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
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 }}
qfxlcyc
/
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 Oct 3, 2023
Fix DeepSpeed ZeRO-{1,2} for DPOTrainer (#825)
lewtun
authored
98845b9
View commit details
Copy full SHA for 98845b9
Browse repository at this point
Commits on Oct 2, 2023
Unify sentiment documentation (#803)
Show description for 9f6326e
3 people
authored
9f6326e
View commit details
Copy full SHA for 9f6326e
Browse repository at this point
Small fixes to the PPO trainer doc. (#811)
Show description for 7dcc71b
namin
authored
7dcc71b
View commit details
Copy full SHA for 7dcc71b
Browse repository at this point
Commits on Sep 29, 2023
add option for compute_metrics in DPOTrainer (#822)
kashif
authored
6b73adc
View commit details
Copy full SHA for 6b73adc
Browse repository at this point
Commits on Sep 26, 2023
Add RMSProp back to DPO (#821)
Show description for 249d3e3
Nathan Lambert
authored
249d3e3
View commit details
Copy full SHA for 249d3e3
Browse repository at this point
init custom eval loop for further DPO evals (#766)
Show description for ad8d50e
Nathan Lambert
and
tomaarsen
authored
ad8d50e
View commit details
Copy full SHA for ad8d50e
Browse repository at this point
Allow passing the token_ids as instruction_template in DataCollatorForCompletionOnlyLM (#749)
Show description for d608fea
devxpy
authored
d608fea
View commit details
Copy full SHA for d608fea
Browse repository at this point
fixes ppo trainer generate nit (#798)
younesbelkada
authored
92b03f5
View commit details
Copy full SHA for 92b03f5
Browse repository at this point
Commits on Sep 22, 2023
Update sft_trainer.mdx (#808)
younesbelkada
authored
7877e92
View commit details
Copy full SHA for 7877e92
Browse repository at this point
Update sft_trainer.mdx to highlight Flash Attention features (#807)
Show description for 1d7e3c2
younesbelkada
authored
1d7e3c2
View commit details
Copy full SHA for 1d7e3c2
Browse repository at this point
Commits on Sep 21, 2023
clarify PEFT docs (#797)
younesbelkada
authored
eb6aa20
View commit details
Copy full SHA for eb6aa20
Browse repository at this point
Commits on Sep 20, 2023
Add deepspeed experiment (#795)
Show description for b8f0c4c
vwxyzjn
authored
b8f0c4c
View commit details
Copy full SHA for b8f0c4c
Browse repository at this point
Revert "Add default Optim to DPO example (#759)" (#799)
Show description for e11a45c
younesbelkada
authored
e11a45c
View commit details
Copy full SHA for e11a45c
Browse repository at this point
Add margin to RM training (#719)
Show description for 08cfc41
jvhoffbauer
and
lewtun
authored
08cfc41
View commit details
Copy full SHA for 08cfc41
Browse repository at this point
Commits on Sep 19, 2023
Add default Optim to DPO example (#759)
Show description for d603e7c
Nathan Lambert
authored
d603e7c
View commit details
Copy full SHA for d603e7c
Browse repository at this point
Changed the default value of the `log_with` argument (#792)
Show description for 5d30cd4
filippobistaffa
authored
5d30cd4
View commit details
Copy full SHA for 5d30cd4
Browse repository at this point
Commits on Sep 18, 2023
Temp benchmark ci dir (#765)
Show description for 4697523
vwxyzjn
authored
4697523
View commit details
Copy full SHA for 4697523
Browse repository at this point
Fix type checking (#748)
lewtun
authored
9a8d52c
View commit details
Copy full SHA for 9a8d52c
Browse repository at this point
Commits on Sep 15, 2023
Update benchmark.yml (#782)
vwxyzjn
authored
0a6c42c
View commit details
Copy full SHA for 0a6c42c
Browse repository at this point
Update benchmark.yml (#781)
vwxyzjn
authored
221be13
View commit details
Copy full SHA for 221be13
Browse repository at this point
Update benchmark.yml (#780)
vwxyzjn
authored
a922af6
View commit details
Copy full SHA for a922af6
Browse repository at this point
Update benchmark.yml (#779)
vwxyzjn
authored
42e7a0a
View commit details
Copy full SHA for 42e7a0a
Browse repository at this point
Update benchmark.yml (#778)
vwxyzjn
authored
15d52e7
View commit details
Copy full SHA for 15d52e7
Browse repository at this point
Update benchmark.yml (#777)
vwxyzjn
authored
24e914a
View commit details
Copy full SHA for 24e914a
Browse repository at this point
Benchmark CI fix (#776)
vwxyzjn
authored
637612d
View commit details
Copy full SHA for 637612d
Browse repository at this point
Benchmark CI fix (#775)
vwxyzjn
authored
35694ba
View commit details
Copy full SHA for 35694ba
Browse repository at this point
Update benchmark.yml (#773)
Show description for d2f27df
vwxyzjn
authored
d2f27df
View commit details
Copy full SHA for d2f27df
Browse repository at this point
Commits on Sep 14, 2023
Support fork in benchmark CI (#764)
vwxyzjn
authored
5cee9a0
View commit details
Copy full SHA for 5cee9a0
Browse repository at this point
docs: add initial version of docs for `PPOTrainer` (#665)
Show description for 3f7710a
davidberenstein1957
and
lvwerra
authored
3f7710a
View commit details
Copy full SHA for 3f7710a
Browse repository at this point
Commits on Sep 13, 2023
Benchmark CI (actual) (#754)
Show description for ca0af39
vwxyzjn
and
lvwerra
authored
ca0af39
View commit details
Copy full SHA for ca0af39
Browse repository at this point
Refactor and benchmark (#662)
Show description for e4f9a48
vwxyzjn
and
lvwerra
authored
e4f9a48
View commit details
Copy full SHA for e4f9a48
Browse repository at this point
[PPOTrainer] - add comment of zero masking (from second query token) (#763)
Show description for 80890b1
zuoxingdong
authored
80890b1
View commit details
Copy full SHA for 80890b1
Browse repository at this point
Imrpove benchmark ci (#760)
vwxyzjn
authored
cf9d2a7
View commit details
Copy full SHA for cf9d2a7
Browse repository at this point
Commits on Sep 12, 2023
Extend DeepSpeed integration to ZeRO-{1,2,3} (#758)
Show description for c02ce6d
lewtun
and
younesbelkada
authored
c02ce6d
View commit details
Copy full SHA for c02ce6d
Browse repository at this point
EOS token processing for multi-turn DPO (#741)
Show description for 9141aa4
Nathan Lambert
authored
9141aa4
View commit details
Copy full SHA for 9141aa4
Browse repository at this point
Previous
Next
You can’t perform that action at this time.