Hugging Face's logo
DeathGodlike's picture
3 62 359

DeathGodlike

DeathGodlike
Moeftie's profile picture Fishtiks's profile picture Gipson658's profile picture
·

AI & ML interests

None yet

Recent Activity

reacted to narugo1992's post with 🤯 about 2 hours ago
Org Rate Limits = Free DDoS Invitation? 🤡 One serious question: Is there any way to actually ban clowns abusing this system? Right now all it takes is one bored script kiddie with a grudge (or too much caffeine) to lawnmower an entire org's API endpoints into the stone age. They get to bathe in 429s while we're sitting here like 🤡 "Gee I wonder whose IP is carpet-bombing us today!" The kicker? Zero accountability. Zero fingerprints. Just vibes™ and chaos. It’s basically a public invitation to hold entire communities hostage while wearing pajamas. "Come for the open-source collaboration, stay for the unhinged DDoS piñata party!" 🎉 Fix when?
liked a model about 2 hours ago
unsloth/GLM-4.6-REAP-268B-A32B-GGUF
reacted to codelion's post with 🔥 1 day ago
On this day in 2019, OpenAI released the final GPT-2 model as part of their staged release. I still remember that November well - so much was happening, but GPT-2's release felt like a watershed moment for the field. It showed us what was possible with carefully trained language models. To recreate some of that GPT-2 magic, I recently tackled an interesting challenge: can you pretrain a language model with just 1 billion tokens - roughly 1/10th of what GPT-2 used - and still get comparable performance? After 50+ systematic experiments testing different dataset mixtures, the answer is yes. The result is https://huggingface.co/codelion/gpt-2-70m, which achieves over 90% of GPT-2's benchmark performance despite being trained on 10x less data. The key was finding the optimal dataset composition: 50% high-quality textbook PDFs, 30% filtered web content, and 20% educational resources. It even beats GPT-2 on TruthfulQA (47.31% vs 40.69%). If you're interested in the full story of how we discovered this optimal mixture and why curriculum learning catastrophically failed, check out the complete article: https://huggingface.co/blog/codelion/optimal-dataset-mixing Sometimes less really is more - when you mix it right.
View all activity

Organizations

None yet