Prateek Sikdar

prateeksikdar's activity

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

published 2 Spaces 9 days ago

Sleeping

CHIAR-former Heatmap

🚀

Token routing heatmap

No application file

Agents

CHIAR-former Demo

💻

updated a model 9 days ago

prateeksikdar/CHIAR-former

Updated 9 days ago

published a model 10 days ago

prateeksikdar/CHIAR-former

Updated 9 days ago

upvoted a paper 21 days ago

Chiaroscuro Attention: Spending Compute in the Dark

Paper • 2606.08327 • Published 24 days ago • 1

submitted 2 papers to Daily Papers 21 days ago

Chiaroscuro Attention: Spending Compute in the Dark

Paper • 2606.08327 • Published 24 days ago • 1

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

Paper • 2606.01838 • Published 29 days ago • 2

authored a paper 22 days ago

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

Paper • 2606.01838 • Published 29 days ago • 2

upvoted a paper 22 days ago

LayerRoute: Input-Conditioned Adaptive Layer Skipping via LoRA Fine-Tuning for Agentic Language Models

Paper • 2606.01838 • Published 29 days ago • 2

updated a model about 2 years ago

prateeksikdar/Bitnet-Llama-70M

Text Generation • 77.5M • Updated Apr 12, 2024 • 4

updated 2 datasets about 2 years ago

prateeksikdar/Cosmopedia-100k-pretrain

Updated Apr 10, 2024 • 3

prateeksikdar/Cosmopedia-100k

Updated Apr 10, 2024 • 1