Pure-Go LLM tokenizer and tiktoken-compatible token counter for OpenAI BPE, WordPiece, SentencePiece, Gemini, Llama, Mistral, and Hugging Face adapters.
A package designed for handling and extracting data from ZIP files efficiently using a tokenizer-based approach. The library provides a customizable way to parse ZIP archives and extract compressed data while minimizing memory usage.
Text tokenizer for linguistic purposes, such as text matching. Supports more than 40 languages, including English, French, Russian, Japanese, Thai etc.