Konstantin PRO

apsys's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a model 3 days ago

whitecircle/GLM-4.7-Flash-Coder

Text Generation • 30B • Updated 7 days ago • 28k • 10

posted an update 9 days ago

view post

Post

65

43% less answer time in a looped transformer by changing answer supervision

check out https://x.com/advprop/status/2098087083470373010?s=20 + full writeup linked there

See translation

🔥

1

1

+

Reply

updated a model 3 months ago

apsys/minang-embedder

Sentence Similarity • 0.2B • Updated Jun 18 • 20

published a model 3 months ago

apsys/minang-embedder

Sentence Similarity • 0.2B • Updated Jun 18 • 20

New activity in inclusionAI/Ring-mini-2.0 7 months ago

Fix _init_weights and RotaryEmbedding for transformers v5.x compatibility

1

#10 opened 7 months ago by

apsys

updated a dataset 7 months ago

Vikhrmodels/s-shlepa-metainfo

Viewer • Updated Feb 12 • 36 • 35

commented on TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell 8 months ago

view reply

sure, https://github.com/advpropsys/fp4-blackwell-bench

published an article 9 months ago

view article

Article

TFLOPS Gap: Why FP4 MoE Kernel Engineering Matters on Blackwell

• 

apsys

•

Jan 5

• 14

updated 2 datasets 9 months ago

Vikhrmodels/s-shlepa-metainfo

Viewer • Updated Feb 12 • 36 • 35

Vikhrmodels/s-shlepa-metainfo

Viewer • Updated Feb 12 • 36 • 35