Data

Tools

Indexes

Applications

Experiments

Open Source Science

https://github.com/algorithmic-alignment-lab/character-training

https://github.com/algorithmic-alignment-lab/character-training

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ○
    CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (3.4%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Algorithmic-Alignment-Lab
  • Language: Python
  • Default Branch: main
  • Size: 123 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created about 1 year ago · Last pushed 10 months ago
Metadata Files
Readme

README.md

Character Training

This repository contains the code for training and evaluating AI characters.

Webapp

To browse and inspect conversation JSON files, you can use the webapp located in evals/webapp.

Setup

  1. Install Flask: bash pip install flask

  2. Navigate to the webapp directory: bash cd evals/webapp

  3. Start the Flask development server: bash python app.py

  4. Open your browser and go to: http://localhost:8555

Screenshot

WebApp Screenshot

Owner

  • Name: Algorithmic Alignment Group
  • Login: Algorithmic-Alignment-Lab
  • Kind: organization
  • Location: United States of America

GitHub Events

Total
  • Public event: 1
  • Push event: 35
  • Create event: 3
Last Year
  • Public event: 1
  • Push event: 35
  • Create event: 3

Dependencies

conversations_ui/requirements.txt pypi
  • anthropic *
  • litellm *
  • openai *
  • pydantic *
  • requests *
  • streamlit *
safety-tooling/pyproject.toml pypi
  • Jinja2 ==3.1.6
  • anthropic ==0.49.0
  • datasets ==3.5.0
  • dotenv ==0.9.9
  • elevenlabs ==1.56.0
  • google-cloud-aiplatform ==1.87.0
  • google-generativeai ==0.8.4
  • grayswan-api ==0.1.0a49
  • huggingface_hub *
  • jsonlines ==4.0.0
  • librosa ==0.10.2.post1
  • llvmlite ==0.44.0
  • matplotlib ==3.10.1
  • openai ==1.70.0
  • opencv-python ==4.11.0.86
  • pandas ==2.2.3
  • plotly ==6.0.1
  • pydantic ==2.11.1
  • pydub ==0.25.1
  • pytest ==8.3.5
  • pytest-asyncio ==0.26.0
  • pytest-xdist ==3.6.1
  • python-io ==0.3
  • redis ==5.2.1
  • scikit-learn ==1.6.1
  • scipy ==1.15.2
  • seaborn ==0.13.2
  • simple-parsing ==0.1.7
  • soundfile ==0.13.1
  • tenacity ==9.1.2
  • termcolor ==3.0.1
  • tiktoken ==0.9.0
  • together ==1.5.4
  • tqdm ==4.67.1
  • transformers ==4.50.3
  • wandb ==0.19.9
safety-tooling/requirements_dev.txt pypi
  • black ==24.10.0 development
  • ipykernel ==6.29.5 development
  • ipywidgets ==8.1.5 development
  • jupyterlab ==4.3.4 development
  • pre-commit * development
  • ruff ==0.9.0 development
safety-tooling/uv.lock pypi
  • 177 dependencies