Expand description
Tokenizer interface for text encoding/decoding
This module provides tokenizer abstractions that are completely separate from model implementations, supporting incremental decoding and various tokenization strategies.
Structs§
- Chat
Message - Chat message for template application
- Padding
Config - Padding configuration
- Tokenizer
Config - Tokenizer configuration
- Tokenizer
Info - Tokenizer information and metadata
- Tokenizer
Stats - Tokenizer performance statistics
- Truncation
Config - Truncation configuration
Enums§
- Padding
Direction - Padding direction
- Padding
Strategy - Padding strategies
- Token
Type - Token types for classification
- Tokenizer
Type - Tokenizer types/algorithms
- Truncation
Strategy - Truncation strategies
Traits§
- Async
Tokenizer - Asynchronous tokenizer operations for I/O-bound tokenization
- Incremental
Tokenizer - Incremental tokenizer state for streaming
- Text
Processor - Text processing utilities
- Tokenizer
- Core tokenizer trait for encoding/decoding operations
- Tokenizer
Capabilities - Advanced tokenizer capabilities
- Tokenizer
Factory - Tokenizer factory for creating tokenizer instances
- Tokenizer
Registry - Tokenizer registry for managing multiple tokenizers