TsinghuaC3I / SoRALinks
[EMNLP 2023, Main Conference] Sparse Low-rank Adaptation of Pre-trained Language Models
☆78Updated last year
Alternatives and similar repositories for SoRA
Users that are interested in SoRA are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆59Updated 3 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆83Updated 7 months ago
- Awesome-Low-Rank-Adaptation☆104Updated 8 months ago
- Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "☆120Updated 2 months ago
- [NeurIPS'24 Oral] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning☆210Updated 6 months ago
- code for ACL24 "MELoRA: Mini-Ensemble Low-Rank Adapter for Parameter-Efficient Fine-Tuning"☆19Updated 4 months ago
- A curated list of Model Merging methods.☆92Updated 9 months ago
- ☆55Updated 6 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆41Updated 11 months ago
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆21Updated 9 months ago
- ☆142Updated 11 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆45Updated 8 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆163Updated last year
- ☆105Updated 11 months ago
- LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning☆31Updated last year
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆88Updated 8 months ago
- [ICLR 2024] This is the repository for the paper titled "DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning"☆96Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆52Updated 2 years ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆39Updated last year
- A Sober Look at Language Model Reasoning☆74Updated last week
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)☆40Updated last year
- A generalized framework for subspace tuning methods in parameter efficient fine-tuning.☆141Updated 4 months ago
- Codes for Merging Large Language Models☆32Updated 10 months ago
- ☆26Updated last year
- Source code of EMNLP 2022 Findings paper "SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters"☆18Updated last year
- ☆28Updated last year
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆61Updated last year
- ☆29Updated last year
- Official Pytorch Implementation of "Outlier-weighed Layerwise Sampling for LLM Fine-tuning" by Pengxiang Li, Lu Yin, Xiaowei Gao, Shiwei …☆32Updated 3 weeks ago
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆85Updated this week