Skip to content
Navigation Menu
Sign in
Products
Platform
GitHub
Repository hosting, code review, and collaboration
Copilot
AI coding agent for tasks, projects and automated work
Build & Ship
Actions
CI/CD and automation
Code Quality
Quality analysis, fixes, and enforcement
Codespaces
Cloud development environments
Secure
Code Security
Vulnerability detection and remediation
Secret Protection
Secret scanning and leak prevention
All Features
Developers
Learn
Documentation
Training
Certifications
Build
Build with Copilot
Customize Copilot
Integrations
Explore
Trending repos
GitHub Sponsors
Developer articles
Changelog
Changelog
Your source for the latest features, improvements, and fixes across GitHub products, all in one place.
Businesses
By Stage
Enterprises
Team
Startups
Nonprofits
By Industry
Healthcare
Financial services
Manufacturing
Government
See all industries
Evaluate GitHub
Why GitHub
Customer Stories
Business insights
Trust Center
Add-ons
GitHub Advanced Security
Enterprise-grade code security
Copilot for business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Resources
Learn & Connect
Documentation
Resource center
Blog
Events & webinars
Community Forum
Customer Stories
Integrations
Support
Customer support
Training
GitHub Status
Company
About
Partners
Changelog
GitHub Universe
GitHub Universe
The event for developers, by developers — talks, workshops, and what’s next for GitHub.
Pricing
Search
/
Sign in
Sign up
Appearance settings
You signed in with another tab or window.
Reload
to refresh your session.
You signed out in another tab or window.
Reload
to refresh your session.
You switched accounts on another tab or window.
Reload
to refresh your session.
Dismiss alert
{{ message }}
coder
ai-tokenizer
Repository navigation
Code
Issues
3
(3)
Pull requests
7
(7)
Actions
Projects
Security and quality
Insights
More
items
feat(encoding): add Gemma 4 (Gemini) and Llama 4 encodings
- #16
#16
Open
ThomasK33
wants to merge 11 commits into
main
coder/ai-tokenizer:main
from
feat/gemma4-llama4-encodings
coder/ai-tokenizer:feat/gemma4-llama4-encodings
Copy head branch name to clipboard
Conversation
Commits
11
(11)
Checks
Files changed
Open
feat(encoding): add Gemma 4 (Gemini) and Llama 4 encodings
#16
ThomasK33
wants to merge 11 commits into
main
coder/ai-tokenizer:main
from
feat/gemma4-llama4-encodings
coder/ai-tokenizer:feat/gemma4-llama4-encodings
Copy head branch name to clipboard
Commits
Commits on Nov 3, 2026
feat: add SentencePieceTokenizer for merge-list BPE vocabularies
Show description for 1147b01
ThomasK33
committed
1147b01
View commit details
Copy full SHA for 1147b01
Browse repository at this point
feat(encoding): add llama4 and gemma4 encodings generated from pinned HF tokenizers
Show description for 1b15e24
ThomasK33
committed
1b15e24
View commit details
Copy full SHA for 1b15e24
Browse repository at this point
test(encoding): check llama4 and gemma4 against Hugging Face tokenizers
Show description for 6b2e606
ThomasK33
committed
6b2e606
View commit details
Copy full SHA for 6b2e606
Browse repository at this point
fix(sentencepiece): keep a BOM when decoding byte tokens, document the new encodings
Show description for 719fec1
ThomasK33
committed
719fec1
View commit details
Copy full SHA for 719fec1
Browse repository at this point
test(encoding): add small-alphabet fuzz samples and a gateway measurement script
Show description for 1cd219f
ThomasK33
committed
1cd219f
View commit details
Copy full SHA for 1cd219f
Browse repository at this point
feat(encoding): let Tokenizer run kind-tagged encodings and export gemma4
Show description for 284918b
ThomasK33
committed
284918b
View commit details
Copy full SHA for 284918b
Browse repository at this point
refactor(tokenizer): mark fields the kind branch skips with definite assignment
Show description for fd7ee75
ThomasK33
committed
fd7ee75
View commit details
Copy full SHA for fd7ee75
Browse repository at this point
Merge origin/main into feat/gemma4-llama4-encodings
Show description for 24145ea
ThomasK33
committed
24145ea
View commit details
Copy full SHA for 24145ea
Browse repository at this point
refactor(encoding): run gemma4 through the Codec interface, fold U+017F in llama4, type large literals
Show description for 9bd1938
ThomasK33
committed
9bd1938
View commit details
Copy full SHA for 9bd1938
Browse repository at this point
docs: note that Llama 4 Scout reads special-token text as special tokens
Show description for ce60dee
ThomasK33
committed
ce60dee
View commit details
Copy full SHA for ce60dee
Browse repository at this point
Merge remote-tracking branch 'origin/main' into feat/gemma4-llama4-encodings
Show description for a5c5e30
ThomasK33
committed
a5c5e30
View commit details
Copy full SHA for a5c5e30
Browse repository at this point
You can’t perform that action at this time.