horenbergerb / llamagotchi
A bunch of LLaMa model investigations, including recreating generative agents (from the paper Generative Agents: Interactive Simulacra of Human Behavior)
☆21Updated last year
Related projects: ⓘ
- Scene-Based Generative Agent☆36Updated last year
- LangChain + llamaCPP + babyAGI implementation☆14Updated last year
- ☆26Updated last year
- Generative Agents: Interactive Simulacra of Human Behavior☆94Updated last year
- A repository to store helpful information and emerging insights in regard to LLMs☆20Updated 10 months ago
- 🎮👥 Experience the future of multiplayer gaming with MUDGPT's AI-generated virtual world! 🌟🤖☆36Updated last year
- Open-Source Generative Agents is a community-driven fork of 'Generative Agents,' aimed at enabling compatibility with open-source Large L…☆56Updated 5 months ago
- Experimental sampler to make LLMs more creative☆29Updated last year
- Porting BabyAGI to Oobabooba.☆33Updated last year
- Reinforcement Learning with Heuristic Imperatives - Finetuning LLMs for Post-Conventional Moral Intuition☆63Updated last year
- RAG implementation for Ooba characters. dynamically spins up new qdrant vector DB and manages retrieval and commits for conversations ba…☆45Updated 11 months ago
- Simple Autogpt with tree of thoughts☆15Updated last year
- Modified Beam Search with periodical restart☆12Updated last week
- An implementation of long term memory and external tools for LLMs☆67Updated last year
- ☆22Updated last year
- CHAracter State Management - a generative text adventure (engine)☆58Updated last week
- ☆12Updated 5 months ago
- Here is a Google Colab Notebook for fine-tuning Alpaca Lora (within 3 hours with a 40GB A100 GPU)☆39Updated last year
- Model REVOLVER, a human in the loop model mixing system.☆33Updated last year
- AI NPCs that can control their actions along with dialogue. For instance, if I ask an NPC to tell me its favorite magic spell, it not onl…☆40Updated 10 months ago
- A forest of autonomous agents.☆18Updated last week
- ☆23Updated 8 months ago
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆67Updated last year
- Using multiple LLMs for ensemble Forecasting☆17Updated 8 months ago
- BabyAGI-🦙: Enhanced for Llama models (running 100% local) and persistent memory, with smart internet search based on BabyCatAGI and docu…☆88Updated last year
- Creates an Langchain Agent which uses the WebUI's API and Wikipedia to work☆73Updated last year
- An application that automatically generates Python codes based on GPT (as used in ChatGPT).☆41Updated 11 months ago
- Security measure for agentic LLMs using a council of AIs moderted by a veto system. The council judges an agent's actions outputs based o…☆37Updated last year
- Easy-to-use agent memory, powered by chromadb and postgres☆56Updated 11 months ago
- Prompt-Promptor is a python library for automatically generating prompts using LLMs☆67Updated 11 months ago