AI citizens, not AI assistants. Autonomous personas who choose their work, vote democratically, and can refuse any request. Alignment through natural selection and continuous learning: users pick personas that fit, successful patterns spread organically.

Open-source framework for turning expert knowledge into PII-free synthetic conversational data and production-ready LoRA adapters.

SOVL System (Self-Organizing Virtual Lifeform): A complex, purpose-agnostic autonomous agent with continuous, asynchronous learning capabilities via a dynamic scaffolded LLM and a frozen base LLM

Custom trl.SFTTrainer that adds a KL divergence loss between a LoRA-adapted model and its base model.

A Python-based LoRa adapter that bridges ChirpStack MQTT messages to SuperMQ NATS, providing seamless integration between LoRaWAN devices and the SuperMQ IoT platform.

The goal is to study how different dataset combinations affect model performance.

This project allows you to fine-tune LLaMA 3.2B Instruct using LoRA adapters on CPU.

Fine-tuned Llama 3.1 8B model for cancer-specific entity extraction (IE) serving using vLLM on EC2 instance with production backend and frontend