JayZhang42

mink-plus-plus

Min-K%++: Improved baseline for detecting pre-training data of LLMs https://arxiv.org/abs/2404.02936

AnyText

Official implementation code of the paper <AnyText: Multilingual Visual Text Generation And Editing>

Time-Series-Library

A Library for Advanced Deep Time Series Models.

DoLa

Official implementation for the paper "DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models"

LLM-Agent-Paper-Digest

papers related to LLM-agent that published on top conferences

LLM-Agent-Survey

2025QuantInternships

Public quant internship repository, maintained by NUFT but available for everyone.

CLIP2FL

laser

The Truth Is In There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

OPERA

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

amago

a simple and scalable agent for training adaptive policies with sequence-based RL

tree-of-thoughts

Plug in and Play Implementation of Tree of Thoughts: Deliberate Problem Solving with Large Language Models that Elevates Model Reasoning by atleast 70%

FederatedGPT-Shepherd

Shepherd: A foundational framework enabling federated instruction tuning for large language models

LADD

Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning

superpower-chatgpt

ChatGPT with superpowers! Search chat history, create folders, export all chats, pin messages, access thousands of community prompts, incognito mode, language and tone selection, and many more features

llm-attacks

Universal and Transferable Attacks on Aligned Language Models

PFL-DocVQA-Competition

FedScale

FedScale is a scalable and extensible open-source federated learning (FL) platform.

Visual-Adversarial-Examples-Jailbreak-Large-Language-Models

Repository for the Paper (AAAI 2024, Oral) --- Visual Adversarial Examples Jailbreak Large Language Models

LLaVAR

Code/Data for the paper: "LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding"

PPOCoder

Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"

trlx

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

promptsource

Toolkit for creating, sharing and using natural language prompts.

HugNLP

HugNLP is a unified and comprehensive NLP library based on HuggingFace Transformer. Please hugging for NLP now!😊 HugNLP will released to @HugAILab

food-ordering-semantic-parsing-dataset

lamp

LAMP: Extracting Text from Gradients with Language Model Priors (NeurIPS '22)

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

GPT-4-LLM

Instruction Tuning with GPT-4