Maxime Labonne PRO

mlabonne's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

commented on Uncensor any LLM with abliteration 2 days ago

view reply

Oh, here's the direct link to the Colab notebook: https://colab.research.google.com/drive/1RmLv-pCMBBsQGXQIM8yF-OdCNyoylUR1?usp=sharing

commented on Uncensor any LLM with abliteration 2 days ago

view reply

Yes, it should work!

commented on Uncensor any LLM with abliteration 2 days ago

view reply

I recommend using AutoAbliteration instead: https://huggingface.co/posts/mlabonne/714992455492422

New activity in mlabonne/drllama-7b 2 days ago

Adding `safetensors` variant of this model

#1 opened 3 days ago by

SFconvertbot

liked a Space 4 days ago

Running on CPU Upgrade

78

78

Try YourBench!

🪄

Generate a custom benchmark from any document

upvoted a collection 5 days ago

🧠 Reasoning datasets

Collection

Datasets with reasoning traces for math and code released by the community • 20 items • Updated 6 days ago • 122

liked a dataset 6 days ago

virtuoussy/Multi-subject-RLVR

Viewer • Updated 5 days ago • 579k • 519 • 42

updated a model 6 days ago

mlabonne/gemma-3-27b-it-abliterated-GGUF

Image-Text-to-Text • Updated 6 days ago • 47.7k • 46

New activity in mlabonne/gemma-3-27b-it-abliterated-GGUF 6 days ago

Need mmproj file

5

#2 opened 7 days ago by

notmebug

liked 2 Spaces 7 days ago

Running on Zero

2

2

TwinLlama-3.1-8B

👥

Generate chat responses based on user input

Sleeping

4

4

TwinLlama-3.1-8B-DPO

👥

Generate responses to text-based prompts

New activity in mlabonne/gemma-3-27b-it-abliterated-GGUF 7 days ago

Need mmproj file

5

#2 opened 7 days ago by

notmebug

reacted to burtenshaw's post with 🚀❤️🤗 7 days ago

view post

Post

2591

NEW UNIT in the Hugging Face Reasoning course. We dive deep into the algorithm behind DeepSeek R1 with an advanced and hands-on guide to interpreting GRPO.

🔗 reasoning-course

This unit is super useful if you’re tuning models with reinforcement learning. It will help with:

- interpreting loss and reward progression during training runs
- selecting effective parameters for training
- reviewing and defining effective reward functions

This unit also works up smoothly toward the existing practical exercises form @mlabonne and Unsloth.

📣 Shout out to @ShirinYamani who wrote the unit. Follow for more great content.

See translation

• 
• 1 reply

·

❤️

11

11

🤗

10

10

🚀

6

6

+

Reply

New activity in mradermacher/gemma-3-27b-it-abliterated-GGUF 7 days ago

This is the best one.

5

#1 opened 8 days ago by

Slaughterpony

liked a model 16 days ago

mlabonne/gemma-3-1b-it-abliterated-GGUF

Image-Text-to-Text • Updated 16 days ago • 1.1k • 5

updated 3 models 16 days ago

mlabonne/gemma-3-1b-it-abliterated-GGUF

Image-Text-to-Text • Updated 16 days ago • 1.1k • 5

mlabonne/gemma-3-1b-it-abliterated

Image-Text-to-Text • Updated 16 days ago • 495 • 3

mlabonne/gemma-3-27b-it-abliterated

Image-Text-to-Text • Updated 16 days ago • 4.83k • 123