319 127 817

Maxime Labonne PRO

mlabonne

https://mlabonne.github.io/blog

AI & ML interests

Post-training, model editing, quantization

Recent Activity

upvoted a paper about 15 hours ago

Enhancing Human-Like Responses in Large Language Models

replied to CultriX's post about 20 hours ago

# Space for Multi-Agent Workflows using AutoGen Hi all, I created this "AutoGen Multi-Agent Workflow" space that allows you to experiment with multi-agent workflows. By default, it allows code generation with built-in quality control and automatic documentation generation. It achieves this by leveraging multiple AI agents working together to produce high-quality code snippets, ensuring they meet the specified requirements. In addition to the default, the space allows users to set custom system messages for each assistant, potentially completely changing the workflow. # Workflow Steps 1. User Input: - The user defines a prompt, such as "Write a random password generator using python." - Outcome: A clear task for the primary assistant to accomplish. 2. Primary Assistant Work: - The primary assistant begins working on the provided prompt. It generates an initial code snippet based on the user's request. - Outcome: An initial proposal for the requested code. 3. Critic Feedback: - The critic reviews the generated code provides feedback or (if the output meets the criteria), broadcasts the APPROVED message. (This process repeats until the output is APPROVED or 10 messages have been exchanged). - Outcome: A revised Python function that incorporates the critic's feedback. 4. Documentation Generation: - Once the code is approved, it is passed to a documentation assistant. The documentation assistant generates a concise documentation for the final code. - Outcome: A short documentation including function description, parameters, and return values. Enjoy! https://huggingface.co/spaces/CultriX/AutoGen-MultiAgent-Example

reacted to CultriX's post with ❤️ about 20 hours ago

View all activity

Articles

Organizations

Posts 5

Post

18059

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?

Post

18662

✂️ 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