arxiv:2510.03528
Ahmed Alajrami
aajrami
·
AI & ML interests
Language Modelling, Interpretability, ML, etc.
Recent Activity
upvoted
a
paper
about 2 months ago
Deconstructing Attention: Investigating Design Principles for Effective
Language Modeling
authored
a paper
2 months ago
How does the pre-training objective affect what large language models
learn about linguistic properties?
authored
a paper
2 months ago
Understanding the Role of Input Token Characters in Language Models: How
Does Information Loss Affect Performance?
Organizations
models
15
aajrami/bert-sr-base
Feature Extraction
•
0.1B
•
Updated
•
12
aajrami/bert-rand-base
Feature Extraction
•
0.1B
•
Updated
•
19
aajrami/bert-fc-base
Feature Extraction
•
0.1B
•
Updated
•
14
aajrami/bert-sr-medium
Feature Extraction
•
51.5M
•
Updated
•
11
aajrami/bert-rand-medium
Feature Extraction
•
51.5M
•
Updated
•
14
aajrami/bert-fc-medium
Feature Extraction
•
51.5M
•
Updated
•
16
aajrami/bert-sr-small
Feature Extraction
•
38.9M
•
Updated
•
10
aajrami/bert-mlm-medium
Feature Extraction
•
51.5M
•
Updated
•
28
aajrami/bert-fc-small
Feature Extraction
•
38.9M
•
Updated
•
11
aajrami/bert-rand-small
Feature Extraction
•
38.9M
•
Updated
•
17
datasets
0
None public yet