Utilities, Baselines, Statistics and Descriptions Related to the MSMARCO DATASET

A tool for extracting plain text from Wikipedia dumps

[ACL 2024] RA-ISF: Learning to Answer and Understand from Retrieval Augmentation via Iterative Self-Feedback.

A Pythonic wrapper for the Wikipedia API

A curated list of Diffusion Model in RL resources (continually updated)

Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"

[NAACL 2021] QAGNN: Question Answering using Language Models and Knowledge Graphs 🤖

Code and Data for EMNLP 2024 Paper "Neeko: Leveraging Dynamic LoRA for Efficient Multi-Character Role-Playing Agent"

[ICML 2024] Selecting High-Quality Data for Training Language Models

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

A quick guide (especially) for trending instruction finetuning datasets

APPS: Automated Programming Progress Standard (NeurIPS 2021)

Learning the Difference that Makes a Difference with Counterfactually-Augmented Data

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

Paper collection of reinforcement learning based combinatorial optimization

[ICML'24] Magicoder: Empowering Code Generation with OSS-Instruct

MindMap: Knowledge Graph Prompting Sparks Graph of Thoughts in Large Language Models

[CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

Fast and memory-efficient exact attention

Official inference library for Mistral models

Example models using DeepSpeed

Code and data for "MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning" (ICLR 2024)

A shared repository for data cleaning scripts used for innovation data.

High-Resolution Image Synthesis with Latent Diffusion Models

This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.

Official implementation of the MM'21 paper "Constrained Graphic Layout Generation via Latent Optimization" (LayoutGAN++, CLG-LO, and Layout evaluation)

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation