Upload README.md with huggingface_hub

README.md

@@ -1,10 +1,27 @@
 ---
-title: POCKET 35B CPU
-emoji: 🔥
-colorFrom: indigo
-colorTo: purple
+title: POCKET-35B CPU Chat
+emoji: 📱
+colorFrom: yellow
+colorTo: green
 sdk: docker
-pinned: false
+app_port: 7860
+pinned: true
+license: apache-2.0
+models:
+- FINAL-Bench/POCKET-35B-GGUF
+- FINAL-Bench/Darwin-36B-Opus
+short_description: A 35B model answering on a CPU-only box. No GPU.
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# POCKET-35B · CPU chat
+
+A live demo of **POCKET-35B** (Q2_K, 13 GB) answering on an **upgraded CPU** Space — **no GPU**.
+
+POCKET is a sparse Mixture-of-Experts model (34.66B total, ~3B active/token) quantized from
+[Darwin-36B-Opus](https://huggingface.co/FINAL-Bench/Darwin-36B-Opus). It runs on stock
+`llama.cpp` — on a phone, and on a PC with no graphics card.
+
+- 📚 [POCKET collection](https://huggingface.co/collections/FINAL-Bench/pocket-models-6a618ee5d23eafb7e185a5c6)
+- 📦 [POCKET-35B-GGUF](https://huggingface.co/FINAL-Bench/POCKET-35B-GGUF) · [POCKET-KR-MLX (iPhone)](https://huggingface.co/FINAL-Bench/POCKET-KR-MLX) · [POCKET-EN-GGUF](https://huggingface.co/FINAL-Bench/POCKET-EN-GGUF)
+
+Built with FastAPI + llama-cpp-python. Apache-2.0.