| title: FLAN-T5 Custom Handler | |
| emoji: 🤖 | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: docker | |
| sdk_version: 3.9 | |
| app_file: handler.py | |
| pinned: false | |
| # FLAN-T5 Custom Inference Handler | |
| This is a custom inference handler for the FLAN-T5-Large model, designed to be deployed as a Hugging Face Inference Endpoint. | |
| ## Features | |
| - Uses FLAN-T5-Large model for text generation | |
| - Customizable generation parameters | |
| - Docker-based deployment | |
| - Optimized for inference | |
| ## Usage | |
| The handler accepts POST requests with the following format: | |
| ```json | |
| { | |
| "inputs": "Your text prompt here" | |
| } | |
| ``` | |
| ## Parameters | |
| The handler supports the following generation parameters: | |
| - max_length: 512 | |
| - min_length: 32 | |
| - temperature: 0.9 | |
| - top_p: 0.95 | |
| - top_k: 50 |