Hugging Face's logo
Maxime Labonne's picture
TFLOPS icon 43.9 TFLOPS
312 124 810

Maxime Labonne PRO

mlabonne
2mal16's profile picture Rizkyy702's profile picture sutianze's profile picture
·
https://mlabonne.github.io/blog

AI & ML interests

Post-training, model editing, quantization

Articles

Organizations

Blog-explorers's profile picture Qwen's profile picture ZeroGPU Explorers's profile picture Merge Crew's profile picture Social Post Explorers's profile picture Liquid AI's profile picture gg-tt's profile picture rg-preview's profile picture

Posts 5

view post
Post
15398
Large models are surprisingly bad storytellers.

I asked 8 LLMs to "Tell me a bedtime story about bears and waffles."

Claude 3.5 Sonnet and GPT-4o gave me the worst stories: no conflict, no moral, zero creativity.

In contrast, smaller models were quite creative and wrote stories involving talking waffle trees and bears ostracized for their love of waffles.

Here you can see a comparison between Claude 3.5 Sonnet and NeuralDaredevil-8B-abliterated. They both start with a family of bears but quickly diverge in terms of personality, conflict, etc.

I mapped it to the hero's journey to have some kind of framework. Prompt engineering can definitely help here, but it's still disappointing that the larger models don't create better stories right off the bat.

Do you know why smaller models outperform the frontier models here?
view post
Post
15880
✂️ 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
View all posts

Collections 10

🧠 Abliteration
Uncensored models using abliteration. See this article for more information: huggingface.co/blog/mlabonne/abliteration

Papers 6