Source code for NoteLLM and NoteLLM-2

在常规推荐系统算法和系统双优化的范式下，一线公司针对单个任务或单个业务的效果挖掘几乎达到极限。从2019年我们开始关注多种信息的萃取融合，提出了OneRec算法，希望通过平台或外部各种各样的信息来进行知识集成，打破数据孤岛，极大扩充推荐的“Extra World Knowledge”。 已实践的算法包括行为数据，内容描述，社交信息，知识图谱等。在OneRec，每种信息和整体算法的集成是可插拔…

HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling

High-Resolution Image Synthesis with Latent Diffusion Models

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

Chinese version of CLIP which achieves Chinese cross-modal retrieval and representation generation.

LLM Generated Code baseline of NoteLLM for Understanding

Repository hosting code used to reproduce results in "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152, I…

A Toolbox for MultiModal Recommendation. Integrating 10+ Models...

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

A PyTorch Library for Multi-Task Learning

Kuaishou Online RL Benchmark

Source code of CIKM 2022 and DLP-KDD workshop 2022 Best Paper: IntTower-“ IntTower: the Next Generation of Two-Tower Model for Pre-ranking System”

Example models using DeepSpeed

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

pytorch open-source library for the paper "AdaTT Adaptive Task-to-Task Fusion Network for Multitask Learning in Recommendations"

Port of Facebook's LLaMA model in C/C++

Inference Llama 2 in one file of pure C

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

A gradio web UI for running Large Language Models like LLaMA, llama.cpp, GPT-J, OPT, and GALACTICA.

A flexible, high-performance framework for large-scale retrieval problems based on TensorFlow.

Advanced Retrieval Algorithms for Decomposing Large-Scale Candidate Set into Pieces.

Input pipeline framework

GraphJet is a real-time graph processing library.

Source code for Twitter's Recommendation Algorithm

骆驼(Luotuo): Open Sourced Chinese Language Models. Developed by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子昂 @ 商汤科技