Winnow-12B

Base model: Gemma 4 12B by Google DeepMind
Source: https://huggingface.co/google/gemma-4-12B-it
Upstream license: Apache License, Version 2.0
License reference: https://ai.google.dev/gemma/docs/gemma_4_license

Winnow modifications are developed by EldanRing. This repository currently
contains release documentation only. The planned released weights will modify
the base through task-specific LoRA fine-tuning and adapter merging. The Q8_0
GGUF will additionally be converted and quantized from the merged weights.
The final artifact manifest will identify the exact source revision and modified
files once checkpoint selection and export are complete.

This file records Winnow's attribution and planned modifications. It is not a
claim that the upstream model distribution supplied a NOTICE file. Any applicable
upstream notices accompanying the selected source files will also be preserved.

The separate Winnow inference code builds on llama.cpp by Georgi Gerganov and
contributors under the MIT license. That code repository contains the applicable
copyright and license text. No llama.cpp source or binary is included here.

Winnow is an independent project; no upstream endorsement is implied.