-
Iterative Layer Pruning for Efficient Translation Inference
Paper • 2510.22763 • Published -
ymoslem/wmt25-ces-deu-24layers-2e-5lr-news-commentary
Text Generation • 6B • Updated • 7 -
ymoslem/wmt25-ces-deu-20layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 10 -
ymoslem/wmt25-ces-deu-16layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 5
Yasmin Moslem PRO
ymoslem
AI & ML interests
Machine Translation, Speech Translation, Large Language Models, Natural Language Processing
Recent Activity
liked
a model
about 4 hours ago
facebook/bart-large-mnli
liked
a dataset
about 4 hours ago
nyu-mll/multi_nli
liked
a model
about 4 hours ago
mistralai/Ministral-3-14B-Reasoning-2512
Organizations
Models for reference-free quality estimation of machine translation
-
ymoslem/ModernBERT-base-long-context-qe-v1
Text Classification • 0.1B • Updated • 31 • 5 -
ymoslem/ModernBERT-large-qe-v1
Text Classification • 0.4B • Updated • 18 • 2 -
ymoslem/xlm-roberta-large-qe-v1
Text Classification • 0.6B • Updated • 16 • 1 -
ymoslem/ModernBERT-large-qe-maxlen512-v1
Text Classification • 0.4B • Updated • 8 • 1
-
Iterative Layer Pruning for Efficient Translation Inference
Paper • 2510.22763 • Published -
ymoslem/wmt25-ces-deu-24layers-2e-5lr-news-commentary
Text Generation • 6B • Updated • 7 -
ymoslem/wmt25-ces-deu-20layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 10 -
ymoslem/wmt25-ces-deu-16layers-2e-5lr-news-commentary
Text Generation • 5B • Updated • 5
Models for reference-free quality estimation of machine translation
-
ymoslem/ModernBERT-base-long-context-qe-v1
Text Classification • 0.1B • Updated • 31 • 5 -
ymoslem/ModernBERT-large-qe-v1
Text Classification • 0.4B • Updated • 18 • 2 -
ymoslem/xlm-roberta-large-qe-v1
Text Classification • 0.6B • Updated • 16 • 1 -
ymoslem/ModernBERT-large-qe-maxlen512-v1
Text Classification • 0.4B • Updated • 8 • 1
models
70
ymoslem/wmt25-eng-arz-16layers-2e-5lr-news-commentary
Text Generation
•
5B
•
Updated
•
5
ymoslem/wmt25-eng-arz-20layers-2e-5lr-news-commentary
Text Generation
•
5B
•
Updated
•
3
ymoslem/wmt25-eng-arz-24layers-2e-5lr-news-commentary
Text Generation
•
6B
•
Updated
•
7
ymoslem/aya-expanse-8b-eng-arz-16layers
Text Generation
•
5B
•
Updated
•
3
ymoslem/aya-expanse-8b-eng-arz-20layers
Text Generation
•
5B
•
Updated
•
3
ymoslem/aya-expanse-8b-eng-arz-24layers
Text Generation
•
6B
•
Updated
•
3
ymoslem/aya-expanse-8b-20layers-cs-de-iter
Text Generation
•
5B
•
Updated
•
5
ymoslem/wmt25-ces-deu-16layers-2e-5lr-news-commentary
Text Generation
•
5B
•
Updated
•
5
ymoslem/wmt25-ces-deu-20layers-2e-5lr-news-commentary
Text Generation
•
5B
•
Updated
•
10
ymoslem/wmt25-ces-deu-24layers-2e-5lr-news-commentary
Text Generation
•
6B
•
Updated
•
7
datasets
37
ymoslem/TeleQnA-processed
Viewer
•
Updated
•
10k
•
87
ymoslem/news-commentary-eng-arz
Viewer
•
Updated
•
83.7k
•
105
ymoslem/Anhui-Telecom-QA
Viewer
•
Updated
•
157k
•
35
•
2
ymoslem/Law-StackExchange
Viewer
•
Updated
•
24.4k
•
581
•
31
ymoslem/IWSLT2025-Test
Viewer
•
Updated
•
772
•
36
ymoslem/news-commentary-en-ar
Viewer
•
Updated
•
84.3k
•
17
•
1
ymoslem/news-commentary-cs-de
Viewer
•
Updated
•
201k
•
44
ymoslem/paragraph-cs-de-src-50k
Viewer
•
Updated
•
44.1k
•
15
ymoslem/paragraph-cs-de-src-tgt-50k
Viewer
•
Updated
•
44.6k
•
26
ymoslem/paragraph-cs-de-src-tgt-10k
Viewer
•
Updated
•
10k
•
27