Hugging Face's logo
Facu Vlad J's picture
Open to Collab
28 2 1007

Facu Vlad J

groxaxo
nekolee's profile picture CrisTheFox's profile picture robert123331's profile picture
·
https://github.com/groxaxo

AI & ML interests

Cloud Engineer · AI Automation Engineer · Quantization Gremlin I build cloud systems, automate the boring parts, and squeeze absurd efficiency out of AI models. Into infra, agents, vLLM, local GPU rigs, and quantizations that make big models run where they probably shouldn’t.

Recent Activity

reacted to mmhamdy's post with 🚀 about 3 hours ago
What if you could train a model on just 10 images instead of 60,000 and still get close to the same performance? Traditional machine learning requires thousands, even millions, of data points to achieve high accuracy. But what if we could "distill" the entire dataset into just a few synthetic samples? This is what Dataset Distillation offers. Unlike traditional knowledge distillation, we keep the model fixed and distill the knowledge contained in a massive training set into a tiny set of synthetic distilled images. The goal is to train a model on this ultra-small set and achieve performance that almost matches what the same model would get when trained on the massive original dataset. For example, training on only 10 distilled MNIST images (this is equivalent to a single image per class) yields 94% accuracy, compared to 99% when training on the full 60,000 images. Interestingly, these distilled images look significantly different (as you can see in the image below) from natural images because they are optimized for model training rather than for matching the correct data distribution. But that's not all. Most importantly, this same method opens the door to a potent form of data poisoning. Because distilled images are specifically optimized for rapid learning, an attacker can create a tiny set of adversarial distilled images to cause a well-trained model to forget or misclassify a specific category. What I find fascinating about dataset distillation is this: it mimics human-like learning by letting a model grasp a concept from a single example, but it does so using alien synthetic images that mean absolutely nothing to a human eye! What about you? What are your thoughts on it?
published a model about 3 hours ago
groxaxo/Carnice-V2-27b-AutoRound-W4A16-g128
updated a model about 23 hours ago
groxaxo/Qwen3.6-27B-uncensored-heretic-v2-Native-MTP-Preserved-W8A8
View all activity

Organizations

None yet