Dicer-Zz / EPI
Code for the paper: Rehearsal-free Continual Language Learning via Efficient Parameter Isolation
☆12Updated last year
Related projects: ⓘ
- Code for ACL 2024 accepted paper titled "SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language …☆19Updated last month
- Code for ACL 2022 paper "BERT Learns to Teach: Knowledge Distillation with Meta Learning".☆80Updated 2 years ago
- On the Effectiveness of Parameter-Efficient Fine-Tuning☆38Updated 10 months ago
- ☆12Updated 3 weeks ago
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)☆28Updated 5 months ago
- Code for the AAAI 2022 publication "Well-classified Examples are Underestimated in Classification with Deep Neural Networks"☆40Updated 2 years ago
- TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models☆56Updated 7 months ago
- ☆113Updated last year
- ☆18Updated 5 months ago
- [ICML 2023] Parameter-Level Soft-Masking for Continual Learning☆17Updated last year
- my commonly-used tools☆46Updated last month
- Code for paper "UniPELT: A Unified Framework for Parameter-Efficient Language Model Tuning", ACL 2022☆58Updated 2 years ago
- Shadow Alignment: The Ease of Subverting Safely-Aligned Language Models☆22Updated 11 months ago
- The code for lifelong few-shot language learning☆53Updated 2 years ago
- ☆13Updated 4 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆23Updated 3 weeks ago
- Source code for our EMNLP'21 paper 《Raise a Child in Large Language Model: Towards Effective and Generalizable Fine-tuning》☆56Updated 2 years ago
- ☆21Updated last year
- Code for EMNLP 2022 paper “Distilled Dual-Encoder Model for Vision-Language Understanding”☆29Updated last year
- Source code of EMNLP 2022 Findings paper "SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters"☆18Updated 5 months ago
- code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification☆26Updated 2 years ago
- [ICLR 2024] This is the repository for the paper titled "DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning"☆90Updated 5 months ago
- ☆139Updated 2 months ago
- ☆22Updated 9 months ago
- ☆21Updated 2 months ago
- Source code for paper "Contrastive Out-of-Distribution Detection for Pretrained Transformers", EMNLP 2021☆40Updated 2 years ago
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆54Updated 9 months ago
- CHAIR metric is a rule-based metric for evaluating object hallucination in caption generation.☆19Updated 10 months ago
- Official repo for "AlignGPT: Multi-modal Large Language Models with Adaptive Alignment Capability"☆29Updated 2 months ago
- The official implementation of the paper **Learning Concise and Descriptive Attributes for Visual Recognition**☆38Updated 9 months ago