# NOTICE — license & attribution

This model is a fine-tune of **LiquidAI/LFM2-1.2B-Extract** and is therefore governed by the **LFM Open License
v1.0** (the LiquidAI `lfm1.0` license), NOT the MIT license of the `experience` source code.

**Change notice (Sec. 4):** fine-tuned from LiquidAI/LFM2-1.2B-Extract by the experience/mindi-dev project into a
structured fact extractor, by LoRA (rank 32) fine-tune (mlx-lm) on real-distribution chat transcripts with
teacher-generated labels. Architecture unchanged (`lfm2`).

**Attribution:** base model © Liquid AI, used under the LFM Open License v1.0. Not endorsed by
or affiliated with Liquid AI; no LiquidAI trademark/naming rights granted (Sec. 7).

**Commercial-use gate (Sec. 5), inherited by you:** Commercial Use by an entity with **≥ US$10M
annual revenue is NOT licensed** without a Liquid AI commercial license. Below that, use is
permitted under the LFM Open License v1.0.

**You must include the full LFM Open License v1.0 in this repo** — fetch it from the base model:

    hf download LiquidAI/LFM2-1.2B-Extract LICENSE --local-dir .   # or copy LICENSE/LICENSE.md from LiquidAI/LFM2-1.2B-Extract

Training labels were teacher-generated (Claude / GPT-5.5-via-codex). Only weights are
distributed here, not the dataset.