creative-help / README.md
roemmele's picture
First commit
c275a0e

A newer version of the Gradio SDK is available: 6.9.0

Upgrade
metadata
title: Creative Help
emoji: ✍️
colorFrom: red
colorTo: pink
sdk: gradio
sdk_version: 5.0.0
app_file: app.py
pinned: false
license: mit

Creative Help

A word processor interface for eliciting text completions from the creative-help language model. Write freely, then type \help\ to trigger generation automatically.

How to use

  1. Write your story in the text area.
  2. Trigger a completion by typing \help\ at the end of your text — generation starts automatically.
  3. The model’s completion is appended to your text.

Setup (Space owner)

This Space calls your deployed creative-help Inference Endpoint. Configure these in Settings → Variables and Secrets:

Name Type Description
HF_ENDPOINT_URL Variable Your Inference Endpoint URL (e.g. https://xxx.us-east-1.aws.endpoints.huggingface.cloud)
HF_TOKEN Secret Your Hugging Face token with access to the endpoint

Alternatively, you can use the serverless Inference API by setting:

Name Type Description
HF_MODEL_ID Variable Model ID (e.g. username/creative-help)
HF_TOKEN Secret Your Hugging Face token

Model

This app uses the creative-help model. Deploy it as an Inference Endpoint for best performance.