3 Repos
Awesome GitHub RepositoriesSequential Text Generation
Techniques for training models to predict subsequent tokens in a sequence using recurrent architectures.
Distinct from Text Generation: Focuses on the sequential prediction process and perplexity calculation, which is distinct from general generative text inference.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Sequential Text Generation. Refine with filters or upvote what's useful.
Awesome Sequential Text Generation GitHub Repositories
Finde die besten Repos mit KI.Wir suchen mit KI nach den am besten passenden Repositories.
- nndl/llm-beginner
nndl/llm-beginner
6,421Auf GitHub ansehenThis project is a collection of educational resources and technical guides focused on the development and implementation of large language models. It provides a comprehensive curriculum covering transformer architectures, training methods, and deployment strategies. The materials provide detailed instructions for building autonomous agents using reasoning loops and tool integration, as well as guides for fine-tuning models through supervised learning and preference optimization. It also includes tutorials for constructing retrieval augmented generation pipelines and implementing transformer m
Trains character-level models using recurrent architectures to predict subsequent text and calculate perplexity.
Pythonagentfudannlpllm - udacity/deep-learning-v2-pytorch
udacity/deep-learning-v2-pytorch
5,505Auf GitHub ansehenDieses Projekt ist eine Sammlung von PyTorch-Kursmaterialien für Deep Learning, bestehend aus praktischen Projekten und Programmierübungen. Es konzentriert sich auf die Implementierung neuronaler Netzwerkarchitekturen und das Modelltraining zur Lösung komplexer Datenprobleme. Das Repository enthält eine Suite für Computer-Vision-Projekte zum Bau von Bildklassifizierern, Autoencodern und Style-Transfer-Anwendungen. Es bietet ein Labor für Generative Adversarial Networks (GANs) zur Erstellung synthetischer Bilder sowie spezifische Implementierungen für Transfer Learning, um vortrainierte Gewichte an neue Aufgaben anzupassen. Die Codebasis deckt die Analyse sequenzieller Daten für Natural Language Processing (NLP) mittels rekurrenter neuronaler Netze und Word-Embeddings ab. Zusätzliche Funktionen umfassen die Vorverarbeitung von Bilddaten, die Evaluierung der Modellleistung und das Deployment trainierter Modelle in Cloud-Infrastrukturen. Die Materialien werden als eine Reihe von Jupyter Notebooks bereitgestellt.
Builds recurrent networks and word embeddings to process sequential data for text generation and sentiment analysis.
Jupyter Notebookconvolutional-networksdeep-learningneural-network - morvanzhou/tensorflow-tutorial
MorvanZhou/Tensorflow-Tutorial
4,334Auf GitHub ansehenThis project is a collection of educational resources and reference implementations for neural network development using TensorFlow. It serves as a comprehensive learning course, machine learning curriculum, and practical implementation guide for building deep learning architectures. The codebase provides instructional materials and examples covering a wide range of model types, including convolutional neural networks for image classification, recurrent networks and long short-term memory cells for sequential data, and autoencoders for generative modeling. It also includes implementations for
Implements techniques for predicting subsequent tokens in a sequence using recurrent architectures for structured content generation.
Pythonautoencoderclassificationcnn
