Downloads · 30 days
1
4% of all-time downloads
ajagota71/irl-reward-pythia-70m
irl-reward-pythia-70m is a machine learning model from ajagota71. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was trained using maxmargin IRL to learn toxicity reward signals.
Downloads · 30 days
1
4% of all-time downloads
All-time downloads
24
Public
Parameters
70.4M
282 MB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors282 MB · 99%
From the Hugging Face model README
This model was trained using max_margin IRL to learn toxicity reward signals.
Base model: EleutherAI/pythia-70M Original model: EleutherAI/pythia-70M Detoxified model: ajagota71/pythia-70m-detox-epoch-100
tags: