Aleksandr Samarin

astrlrd's activity

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

updated 8 models about 14 hours ago

nebius/EAGLE3-Qwen3-235B-A22B-Instruct-2507

Text Generation • 0.6B • Updated about 14 hours ago • 2

nebius/EAGLE3-Llama-3.3-70B-Instruct

Text Generation • 1B • Updated about 14 hours ago • 2

nebius/EAGLE3-gpt-oss-120b

Text Generation • 0.4B • Updated about 14 hours ago • 2

nebius/EAGLE3-gpt-oss-20b

Text Generation • 0.4B • Updated about 14 hours ago • 4

nebius/MLP-Speculator-Llama-3.1-8B-Instruct

Text Generation • 0.2B • Updated about 14 hours ago • 5

nebius/MEDUSA-Llama-3.1-8B-Instruct

Text Generation • 3B • Updated about 14 hours ago • 13

nebius/EAGLE3-Llama-3.1-8B-Instruct

Text Generation • 0.4B • Updated about 14 hours ago • 12

nebius/MTP-DeepSeek-V3-0324

Text Generation • 13B • Updated about 14 hours ago • 29 • 1

upvoted a paper about 14 hours ago

LK Losses: Direct Acceptance Rate Optimization for Speculative Decoding

Paper • 2602.23881 • Published 4 days ago • 15

updated 6 datasets about 14 hours ago

nebius/DeepSeek-V3-Infinity-Instruct-0625

Viewer • Updated about 8 hours ago • 660k • 5

nebius/Qwen3-235B-Instruct-Infinity-Instruct-0625

Viewer • Updated about 8 hours ago • 660k • 5

nebius/gpt-oss-20b-Infinity-Instruct-0625

Viewer • Updated about 8 hours ago • 660k • 6

nebius/Llama-3.3-70B-Instruct-Infinity-Instruct-0625

Viewer • Updated about 8 hours ago • 660k • 5

nebius/Llama-3.1-8B-Instruct-Infinity-Instruct-0625

Viewer • Updated about 8 hours ago • 660k • 25

nebius/gpt-oss-120b-Infinity-Instruct-0625

Viewer • Updated about 8 hours ago • 659k • 5

upvoted 2 collections about 14 hours ago

Infinity-Instruct-Completions

Collection

Training data for speculative decoding draft models, containing model-generated responses for 660K prompts from Infinity-Instruct-0625. • 6 items • Updated about 12 hours ago • 2

LK-Speculators

Collection

High-performance speculative decoding draft models trained using LK losses, a novel training objectives that directly optimize acceptance rate • 8 items • Updated about 12 hours ago • 4

published 3 models about 14 hours ago

nebius/EAGLE3-Qwen3-235B-A22B-Instruct-2507

Text Generation • 0.6B • Updated about 14 hours ago • 2

nebius/EAGLE3-Llama-3.3-70B-Instruct

Text Generation • 1B • Updated about 14 hours ago • 2

nebius/EAGLE3-gpt-oss-120b

Text Generation • 0.4B • Updated about 14 hours ago • 2