Hugging Face's logo

Spaces:
ButterM40
/
Roleplay-Chat-Box
Running

App Files Community
Roleplay-Chat-Box / README.md
ButterM40's picture
ButterM40
Switch from Gradio to Streamlit - more stable for HF Spaces
9fb3586
preview code
|
raw
history blame contribute delete
1.29 kB

A newer version of the Streamlit SDK is available: 1.52.2

Upgrade
metadata
title: Roleplay Chat Box 🎭
emoji: 🎭
colorFrom: purple
colorTo: pink
sdk: streamlit
app_file: app_streamlit.py
pinned: false
license: mit
short_description: AI roleplay chat with 3 unique characters
tags:
  - conversational-ai
  - roleplay
  - lora
  - character-ai
  - chatbot
  - transformers
  - qwen

Roleplay Chat Box 🎭

An intelligent conversational AI system featuring multiple character personalities powered by LoRA (Low-Rank Adaptation) fine-tuned language models.

⚠️ Important Notes for HuggingFace Spaces

This app requires significant resources:

  • Model: Qwen/Qwen3-0.6B (will be downloaded from HuggingFace Hub)
  • Memory: ~4GB RAM minimum for model loading
  • Storage: LoRA adapters are included in the repo

The app will automatically download the base model from HuggingFace on first run. This may take a few minutes.

Characters

  1. Moses - Biblical prophet with wisdom and authority
  2. Samsung Employee - Tech-savvy corporate representative
  3. Jinx - Complex, chaotic character from Arcane

How It Works

  • Uses a shared base model (Qwen3-0.6B) from HuggingFace
  • Switches between character-specific LoRA adapters
  • LoRA adapters are tiny (few MB each) vs full models (GB each)
  • Efficient memory usage by sharing one base model