Transformers documentation
Time Series Utilities
Get started
Tutorials
Run inference with pipelinesWrite portable code with AutoClassPreprocess dataFine-tune a pretrained modelTrain with a scriptSet up distributed training with 🤗 AccelerateLoad and train adapters with 🤗 PEFTShare your modelAgentsGeneration with LLMs
Task Guides
Natural Language Processing
Audio
Computer Vision
Multimodal
Generation
Developer guides
Use fast tokenizers from 🤗 TokenizersRun inference with multilingual modelsUse model-specific APIsShare a custom modelRun training on Amazon SageMakerExport to ONNXExport to TFLiteExport to TorchScriptBenchmarksNotebooks with examplesCommunity resourcesCustom Tools and PromptsTroubleshoot
Performance and scalability
Overview Instantiating a big modelTroubleshootingXLA Integration for TensorFlow ModelsOptimize inference using `torch.compile()`
Efficient training techniques
Methods and tools for efficient training on a single GPUMultiple GPUs and parallelismEfficient training on CPUDistributed CPU trainingTraining on TPUsTraining on TPU with TensorFlowTraining on Specialized HardwareCustom hardware for trainingHyperparameter Search using Trainer API
Optimizing inference
Contribute
How to contribute to transformers?How to add a model to 🤗 Transformers?How to convert a 🤗 Transformers model to TensorFlow?How to add a pipeline to 🤗 Transformers?TestingChecks on a Pull Request
Conceptual guides
PhilosophyGlossaryWhat 🤗 Transformers can doHow 🤗 Transformers solve tasksThe Transformer model familySummary of the tokenizersAttention mechanismsPadding and truncationBERTologyPerplexity of fixed-length modelsPipelines for webserver inferenceModel training anatomy
API
Main Classes
Agents and ToolsAuto ClassesCallbacksConfigurationData CollatorKeras callbacksLoggingModelsText GenerationONNXOptimizationModel outputsPipelinesProcessorsQuantizationTokenizerTrainerDeepSpeed IntegrationFeature ExtractorImage Processor
Models
Text models
Vision models
Audio models
Multimodal models
Reinforcement learning models
Time series models
Graph models
Internal Helpers
You are viewing v4.33.0 version. A newer version v5.8.1 is available.
Time Series Utilities
This page lists all the utility functions and classes that can be used for Time Series based models.
Most of those are only useful if you are studying the code of the time series models or you wish to add to the collection of distributional output classes.
Distributional Output
Normal distribution output class.
Student-T distribution output class.
Negative Binomial distribution output class.