Update README.md

README.md

@@ -1,63 +1,8 @@
-# OpenAI-compatible API for LiquidAI/LFM2-1.2B
-
-This is a minimal FastAPI server that exposes OpenAI-compatible endpoints backed by the Hugging Face Transformers model `LiquidAI/LFM2-1.2B`.
-
-Endpoints:
-- `POST /v1/chat/completions` (OpenAI Chat Completions)
-- `POST /v1/completions` (OpenAI Completions)
-- `GET /health` health check
-
-Runs on port 7860 by default.
-
-## Setup
-
-1. Create and activate a Python environment (recommended).
-2. Install dependencies:
-
-```bash
-pip install -r requirements.txt
-```
-
-3. Run the server:
-
-```bash
-python app.py
-```
-
-The API will be available at `http://localhost:7860`. Interactive docs: `http://localhost:7860/docs`.
-
-## Example requests
-
-Chat:
-
-```bash
-curl http://localhost:7860/v1/chat/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "LiquidAI/LFM2-1.2B",
-    "messages": [
-      {"role": "system", "content": "You are a helpful assistant."},
-      {"role": "user", "content": "Write a haiku about the ocean"}
-    ],
-    "temperature": 0.7,
-    "max_tokens": 128
-  }'
-```
-
-Completions:
-
-```bash
-curl http://localhost:7860/v1/completions \
-  -H "Content-Type: application/json" \
-  -d '{
-    "model": "LiquidAI/LFM2-1.2B",
-    "prompt": "Explain quantum computing in simple terms",
-    "temperature": 0.7,
-    "max_tokens": 128
-  }'
-```
-
-## Notes
-- The server auto-selects FP16/BF16 on CUDA if available, otherwise runs on CPU (slow).
-- Configure with env vars: `MODEL_ID`, `MAX_TOKENS`, `PORT`.
-- This minimal server supports only `n=1` and returns the first completion.
+title: LFM2-1.2B
+emoji: 😎
+colorFrom: yellow
+colorTo: green
+sdk: gradio
+sdk_version: 5.39.0
+app_file: app.py
+pinned: false