--- title: Alloy Maintenance AI emoji: 🏭 colorFrom: blue colorTo: indigo sdk: gradio sdk_version: 4.44.1 app_file: app.py pinned: false license: mit python_version: "3.11" --- # 🏭 Alloy Maintenance AI Assistant Fine-tuned Phi-3 model specialized for steel manufacturing equipment maintenance, diagnostics, and safety procedures. ## Features - **Equipment Diagnostics**: Analyze sensor data and identify issues - **Root Cause Analysis**: Determine failure modes and causes - **Maintenance Procedures**: Step-by-step repair and safety guides - **Domain Expertise**: Trained on steel manufacturing maintenance data ## Usage ### Web Interface Simply type your maintenance query in the text box and click Submit. ### API Access You can call this model programmatically from your application: ```python import requests response = requests.post( "https://huggingface.co/spaces/YOUR_USERNAME/alloy-maintenance-ai/api/predict", json={ "data": [ "What causes bearing failure?", # prompt 500, # max_tokens 0.3 # temperature ] } ) result = response.json() answer = result["data"][0] ``` ### Python Gradio Client ```python from gradio_client import Client client = Client("YOUR_USERNAME/alloy-maintenance-ai") result = client.predict( "What causes high vibration in compressors?", # prompt 500, # max_tokens 0.3, # temperature api_name="/predict" ) print(result) ``` ## Model Details - **Base Model**: microsoft/Phi-3-mini-4k-instruct - **Fine-tuned On**: Steel manufacturing maintenance procedures, fault diagnostics, safety protocols - **Training Data**: Equipment manuals, maintenance logs, incident reports - **Specialization**: Air compressors, rolling mills, cooling systems, blast furnaces ## Example Queries - "What causes bearing failure in air compressors?" - "Diagnose: high temperature, low pressure, normal vibration" - "Safety procedure for emergency compressor shutdown" - "Root cause of shaft misalignment" ## License MIT License - Free for commercial and non-commercial use