gortizji / tangent_task_arithmeticLinks
Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".
☆102Updated 2 years ago
Alternatives and similar repositories for tangent_task_arithmetic
Users that are interested in tangent_task_arithmetic are comparing it to the libraries listed below
Sorting:
- ☆69Updated 3 years ago
- Official repository of "Localizing Task Information for Improved Model Merging and Compression" [ICML 2024]☆45Updated 8 months ago
- ☆49Updated last year
- Code for paper "Parameter Efficient Multi-task Model Fusion with Partial Linearization"☆21Updated 9 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆70Updated 8 months ago
- ☆30Updated 11 months ago
- AdaMerging: Adaptive Model Merging for Multi-Task Learning. ICLR, 2024.☆83Updated 7 months ago
- Git Re-Basin: Merging Models modulo Permutation Symmetries in PyTorch☆75Updated 2 years ago
- AI Logging for Interpretability and Explainability🔬☆123Updated last year
- ☆183Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 3 months ago
- This is the repository for "Model Merging by Uncertainty-Based Gradient Matching", ICLR 2024.☆27Updated last year
- ☆95Updated last year
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆59Updated 3 months ago
- ☆95Updated 4 months ago
- ☆35Updated 6 months ago
- official code for paper Probing the Decision Boundaries of In-context Learning in Large Language Models. https://arxiv.org/abs/2406.11233…☆18Updated 9 months ago
- Code accompanying the paper "Massive Activations in Large Language Models"☆163Updated last year
- ☆59Updated 11 months ago
- What do we learn from inverting CLIP models?☆55Updated last year
- Preprint: Asymmetry in Low-Rank Adapters of Foundation Models☆35Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆156Updated last week
- Function Vectors in Large Language Models (ICLR 2024)☆170Updated 2 months ago
- ☆44Updated 3 months ago
- Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic☆26Updated 5 months ago
- General-purpose activation steering library☆78Updated last month
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆77Updated 2 weeks ago
- Code for paper: Aligning Large Language Models with Representation Editing: A Control Perspective☆32Updated 4 months ago
- [NeurIPS 2023 Spotlight] Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training☆35Updated 2 months ago
- ☆40Updated last year