Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
171.2
TFLOPS
6
1
4
Serveurperso
PRO
Serveurperso
Follow
victor's profile picture
1 follower
·
19 following
https://www.serveurperso.com
AI & ML interests
None yet
Recent Activity
liked
a Space
5 days ago
lerobot/robot-learning-tutorial
updated
a model
7 days ago
Serveurperso/OuteTTS-Voices
reacted
to
grimjim
's
post
with 👍
10 days ago
Going forward, I will be adopting the term Magnitude-Preserving Orthogonal Ablation (MPOA) for my recent work in mitigating model damage from abliteration. The technique potentially unlocks reasoning capacity previously occupied with safety refusal processing. For details, start here: https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration Showcase results: https://huggingface.co/grimjim/gemma-3-12b-it-norm-preserved-biprojected-abliterated (outperforms base instruct on UGI Leaderboard NatInt) (The existing name, while technically accurate, was a bit of a mouthful.)
View all activity
Organizations
Serveurperso
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
upvoted
a
paper
9 months ago
Qwen2.5-VL Technical Report
Paper
•
2502.13923
•
Published
Feb 19
•
211