Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
32
3
1
Stas Bekman
stas
Follow
JonathanFly's profile picture
RafaelZequeira's profile picture
stefan-it's profile picture
127 followers
·
4 following
https://stasosphere.com/machine-learning/
StasBekman
stas00
stasbekman
AI & ML interests
Toolmaker. Software creator, optimizer and harmonizer. Makes things work and fly at Snowflake AI Research Training LLM/RAG/Generative AI/Machine Learning/Scalability
Recent Activity
posted
an
update
about 16 hours ago
Good news! Ulysses Sequence Parallelism from the Snowflake AI Research and the Deepspeed teams has been integrated into HuggingFace Trainer, Accelerate and TRL For extensive details please see this writeup: https://huggingface.co/blog/ulysses-sp Thanks a lot to Kashif Rasul for helping make it happen. Also the others in the HF team who helped with integration.
published
an
article
2 days ago
Ulysses Sequence Parallelism: Training with Million-Token Contexts
authored
a paper
about 1 month ago
Arctic Long Sequence Training: Scalable And Efficient Training For Multi-Million Token Sequences
View all activity
Organizations
stas
's datasets
9
Sort:Â Recently updated
stas/gutenberg-100
Viewer
•
Updated
Nov 3, 2025
•
99
•
449
stas/openwebtext-synthetic-testing
Updated
Nov 14, 2023
•
30
•
4
stas/oscar-en-10k
Viewer
•
Updated
Oct 19, 2022
•
10k
•
87
•
2
stas/c4-en-10k
Viewer
•
Updated
Oct 19, 2022
•
10k
•
422
•
5
stas/general-pmd-synthetic-testing
Updated
Oct 18, 2022
•
29
stas/cm4-synthetic-testing
Updated
Oct 18, 2022
•
41
stas/openwebtext-10k
Updated
Sep 15, 2021
•
3.46k
•
32
stas/wmt14-en-de-pre-processed
Viewer
•
Updated
Feb 16, 2021
•
4.55M
•
47
•
3
stas/wmt16-en-ro-pre-processed
Viewer
•
Updated
Feb 16, 2021
•
614k
•
44