Switch language한국어
Back to the list

Open-sourcing a full fine-tuning pipeline for embedded engineering — training toolkit + 35-domain MoE-LoRA model

TL;DR AI

Key summary

2 min read
  1. L'Électron Rare open-sourced two Apache 2.0 projects: KIKI-Mac_tunner, an MLX-based training toolkit for Mac Studio, and micro-kiki-v3, a routed embedded-engineering model.

  2. micro-kiki-v3 is built on Qwen3.5-35B-A3B and uses a domain router plus 35 domain-specific LoRA stacks to handle specialized engineering tasks.

  3. The release also includes supporting pieces for conflict resolution, bias reduction, memory, and a published dataset/pipeline with real engineering sessions and filtered open-source sources.

  4. The goal is to reduce hallucinations and improve accuracy in embedded systems and electronics workflows, where general-purpose LLMs often struggle.

Read the original