gortizji / tangent_task_arithmetic
Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
☆92Updated last year
Alternatives and similar repositories for tangent_task_arithmetic:
Users that are interested in tangent_task_arithmetic are comparing it to the libraries listed below
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆39Updated 2 months ago
- ☆63Updated 2 years ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆61Updated 2 months ago
- ☆47Updated last year
- AI Logging for Interpretability and Explainability🔬☆97Updated 7 months ago
- Landing Page for TOFU☆107Updated 3 weeks ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆42Updated 2 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆61Updated 2 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆131Updated 3 months ago
- ☆82Updated 11 months ago
- A resource repository for representation engineering in large language models☆90Updated 2 months ago
- ☆159Updated 11 months ago
- official code for paper Probing the Decision Boundaries of In-context Learning in Large Language Models. https://arxiv.org/abs/2406.11233…☆15Updated 4 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆57Updated 3 months ago
- Official Repository for The Paper: Safety Alignment Should Be Made More Than Just a Few Tokens Deep☆63Updated 6 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆133Updated 10 months ago
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆24Updated 8 months ago
- ☆12Updated 8 months ago
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆22Updated last week
- Official Code for Paper: Assessing the Brittleness of Safety Alignment via Pruning and Low-Rank Modifications☆65Updated 3 months ago
- ☆85Updated last year
- ☆30Updated 3 weeks ago
- ☆61Updated last year
- ☆20Updated 6 months ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆55Updated 2 weeks ago
- [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging☆47Updated last month
- Revisiting Efficient Training Algorithms For Transformer-based Language Models (NeurIPS 2023)☆80Updated last year
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆71Updated 3 weeks ago
- ☆43Updated 5 months ago
- [NeurIPS 2023] Github repository for "Composing Parameter-Efficient Modules with Arithmetic Operations"☆58Updated last year