EnnengYang / RepresentationSurgeryLinks
Representation Surgery for Multi-Task Model Merging. ICML, 2024.
☆45Updated 7 months ago
Alternatives and similar repositories for RepresentationSurgery
Users that are interested in RepresentationSurgery are comparing it to the libraries listed below
Sorting:
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆21Updated 8 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆82Updated 7 months ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆44Updated 7 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆59Updated 3 months ago
- Code for paper "Merging Multi-Task Models via Weight-Ensembling Mixture of Experts"☆24Updated 11 months ago
- A block pruning framework for LLMs.☆23Updated 2 weeks ago
- Analyzing and Reducing Catastrophic Forgetting in Parameter Efficient Tuning☆31Updated 6 months ago
- ☆12Updated 4 months ago
- Official code for SEAL: Steerable Reasoning Calibration of Large Language Models for Free☆25Updated last month
- ☆49Updated last year
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆35Updated last year
- [ICLR 2025] Code&Data for the paper "Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization"☆13Updated 11 months ago
- Less is More: Task-aware Layer-wise Distillation for Language Model Compression (ICML2023)☆35Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆85Updated 7 months ago
- ☆15Updated 9 months ago
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆25Updated 4 months ago
- A Sober Look at Language Model Reasoning☆52Updated last week
- Codes for Merging Large Language Models☆31Updated 9 months ago
- Task Singular Vectors: Reducing Task Interference in Model Merging. Merge models avoiding task interference through separable models.☆14Updated last week
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆16Updated last month
- TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models☆71Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆51Updated 2 years ago
- Code for ACL 2024 accepted paper titled "SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language …☆35Updated 4 months ago
- [NeurIPS 2024] "Can Language Models Perform Robust Reasoning in Chain-of-thought Prompting with Noisy Rationales?"☆35Updated 4 months ago
- ☆27Updated last year
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆47Updated last year
- ☆35Updated last year
- [EMNLP 2023, Main Conference] Sparse Low-rank Adaptation of Pre-trained Language Models☆76Updated last year
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆38Updated 11 months ago
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆61Updated last year