Buckets:

hf-doc-build/doc-dev / tokenizers /pr_2449 /en /api /post-processors.md
|
download
raw
941 Bytes

Post-processors

TODO -- coming soon. Reference documentation on this page is not generated yet: the rc0 bindings do not expose all of these APIs. It comes back with them, along with the other bindings. See REQUIRED_FOR_V1.md for the full list.

Every post-processor is a template. BertProcessing, RobertaProcessing, ByteLevel and a Sequence of post-processors were spellings of one, so a tokenizer.json using any of them is rewritten into a TemplateProcessing when it is converted, and there is no separate class for them.

PostProcessor[[tokenizers.processors.PostProcessor]]

tokenizers.processors.PostProcessor

TemplateProcessing[[tokenizers.processors.TemplateProcessing]]

tokenizers.processors.TemplateProcessing

The Rust API Reference is available directly on the Docs.rs website.

Xet Storage Details

Size:
941 Bytes
·
Xet hash:
3a507b4f623926a95b0ccc6c25faf25a86b7416be0be85fd724a158aeb63364d

Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.