Suchir Salhan

suchirsalhan

AI & ML interests

Multilinguality and Cognitively-Inspired AI. Tokenization, Pretraining, Interpretability & Alignment.

Recent Activity

updated a dataset about 1 hour ago
MultilingualUnigramLM/FineWeb2-10K
published a dataset about 2 hours ago
MultilingualUnigramLM/FineWeb2-10K
published a model 11 days ago
suchirsalhan/unimix-ru_uk-xlm-roberta-base
View all activity

Organizations

SomosNLP's profile picture CLIMB's profile picture ALTA's profile picture CLIMB-MAO's profile picture Pico Language Model's profile picture ADA-LM's profile picture Looking to Learn's profile picture Cambridge-KAIST's profile picture Cambridge-KAIST2's profile picture BabyLM Challenge's profile picture ByteSpan Tokenisers's profile picture BabyLM Sequence Length's profile picture ContingentChat's profile picture Multilingual UnigramLM's profile picture Beetles's profile picture