Orion-zhen / abliteration
Make abliterated models with transformers, easy and fast
Why this job: works in the areas we cover, but does not say which job it does
What it does
There exist some directions that make LLMs to refuse users' input. Abliteration is a technique that can calculate the most significant refusal directions with harmful and harmless prompts, and then remove them from the model. This is a crude, proof-of-concept implementation to remove refusals from an LLM model without using TransformerLens.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 2 days ago
- Stars
- 203
- +7 this week
- Licence
- GPL-3.0
- Share-alike terms
- Downloads for
- None listed
- No release files
- Latest version
- None yet
- No releases
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 5 merged
- 0 waiting
- Releases
- None
- Never published
- No contributing guide
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| p-e-w / heretic | 40,366 | 2 days ago | AGPL-3.0 | No downloads |
| lordx64 / phantom-kv | 274 | 52 days ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 100%
Topics
- llm
- uncensored
- abliterate
- abliteration
- abliterator
Project record
- JobOther AI tools
- StatusListed
- Commits79
- Forks111
- Watching2
- Stars in 28 days+21
- CreatedDec 12, 2024
- First seen by usNov 7, 2026
- CheckedNov 12, 2026