Timothy Pogue

The Freqtrade Operator is a Kubernetes operator designed to manage Freqtrade instances within a Kubernetes cluster.

Lockbox is a secure API key management system designed to help provide authentication for Rest APIs.

No description.

Free, open source crypto trading bot

A thin abstraction for pubsub broadcasting in Rust.

JobQ is a lightweight, in-memory job queue implementation in Rust designed for asynchronous task processing within the same process.

A thin abstraction layer for document databases in Rust.

Rust SDK for the Machine Payments Protocol

AG-UI: the Agent-User Interaction Protocol. Bring Agents into Frontend Applications.

Rust language bindings for Microsoft Playwright

A thin abstraction for columnar databases in Rust.

A thin abstraction layer for message brokers in Rust.

A Python ORM-like abstraction layer for vector databases

WebSocket support for HTTPX

Locally run an Instruction-Tuned Chat-Style LLM

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

The Open Assistant API is a ready-to-use, open-source, self-hosted agent/gpts orchestration creation framework, supporting customized extensions for LLM, RAG, function call, and tools capabilities. It also supports seamless integration with the openai/langchain sdk.

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

An easy-to-use model quantization package with user-friendly apis, based on GPTQ algorithm.

Compositional Differentiable Programming Library

:robot: Self-hosted, community-driven simple local OpenAI-compatible API written in go. Can be used as a drop-in replacement for OpenAI, running on CPU with consumer-grade hardware. Supports ggml compatible models, for instance: LLaMA, alpaca, gpt4all, vicuna, koala, gpt4all-j, cerebras

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Inference Llama 2 in one file of pure C

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a toolkit of libraries (Ray AIR) for accelerating ML workloads.

Seed, Code, Harvest: Grow Your Own App with Tree of Thoughts!

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

4 bits quantization of LLaMA using GPTQ

An implementation of a Reflexion agent for SOTA Human-Eval Python results.

FauxPilot - an open-source alternative to GitHub Copilot server

Alpaca-LoRA as Chatbot service

A ChatGPT clone for running locally in your browser.

Instruct-tuning LLaMA on consumer hardware

[EMNLP 2022] This is the code repo for our EMNLP‘22 paper "COCO-DR: Combating Distribution Shifts in Zero-Shot Dense Retrieval with Contrastive and Distributionally Robust Learning".

An interface that lets users build, test, and deploy custom adaptive machine learning models in freqtrade. Mirrored development on github.com/freqtrade/freqtrade

A Human-in-the-Loop workflow for creating HD images from text

Embed images and sentences into fixed-length vectors with CLIP

High-Resolution Image Synthesis with Latent Diffusion Models

1.4B latent diffusion model fine tuning

SwinIR: Image Restoration Using Swin Transformer

:mag: Haystack is an open source NLP framework that leverages Transformer models. It enables developers to implement production-ready neural search, question answering, semantic document search and summarization for a wide range of applications.

Server & client for DeepSpeech using WebSockets for real-time speech recognition in separate environments

A demo for a financial services bot