Set license: apache-2.0

README.md

@@ -1,6 +1,5 @@
 ---
-license: other
-license_name: set-before-distribution
+license: apache-2.0
 pipeline_tag: image-text-to-text
 tags:
   - multimodal
@@ -21,8 +20,7 @@ the sovereign **`.knot`** format and served by the [Gnosis](https://forkjoin.ai)
 Qwen3-class dense text decoder, and is designed to run **CPU-only, scale-to-zero** on
 commodity edge compute (e.g. Cloudflare Containers) with no GPU and no fixed cost.
 
-> **License note:** `license: other` is a placeholder. Set the correct license and
-> base-model attribution before wide distribution — this card does not assert one.
+Released under the **Apache-2.0** license.
 
 ## Files
 
@@ -128,7 +126,7 @@ accuracy benchmarks in this card.
 - CPU-first design: high-quality but latency-bound (seconds/token), with multi-minute cold
   starts under scale-to-zero.
 - No safety tuning, RLHF, or content filtering is claimed. No training-data or provenance
-  disclosure is made here — set attribution and license before distribution.
+  disclosure is made in this card beyond the architecture above.
 
 ## Download