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 }}
tmm1
/
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 Jul 22, 2023
[`SFTTrainer`] Add warning for wrong padding_side (#550)
Show description for 170d58f
younesbelkada
authored
170d58f
View commit details
Copy full SHA for 170d58f
Browse repository at this point
Commits on Jul 20, 2023
ADD: num_proc to SFTTrainer (#547)
Show description for 84c9209
3 people
authored
84c9209
View commit details
Copy full SHA for 84c9209
Browse repository at this point
Commits on Jul 19, 2023
Add `use_auth_token` arg to sft_trainer example (#544)
Show description for d0fe348
corey-lambda
and
lvwerra
authored
d0fe348
View commit details
Copy full SHA for d0fe348
Browse repository at this point
[`examples`] make the sft script more modulable (#543)
Show description for 5857d0a
younesbelkada
authored
5857d0a
View commit details
Copy full SHA for 5857d0a
Browse repository at this point
[DPO] remove response/pairs from the DPO side (#540)
Show description for fd50e06
3 people
authored
fd50e06
View commit details
Copy full SHA for fd50e06
Browse repository at this point
Relax reward trainer constraint (#539)
Show description for bcff7c2
younesbelkada
and
tomaarsen
authored
bcff7c2
View commit details
Copy full SHA for bcff7c2
Browse repository at this point
fix offline case (#538)
younesbelkada
authored
0e8d9f8
View commit details
Copy full SHA for 0e8d9f8
Browse repository at this point
Commits on Jul 18, 2023
all the concated batches are on same device (#528)
kashif
authored
7f297b3
View commit details
Copy full SHA for 7f297b3
Browse repository at this point
Commits on Jul 17, 2023
DPO Trainer (#416)
Show description for 84393f3
4 people
authored
84393f3
View commit details
Copy full SHA for 84393f3
Browse repository at this point
Commits on Jul 14, 2023
Fix sentiment nit (#517)
younesbelkada
authored
388bdc0
View commit details
Copy full SHA for 388bdc0
Browse repository at this point
[`examples`] Big refactor of examples and documentation (#509)
Show description for 5c7bfbc
younesbelkada
authored
5c7bfbc
View commit details
Copy full SHA for 5c7bfbc
Browse repository at this point
Use local process index for `_get_current_device()` (#515)
Show description for 36b77ae
lewtun
authored
36b77ae
View commit details
Copy full SHA for 36b77ae
Browse repository at this point
Commits on Jul 13, 2023
Put labels tensors onto GPU to fix eval bug on deepspeed (#513)
rlindskog
authored
2049d03
View commit details
Copy full SHA for 2049d03
Browse repository at this point
set dev version
younesbelkada
committed
31b98aa
View commit details
Copy full SHA for 31b98aa
Browse repository at this point
git commit -m 'Release: v0.4.7'
younesbelkada
committed
d06b131
View commit details
Copy full SHA for d06b131
Browse repository at this point
Commits on Jul 12, 2023
[`SFTTrainer`] Fix the sequence length check of `SFTTrainer` (#512)
Show description for f323090
3 people
authored
f323090
View commit details
Copy full SHA for f323090
Browse repository at this point
Commits on Jul 6, 2023
[`PPOTrainer`] Add prompt tuning support on TRL (#500)
Show description for bbc7eeb
younesbelkada
authored
bbc7eeb
View commit details
Copy full SHA for bbc7eeb
Browse repository at this point
[`PPOTrainer`] Add prefix tuning support (#501)
Show description for 163dae5
younesbelkada
authored
163dae5
View commit details
Copy full SHA for 163dae5
Browse repository at this point
Update ppo_trainer.py (#499)
younesbelkada
authored
64c8db2
View commit details
Copy full SHA for 64c8db2
Browse repository at this point
Disable mlm by default in DataCollatorForCompletionOnlyLM, add ignore_index and docstring (#476)
Show description for 25d4d81
BramVanroy
and
Bram Vanroy
authored
25d4d81
View commit details
Copy full SHA for 25d4d81
Browse repository at this point
correctly implement gradient checkpointing (#479)
Show description for 685620a
mnoukhov
authored
685620a
View commit details
Copy full SHA for 685620a
Browse repository at this point
Commits on Jul 5, 2023
Adds some options to stabilize the KL penalty (#486)
Show description for 2b531b9
3 people
authored
2b531b9
View commit details
Copy full SHA for 2b531b9
Browse repository at this point
Remove padding in batched generation. (#487)
Show description for 4f7f73d
lvwerra
and
leandro von werra
authored
4f7f73d
View commit details
Copy full SHA for 4f7f73d
Browse repository at this point
Commits on Jul 4, 2023
FIX: contributing guidelines command (#493)
Show description for c60c416
BramVanroy
and
lvwerra
authored
c60c416
View commit details
Copy full SHA for c60c416
Browse repository at this point
fix typo in reward_modeling.py (#494)
csyourui
authored
cbb98da
View commit details
Copy full SHA for cbb98da
Browse repository at this point
add ratio threshold to avoid spikes (#488)
lvwerra
authored
a86eaab
View commit details
Copy full SHA for a86eaab
Browse repository at this point
Commits on Jul 3, 2023
Refactor README (#460)
Show description for aa9770c
younesbelkada
authored
aa9770c
View commit details
Copy full SHA for aa9770c
Browse repository at this point
Commits on Jun 27, 2023
Update sft_trainer.py (#474)
Show description for 0fe603e
JulesGM
authored
0fe603e
View commit details
Copy full SHA for 0fe603e
Browse repository at this point
Commits on Jun 26, 2023
fix CI RM (#468)
younesbelkada
authored
843c145
View commit details
Copy full SHA for 843c145
Browse repository at this point
Commits on Jun 24, 2023
Debug the tortuous logic in `_prepare_dataset` function (#464)
Show description for 009b824
BeibinLi
authored
009b824
View commit details
Copy full SHA for 009b824
Browse repository at this point
Commits on Jun 23, 2023
Pre-commit (#448)
Show description for 82c8f20
vwxyzjn
authored
82c8f20
View commit details
Copy full SHA for 82c8f20
Browse repository at this point
Improve stabiliy: change default hyperparamers
vwxyzjn
committed
b56e8b3
View commit details
Copy full SHA for b56e8b3
Browse repository at this point
added shuffle parameter. I found it useful to turn off shuffle here and shuffle independently of this. (#457)
lopez-hector
authored
0161a8e
View commit details
Copy full SHA for 0161a8e
Browse repository at this point
set dev version
younesbelkada
committed
6e34c59
View commit details
Copy full SHA for 6e34c59
Browse repository at this point
Release: v0.4.6
younesbelkada
committed
e1531aa
View commit details
Copy full SHA for e1531aa
Browse repository at this point
Previous
Next
You can’t perform that action at this time.