osehmathias / lisaLinks
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
☆35Updated last year
Alternatives and similar repositories for lisa
Users that are interested in lisa are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆116Updated last month
- [EMNLP 2023, Main Conference] Sparse Low-rank Adaptation of Pre-trained Language Models☆81Updated last year
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆83Updated 6 months ago
- A curated list of Model Merging methods.☆92Updated 11 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆66Updated 5 months ago
- ☆57Updated 8 months ago
- ☆20Updated 9 months ago
- A Sober Look at Language Model Reasoning☆81Updated 2 months ago
- State-of-the-art Parameter-Efficient MoE Fine-tuning Method☆178Updated last year
- Official Pytorch Implementation of "Outlier-weighed Layerwise Sampling for LLM Fine-tuning" by Pengxiang Li, Lu Yin, Xiaowei Gao, Shiwei …☆34Updated 2 months ago
- Official code for our paper, "LoRA-Pro: Are Low-Rank Adapters Properly Optimized? "☆129Updated 4 months ago
- ☆161Updated 3 months ago
- One-shot Entropy Minimization☆178Updated 2 months ago
- An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT☆108Updated 5 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆176Updated last year
- ☆151Updated last year
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆173Updated last month
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆49Updated last year
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆91Updated 2 months ago
- Representation Surgery for Multi-Task Model Merging. ICML, 2024.☆46Updated 10 months ago
- A block pruning framework for LLMs.☆24Updated 3 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆88Updated 9 months ago
- A generalized framework for subspace tuning methods in parameter efficient fine-tuning.☆154Updated 2 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆125Updated last month
- [ICML 2024] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".☆110Updated last month
- SLTrain: a sparse plus low-rank approach for parameter and memory efficient pretraining (NeurIPS 2024)☆32Updated 9 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆77Updated 2 months ago
- ☆98Updated 4 months ago
- ☆26Updated last year
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆47Updated 10 months ago