mlfoundations / task_vectorsLinks
Editing Models with Task Arithmetic
☆495Updated last year
Alternatives and similar repositories for task_vectors
Users that are interested in task_vectors are comparing it to the libraries listed below
Sorting:
- Source code of "Task arithmetic in the tangent space: Improved editing of pre-trained models".☆103Updated 2 years ago
- ☆187Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆516Updated 2 weeks ago
- ☆223Updated last year
- ☆73Updated 3 years ago
- ☆508Updated last year
- Code accompanying the paper "Massive Activations in Large Language Models"☆176Updated last year
- A fast, effective data attribution method for neural networks in PyTorch☆217Updated 9 months ago
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- LLM-Merging: Building LLMs Efficiently through Merging☆203Updated 11 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆177Updated 4 months ago
- AI Logging for Interpretability and Explainability🔬☆125Updated last year
- Repo for Rho-1: Token-level Data Selection & Selective Pretraining of LLMs.☆431Updated last year
- Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time☆480Updated last year
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆793Updated 3 weeks ago
- ☆276Updated last year
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆159Updated 2 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆298Updated last month
- Implementation of ST-Moe, the latest incarnation of MoE after years of research at Brain, in Pytorch☆359Updated last year
- ☆238Updated last year
- Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. arXiv:2408.07666.☆506Updated this week
- ☆327Updated this week
- ☆269Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆542Updated 6 months ago
- PyTorch library for Active Fine-Tuning☆89Updated 6 months ago
- Code for T-Few from "Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning"☆456Updated last year
- ☆103Updated 6 months ago
- Code release for Dataless Knowledge Fusion by Merging Weights of Language Models (https://openreview.net/forum?id=FCnohuR6AnM)☆90Updated 2 years ago
- ☆114Updated last month
- ☆96Updated last year