Hugging Face's logo

Merge Crew

Activity Feed Request to join this org

AI & ML interests

Merging models

merge-crew's activity

mlabonne 
posted an update 11 days ago
view post
Post
3292
🆕 LLM Course 2025 edition!

I updated the LLM Scientist roadmap and added a ton of new information and references. It covers training, datasets, evaluation, quantization, and new trends like test-time compute scaling.

The LLM Course has been incredibly popular (41.3k stars!) and I've been touched to receive many, many messages about how it helped people in their careers.

I know how difficult this stuff can be, so I'm super proud of the impact it had. I want to keep updating it in 2025, especially with the LLM Engineer roadmap.

Thanks everyone, hope you'll enjoy it!

💻 LLM Course: https://huggingface.co/blog/mlabonne/llm-course
mlabonne 
authored a paper 2 months ago
SyedAbdul 
authored a paper 3 months ago
KennethEnevoldsen 
authored 4 papers 5 months ago
saattrupdan 
authored a paper 6 months ago
mlabonne 
posted an update 7 months ago
view post
Post
19000
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?
·
buzzcraft 
authored 2 papers 7 months ago
KennethEnevoldsen 
authored 3 papers 8 months ago
mlabonne 
posted an update 8 months ago
view post
Post
18911
✂️ 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
·
birgermoell 
authored 4 papers 8 months ago
birgermoell 
authored a paper 9 months ago