Kaiju-Coder MLX 1.0 by Kiyomi
=============================

This product includes a fine-tune of and derivative work from a third-party
base model, redistributed under the Apache License, Version 2.0. The full
license text is in the accompanying LICENSE file.

-------------------------------------------------------------------------------
Base model
-------------------------------------------------------------------------------

Qwen3.6-35B-A3B
Copyright 2026 Alibaba Cloud
Licensed under the Apache License, Version 2.0.

The base model is available from the Qwen team at Alibaba Cloud
(Hugging Face repo: Qwen/Qwen3.6-35B-A3B). Architecture id: qwen3_5_moe;
35.9B total parameters with roughly 3B active per token (mixture-of-experts).

-------------------------------------------------------------------------------
Modifications made in this work
-------------------------------------------------------------------------------

This work MODIFIED the base model. Specifically:

- A LoRA fine-tune was trained on top of the base model and fused into the
  released weights. The fine-tune data is RMDW/Kiyomi-owned deterministic
  output for a business-niche builder use case (websites, Stripe, invoices,
  leads, CRM/intake, automations).
- The redistributed GGUF is a TEXT-ONLY derivative. The base Qwen3.6-35B-A3B
  is a vision-language model; the vision pathway is stripped in this GGUF.
  This work does not provide and does not advertise vision capabilities.
- Tokenizer, chat-template, and serving configuration were adapted for the
  GGUF/Ollama/llama.cpp local-serving path.

These modifications were made by Richard Echols / RMDW. As required by the
Apache License, Version 2.0, Section 4(b), the changed files carry notices
stating that they were changed.

-------------------------------------------------------------------------------
Additions and fine-tune by this work
-------------------------------------------------------------------------------

Kaiju-Coder MLX additions, fine-tune weights, training and packaging scripts,
model card, and documentation
Copyright 2026 Richard Echols / RMDW
Licensed under the Apache License, Version 2.0.

-------------------------------------------------------------------------------
Attribution and endorsement
-------------------------------------------------------------------------------

This is an independent fine-tune. Alibaba Cloud and the Qwen team do not
endorse, sponsor, or support this work, and nothing in this distribution
should be read as implying such endorsement. "Qwen" and "Alibaba Cloud" are
used only to describe the origin of the base model, as permitted by Section 6
of the Apache License, Version 2.0.