code for Sparse Autoencoders on Embedding models
Training Sparse Autoencoders on Language Models
An innovative superfamily of fonts for code
utilities for decoding deep representations (like sentence embeddings) back to text
WebAssembly binding for llama.cpp - Enabling in-browser LLM inference
⚡ A fast embedded library for approximate nearest neighbor search
C implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)
Natural language search for complex JSON arrays, with AI Quickstart.
Convert PDF to markdown quickly with high accuracy
A python script to help manage a Gmail inbox by filtering out promotional emails using GPT-3 or GPT-4.
A customized version of the Gnome shell default theme.
QLoRA: Efficient Finetuning of Quantized LLMs
Interpolation and function approximation with JAX
ONNX-compatible Fast SeamlessM4T—Massively Multilingual & Multimodal Machine Translation
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Nonlinear optimisation (root-finding, least squares, ...) in JAX Equinox. https://docs.kidger.site/optimistix/
A high-throughput and memory-efficient inference and serving engine for LLMs
Universal LLM Deployment Engine with ML Compilation
Access large language models from the command-line
Simple embedding -> text model trained on a small subset of Wikipedia sentences.
4 bits quantization of LLaMA using GPTQ
Linux Driver for USB WiFi Adapters that are based on the RTL8812BU and RTL8822BU Chipsets - v5.13.1
The simplest, fastest repository for training/finetuning medium-sized GPTs.