Upload README.md with huggingface_hub

README.md

@@ -1,10 +1,34 @@
 ---
-title: Gemma Api
-emoji: 🏆
-colorFrom: gray
-colorTo: purple
+title: Gemma API
+emoji: 🚀
+colorFrom: blue
+colorTo: red
 sdk: docker
-pinned: false
+app_port: 7860
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Gemma 2 2B OpenAI-Compatible API
+
+This Space runs `gemma-2-2b-it` (Q4_K_M GGUF) via `llama-cpp-python[server]`, providing an OpenAI-compatible API endpoint.
+
+## Endpoint
+
+You can use this just like the OpenAI API by pointing your base URL to the Space URL + `/v1`.
+
+```python
+from openai import OpenAI
+
+client = OpenAI(
+    base_url="https://cloudunity-gemma-api.hf.space/v1",
+    api_key="your_huggingface_token" # Usually ignored by llama.cpp but required by client
+)
+
+response = client.chat.completions.create(
+    model="gemma-2-2b-it-Q4_K_M", # Model name is ignored if there's only one, but good practice
+    messages=[
+        {"role": "user", "content": "Write a short poem about coding."}
+    ]
+)
+
+print(response.choices[0].message.content)
+```