Eyla: Toward an Identity-Anchored LLM Architecture with Integrated Biological Priors -- Vision, Implementation Attempt, and Lessons from AI-Assisted Development
Paper • 2604.00009 • Published
BitNet tool-calling — training recipe
Training script and configuration for fine-tuning a BitNet-architecture model on Adiuk/adis-tool-calling-dataset.
This repo contains the recipe (train.py + training_config.json), not model weights.
Part of the Eyla project's exploration of extremely low-bit on-device agent models.
Author & research
- 🌐 Website: arifadito.com
- 💻 GitHub: github.com/Adiuk24
- 📄 Eyla identity paper: arXiv:2604.00009
- 🔧 Rust ML training verification tooling: gradient-flow-arbiter
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support