clam004 / rlhf

fine tuning natural language generation using a reinforcement learning signal

language_reinforce

fine tuning natural language generation using a reinforcement learning signal

python virtual environment

you@you chat-api % python3 -m venv venv
you@you chat-api % source venv/bin/activate
(venv) you@you chat-api % pip install --upgrade pip
(venv) you@you chat-api % pip install -r requirements.txt