ronigold / TokenSHAPLinks
TokenSHAP: Explain individual token importance in large language model prompts with SHAP values. Gain insights, debug models, detect biases, and enhance transparency effortlessly
☆55Updated last month
Alternatives and similar repositories for TokenSHAP
Users that are interested in TokenSHAP are comparing it to the libraries listed below
Sorting:
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆290Updated 8 months ago
- Interpret text data with LLMs (sklearn compatible).☆171Updated last month
- code for training & evaluating Contextual Document Embedding models☆199Updated 5 months ago
- Flexible library for merging large language models (LLMs) via evolutionary optimization (ACL 2025 Demo).☆91Updated 3 months ago
- ☆142Updated 2 months ago
- ☆124Updated last year
- Attribute (or cite) statements generated by LLMs back to in-context information.☆296Updated last year
- A mechanistic approach for understanding and detecting factual errors of large language models.☆46Updated last year
- 🦄 Unitxt is a Python library for enterprise-grade evaluation of AI performance, offering the world's largest catalog of tools and data …☆211Updated last week
- ☆119Updated last year
- Truth Forest: Toward Multi-Scale Truthfulness in Large Language Models through Intervention without Tuning☆46Updated last year
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆50Updated last year
- The Foundation Model Transparency Index☆83Updated last year
- ☆78Updated last year
- This is the reproduction repository for my 🤗 Hugging Face blog post on synthetic data☆68Updated last year
- Notebooks for training universal 0-shot classifiers on many different tasks☆136Updated 10 months ago
- ☆373Updated last week
- A framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings.☆170Updated last week
- ☆163Updated last year
- Let's build better datasets, together!☆263Updated 10 months ago
- ☆146Updated last year
- ☆138Updated 2 months ago
- A small library of LLM judges☆299Updated 3 months ago
- ☆52Updated 9 months ago
- LangFair is a Python library for conducting use-case level LLM bias and fairness assessments☆240Updated last week
- Official codebase for "Quantile Reward Policy Optimization: Alignment with Pointwise Regression and Exact Partition Functions" (Matrenok …☆27Updated 3 months ago
- Generalist and Lightweight Model for Text Classification☆164Updated 4 months ago
- PyTorch library for Active Fine-Tuning☆93Updated last month
- ☆43Updated last year
- Library to facilitate pruning of LLMs based on context☆32Updated last year