ColinLu50

O-LoRA

continual-learning

PyTorch implementation of various methods for continual learning (XdG, EWC, SI, LwF, FROMP, DGR, BI-R, ER, A-GEM, iCaRL, Generative Classifier) in three different scenarios.

LoRA-GA

trak

A fast, effective data attribution method for neural networks in PyTorch

SGP

Official [AAAI] Code Repository for "Continual Learning with Scaled Gradient Projection".

GPM

Official [ICLR] Code Repository for "Gradient Projection Memory for Continual Learning"

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

world-model-for-language-model

PTST

Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"

resta

Restore safety in fine-tuned language models through task arithmetic

MAP-NEO

mistral-finetune

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

Open-Sora-Plan

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

ares

Ares: A framework for quantifying the resilience of deep neural networks

pytorchfi

A runtime fault injection tool for PyTorch :fire:

TensorFI

TensorFI is a fault injection framework for injecting both hardware and software faults into applications written using the TensorFlow framework. You can find more information about TensorFI in the paper below.

Ziwei

基于已有基座模型微调的算命大模型

llama3

The official Meta Llama 3 GitHub site

OS

SUSTech Operating System, Pintos Projects

awesome-LLMs-In-China

**大模型

grok-1

Grok open release

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

test_set_contamination

StableCascade

Official Code for Stable Cascade

lm-evaluation-harness

A framework for few-shot evaluation of language models.

human-eval

Code for the paper "Evaluating Large Language Models Trained on Code"

PromptInject

PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022

Open-Prompt-Injection

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

langchain

🦜🔗 Build context-aware reasoning applications