🤝 Open to Collab

Ramshankar

Ram07

13 7 6

AI & ML interests

NLP, GPU Inference Optimization, GAN

Recent Activity

upvoted an article about 20 hours ago

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

upvoted an article 16 days ago

Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs

new activity about 1 month ago

Aryagm/HRM-Text-1B-MLX-4bit:Benchmark and token/sec is missing!

View all activity

Organizations

upvoted an article about 20 hours ago

Article

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, nouamanetazi, lvwerra, sergiopaniego

•

Mar 10

• 168

upvoted an article 16 days ago

Article

Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs

lujangusface

•

Apr 3

• 9

upvoted 2 articles 9 months ago

Article

Uncensor any LLM with abliteration

mlabonne

•

Jun 13, 2024

• 871

Article

ModernVBERT: Towards Smaller Visual Document Retrievers

paultltc

•

Oct 3, 2025

• 46

upvoted an article about 1 year ago

Article

Introduction to State Space Models (SSM)

lbourdois

•

Jul 19, 2024

• 233

upvoted a paper over 1 year ago

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13, 2025 • 172

upvoted a paper over 2 years ago

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Paper • 2403.03507 • Published Mar 6, 2024 • 191

Ramshankar

AI & ML interests

Recent Activity

Organizations

Ram07's activity

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

Speculative Decoding in Practice: How EAGLE3 Makes LLMs Faster Without Changing Their Outputs

Uncensor any LLM with abliteration

ModernVBERT: Towards Smaller Visual Document Retrievers

Introduction to State Space Models (SSM)