tiktoken-go
tokenizer
tiktoken-go | tokenizer | |
---|---|---|
1 | 2 | |
552 | 228 | |
- | 0.4% | |
4.6 | 4.3 | |
about 1 month ago | about 1 year ago | |
Go | Go | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
tiktoken-go
-
Pure Go implementation of OpenAI's tokenizer
It is great! I was searching for a such library several days ago. Unfortunately, I have already found another pure go port: https://github.com/pkoukk/tiktoken-go
tokenizer
-
Understanding GPT Tokenizers
How I wish this post had appeared a few days earlier... I am writing on my own library for some agent experiments (in go, to make my life more interesting I guess), and knowing the number of tokens is important to implement a token buffer memory (as you approach the model's context window size, you prune enough messages from the beginning of the conversation that the whole thing keeps some given size, in tokens). While there's a nice native library in go for OpenAI models (https://github.com/tiktoken-go/tokenizer), the only library I found for Hugging Face models (and Claude, they published their tokenizer spec in the same JSON format) calls into HF's Rust implementation, which makes it challenging as a dependency in Go. What is more, any tokenizer needs to keep some representation of its vocabulary in memory. So, in the end I removed the true tokenizers, and ended up using an approximate version (just split it in on spaces and multiply by a factor I determined experimentally for the models I use using the real tokenizer, with a little extra for safety). If it turns out someone needs the real thing they can always provide their own token counter). I was actually rather happy with this result: I have less dependencies, and use less memory. But to get there I needed to do a deep dive too understand BPE tokenizers :)
(The library, if anyone is interested: https://github.com/ryszard/agency.)
- Pure Go implementation of OpenAI's tokenizer
What are some alternatives?
jotbot - JotBot generates the missing code documentation for your Go and TypeScript projects. Powered by AI.
tiktoken - tiktoken is a fast BPE tokeniser for use with OpenAI's models.
chatgptui - ChatGPT 🤖 with Textual User Interface (TUI) mode written in Go.
llama.go - llama.go is like llama.cpp in pure Golang!
tokenizer-go - A Go wrapper for GPT-3 token encode/decode. https://platform.openai.com/tokenizer
agency - Agency: Robust LLM Agent Management with Go
sentences - A multilingual command line sentence tokenizer in Golang
go-openai - OpenAI ChatGPT, GPT-3, GPT-4, DALL·E, Whisper API wrapper for Go
Constrained-Text-Genera
Constrained-Text-Generation-Studio - Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)