atlasia/MoulSot_Extra
Viewer
ā¢
Updated
ā¢
275k
ā¢
20
ā¢
2
abdeljalil_elma
abdeljalilELmajjodi
AI & ML interests
None yet
Recent Activity
liked
a dataset
4 days ago
atlasia/MoulSot_Extra
liked
a model
4 days ago
nari-labs/Dia2-2B
liked
a model
9 days ago
facebook/sam3
Organizations
liked
a
dataset
4 days ago
liked
a
model
4 days ago
liked
a
model
9 days ago
liked
a
dataset
12 days ago
liked
a
dataset
16 days ago
reacted to
nouamanetazi's
post with ššš¤ā¤ļø
20 days ago
Post
3889
After training šš¦šØš„ššš on ššš ššššš¬ for nearly a month, I've come to realize something most people overlook: š¢š§šš«šš¬šš«š®ššš®š«š š¢š¬ šš”š š¦šš¤š-šØš«-šš«ššš¤ šššššØš« š¢š§ ššš šš«šš¢š§š¢š§š . š„
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious šššš šš«š«šØš«š¬, or when your expensive GPU cluster is running at šš% šššš¢šš¢šš§šš², the problem isn't your model. It's most probably a š¦š¢š¬š®š¬š šØš šš”š š”šš«šš°šš«š. š ļø
Questions that seemed simple but had no clear answers: Why is ššØš šš«šš¢š§š¢š§š š¬š„šØš°šš« šš”šš§ ššš§š¬š š¦šØššš„š¬? Which šššš šš„šš š¬ should we actually set? How often should we checkpoint without killing throughput?
That's why we built šš”š šš¦šØš„ šš«šš¢š§š¢š§š šš„šš²ššØšØš¤ š: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the š¢š§šš«šš¬šš«š®ššš®š«š š„šš²šš« that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: šššš š”š¢ššš¢š§š š šš/š¬, šššš¢š§š¤ š.š š«šššš”š¢š§š ššš šš/š¬, šššš ššš§š šš šš.š šš/š¬. Then we ran collective operations across ššš šššš¬ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ššš šš/š¬ on a single node to ššš-ššš šš/š¬ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
šš”š šš¦šØš„ šš«šš¢š§š¢š§š šš„šš²ššØšØš¤: https://lnkd.in/e5MKXUHS
Shared with ā¤ļø by the HuggingFace team
Everyone talks about model architecture and data quality. And yes, those matter immensely. But here's what nobody tells you: when your training run fails at 2 AM because of mysterious šššš šš«š«šØš«š¬, or when your expensive GPU cluster is running at šš% šššš¢šš¢šš§šš², the problem isn't your model. It's most probably a š¦š¢š¬š®š¬š šØš šš”š š”šš«šš°šš«š. š ļø
Questions that seemed simple but had no clear answers: Why is ššØš šš«šš¢š§š¢š§š š¬š„šØš°šš« šš”šš§ ššš§š¬š š¦šØššš„š¬? Which šššš šš„šš š¬ should we actually set? How often should we checkpoint without killing throughput?
That's why we built šš”š šš¦šØš„ šš«šš¢š§š¢š§š šš„šš²ššØšØš¤ š: a complete guide covering everything from model architecture and data curation to the SmolLM3 training marathon, post-training techniques, and crucially, the š¢š§šš«šš¬šš«š®ššš®š«š š„šš²šš« that most teams get wrong.
We validated real vs theoretical bandwidth across the entire stack: šššš š”š¢ššš¢š§š š šš/š¬, šššš¢š§š¤ š.š š«šššš”š¢š§š ššš šš/š¬, šššš ššš§š šš šš.š šš/š¬. Then we ran collective operations across ššš šššš¬ (16 nodes, 8xH100s each) and measured how performance degrades at scale: all-reduce drops from ššš šš/š¬ on a single node to ššš-ššš šš/š¬ across 16 nodes.
If you've ever wondered why your training runs are slower than they should be, or you're planning to scale up and want to avoid expensive mistakes, this guide might save you weeks of debugging.
šš”š šš¦šØš„ šš«šš¢š§š¢š§š šš„šš²ššØšØš¤: https://lnkd.in/e5MKXUHS
Shared with ā¤ļø by the HuggingFace team
liked
a
model
20 days ago
liked
a
model
21 days ago
liked
a
Space
21 days ago
updated
a
dataset
22 days ago
published
a
dataset
22 days ago
liked
a
model
22 days ago
upvoted
a
paper
22 days ago
liked
a
Space
24 days ago
liked
a
model
24 days ago
liked
a
Space
26 days ago
reacted to
DmitryRyumin's
post with š„
29 days ago
Post
2825
ššš New Research Alert - ICCV 2025 (Oral)! šš¤š
š Title: Understanding Co-speech Gestures in-the-wild š
š Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
š„ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
š Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
š Repository: https://github.com/Sindhu-Hegde/jegal
šŗ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight
š Title: Understanding Co-speech Gestures in-the-wild š
š Description: JEGAL is a tri-modal model that learns from gestures, speech and text simultaneously, enabling devices to interpret co-speech gestures in the wild.
š„ Authors: @sindhuhegde , K R Prajwal, Taein Kwon, and Andrew Zisserman
š Conference: ICCV, 19 ā 23 Oct, 2025 | Honolulu, Hawai'i, USA šŗšø
š Paper: Understanding Co-speech Gestures in-the-wild (2503.22668)
š Web Page: https://www.robots.ox.ac.uk/~vgg/research/jegal
š Repository: https://github.com/Sindhu-Hegde/jegal
šŗ Video: https://www.youtube.com/watch?v=TYFOLKfM-rM
š ICCV-2023-25-Papers: https://github.com/DmitryRyumin/ICCV-2023-25-Papers
š Added to the Human Modeling Section: https://github.com/DmitryRyumin/ICCV-2023-25-Papers/blob/main/sections/2025/main/human-modeling.md
š More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
š Keywords: #CoSpeechGestures #GestureUnderstanding #TriModalRepresentation #MultimodalLearning #AI #ICCV2025 #ResearchHighlight