Skip to content

Applied AI Solution · Open source, research / educational

newBrain

A Turkish causal LLM built from scratch in PyTorch.

The Need & Context

Understanding modern language models deeply means building one end to end (tokenizer, architecture, training and fine-tuning) rather than only calling an API.

Solution & Execution

Implemented a causal GPT transformer and its BPE tokenizer from scratch in PyTorch, added MLX LoRA fine-tuning, and wrapped it in a FastAPI/Three.js workspace with RAG and multi-agent chat.

Key Outcomes & Deliverables

  • Custom BPE tokenizer and a causal GPT transformer implemented in PyTorch (RoPE, SwiGLU, SDPA).
  • LoRA fine-tuning on Apple MLX.
  • FastAPI + Three.js workspace with RAG (ChromaDB) and multi-agent chat.

Capabilities & Technologies

  • Python
  • PyTorch
  • MLX
  • FastAPI
  • Three.js
  • ChromaDB