Zhuoxuan-Zhang
Follow
Stars
A library for mechanistic interpretability of GPT-style language models
General-purpose activation steering library
Steer LLM outputs towards a certain topic/subject and enhance response capabilities using activation engineering by adding steering vectors
Must-read Papers on Knowledge Editing for Large Language Models.
𝔸𝕄𝔹ℝ𝕆𝕊𝕀𝔸: A Benchmark for Parsing Ambiguous Questions into Database Queries
An original implementation of EMNLP 2020, "AmbigQA: Answering Ambiguous Open-domain Questions"
Multidocument Summarization for Literature Review Shared Task 2022
A curated list of Large Language Model (LLM) Interpretability resources.
This repository contains data, code and models for contextual noncompliance.
Curation of resources for LLM mathematical reasoning, most of which are screened by @tongyx361 to ensure high quality and accompanied with elaborately-written concise descriptions to help readers g…
List of papers on hallucination detection in LLMs.
👽 Out-of-Distribution Detection with PyTorch
Benchmarking LLMs via Uncertainty Quantification
Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
A collection of various deep learning architectures, models, and tips
PyTorch implementation of SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
pytorch implementation of the paper ``Large Scale Image Completion via Co-Modulated Generative Adversarial Networks"
syzkaller is an unsupervised coverage-guided kernel fuzzer
Efficient Triton Kernels for LLM Training
Lightweight static analysis for many languages. Find bug variants with patterns that look like source code.
weggli is a fast and robust semantic search tool for C and C++ codebases. It is designed to help security researchers identify interesting functionality in large codebases.