Update notice

NOTICE.md

@@ -10,12 +10,15 @@ The scripts, evaluation code and results in this repository are Copyright 2026 v
 
 ## Maya's weights
 
-Maya is fine-tuned from MoritzLaurer/ModernBERT-base-zeroshot-v2.0 (Apache-2.0, https://huggingface.co/MoritzLaurer/ModernBERT-base-zeroshot-v2.0), itself fine-tuned from answerdotai/ModernBERT-base (Apache-2.0). Changes: full fine-tune on Maya's synthetic yes/no data plus MNLI, labels renamed to yes/no. The released weights are a modified derivative.
+- Maya v0.2 is fine-tuned from MoritzLaurer/deberta-v3-large-zeroshot-v2.0 (MIT license, https://huggingface.co/MoritzLaurer/deberta-v3-large-zeroshot-v2.0), itself fine-tuned from microsoft/deberta-v3-large (MIT). Changes: fine-tuned on Maya's synthetic yes/no data plus BoolQ and MNLI pairs, labels renamed to yes/no.
+- Maya v0.1 (tag `v0.1` on Hugging Face) is fine-tuned from MoritzLaurer/ModernBERT-base-zeroshot-v2.0 (Apache-2.0), itself fine-tuned from answerdotai/ModernBERT-base (Apache-2.0).
+
+The released weights are modified derivatives of those models. The card of deberta-v3-large-zeroshot-v2.0 states that its versions without "-c" in the name were trained on data that includes non-commercially licensed datasets; check it before commercial use of Maya v0.2.
 
 ## Training data
 
 - `gen/laya_domains.py` is copied from the author's layaMOE repository (same license).
-- During training, a few thousand MNLI pairs (GLUE `mnli`, https://huggingface.co/datasets/nyu-mll/glue) are mixed in. They are downloaded at run time and not redistributed.
+- During training, MNLI pairs (GLUE `mnli`, https://huggingface.co/datasets/nyu-mll/glue) and BoolQ questions (https://huggingface.co/datasets/google/boolq, CC BY-SA 3.0) are mixed in. They are downloaded at run time and not redistributed.
 
 ## Models used as baselines