ClusterAnon/phi-3-mini-ONNX

Phi-3 ONNX API

This Hugging Face Space provides an efficient API for Microsoft's Phi-3-mini-4k-instruct model for text generation using ONNX runtime for optimal performance on resource-constrained environments. This implementation is specifically optimized to run on Hugging Face's free tier.

Features

• —Text Generation: Generate high-quality text responses using Microsoft's Phi-3-mini model
• —ONNX Optimization: Uses ONNX runtime for faster inference and reduced memory usage
• —Multilingual Support: Works with multiple languages for text generation
• —Free-Tier Compatible: Designed to run efficiently on Hugging Face's free tier resources

API Usage

Text Generation

Send POST requests to the /generate endpoint with the following JSON structure: