Skip to content
Navigation Menu
Sign in
Appearance settings
Platform
AI CODE CREATION
GitHub Copilot
Write better code with AI
GitHub Copilot app
Direct agents from issue to merge
MCP Registry
Integrate external tools
DEVELOPER WORKFLOWS
Actions
Automate any workflow
Codespaces
Instant dev environments
Issues
Plan and track work
Code Review
Manage code changes
Code Quality
Enforce quality at merge
APPLICATION SECURITY
GitHub Advanced Security
Find and fix vulnerabilities
Code security
Secure your code as you build
Secret protection
Stop leaks before they start
EXPLORE
Why GitHub
Documentation
Blog
Changelog
Marketplace
View all features
Solutions
BY COMPANY SIZE
Enterprises
Small and medium teams
Startups
Nonprofits
BY USE CASE
App Modernization
DevSecOps
DevOps
CI/CD
View all use cases
BY INDUSTRY
Healthcare
Financial services
Manufacturing
Government
View all industries
View all solutions
Resources
EXPLORE BY TOPIC
AI
Software Development
DevOps
Security
View all topics
EXPLORE BY TYPE
Customer stories
Events & webinars
Ebooks & reports
Business insights
GitHub Skills
SUPPORT & SERVICES
Documentation
Customer support
Community forum
Trust center
Partners
View all resources
Open Source
COMMUNITY
GitHub Sponsors
Fund open source developers
PROGRAMS
Security Lab
Maintainer Community
Accelerator
GitHub Stars
Archive Program
REPOSITORIES
Topics
Trending
Collections
Enterprise
ENTERPRISE SOLUTIONS
Enterprise platform
AI-powered developer platform
AVAILABLE ADD-ONS
GitHub Advanced Security
Enterprise-grade security features
Copilot for Business
Enterprise-grade AI features
Premium Support
Enterprise-grade 24/7 support
Pricing
Type
/
to 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 }}
JiwanChung
/
trl
Public
forked from
huggingface/trl
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Commits
Branch selector
main
User selector
All users
All time
Commit history
Commits on Apr 30, 2024
[`KTOTrainer`] add BCO (reward shift and underlying distribution matching) (#1599)
Show description for d1aa0b6
seanexp
authored
d1aa0b6
View commit details
Copy full SHA for d1aa0b6
Browse repository at this point
Update __init__.py (#1602)
younesbelkada
authored
d88ec14
View commit details
Copy full SHA for d88ec14
Browse repository at this point
Commits on Apr 29, 2024
fix typo (#1594)
qgallouedec
authored
6c18e40
View commit details
Copy full SHA for 6c18e40
Browse repository at this point
Commits on Apr 23, 2024
add warning in SFTTrainer (#1577)
younesbelkada
authored
1d0a7ea
View commit details
Copy full SHA for 1d0a7ea
Browse repository at this point
FIX: Fix CI on transformers main (#1576)
Show description for 9f68ead
younesbelkada
authored
9f68ead
View commit details
Copy full SHA for 9f68ead
Browse repository at this point
[SFT] add SFT Trainer Config dataclass (#1530)
Show description for f30daa4
kashif
and
lewtun
authored
f30daa4
View commit details
Copy full SHA for f30daa4
Browse repository at this point
[DPO] DPOConfig class (#1554)
Show description for 24fd8dd
kashif
and
lewtun
authored
24fd8dd
View commit details
Copy full SHA for 24fd8dd
Browse repository at this point
Commits on Apr 22, 2024
[DPO] add 'bco_pair' loss_type (#1524)
Show description for c050ebc
seanexp
and
sean.jung
authored
c050ebc
View commit details
Copy full SHA for c050ebc
Browse repository at this point
fix add_special_tokens issue for data with template (#1509)
edixiong
authored
abc0584
View commit details
Copy full SHA for abc0584
Browse repository at this point
set dev version (#1568)
younesbelkada
authored
6d1cb85
View commit details
Copy full SHA for 6d1cb85
Browse repository at this point
Release: v0.8.6 (#1567)
younesbelkada
authored
e90e8d9
View commit details
Copy full SHA for e90e8d9
Browse repository at this point
CLI: Add warning when ignored params are passed + parse config file if config if passed (#1565)
Show description for 113aaae
