VectorInstitute / kaleidoscope
A user toolkit for analyzing and interfacing with Large Language Models (LLMs)
☆21Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for kaleidoscope
- Efficient LLM inference on Slurm clusters using vLLM.☆38Updated last week
- A mechanistic approach for understanding and detecting factual errors of large language models.☆39Updated 4 months ago
- ☆32Updated last year
- ☆12Updated 8 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆25Updated 5 months ago
- ☆13Updated 2 months ago
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆41Updated last year
- ☆70Updated 3 months ago
- ☆21Updated last week
- Source code and data for ADEPT: A DEbiasing PrompT Framework (AAAI-23).☆13Updated last year
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆29Updated 8 months ago
- AI Logging for Interpretability and Explainability🔬☆88Updated 5 months ago
- ☆105Updated this week
- Sparse and discrete interpretability tool for neural networks☆54Updated 9 months ago
- ☆50Updated last year
- A user toolkit for analyzing and interfacing with Large Language Models (LLMs)☆24Updated 4 months ago
- Finding semantically meaningful and accurate prompts.☆46Updated last year
- Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆61Updated 10 months ago
- Conformal Language Modeling☆22Updated 10 months ago
- Extending Conformal Prediction to LLMs☆57Updated 4 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆118Updated last month
- ☆75Updated 4 months ago
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆109Updated last year
- Interpretable and efficient predictors using pre-trained language models. Scikit-learn compatible.☆38Updated 6 months ago
- NanoGPT-like codebase for LLM training☆73Updated this week
- Implementation of PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆26Updated last week
- ☆102Updated last month
- Evaluation of neuro-symbolic engines☆33Updated 3 months ago
- LLM finetuning in resource-constrained environments.☆41Updated 4 months ago
- Research on Tabular Foundation Models☆27Updated 2 months ago