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 }}
ipackhu
/
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 Jun 14, 2023
Fix correct gradient accumulation (#407)
Show description for 61af5f2
younesbelkada
authored
61af5f2
View commit details
Copy full SHA for 61af5f2
Browse repository at this point
Commits on Jun 13, 2023
handle the offline case (#431)
Show description for 7a89a43
younesbelkada
authored
7a89a43
View commit details
Copy full SHA for 7a89a43
Browse repository at this point
best-of-n sampler class (#375)
Show description for fead2c8
metric-space
authored
fead2c8
View commit details
Copy full SHA for fead2c8
Browse repository at this point
Commits on Jun 9, 2023
Update test_reward_trainer.py (#421)
younesbelkada
authored
b4bb129
View commit details
Copy full SHA for b4bb129
Browse repository at this point
[doc build] Use secrets (#420)
Mishig
authored
b21badd
View commit details
Copy full SHA for b21badd
Browse repository at this point
Enable autotag feature w/ wandb (#411)
Show description for 216c119
vwxyzjn
and
younesbelkada
authored
216c119
View commit details
Copy full SHA for 216c119
Browse repository at this point
Add slurm utility (#412)
Show description for a2747ac
vwxyzjn
authored
a2747ac
View commit details
Copy full SHA for a2747ac
Browse repository at this point
Commits on Jun 8, 2023
set dev version
younesbelkada
committed
b61a4b9
View commit details
Copy full SHA for b61a4b9
Browse repository at this point
Release: v0.4.4
younesbelkada
committed
5c5d768
View commit details
Copy full SHA for 5c5d768
Browse repository at this point
unpin accelerate (#418)
younesbelkada
authored
096f5e9
View commit details
Copy full SHA for 096f5e9
Browse repository at this point
set dev version
younesbelkada
committed
2a0ed3a
View commit details
Copy full SHA for 2a0ed3a
Browse repository at this point
Release: v0.4.3
younesbelkada
committed
ff13c5b
View commit details
Copy full SHA for ff13c5b
Browse repository at this point
Update setup.py (#414)
younesbelkada
authored
d3e05d6
View commit details
Copy full SHA for d3e05d6
Browse repository at this point
Commits on Jun 7, 2023
Update test_reward_trainer.py (#410)
younesbelkada
authored
fadffc2
View commit details
Copy full SHA for fadffc2
Browse repository at this point
set dev version
younesbelkada
committed
d405c87
View commit details
Copy full SHA for d405c87
Browse repository at this point
Release: v0.4.2
younesbelkada
committed
b46716c
View commit details
Copy full SHA for b46716c
Browse repository at this point
Commits on Jun 6, 2023
Remove unused imports in docs. (#406)
Show description for ec8a5b7
vwxyzjn
authored
ec8a5b7
View commit details
Copy full SHA for ec8a5b7
Browse repository at this point
Resolve broken evaluation/prediction for RewardTrainer (#404)
Show description for 376d152
tomaarsen
authored
376d152
View commit details
Copy full SHA for 376d152
Browse repository at this point
StackLLaMA: fix supervised finetuning and reward model training (#399)
Show description for ef57cdd
mnoukhov
authored
ef57cdd
View commit details
Copy full SHA for ef57cdd
Browse repository at this point
Fixed some type annotations of trl.trainer.PPoTrainer (#392)
Show description for 20111ad
JulesGM
authored
20111ad
View commit details
Copy full SHA for 20111ad
Browse repository at this point
Commits on Jun 5, 2023
StackLlama: fixed RL training and added args (#400)
Show description for a4793c2
mnoukhov
authored
a4793c2
View commit details
Copy full SHA for a4793c2
Browse repository at this point
StackLLaMA: correctly merge peft model (#398)
Show description for 0ddf9f6
mnoukhov
authored
0ddf9f6
View commit details
Copy full SHA for 0ddf9f6
Browse repository at this point
Commits on Jun 2, 2023
fix 4 bit SFT (#396)
younesbelkada
authored
3138ef6
View commit details
Copy full SHA for 3138ef6
Browse repository at this point
Commits on May 31, 2023
keep state_dict kwargs instead of popping it in save_pretrained (#393)
rizar
authored
a5b0414
View commit details
Copy full SHA for a5b0414
Browse repository at this point
from_pretrain with peft adapter on the hub (# 379) (#380)
Show description for e174bd5
glerzing
authored
e174bd5
View commit details
Copy full SHA for e174bd5
Browse repository at this point
Commits on May 30, 2023
fix typo in ppo_trainer.py (#389)
Show description for 86c1174
LZY-the-boys
authored
86c1174
View commit details
Copy full SHA for 86c1174
Browse repository at this point
Update customization.mdx (#390)
binganao
authored
a94761a
View commit details
Copy full SHA for a94761a
Browse repository at this point
Commits on May 24, 2023
[`core`] Add 4bit QLora (#383)
Show description for 5fb5af7
younesbelkada
authored
5fb5af7
View commit details
Copy full SHA for 5fb5af7
Browse repository at this point
Commits on May 18, 2023
fix warning issue (#377)
younesbelkada
authored
25fa1bd
View commit details
Copy full SHA for 25fa1bd
Browse repository at this point
Commits on May 15, 2023
[`docs`] fix SFT doc (#367)
Show description for 6916e0d
younesbelkada
authored
6916e0d
View commit details
Copy full SHA for 6916e0d
Browse repository at this point
Delete test_training.py (#371)
younesbelkada
authored
1704a86
View commit details
Copy full SHA for 1704a86
Browse repository at this point
Remove obsolete layer_norm_names parameter and add peft>=0.3.0 to requirements (#366)
Show description for e547c39
teticio
authored
e547c39
View commit details
Copy full SHA for e547c39
Browse repository at this point
add is_trainable in kwargs (#363)
Show description for a31bad8
Opdoop
authored
a31bad8
View commit details
Copy full SHA for a31bad8
Browse repository at this point
Commits on May 11, 2023
Fix bug when loading local peft model (#342)
Show description for 31cc361
Opdoop
authored
31cc361
View commit details
Copy full SHA for 31cc361
Browse repository at this point
140/best n sampling (#326)
Show description for ab453ec
metric-space
authored
ab453ec
View commit details
Copy full SHA for ab453ec
Browse repository at this point
Previous
Next
You can’t perform that action at this time.