This project is a PyTorch-based generative model framework designed to transform noise into complex data distributions by learning vector fields and probability paths. It serves as a multimodal generative toolkit for producing synthetic text and images through learned probability flows. The library distinguishes itself by supporting continuous, discrete, and Riemannian manifold integrations. This allows the framework to handle a variety of data types, including categorical data via discrete-state flow matching and non-Euclidean spaces through Riemannian manifold integration. The toolkit cove
2022-1-5: Our new work (ScriptWriter-CPre) has been accepted by TOIS! - 2021-10-19: We upload the code and data for our new model ScriptWriter-CPre. - 2020-06-11: We find a minor error in the data thus we upload a new one. We provide the code for building data file from text file. You can now…
a bert for retrieval and generation
Die Hauptfunktionen von zhuiyitechnology/simbert sind: Text Generation.
Open-Source-Alternativen zu zhuiyitechnology/simbert sind unter anderem: facebookresearch/flow_matching — This project is a PyTorch-based generative model framework designed to transform noise into complex data distributions… cluebenchmark/clge — Chinese Language Generation Evaluation 中文生成任务基准测评. daod/scriptwriter — 2022-1-5: Our new work (ScriptWriter-CPre) has been accepted by TOIS! - 2021-10-19: We upload the code and data for… beyondguo/genius — 基于草稿的文本生成模型. harvardnlp/talk-latent. asyml/texar — Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the…
