fix: Zen MoDE = Mixture of Diverse Experts

README.md

@@ -14,22 +14,19 @@ library_name: transformers
 
 # Zen 5
 
-> **Parameters**: TBA | **Architecture**: Zen MoDE | **Context**: 1M | **Status**: In training — expected 2025-06-01
+> **Parameters**: TBA | **Architecture**: Zen MoDE (Mixture of Diverse Experts) | **Context**: 1M | **Status**: In training
 
-Zen 5 — next-generation flagship. In training. Expected Q3 2025.
+Zen 5 — next-generation flagship. Currently in training.
 
-**Zen MoDE** (Mixture of Distilled Experts) — next-generation sparse routing architecture with 1M+ context, enhanced chain-of-thought, and multi-modal reasoning. First introduced with Zen 5.
+**Zen MoDE** is our next-generation architecture: Mixture of Diverse Experts with sparse activation, extended context, and enhanced multi-step reasoning. First introduced with Zen 5.
 
-[Subscribe for updates → zenlm.org](https://zenlm.org)
+[Learn more → zenlm.org](https://zenlm.org)
 
 ---
 ## The Zen LM Family
 
-Joint research collaboration:
-- **Hanzo AI** (Techstars '17) — AI infrastructure, API gateway, inference optimization
-- **Zoo Labs Foundation** (501c3) — Open AI research, ZIPs governance, decentralized training
-- **Lux Partners Limited** — Compute coordination and settlement layer
+Joint research between **Hanzo AI** (Techstars '17), **Zoo Labs Foundation** (501c3), and **Lux Partners Limited**.
 
 All weights Apache 2.0. Download, run locally, fine-tune, deploy commercially.
 
-[HuggingFace](https://huggingface.co/zenlm) · [Chat free](https://hanzo.chat) · [API](https://api.hanzo.ai) · [Docs](https://zenlm.org)
+[HuggingFace](https://huggingface.co/zenlm) · [Chat](https://hanzo.chat) · [API](https://api.hanzo.ai) · [Docs](https://zenlm.org)