niieani/gpt-tokenizer

Picture tokens

Open

#41 opened on Jan 27, 2024

View on GitHub
 (3 comments) (1 reaction) (0 assignees)TypeScript (56 forks)github user discovery
help wanted

Repository metrics

Stars
 (808 stars)
PR merge metrics
 (PR metrics pending)

Description

Hello.

The new -vision model lets you pass images (which end up as tokens). To properly calculate token use for my stuff, I'd need to be able to pass my full conversation/payload, which includes images. Does this tokenizer support that (reading the docs I don't see signs it does). Would you have recommendations of how to implement that on my side? And if I do implement it would that be a welcome PR?

Cheers.

Contributor guide

Research direction
Investigate how the current tokenizer handles text tokens and explore the tiktoken library to understand picture token support. Look at OpenAI's vision model documentation and consider adding a new token type for images.
Tech stack
typescript
Domain
backenddeveloper experience
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
TypeScriptFamiliarity with tokenization
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
50