.env.example
Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow.
WANDB_API_KEY
secret
I recommend setting your API key here if you're going to ssh into a new machine and use the local backend
GIT_USER_NAME
Optional, git-related environment variables You may need these if you want to make any git commits on a new machine
GIT_USER_EMAIL
GITHUB_TOKEN
secret
A GitHub token might be required for commiting to the private `agent-reinforcement-training` repository
HF_TOKEN
secret
HuggingFace Token (optional for most models, necessary for training gated models like Llama 3.1)
OPENPIPE_API_KEY
secret
Optional, OpenPipe API key
TOGETHER_API_KEY
secret
Optional, Together API key (used for deploying models to Together)
AWS_ACCESS_KEY_ID
secret
Optional, S3 configuration for log and model backups
AWS_SECRET_ACCESS_KEY
secret
AWS_REGION
secret
BACKUP_BUCKET
brew install flyctl && fly launch --from https://github.com/abidlabs/art
curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/abidlabs/art
iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/abidlabs/art