Details update

README.md

@@ -7,16 +7,15 @@ sdk: docker
 python_version: "3.11"
 app_port: 7860
 tags:
-  - thousand-token-wood
-  - nemotron
-  - fine-tuned
-  - custom-ui
-  - tiny-titan
-  - self-play
-  - rl
-  - fighting-game
-  - modal
-pinned: false
+  - track:wood
+  - sponsor:nvidia
+  - sponsor:modal
+  - achievement:offgrid
+  - achievement:welltuned
+  - achievement:offbrand
+  - achievement:llama
+  - achievement:sharing
+  - achievement:fieldnotes
 ---
 
 # Duel of Nemotron ⚔️ — Hybrid Self-Play AI Fighter
@@ -34,6 +33,9 @@ This is a tiny-model-implements-the-fast-loop + fine-tuned-LLM-sets-the-directio
 pattern: a small CPU policy network for real-time play, a larger fine-tuned
 model for strategic depth.
 
+https://sankalphs.blogspot.com/2026/06/duel-of-albion.html
+https://x.com/sankalphs/status/2066675345080852567
+
 ## How It Works
 
 ```
@@ -45,8 +47,8 @@ Browser (React + Three.js)  ──fight state──▶  Space backend (HF Space
     │                                              └──▶ Modal Nemotron (A10, cold start)
     │                                                    every ~10 moves:
     │                                                    returns strategic weights
-    │                                              ▲
-    └──────────────────weights + reasoning────────┘
+    │                                                      ▲
+    └──────────────────weights + reasoning────────-----------┘
 ```
 
 ### Training Pipeline (on Modal A100-40GB)