VectorInstitute / kaleidoscope-sdk
A user toolkit for analyzing and interfacing with Large Language Models (LLMs)
☆24Updated 4 months ago
Related projects ⓘ
Alternatives and complementary repositories for kaleidoscope-sdk
- LLM finetuning in resource-constrained environments.☆41Updated 4 months ago
- A user toolkit for analyzing and interfacing with Large Language Models (LLMs)☆21Updated 2 months ago
- A fast, effective data attribution method for neural networks in PyTorch☆179Updated this week
- ☆12Updated 8 months ago
- Influence Functions with (Eigenvalue-corrected) Kronecker-Factored Approximate Curvature☆107Updated 3 months ago
- Conformal Language Modeling☆24Updated 11 months ago
- Efficient LLM inference on Slurm clusters using vLLM.☆39Updated last week
- This repository collects all relevant resources about interpretability in LLMs☆289Updated 3 weeks ago
- ☆74Updated 2 months ago
- Tools for understanding how transformer predictions are built layer-by-layer☆430Updated 5 months ago
- ☆188Updated last month
- Layer-Wise Relevance Propagation for Large Language Models and Vision Transformers [ICML 2024]☆100Updated last week
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆53Updated last month
- Fairness toolkit for pytorch, scikit learn and autogluon☆22Updated 2 weeks ago
- Sparse probing paper full code.☆51Updated 11 months ago
- Mechanistic Interpretability Visualizations using React☆200Updated 4 months ago
- Code for Language-Interfaced FineTuning for Non-Language Machine Learning Tasks.☆120Updated last week
- ☆76Updated 9 months ago
- A simple PyTorch implementation of influence functions.☆79Updated 5 months ago
- ☆199Updated 6 months ago
- ☆108Updated last year
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆406Updated this week
- ☆12Updated 4 months ago
- Interpretability for sequence generation models 🐛 🔍☆377Updated last week
- ☆37Updated 11 months ago
- Using sparse coding to find distributed representations used by neural networks.☆185Updated last year
- Training data extraction on GPT-2☆176Updated last year
- ☆105Updated last month
- ☆253Updated 8 months ago
- ☆146Updated last month