bytedance / bytedance/1d-tokenizer

Question about the MaskGIT

Open
#68 2 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
1.2k
Forks
70
PR merge metrics
No merged PRs in 30d

Description

Thanks for this great work! What is the training cost of the generator for MaskGIT? From Table 1, the codebook size is 1024. Is the tokenizer available online? Also, what is the training setting and shell command for training this MaskGIT generator? Would it be sufficient to run train_maskgit.py directly? Thanks!

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with train_maskgit.py and the repository's MaskGIT training materials. Determine the documented training cost, tokenizer availability, training settings, and whether the named script is sufficient; done means these questions have a clear, reproducible answer with the required command and configuration.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, shell
Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.