ronigold / TokenSHAP
TokenSHAP: Explain individual token importance in large language model prompts with SHAP values. Gain insights, debug models, detect biases, and enhance transparency effortlessly
☆19Updated this week
Related projects ⓘ
Alternatives and complementary repositories for TokenSHAP
- HeBERT: Pre-training BERT for modern Hebrew☆72Updated last year
- A Lossless Compression Library for AI pipelines☆171Updated this week
- ☆47Updated 2 years ago
- ☆32Updated 11 months ago
- Neural Modeling for Named Entities and Morphology (Hebrew NER)☆30Updated last year
- ☆29Updated last year
- Mistral + Haystack: build RAG pipelines that rock 🤘☆100Updated 9 months ago
- AlephBertGimmel - Modern Hebrew pretrained BERT model with a 128K token vocabulary.☆21Updated last year
- ☆69Updated 10 months ago
- Visualization for a Retrieval-Augmented Generation (RAG) Assistant 🤖❤️📚☆174Updated 2 months ago
- Tools, examples, and resources to assist in the development of Gen-AI (Generative Artificial Intelligence) applications in Hebrew, with a…☆30Updated 8 months ago
- End-to-End LLM Guide☆97Updated 4 months ago
- A curated list of papers that released datasets along with their work☆124Updated 3 weeks ago
- ☆47Updated last year
- Designed for offline use, this RAG application template is based on Andrej Baranovskij's tutorials. It offers a starting point for buildi…☆38Updated 8 months ago
- ☆28Updated last year
- A comprehensive list of Hebrew NLP resources.☆248Updated 3 weeks ago
- Tools for merging pretrained large language models.☆19Updated 5 months ago
- A question answering dataset in Modern Hebrew, containing 30,147 questions.☆18Updated last year
- Toolkit for attaching, training, saving and loading of new heads for transformer models☆242Updated last week
- ☆138Updated last year
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆48Updated 4 months ago
- Notebook and Scripts that showcase running quantized diffusion models on consumer GPUs☆33Updated 2 weeks ago
- How far can we go with an LLM for a classification problem☆19Updated last month
- ☆16Updated last year
- Hebrew text generation models based on EleutherAI's gpt-neo. Each was trained on a TPUv3-8 made avilable via TPU Research Cloud Program.☆21Updated 2 years ago
- sdstudio project for image generation and modification☆30Updated last year
- ☆17Updated 3 months ago
- ☆115Updated 2 weeks ago