Ramsey's repositories
AIAS
AIAS (AI Acceleration Suite), AI算法落地加速器套件(超过100个项目组成的项目集，包含了sdk，平台引擎，场景套件)
arfs
All Relevant Feature Selection
cornac
A Comparative Framework for Multimodal Recommender Systems
czsc
缠中说禅技术分析工具；缠论；股票；期货；Quant；量化交易
DeepLearningSystem
Deep Learning System core principles introduction.
Diffusion-Tensorflow
Tensorflow implementations of Diffusion models (DDPM, DDIM)
e2e_ml
An end to end solution for automl.
gAnswer
A KBQA system based on DBpedia.
intel-extension-for-transformers
Extending Hugging Face transformers APIs for Transformer-based models and improve the productivity of inference deployment. With extremely compressed models, the toolkit can greatly improve the inference efficiency on Intel platforms.
KB-NER
Winner system (DAMO-NLP) of SemEval 2022 MultiCoNER shared task over 10 out of 13 tracks.
machine-learning
:earth_americas: machine learning tutorials (mainly in Python3)
multilingual_keyphrase_generation
[NAACL'22-Findings] Dataset for "Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training"
openmlsys-zh
《Machine Learning Systems: Design and Implementation》- Chinese Version
paper-reading
比做算法的懂工程落地，比做工程的懂算法模型。
primeqa
The prime repository for state-of-the-art Multilingual Question Answering research and development.
PruningRadixTrie
PruningRadixTrie - 1000x faster Radix trie for prefix search & auto-complete
Quantitative-analysis
量化研究-券商金工研报复现
recs-at-resonable-scale
Recommendations at "Reasonable Scale": joining dataOps with recSys through dbt, Merlin and Metaflow
rince
This is the code accompanying the AAAI 2022 paper "Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives" https://arxiv.org/abs/2201.11736 . The method allows you to use additional ranking information for representation learning.
sematic
An open-source ML pipeline development toolkit
spark-extension
A library that provides useful extensions to Apache Spark and PySpark.
tldr
TLDR is an unsupervised dimensionality reduction method that combines neighborhood embedding learning with the simplicity and effectiveness of recent self-supervised learning losses
unlocking-the-power-of-llms
使用 Prompts 和 Chains 让 ChatGPT 成为神奇的生产力工具！每日更新～
VL-BERT
Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".