Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts
Paper • 2608.20061 • Published • 42
Jaegeun Han
haanjack
AI & ML interests
LLM, LLM finetuning, Network Optimization, Hardware Acceleration
Recent Activity
updated a model 3 months ago
haanjack/gemma-4-31B-mxfp4 published a model 3 months ago
haanjack/gemma-4-31B-mxfp4Organizations
upvoted a paper 5 days ago
upvoted a collection 5 months ago
upvoted an article 7 months ago
Article
Model statistics of the 50 most downloaded entities on Hugging Face
lbourdois
• • 44 upvoted a paper 12 months ago
upvoted an article about 1 year ago
Article
Welcome GPT OSS, the new open-source model family from OpenAI!
- +10
reach-vb, pcuenq, lewtun, clem, Rocketknight1, clefourrier, celinah, Wauplin, marcsun13, pagezyhf, ahadnagy, joaogante
• • 514 upvoted a collection about 1 year ago
upvoted a paper about 1 year ago
upvoted 2
articles over 1 year ago
Article
What is test-time compute and how to scale it?
Kseniase
• • 126 Article
Open-source DeepResearch – Freeing our search agents
- +3
m-ric, albertvillanova, merve, thomwolf, clefourrier
• • 1.32k