← 트렌딩
Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.
tokenizers-cpp
github.com
Universal cross-platform tokenizers binding to HF and sentencepiece
오픈소스
비슷한 프로덕트
설명이 비슷한 순
Tokensift
an open-sourced token-efficiency linter for LLM prompts
Steerling-8B
a language model that can explain any token it generates
Byte-Pair Encoding tokenizer for training LLMs on large datasets
Byte-Pair Encoding tokenizer for training large language models on huge datasets
S3Tokenizer
Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice
magvit2-pytorch
Implementation of MagViT2 Tokenizer in Pytorch