Stars
AI agents running research on single-GPU nanochat training automatically
A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.
[COLING 2022] CSL: A Large-scale Chinese Scientific Literature Dataset 中文科学文献数据集
Computing similarity of two sentences with google's BERT algorithm。利用Bert计算句子相似度。语义相似度计算。文本相似度计算。
Original implementation for wide-and-deep matching network (WDMN) [Response Ranking with Multi-Types of Deep Interactive Representations in Retrieval-based Dialogues]
Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals
Text-to-Image generation. The repo for NeurIPS 2021 paper "CogView: Mastering Text-to-Image Generation via Transformers".
A Flexible and Powerful Parameter Server for large-scale machine learning
Header-only C++/python library for fast approximate nearest neighbors
Serve, optimize and scale PyTorch models in production
a Fairseq fork for sequence tagging/labeling tasks
XPersona: Evaluating Multilingual Personalized Chatbot
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
Fast inference engine for Transformer models
Web interface for browsing, search and filtering recent arxiv submissions
Multi-layer Recurrent Neural Networks (LSTM, GRU, RNN) for character-level language models in Torch
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
Fast, flexible and easy to use probabilistic modelling in Python.
Ranking Google Scholar search results based on the number of citations
Fine tuning of the Retrieval-Augmented Generation (RAG) with a custom knowledge source.
Source Code for DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances (https://arxiv.org/pdf/2012.01775.pdf)
🔥基于 JupyterLab 的比特币极速入门指南
Author: Wenhao Yu (wyu1@nd.edu). ACM Computing Survey'22. Reading list for knowledge-enhanced text generation, with a survey.