Sabri Boughorbel

sboughorbel

5

·

https://scholar.google.nl/citations?hl=en&user=EhFf3j0AAAAJ&view_op=list_works&sortby=pubdate

AI & ML interests

Multilingual NLP

Organizations

sboughorbel 's datasets 23

sboughorbel/arabic-web-edu-seed

Viewer • Updated Oct 18, 2025 • 236k • 25 • 3

sboughorbel/diffing-stats-gemma-2-9b-L20-k100-lr1e-04-base-it-Crosscoder

Viewer • Updated May 17, 2025 • 115k • 25

sboughorbel/diffing-stats-gemma-2-9b-it-L20-k100-lr1e-04-Crosscoder

Viewer • Updated May 16, 2025 • 115k • 23

sboughorbel/diffing-stats-gemma-2-9b-it-DPO-L20-k100-lr1e-04-dpo-simpo-Crosscoder

Viewer • Updated May 15, 2025 • 115k • 42

sboughorbel/latent-activations-gemma-2-9b-L20-k100-lr1e-04-base-it-Crosscoder

Updated May 14, 2025 • 19

sboughorbel/latent-activations-gemma-2-9b-it-DPO-L20-k100-lr1e-04-dpo-simpo-Crosscoder

Updated May 14, 2025 • 19

sboughorbel/diffing-stats-gemma-2-9b-L20-k100-lr1e-04-base-dpo-Crosscoder

Viewer • Updated May 14, 2025 • 115k • 38

sboughorbel/latent-activations-gemma-2-9b-L20-k100-lr1e-04-base-dpo-Crosscoder

Updated May 14, 2025 • 18

sboughorbel/diffing-stats-gemma-2-9b-L20-k100-lr1e-04-Crosscoder

Viewer • Updated May 14, 2025 • 115k • 28

sboughorbel/latent-activations-gemma-2-9b-it-L20-k100-lr1e-04-Crosscoder

Updated May 14, 2025 • 10

sboughorbel/latent-activations-gemma-2-9b-L20-k100-lr1e-04-Crosscoder

Updated May 12, 2025 • 18

sboughorbel/latent-activations-gemma-2-9b-it-L20-mu4.0e-02-lr1e-04-CrosscoderLoss

Updated May 12, 2025 • 32

sboughorbel/diffing-stats-gemma-2-9b-it-L20-mu4.0e-02-lr1e-04-CrosscoderLoss

Viewer • Updated May 11, 2025 • 115k • 7

sboughorbel/diffing-stats-gemma-2-9b-it-SimPO-L20-mu1.0e-01-lr1e-04-CrosscoderLoss

Viewer • Updated May 9, 2025 • 115k • 7

sboughorbel/diffing-stats-gemma-2-9b-it-L20-mu1.0e-01-lr1e-04-local-shuffling-CrosscoderLoss

Viewer • Updated May 9, 2025 • 115k • 26

sboughorbel/latent-activations-gemma-2-9b-it-L20-k100-lr1e-04-CCLoss

Updated May 8, 2025 • 27

sboughorbel/latent-activations-gemma-2-9b-it-SimPO-L20-k100-lr1e-04-CCLoss

Updated May 8, 2025 • 31

sboughorbel/diffing-stats-gemma-2-9b-it-L20-k100-lr1e-04-CCLoss

Viewer • Updated May 7, 2025 • 115k • 10

sboughorbel/redpajama-data-1b-tokenized-olmo-1b

Viewer • Updated Apr 28, 2025 • 10 • 15

sboughorbel/redpajama-data-1b-tokenized-pythia-1b-deduped

Viewer • Updated Nov 15, 2024 • 931k • 18

sboughorbel/auto_math_ar

Viewer • Updated Oct 20, 2024 • 2.69M • 40

sboughorbel/tinystories_dataset_arabic

Viewer • Updated Aug 14, 2024 • 2.12M • 496 • 1

sboughorbel/mmlu_arabic

Updated Jan 1, 2024 • 19