Expand description
§Common blocks for generic pipelines (e.g. token classification or sequence classification)
Provides Enums holding configuration or tokenization resources that can be used to create generic pipelines. The model component is defined in the generic pipeline itself as the pre-processing, forward pass and postprocessing differs between pipelines while basic config and tokenization objects don’t.
Structs§
- ONNX
Local Paths - ONNX
Model Resources - Container for ONNX model resources, containing 3 optional resources (Encoder, Decoder and Decoder with past)
Enums§
- Config
Option - Abstraction that holds a model configuration, can be of any of the supported models
- Model
Resource - Variants to store either a Torch model resource or ONNX resources
- Model
Type - Identifies the type of model
- Tokenizer
Option - Abstraction that holds a particular tokenizer, can be of any of the supported models