[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning

Ongoing research training transformer models at scale

Large Concept Models: Language modeling in a sentence representation space

This repository contains demos I made with the Transformers library by HuggingFace.

Machine Learning and Computer Vision Engineer - Technical Interview Questions

算法工程师-机器学习面试题总结

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

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

Official implementation of "Why are Visually-Grounded Language Models Bad at Image Classification?" (NeurIPS 2024)

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4o. 接近GPT-4o表现的开源多模态对话模型

This repository is the official implementation of "Red Teaming Language Models for Processing Contradictory Dialogues"

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to end problems using Llama mode…

Code for paper "Unraveling Cross-Modality Knowledge Conflicts in Large Vision-Language Models."

An open-source framework for self-supervised recommender systems.

A unified, comprehensive and efficient recommendation library

[WSDM'2024 Oral] "LLMRec: Large Language Models with Graph Augmentation for Recommendation"

This is for the knowledge graph embedding recommendation framework – RKGE

SGL PyTorch version

Knowledge-enhanced Neighborhood Interaction model for recommendation

[SIGIR'22] Knowledge Graph Contrastive Learning for Recommendation

Several data modalities for KBs (visual, numerical, temporal, etc.)

List of Computer Science courses with video lectures.

🚀 This tool contains mini GUI components that you can hook together to automatically generate markdown code for a perfect readme.

Multimodal Masked Autoencoders (M3AE): A JAX/Flax Implementation

Generative Adversarial Zero-Shot Relational Learning for Knowledge Graphs

Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback

An Open-Source Package for Knowledge Embedding (KE)