1 9 2

Farid Adilazuarda

faridlazuarda

https://faridlazuarda.github.io/

AI & ML interests

Multilinguality, Compositional Modelling, Culture

Recent Activity

liked a Space about 1 month ago

HuggingFaceTB/smol-training-playbook

upvoted a paper 2 months ago

OpenSIR: Open-Ended Self-Improving Reasoner

upvoted a paper 4 months ago

Predicting the Order of Upcoming Tokens Improves Language Modeling

View all activity

Organizations

liked a Space about 1 month ago

The Smol Training Playbook

📚

2.81k

The secrets to building world-class LLMs

upvoted a paper 2 months ago

OpenSIR: Open-Ended Self-Improving Reasoner

Paper • 2511.00602 • Published Nov 1, 2025 • 20

upvoted a paper 4 months ago

Predicting the Order of Upcoming Tokens Improves Language Modeling

Paper • 2508.19228 • Published Aug 26, 2025 • 23

New activity in GoToCompany/gemma2-9b-cpt-sahabatai-v1-instruct 5 months ago

Fix tokenizer model_max_length to match model config (8192)

#11 opened 5 months ago by

faridlazuarda

upvoted a paper 7 months ago

Datasheets Aren't Enough: DataRubrics for Automated Quality Metrics and Accountability

Paper • 2506.01789 • Published Jun 2, 2025 • 14

liked a dataset 8 months ago

NusaAksara/NusaAksara

Viewer • Updated Feb 14, 2025 • 61.2k • 87 • 10

upvoted 2 papers 8 months ago

Crosslingual Reasoning through Test-Time Scaling

Paper • 2505.05408 • Published May 8, 2025 • 8

Softpick: No Attention Sink, No Massive Activations with Rectified Softmax

Paper • 2504.20966 • Published Apr 29, 2025 • 31

authored a paper about 1 year ago

WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines

Paper • 2410.12705 • Published Oct 16, 2024 • 32

updated 11 models over 1 year ago