Menan Velayuthan's picture

Menan Velayuthan

velmen

·

AI & ML interests

Machine learning with graphs

Organizations

upvoted an article 3 months ago

Article

You could have designed state of the art positional encoding

FL33TW00D-HF

•

Nov 25, 2024

• 477

upvoted 4 articles 5 months ago

Article

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

+4

itazap, ariG23498, ArthurZ, sergiopaniego, merve, pcuenq

•

Dec 18, 2025

• 124

Article

Gotchas in Tokenizer Behavior Every Developer Should Know

qgallouedec

•

Apr 18, 2025

• 72

Article

Tensor Parallelism (TP) in Transformers: 5 Minutes to Understand

qgallouedec

•

Dec 4, 2025

• 69

Article

We Got Claude to Fine-Tune an Open Source LLM

burtenshaw, evalstate

•

Dec 4, 2025

• 624

upvoted an article 6 months ago

Article

Continuous batching from first principles

+1

ror, ArthurZ, mcpotato

•

Nov 25, 2025

• 378

upvoted a paper almost 2 years ago

An Image is Worth More Than 16x16 Patches: Exploring Transformers on Individual Pixels

Paper • 2406.09415 • Published Jun 13, 2024 • 51

upvoted a collection over 2 years ago

Computer Vision Backbones 🧩

Collection of useful computer vision backbones to fine-tune. It also includes large image classification models, that can be used as backbone. • 22 items • Updated Sep 19, 2023 • 22