Enhanced MCP server for Bloomberg Terminal β BDP/BDH/BDS/BQL/TA with 18 tools, caching, and dynamic screening. Based on tallinn102/bloomberg-mcp.
burn inference and training of dragon models π₯π
An educational implementation of the Dragon Hatchling (BDH), applied to a pathfinding task
Native Spiking Neural Network (SNN) implementation of the Baby Dragon Hatchling (BDH) architecture for Neuromorphic & Edge AI with Continual Learning.
Repository with code for 'The little dragon learns to fly' article
Interactive explainer: BDH's attention has no softmax, so it is exactly a Hebbian synaptic memory β one fixed-size matrix written once per token. Run both forms, watch them agree to 1e-16, then break it with one toggle. DataForge 2026, Pathway track.
ππππ ππ π πππππππ ππππππππππ’
Small Dragon Hatchling (BDH) language models, 25M to 100M parameters, on bytes and BPE, with streaming inference over the synaptic state
Interactive explainer connecting Sparse Non-Negative Activations to Pathway's BDH - DataForge 2026, Pathway Track
To associate your repository with the bdh topic, visit your repo's landing page and select "manage topics."