Hugging Face's logo
Marcus Hobbs's picture
2 41

Marcus Hobbs PRO

marcushobbs
21world's profile picture Mi6paulino's profile picture v011d's profile picture
·
https://wilsonic.co

AI & ML interests

SFT of domain expertise and conversation, edge inference, TTS, microtonality, software synthesis

Recent Activity

liked a model 3 days ago
finnvoorhees/coreml-Llama-3.2-1B-Instruct-4bit
liked a model about 1 month ago
OuteAI/OuteTTS-0.2-500M-GGUF
liked a dataset about 2 months ago
allenai/WildChat-1M
View all activity

Organizations

MLX Community's profile picture Hugging Face Discord Community's profile picture

marcushobbs's activity

liked a model 3 days ago
liked a model about 1 month ago
liked a dataset about 2 months ago
liked 2 models about 2 months ago
liked a dataset about 2 months ago
liked 4 models 2 months ago
upvoted a paper 2 months ago
liked a dataset 2 months ago
upvoted an article 2 months ago
reacted to mlabonne's post with ❤️🔥 2 months ago
view post
Post
18354
✂️ Uncensor any LLM with abliteration

I wrote an article about abliteration and how NeuralDaredevil-8B was created. Beyond removing alignment, I believe it's an interesting technique with a lot of potential. It's basically fine-tuning without retraining.

In this article, we see how it works, implement it in Google Colab, and heal the abliterated model to recover the performance drop due to this technique. The final model is an uncensored and high-quality model with the highest MMLU score on the Open LLM Leaderboard (8B category).

https://huggingface.co/blog/mlabonne/abliteration
·
liked 3 datasets 2 months ago
liked a model 2 months ago
liked a dataset 3 months ago