Stars
Examples for Recommenders - easy to train and deploy on accelerated infrastructure.
Kimi K2 is the large language model series developed by Moonshot AI team
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
🚀 Efficient implementations for emerging model architectures
Reverse Engineering Gemma 3n: Google's New Edge-Optimized Language Model
Reinforcement Learning for Relation Classification from Noisy Data(TensorFlow)
Parallel Scaling Law for Language Model — Beyond Parameter and Inference Time Scaling
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Repository hosting code for "Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations" (https://arxiv.org/abs/2402.17152).
Hackable and optimized Transformers building blocks, supporting a composable construction.
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.
推荐系统论文算法实现，包括序列推荐，多任务学习，元学习等。 Recommendation system papers implementations, including sequence recommendation, multi-task learning, meta-learning, etc.
Graph Attention Networks (https://arxiv.org/abs/1710.10903)
ACL2020 Tutorial: Open-Domain Question Answering
Umbrella repository for projects related to the MWT Decision Service
TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
SASRec: Self-Attentive Sequential Recommendation
Sequential-based Adversarial Optimisation for Personalised Top-N Item Recommendation
tensorflow实战练习，包括强化学习、推荐系统、nlp等
AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
Example code for paper "Distilling Knowledge from Well-informed Soft Labels for Neural Relation Extraction" (AAAI 2020).