peytontolbert

AgentForge

Extensible AGI Framework

ai-space-calls

AI Space Call is a web application that allows users to create personalized space calls to engage in conversations with AI participants. It leverages advanced AI models like LLaMA for generating responses and Whisper for transcription.

buddy

DynamicAgent

Dynamic Agent, empowered by a Graph RAG LLM

GPTDev

Collection of Autonomous Software Development Scripts and Actions utilizing local LLM

Griffin

Griffin: Mixing Gated Linear Recurrences with Local Attention for Efficient Language Models

swarm-drone-hrtx

Drone swarm simulation environment operated through HRTX self attention (multi input multi output multi modality)

T5-SpeechtoSpeech

Leverages state-of-the-art pretrained models to convert spoken language in real-time. By utilizing a teacher-student training paradigm, this project enables the creation of efficient and accurate speech-to-speech systems suitable for various applications such as virtual assistants, transcription services, and more.

TransformerWeightsTransfer

This project demonstrates how to create a Linear State Space Model (LSSM) by transferring weights from a pretrained LLaMA model. The LSSM is a simplified linear approximation of the LLaMA model's MLP layer, designed to process input text and compare its outputs with those of the original LLaMA model.

swarms-cloud

Deploy your autonomous agents to production grade environments with 99% Uptime Guarantee, Infinite Scalability, and self-healing.

peytontolbert/ai-space-calls

AI Space Call is a web application that allows users to create personalized space calls to engage in conversations with AI participants. It leverages advanced AI models like LLaMA for generating responses and Whisper for transcription.

peytontolbert/DynamicAgent

Dynamic Agent, empowered by a Graph RAG LLM

peytontolbert/GPTDev

Collection of Autonomous Software Development Scripts and Actions utilizing local LLM

peytontolbert/continuous-learning-assistant

The Continuous Learning Assistant is an intelligent chat-based system designed to interact with users, process their inputs, retrieve relevant knowledge, generate meaningful responses, collect feedback, and continuously improve its performance through fine-tuning.

peytontolbert/DPOAssistant

Continuous learning to fine-tune a pre-trained generative transformer model with DPO from real examples and a knowledge retrieval system

peytontolbert/SelfImprove

Self improvement components and utilities

peytontolbert/swarm-drone-hrtx

Drone swarm simulation environment operated through HRTX self attention (multi input multi output multi modality)

peytontolbert/TransformerWeightsTransfer

This project demonstrates how to create a Linear State Space Model (LSSM) by transferring weights from a pretrained LLaMA model. The LSSM is a simplified linear approximation of the LLaMA model's MLP layer, designed to process input text and compare its outputs with those of the original LLaMA model.

peytontolbert/T5-SpeechtoSpeech

Leverages state-of-the-art pretrained models to convert spoken language in real-time. By utilizing a teacher-student training paradigm, this project enables the creation of efficient and accurate speech-to-speech systems suitable for various applications such as virtual assistants, transcription services, and more.

peytontolbert/AgentEnvironment

autonomous agent environment

peytontolbert/AutonomousDigitalSociety

Digital Entity Society Controller is a Python project that provides functionalities for managing digital entities, actions, and states. The core component of this project is the Controller class, which manages personas and interacts with a local model by default.

peytontolbert/bob-agi

Bob - Your 24/7 Discord Assistant ( IN PROGRESS / NOT WORKING YET )

peytontolbert/caravel-user-project

peytontolbert/ConfidenceTransformer

This repository contains the implementation of a Confidence Transformer model based on GPT-2. The model is designed to provide confidence scores for its predictions, detect out-of-distribution (OOD) inputs, and perform language modeling tasks.

peytontolbert/ConversationalTransformer

peytontolbert/GCBMS

Graph-Based Codebase Management System (GBCMS) integrates a graph database with a web-based UI and an LLM agent. This system enables users to interact with and manage codebases through a chat interface by representing code as interconnected nodes and edges within a graph.

peytontolbert/LLMAgentSystem

AGI Prototype with AgentZero Implementation

peytontolbert/model-hub

A flexible framework for generating, training, and evaluating diverse neural network architectures. This project automatically generates and tests various neural network architectures, supporting multiple architectural patterns and combinations.

peytontolbert/musicgen-fastapi

Musicgen by Meta on FastAPI. Contains Dockerfile.

peytontolbert/Nimbus

Autonomous Self Improving GPT Assistant

peytontolbert/OpenStrawberry

An open source replication of the stawberry method that leverages Monte Carlo Search with PPO and or DPO

peytontolbert/Ozzie

AGI prototype

peytontolbert/peytontolbert

peytontolbert/qtransformer

Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions

peytontolbert/SinglePassTransformer

The single-pass training method revolutionizes the way datasets are loaded and processed during model training. Unlike traditional methods that may require multiple passes over the data, our approach ensures that each data batch is processed in a single pass, significantly enhancing training efficiency.

peytontolbert/SOPLibrary

Library of Software Engineering Standard Operating Procedures (SOP)

peytontolbert/swarms

Build, Deploy, and Scale Reliable Swarms of Autonomous Agents for Workflow Automation. Join our Community: https://discord.gg/DbjBMJTSWD

peytontolbert/swarms-cloud-agents

This project provides an autoscaling infrastructure for hosting intelligent Swarms Agent API.

peytontolbert/swarms-examples

A vast array of examples for the enterprise-grade and production-ready swarms framework.

peytontolbert/vision-gpt-control