which47 / LLMCL
Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning
☆30Updated 4 months ago
Alternatives and similar repositories for LLMCL:
Users that are interested in LLMCL are comparing it to the libraries listed below
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆67Updated 4 months ago
- Code for ACL 2024 accepted paper titled "SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language …☆32Updated 2 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆40Updated 5 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆50Updated 2 weeks ago
- TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models☆66Updated last year
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆13Updated 8 months ago
- ☆26Updated 11 months ago
- source code for NeurIPS'24 paper "HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection"☆31Updated 2 months ago
- ☆30Updated 5 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆69Updated 5 months ago
- ☆17Updated 3 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆52Updated 5 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.☆69Updated 4 months ago
- code for ACL24 "MELoRA: Mini-Ensemble Low-Rank Adapter for Parameter-Efficient Fine-Tuning"☆19Updated last month
- Mosaic IT: Enhancing Instruction Tuning with Data Mosaics☆17Updated last month
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆20Updated 6 months ago
- [ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"☆55Updated 5 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆34Updated 2 months ago
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆23Updated 2 months ago
- [ICML 2024 Oral] Official code repository for MLLM-as-a-Judge.☆65Updated last month
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆33Updated 8 months ago
- Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "☆104Updated this week
- ☆32Updated last year
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆41Updated 4 months ago
- ☆31Updated last year
- Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"☆20Updated 9 months ago
- Multimodal Instruction Tuning with Conditional Mixture of LoRA (ACL 2024)☆14Updated 7 months ago
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)☆34Updated 11 months ago