Article
Improving Hugging Face Training Efficiency Through Packing with Flash Attention
•
33
Daniil Suhoi
Isayoften
AI & ML interests
LLM pretrain research engineer
Recent Activity
liked
a model
about 1 month ago
yandex/YandexGPT-5-Lite-8B-pretrain
upvoted
an
article
6 months ago
Improving Hugging Face Training Efficiency Through Packing with Flash Attention
new activity
7 months ago
ai-forever/ru-en-RoSBERTa:Подходит ли эта модель для similarity search?
Organizations
Isayoften's activity
upvoted
an
article
6 months ago
upvoted
an
article
10 months ago
Article
Universal Image Segmentation with Mask2Former and OneFormer
•
11