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 }}
zhuango
/
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 Nov 15, 2023
Fixed wrong trigger for warning (#971)
Show description for 28bdb6a
zabealbe
authored
28bdb6a
View commit details
Copy full SHA for 28bdb6a
Browse repository at this point
make distributed true for multiple process (#997)
Show description for e140d22
allanj
and
younesbelkada
authored
e140d22
View commit details
Copy full SHA for e140d22
Browse repository at this point
Commits on Nov 14, 2023
add docs (#992)
younesbelkada
authored
e23a541
View commit details
Copy full SHA for e23a541
Browse repository at this point
[DataCollatorForCompletionOnlyLM] warn if eos_token_id and pad_token_id are identical (#988)
Show description for be3faa7
MustSave
authored
be3faa7
View commit details
Copy full SHA for be3faa7
Browse repository at this point
Update README.md (#994)
GeekDream-x
authored
13679aa
View commit details
Copy full SHA for 13679aa
Browse repository at this point
Commits on Nov 10, 2023
Fix a bunch of outdated references to `examples/` (#977)
alvarobartt
authored
9e9f024
View commit details
Copy full SHA for 9e9f024
Browse repository at this point
Commits on Nov 9, 2023
[`Tests`] Add non optional packages tests (#974)
Show description for c2884b5
younesbelkada
authored
c2884b5
View commit details
Copy full SHA for c2884b5
Browse repository at this point
Commits on Nov 8, 2023
set dev version (#970)
younesbelkada
authored
2f726ce
View commit details
Copy full SHA for 2f726ce
Browse repository at this point
Release: v0.7.4
younesbelkada
committed
a78a05d
View commit details
Copy full SHA for a78a05d
Browse repository at this point
Pin bnb to <=0.41.1 (#968)
Show description for 1b25824
younesbelkada
authored
1b25824
View commit details
Copy full SHA for 1b25824
Browse repository at this point
fix peft config typehint (#967)
younesbelkada
authored
9c93dec
View commit details
Copy full SHA for 9c93dec
Browse repository at this point
set dev version (#966)
younesbelkada
authored
d1dad6e
View commit details
Copy full SHA for d1dad6e
Browse repository at this point
Release: v0.7.3 (#965)
younesbelkada
authored
8ce8102
View commit details
Copy full SHA for 8ce8102
Browse repository at this point
Commits on Nov 6, 2023
fix: dpo trainer ds config (#957)
Show description for 8e9cae8
mengban
authored
8e9cae8
View commit details
Copy full SHA for 8e9cae8
Browse repository at this point
Added support for custom EncoderDecoder models (#911)
ribesstefano
authored
654543a
View commit details
Copy full SHA for 654543a
Browse repository at this point
Adds model kwargs to SFT and DPO trainers (#951)
Show description for c273b18
edbeeching
authored
c273b18
View commit details
Copy full SHA for c273b18
Browse repository at this point
[DPO] Merge initial peft model if trainer has a peft_config (#956)
Show description for 6c6ff24
kashif
authored
6c6ff24
View commit details
Copy full SHA for 6c6ff24
Browse repository at this point
Commits on Nov 5, 2023
Fix unwrapping peft models (#948)
Show description for 6ff0fac
kkteru
authored
6ff0fac
View commit details
Copy full SHA for 6ff0fac
Browse repository at this point
Commits on Nov 3, 2023
[`CI`] Fix CI with new transformers release (#946)
Show description for 951ca18
younesbelkada
authored
951ca18
View commit details
Copy full SHA for 951ca18
Browse repository at this point
Commits on Nov 2, 2023
Introducing the Iterative Trainer (#737)
Show description for cc1de98
gaetanlop
authored
cc1de98
View commit details
Copy full SHA for cc1de98
Browse repository at this point
Update dpo_trainer.py (#941)
younesbelkada
authored
a64a522
View commit details
Copy full SHA for a64a522
Browse repository at this point
Commits on Oct 31, 2023
Optionally logging reference response (#847)
Show description for 5b32372
vwxyzjn
and
younesbelkada
authored
5b32372
View commit details
Copy full SHA for 5b32372
Browse repository at this point
Fix stale bot (#935)
Show description for d759004
younesbelkada
authored
d759004
View commit details
Copy full SHA for d759004
Browse repository at this point
[`core` / `DDP`] Fix RM trainer + DDP + quantization + propagate `gradient_checkpointing_kwargs` in SFT & DPO (#912)
Show description for cbc6c9b
younesbelkada
authored
cbc6c9b
View commit details
Copy full SHA for cbc6c9b
Browse repository at this point
Update dpo_llama2.py (#934)
younesbelkada
authored
f3cd865
View commit details
Copy full SHA for f3cd865
Browse repository at this point
[`SFTTrainer`] Make sure to not conflict between `transformers` and TRL implementation (#933)
Show description for b763432
younesbelkada
authored
b763432
View commit details
Copy full SHA for b763432
Browse repository at this point
hotfix for dpo trainer (#919)
Show description for 2bbd594
mnoukhov
authored
2bbd594
View commit details
Copy full SHA for 2bbd594
Browse repository at this point
fix DPO + GC issues (#927)
younesbelkada
authored
b89b712
View commit details
Copy full SHA for b89b712
Browse repository at this point
[Feature] Enable Intel XPU support (#839)
Show description for ec9e766
6 people
authored
ec9e766
View commit details
Copy full SHA for ec9e766
Browse repository at this point
Bump `tyro` (#928)
brentyi
authored
d192244
View commit details
Copy full SHA for d192244
Browse repository at this point
Commits on Oct 30, 2023
updating PPOTrainer docstring (#897)
Show description for 051d5a1
3 people
authored
051d5a1
View commit details
Copy full SHA for 051d5a1
Browse repository at this point
Generalize NEFTune for FSDP, DDP, ... (#924)
Show description for 2068fdc
younesbelkada
authored
2068fdc
View commit details
Copy full SHA for 2068fdc
Browse repository at this point
Commits on Oct 25, 2023
fix stackllama2 sft gradient checkpointing (#906)
Show description for 02f5c1d
nrailg
authored
02f5c1d
View commit details
Copy full SHA for 02f5c1d
Browse repository at this point
Commits on Oct 24, 2023
deactivate MacOS CI (#913)
lvwerra
authored
7de7db6
View commit details
Copy full SHA for 7de7db6
Browse repository at this point
[Update reward_trainer.py] append PeftSavingCallback if callbacks is not None (#910)
zuoxingdong
authored
4e7d5b5
View commit details
Copy full SHA for 4e7d5b5
Browse repository at this point
Previous
Next
You can’t perform that action at this time.