Byte-Pair Encoding

mentions 2 type Person feed RSS

// recent coverage 2 mentions

20:31

2026-09-18

pub.towardsai.net

large-language-models

I Built a Tool-Calling LLM From Absolute Zero — Here’s Everything I Learned

Developer Vidit Raj released Pebble, an open-source 25-million-parameter language model built entirely from scratch that can call tools such as a calculator or weather API, publishing the code on GitH…

04:00

2026-07-28

arxiv.org

natural-language-processing

BHARATI: Morphology-Aware Tokenizers for Classical Indian Languages with Subword Fertility Analysis

Researchers have developed BHARATI, a set of SentencePiece BPE tokenizers for classical Indian languages, achieving a 90% reduction in sequence length compared to GPT-2 on a held-out test set of 490 I…

// co-occurs with top 8 entities

GPT-2 2 Pebble 1 Vidit Raj 1 GitHub 1 GPT-4 1 Claude 1 GPT-5 1 BHARATI 1

// topics top 6 topics

large language models 2 ai research 2 developer tools 2 ai agents 1 ai tools 1 natural language processing 1