This repository contains sample code demonstrating how to implement a verified semantic cache using Amazon Bedrock Knowledge Bases to prevent hallucinations in Large Language Model (LLM) responses …

Face Verification Example with Flower / Federated Learning

Cloud-Native Architecture for Vertical Federated Learning

CycleQD is a framework for parameter space model merging.

The repository contains the code for analysing the leakage of personally identifiable (PII) information from the output of next word prediction language models.

Official Code Repository for the paper - Personalized Subgraph Federated Learning (ICML 2023)

DeepWalk - Deep Learning for Graphs

Function Vectors in Large Language Models (ICLR 2024)

An Emulator for Fine-tuning Large Language Models using Small Language Models

Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implicit Bayesian Inference"

Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Official repository of Evolutionary Optimization of Model Merging Recipes

Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]

Python bindings for llama.cpp

autodp: A flexible and easy-to-use package for differential privacy

A fast algorithm to optimally compose privacy guarantees of differentially private (DP) mechanisms to arbitrary accuracy.

Must-read Papers on LLM Agents.

Official implementation for "Pruning Randomly Initialized Neural Networks with Iterative Randomization"

The entrance repository of Markdown presentation ecosystem

An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.

Yet another kaleidoscope

Flower: A Friendly Federated AI Framework