Menan Velayuthan's picture

3 8 2

Menan Velayuthan

velmen

·

AI & ML interests

Machine learning with graphs

Recent Activity

reacted to Jaward's post with ❤️ 24 days ago

nanoBLT: Simplified lightweight implementation of a character-level Byte Latent Transformer model (under 500 lines of code). The model is 2x4x2 (n_layers_encoder, n_layers_latent, n_layers_decoder) layer deep trained on ~1M bytes of tiny Shakespeare with a patch size of 4. Code: https://github.com/Jaykef/ai-algorithms/blob/main/byte_latent_transformer.ipynb

upvoted an article 26 days ago

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

upvoted an article 30 days ago

Gotchas in Tokenizer Behavior Every Developer Should Know

View all activity

Organizations

models 1

velmen/phi3-mini-yoda-adapter

Updated May 13, 2025

datasets 0

None public yet