xinleihe

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

vllm

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

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

ML-Papers-of-the-Week

🔥Highlighting the top ML papers every week.

lm-evaluation-harness

A framework for few-shot evaluation of language models.

mergekit

Tools for merging pretrained large language models.

secretflow

A unified framework for privacy-preserving data analysis and machine learning

CVinW_Readings

A collection of papers on the topic of ``Computer Vision in the Wild (CVinW)''

natural-instructions

Expanding natural instructions

vec2text

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

Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

llm-sp

Papers and resources related to the security and privacy of LLMs 🤖

Awesome-LLM-Watermark

UP-TO-DATE LLM Watermark paper. 🔥🔥🔥

haltt4llm

This project is an attempt to create a common metric to test LLM's for progress in eliminating hallucinations which is the most serious current problem in widespread adoption of LLM's for many real purposes.

Awesome-Machine-Generated-Text

Continuously updated list of related resources for generative LLMs like GPT and their analysis and detection.

ai-detection-paraphrases

Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).

AI-Security-and-Privacy-Events

A curated list of academic events on AI Security & Privacy

TransferAttackEval

Revisiting Transferable Adversarial Images (arXiv)

ICLR2023-OpenReviewData

Crawl & Visualize ICLR 2023 Data from OpenReview

MarkMyWords

Quantize-Watermark

mm_poison

TePA

[S&P'24] Test-Time Poisoning Attacks Against Test-Time Adaptation Models

Stealing-the-Decoding-Algorithms-of-Language-Models

easy-bib

Label-Only-MIA

ML-Doctor

Code for ML Doctor

Link-Stealing-Attack

MGTBench

xinleihe.github.io