younesbelkada
authored
113aaae
View commit details
Copy full SHA for 113aaae
Browse repository at this point
Commits on Apr 18, 2024
Update __init__.py (#1557)
kashif
authored
0865572
View commit details
Copy full SHA for 0865572
Browse repository at this point
set dev version (#1556)
younesbelkada
authored
a6532a1
View commit details
Copy full SHA for a6532a1
Browse repository at this point
Release: v0.8.5 (#1555)
younesbelkada
authored
3595eb0
View commit details
Copy full SHA for 3595eb0
Browse repository at this point
enable multiple eos tokens (#1553)
lvwerra
authored
9afd901
View commit details
Copy full SHA for 9afd901
Browse repository at this point
FIX: make the train / test fields modulable (#1551)
Show description for e04432d
younesbelkada
authored
e04432d
View commit details
Copy full SHA for e04432d
Browse repository at this point
Commits on Apr 17, 2024
set dev version (#1548)
younesbelkada
authored
75c1c47
View commit details
Copy full SHA for 75c1c47
Browse repository at this point
Release: v0.8.4 (#1547)
younesbelkada
authored
a5788ac
View commit details
Copy full SHA for a5788ac
Browse repository at this point
Fixed ref model not used in PPO generation (#1534)
ejmejm
authored
3bbe7e0
View commit details
Copy full SHA for 3bbe7e0
Browse repository at this point
Update run_sft.sh (#1546)
younesbelkada
authored
edf60e8
View commit details
Copy full SHA for edf60e8
Browse repository at this point
CLI: Set `dataset_text_field` to `None` to allow ChatML automatic template (#1545)
Show description for 5d1deb1
younesbelkada
authored
5d1deb1
View commit details
Copy full SHA for 5d1deb1
Browse repository at this point
Commits on Apr 16, 2024
[KTO] support to load the adapter twice (#1542)
Show description for 476c4b8
claralp
and
Clara Luise Pohland
authored
476c4b8
View commit details
Copy full SHA for 476c4b8
Browse repository at this point
Commits on Apr 15, 2024
save_model -> save_pretrained in ppo_trainer.mdx (#1537)
ejmejm
authored
e823458
View commit details
Copy full SHA for e823458
Browse repository at this point
Commits on Apr 12, 2024
VSFT hotfix - adds gen prompt to template and processor to hub (#1532)
Show description for 1c0d8bc
edbeeching
authored
1c0d8bc
View commit details
Copy full SHA for 1c0d8bc
Browse repository at this point
[CPO] fix memory leak due to retained value (#1531)
kashif
authored
363369a
View commit details
Copy full SHA for 363369a
Browse repository at this point
set dev version (#1529)
younesbelkada
authored
aba4df0
View commit details
Copy full SHA for aba4df0
Browse repository at this point
Release: v0.8.3 (#1528)
younesbelkada
authored
9822647
View commit details
Copy full SHA for 9822647
Browse repository at this point
[CLI] fix imports (#1527)
kashif
authored
87f4c70
View commit details
Copy full SHA for 87f4c70
Browse repository at this point
Commits on Apr 11, 2024
set dev version (#1523)
younesbelkada
authored
995f117
View commit details
Copy full SHA for 995f117
Browse repository at this point
Release: v0.8.2 (#1522)
younesbelkada
authored
143e111
View commit details
Copy full SHA for 143e111
Browse repository at this point
Adds VLM Training support to SFTTrainer + VSFT script (#1518)
Show description for 346c99d
edbeeching
and
younesbelkada
authored
346c99d
View commit details
Copy full SHA for 346c99d
Browse repository at this point
add data for sfttrainer doc (#1521)
BramVanroy
authored
087fe54
View commit details
Copy full SHA for 087fe54
Browse repository at this point
allow pre-tokenized datasets (#1520)
BramVanroy
authored
ebbd37b
View commit details
Copy full SHA for ebbd37b
Browse repository at this point
Allow streaming (datasets.IterableDataset) (#1468)
Show description for e667550
BramVanroy
authored
e667550
View commit details
Copy full SHA for e667550
Browse repository at this point
Previous
Next
You can’t perform that action at this time.