abliteration.org

An open catalog and research platform for abliterated language models. Live at abliteration.org.

What we do

We track the entire market of language models that have had their refusal direction removed - through direct weight editing, layer ablation, DPO healing, custom fine-tuning, or repackaging. Every model, every quantization, every weight file, with a timestamp of when it entered the market.

At present, the catalog tracks 15,000+ abliterated models from 3,600+ distinct authors, across more than 1,000 TB of weight files. Refreshed hourly.

Three parallel pieces of work

• The catalog - every abliterated model as it appears, with metadata, weight files, sizes, and hashes. Browse it at abliteration.org/models
• Market analytics - the whole field measured at once: reaction time to new base models, generational depth of fork chains, author concentration, community favourites, disappearances. Live at abliteration.org/market
• The wiki - long-form context on what abliteration is, how our numbers are computed, and what the fork graph reveals about the open-weight ecosystem. At abliteration.org/wiki

Why this matters

When a model's refusal layer is removed, what remains is not the same model with an off switch flipped. The operation changes behavior in ways that are still not fully understood. Studying those shifts across thousands of abliterated variants is a way of studying what the refusal layer was actually doing in the first place.

The population itself is a cultural artifact: chains six generations deep, authors who publish hundreds of models, families that dominate the market for a season and fade. This is the first place where any of that becomes visible.

Get in touch

• Website: abliteration.org
• Contact: contact@catyonic.com
• RSS feed: abliteration.org/rss.xml - new models as they appear

Operated by Catyonic OÜ, Tallinn, Estonia.