README.md

metadata

title: Apertus on FastAPI
emoji: 🌖
colorFrom: red
colorTo: gray
sdk: docker
app_port: 8000
fullWidth: false
suggested_storage: small
suggested_hardware: t4-medium
tags:
  - apertus
license: apache-2.0

Apertus transformer on FastAPI

A FastAPI-based Python application that provides an API to interface with the Apertus LLM from the Swiss AI Initiative.

The OpenAI-compatible API is inspired by openai-compatible-fastapi.

The goal is to use the Apertus Format API in a lightweight service with an efficient, paged attention mechanism.

If you're debugging locally, it may help you to use tiny-random/apertus instead of the full model.

Terms of use

For more information on Apertus, go to https://huggingface.co/swiss-ai

This is an open source project under the Apache 2.0 License

If you have further suggestions please leave them on Codeberg Issues