locuslab / massive-activationsLinks
Code accompanying the paper "Massive Activations in Large Language Models"
☆183Updated last year
Alternatives and similar repositories for massive-activations
Users that are interested in massive-activations are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆125Updated 3 months ago
- ☆50Updated last year
- Test-time-training on nearest neighbors for large language models☆46Updated last year
- ☆30Updated 2 years ago
- ☆75Updated 3 years ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆95Updated 3 months ago
- [NeurIPS'24 Spotlight] Observational Scaling Laws☆57Updated last year
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆101Updated 2 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆102Updated last year
- ☆191Updated last year
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆214Updated last year
- LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning☆35Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆180Updated 5 months ago
- ☆20Updated 10 months ago
- AnchorAttention: Improved attention for LLMs long-context training☆213Updated 8 months ago
- [NAACL 2025] A Closer Look into Mixture-of-Experts in Large Language Models☆55Updated 8 months ago
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆16Updated 5 months ago
- [EMNLP 2023, Main Conference] Sparse Low-rank Adaptation of Pre-trained Language Models☆83Updated last year
- ☆59Updated 9 months ago
- Language models scale reliably with over-training and on downstream tasks☆100Updated last year
- A curated list of Model Merging methods.☆92Updated last year
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆105Updated 2 years ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆69Updated 7 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆172Updated last year
- Code for "Reasoning to Learn from Latent Thoughts"☆119Updated 6 months ago
- ☆33Updated last year
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆124Updated last year
- ☆192Updated 5 months ago
- The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".☆177Updated 6 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆44Updated last year