-
Alimama, Alibaba Group & Beihang University
- Beijing, China
Stars
Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.
Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.
A PyTorch Library for Multi-Task Learning
Code for "Stochastic Optimization of Sorting Networks using Continuous Relaxations", ICLR 2019.
Fast Differentiable Sorting and Ranking
Fast, differentiable sorting and ranking in PyTorch
PiRank: Learning to Rank via Differentiable Sorting
My experiences and thoughts on computational advertising technology
应用博弈树搜索,人工神经网络实现五子棋博弈AI。171129:计划更新基于RL训练的新版本,预计18年1月完成
This project aims to help people implement tensorflow model pipelines quickly for different nlp tasks.
A machine translation reading list maintained by Tsinghua Natural Language Processing Group
Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization
计算广告机制策略相关材料整理(A collection of research and application papers about Strategy in Internet advertising.)
A collection of research and application papers of (uncertainty) calibration techniques.
The repo of the paper "Formality Style Transfer with Shared Latent Space"
An industrial deep learning framework for high-dimension sparse data
A Multi-Task Learning Formulation for Survival Analysis
Deep learning for flexible market price modeling (landscape forecasting) in real-time bidding advertising. An implementation of our KDD 2019 paper with some other (Python) implemented prediction mo…
BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Faster and elegant TensorFlow Implementation of paper: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Learning to Learn using One-Shot Learning, MAML, Reptile, Meta-SGD and more with Tensorflow
gaodayihao / QSanguosha
Forked from Mogara/QSanguoshaAn open source online version of the famous board game Sanguosha
Ekphrasis is a text processing tool, geared towards text from social networks, such as Twitter or Facebook. Ekphrasis performs tokenization, word normalization, word segmentation (for splitting has…
Harnessing Pre-Trained Neural Networks with Rules for Formality Style Transfer