-
AfriNLLB: Efficient Translation Models for African Languages
Paper • 2602.09373 • Published • 2 -
AfriNLP/AfriNLLB-train
Viewer • Updated • 3.22M • 59 • 4 -
AfriNLP/AfriNLLB-train-distilled
Viewer • Updated • 568k • 47 -
AfriNLP/AfriNLLB-12enc-12dec-full-ft-kd
Translation • 0.6B • Updated • 138
Yasmin Moslem PRO
ymoslem
AI & ML interests
Machine Translation, Speech Translation, Large Language Models, Natural Language Processing
Recent Activity
liked a model about 9 hours ago
Qwen/Qwen3.6-35B-A3B liked a dataset 9 days ago
Omartificial-Intelligence-Space/Arabic-Math-SFT liked a Space 10 days ago
librarian-bots/recommend_similar_papersOrganizations
WMT-Model-Compression
-
Iterative Layer Pruning for Efficient Translation Inference
Paper • 2510.22763 • Published -
ymoslem/wmt25-ces-deu-24layers-2e-5lr-news-commentary
Text Generation • 6B • Updated • 6 -
ymoslem/wmt25-ces-deu-20layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 11 -
ymoslem/wmt25-ces-deu-16layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 9
AfriNLLB Models and Data
-
AfriNLLB: Efficient Translation Models for African Languages
Paper • 2602.09373 • Published • 2 -
AfriNLP/AfriNLLB-train
Viewer • Updated • 3.22M • 59 • 4 -
AfriNLP/AfriNLLB-train-distilled
Viewer • Updated • 568k • 47 -
AfriNLP/AfriNLLB-12enc-12dec-full-ft-kd
Translation • 0.6B • Updated • 138
WMT-Model-Compression
-
Iterative Layer Pruning for Efficient Translation Inference
Paper • 2510.22763 • Published -
ymoslem/wmt25-ces-deu-24layers-2e-5lr-news-commentary
Text Generation • 6B • Updated • 6 -
ymoslem/wmt25-ces-deu-20layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 11 -
ymoslem/wmt25-ces-deu-16layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 9
models 69
ymoslem/wmt25-eng-arz-16layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 6
ymoslem/wmt25-eng-arz-20layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 7
ymoslem/wmt25-eng-arz-24layers-2e-5lr-news-commentary
Text Generation • 6B • Updated • 6
ymoslem/aya-expanse-8b-eng-arz-16layers
Text Generation • 5B • Updated • 4
ymoslem/aya-expanse-8b-eng-arz-20layers
Text Generation • 5B • Updated • 7
ymoslem/aya-expanse-8b-eng-arz-24layers
Text Generation • 6B • Updated • 2
ymoslem/aya-expanse-8b-20layers-cs-de-iter
Text Generation • 5B • Updated • 2
ymoslem/wmt25-ces-deu-16layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 9
ymoslem/wmt25-ces-deu-20layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 11
ymoslem/wmt25-ces-deu-24layers-2e-5lr-news-commentary
Text Generation • 6B • Updated • 6
datasets 42
ymoslem/AIME-clustered
Viewer • Updated • 951 • 5
ymoslem/TeleQnA-clustered-2
Viewer • Updated • 10k • 17
ymoslem/news-commentary-eng-arz
Viewer • Updated • 83.7k • 20
ymoslem/flores-test-pruning
Viewer • Updated • 1.1k • 9
ymoslem/aime-1983-2024
Viewer • Updated • 950 • 51
ymoslem/TeleQnA-processed
Viewer • Updated • 10k • 99
ymoslem/Anhui-Telecom-QA
Viewer • Updated • 157k • 29 • 2
ymoslem/TeleQnA-clustered-3
Viewer • Updated • 10k • 2
ymoslem/Law-StackExchange
Viewer • Updated • 24.4k • 220 • 32
ymoslem/IWSLT2025-Test
Viewer • Updated • 772 • 19