Collection for the paper titled "How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning"
AI & ML interests
Language Models for Code
Recent Activity
View all activity
Collection of models for the course. Naming convention: ML4SE23_G{group_number}_{model_name}
Models for the paper: "A Transformer-Based Approach for Smart Invocation of Automatic Code Completion" – https://arxiv.org/abs/2405.14753
-
AISE-TUDelft/CodeBERTa-ft-coco-1e-05lr
Text Classification • 83.5M • Updated -
AISE-TUDelft/CodeBERTa-ft-coco-2e-05lr
Text Classification • 83.5M • Updated • 1 -
AISE-TUDelft/CodeBERTa-ft-coco-5e-05lr
Text Classification • 83.5M • Updated -
AISE-TUDelft/JonBERTa-head-ft-coco
Text Classification • 83.5M • Updated
Collection for the paper titled "How Much Do Code Language Models Remember? An Investigation on Data Extraction Attacks before and after Fine-tuning"
STACC: a set of SentenceTransformer Assisted Comment Classifiers 📚
Collection of models for the course. Naming convention: ML4SE23_G{group_number}_{model_name}
BinT5: Binary Code Summarisation Models
Models for the paper: "A Transformer-Based Approach for Smart Invocation of Automatic Code Completion" – https://arxiv.org/abs/2405.14753
-
AISE-TUDelft/CodeBERTa-ft-coco-1e-05lr
Text Classification • 83.5M • Updated -
AISE-TUDelft/CodeBERTa-ft-coco-2e-05lr
Text Classification • 83.5M • Updated • 1 -
AISE-TUDelft/CodeBERTa-ft-coco-5e-05lr
Text Classification • 83.5M • Updated -
AISE-TUDelft/JonBERTa-head-ft-coco
Text Classification • 83.5M • Updated
Models for the 2024-Q4 BSc. Research Project: "Architectural Decisions for Language Modelling with Small Transformers".