Update README.md

README.md

@@ -1,13 +1,20 @@
 ---
-title: FastLLM
+title: FastLLM 150M Demo
 emoji: ⚡
-colorFrom: red
-colorTo: green
+colorFrom: indigo
+colorTo: purple
 sdk: gradio
-sdk_version: 6.25.0
-python_version: '3.12'
+sdk_version: 5.31.0
 app_file: app.py
 pinned: false
+license: apache-2.0
+short_description: Text generation demo for devoppro/FastLLM (150M)
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# FastLLM (150M) Demo
+
+Interactive text-generation demo for [devoppro/FastLLM](https://huggingface.co/devoppro/FastLLM),
+a ~150M parameter decoder-only causal LM (GQA, SwiGLU, RMSNorm, RoPE) trained from scratch.
+
+Runs on ZeroGPU — the model loads once and `@spaces.GPU` requests a GPU
+slice only for the duration of each generation call.