Arrow / README.md
noblyon22
Clean deployment - only Flask API files
4088c7e
metadata
title: Mini-Omni2 Flask API
emoji: 🤖
colorFrom: blue
colorTo: purple
sdk: docker
pinned: false
license: mit

Mini-Omni2 Flask API

A Flask API serving the Noblhyon/mini-omni2 model from Hugging Face.

Features

  • RESTful API endpoints for text generation
  • Chat interface endpoint
  • Health checks and model information
  • Docker support for easy deployment
  • Hugging Face Spaces compatible

API Endpoints

Health Check

GET /

Returns the health status of the API and model loading status.

Chat Endpoint

POST /chat

Chat with the model using a simple message format.

Request Body:

{
  "message": "Your message here",
  "max_length": 512,
  "temperature": 0.7
}

Generate Endpoint

POST /generate

Generate text with advanced parameters.

Request Body:

{
  "prompt": "Your prompt here",
  "max_length": 512,
  "temperature": 0.7,
  "top_p": 0.9,
  "top_k": 50
}

Model Info

GET /model-info

Get information about the loaded model.

Usage Examples

Chat Example

curl -X POST https://noblhyon-arrow.hf.space/chat \
  -H "Content-Type: application/json" \
  -d '{"message": "Hello, how are you today?"}'

Generate Example

curl -X POST https://noblhyon-arrow.hf.space/generate \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "The future of artificial intelligence is",
    "max_length": 200,
    "temperature": 0.8,
    "top_p": 0.9
  }'

Model Information

  • Model: Noblhyon/mini-omni2
  • Platform: Hugging Face Transformers
  • Framework: PyTorch
  • API Framework: Flask

License

MIT