Fabian

Fabian on Hugging Face Daily Papers: 3 papers, 1 in the top 3 of their day, 109 upvotes.

1. ZClip: Adaptive Spike Mitigation for LLM Pre-Training 74 upvotes, #2 of 2025-04-04
2. A Refined Analysis of Massive Activations in LLMs 13 upvotes, #14 of 2025-03-31
3. Variance Control via Weight Rescaling in LLM Pre-training 4 upvotes, #27 of 2025-03-25

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.