MarcellusZhao

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text

RULER

This repo contains the source code for RULER: What’s the Real Context Size of Your Long-Context Language Models?

long-context-icl

Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"

Toolkit-for-Prompt-Compression

Toolkit for Prompt Compression

LMFlow

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

icl-alignment

Is In-Context Learning Sufficient for Instruction Following in LLMs?

Long-Context-Data-Engineering

Implementation of paper Data Engineering for Scaling Language Models to 128K Context

manim

Animation engine for explanatory math videos

dl-visualization

This is the source code for the animations in the series "Visualizing Deep Learning"

llm-baselines

rlhf-trojan-competition-submission

llm-adaptive-attacks

Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [arXiv, Apr 2024]

jailbreakbench

An Open Robustness Benchmark for Jailbreaking Language Models [arXiv 2024]

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

pythia

The hub for EleutherAI's work on interpretability and learning dynamics

WildBench

Benchmarking LLMs with Challenging Tasks from Real Users

long-is-more-for-alignment

Long Is More for Alignment: A Simple but Tough-to-Beat Baseline for Instruction Fine-Tuning [ICML 2024]

emoji-cheat-sheet

A markdown version emoji cheat sheet

custom-brand-icons

Custom brand icons for Home Assistant

website

csl

[Preprint] Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts

HarmBench

HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

arxiv-latex-cleaner

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Reflection_Tuning

[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

WizardLM

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

adversarial-random-search-gpt4

Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]

RDED

[CVPR 2024] On the Diversity and Realism of Distilled Dataset: An Efficient Dataset Distillation Paradigm

URIAL

just-eval

A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.

GPT-Fathom

GPT-Fathom is an open-source and reproducible LLM evaluation suite, benchmarking 10+ leading open-source and closed-source LLMs as well as OpenAI's earlier models on 20+ curated benchmarks under aligned settings.