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 }}
qlycool
/
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
Breadcrumbs
History for
trl
tests
on
main
User selector
All users
All time
Commit history
Commits on Sep 15, 2025
🗑️ Remove deprecated `AlignPropTrainer`, `DDPOTrainer` and `IterativeSFTTrainer` (#4068)
qgallouedec
authored
78f1a92
View commit details
Copy full SHA for 78f1a92
View code at this point
Browse repository at this point
Commits on Sep 13, 2025
🛠️ Fix CI (#4076)
qgallouedec
authored
304eaf8
View commit details
Copy full SHA for 304eaf8
View code at this point
Browse repository at this point
✂️ [GRPO VLM] Update split sizes to generalize (#4032)
Show description for 69e288e
zucchini-nlp
and
qgallouedec
authored
69e288e
View commit details
Copy full SHA for 69e288e
View code at this point
Browse repository at this point
Commits on Sep 12, 2025
♨️ [GRPO] Fix potential hang in `get_high_entropy_mask` (#4041)
akakakakakaa
authored
f4ff248
View commit details
Copy full SHA for f4ff248
View code at this point
Browse repository at this point
Commits on Sep 11, 2025
Remove redundant 'None' from docstrings (#4058)
albertvillanova
authored
e8b8499
View commit details
Copy full SHA for e8b8499
View code at this point
Browse repository at this point
Commits on Sep 9, 2025
🧨 DFT (#4042)
qgallouedec
authored
659d2c1
View commit details
Copy full SHA for 659d2c1
View code at this point
Browse repository at this point
CI hotfix: xfail test_training_with_transformers_paged (#4046)
albertvillanova
authored
27e30f8
View commit details
Copy full SHA for 27e30f8
View code at this point
Browse repository at this point
Commits on Sep 5, 2025
⚖️ Add vLLM server mode and VLM support to OnlineDPOTrainer (#3783)
Show description for d1bf560
4 people
authored
d1bf560
View commit details
Copy full SHA for d1bf560
View code at this point
Browse repository at this point
Commits on Sep 4, 2025
[SFTTrainer]: Add Aux Loss for MoE models. (#4012)
Show description for 1eb3801
pramodith
and
qgallouedec
authored
1eb3801
View commit details
Copy full SHA for 1eb3801
View code at this point
Browse repository at this point
🌵 Refactor entropy_from_logits for memory efficiency (#4013)
qgallouedec
authored
deae7e0
View commit details
Copy full SHA for deae7e0
View code at this point
Browse repository at this point
Commits on Sep 3, 2025
📏 `torch_dype` to `dtype` everywhere (#4000)
Show description for 208e9f7
sergiopaniego
and
qgallouedec
authored
208e9f7
View commit details
Copy full SHA for 208e9f7
View code at this point
Browse repository at this point
✖️ Support pad-to-multiple-of and padding-free (#3996)
qgallouedec
authored
18633db
View commit details
Copy full SHA for 18633db
View code at this point
Browse repository at this point
[GRPO] Truncated Importance Sampling to address rollout-training mismatch (#3867)
Show description for 12fc85f
LeonEricsson
and
qgallouedec
authored
12fc85f
View commit details
Copy full SHA for 12fc85f
View code at this point
Browse repository at this point
⏰ fix: add return to shift_tokens_right (#3987)
ginkyenglee
authored
cb84da0
View commit details
Copy full SHA for cb84da0
View code at this point
Browse repository at this point
Commits on Aug 29, 2025
🔥 [Refactor] RLOOTrainer (#3801)
Show description for e7b37d4
3 people
authored
e7b37d4
View commit details
Copy full SHA for e7b37d4
View code at this point
Browse repository at this point
Commits on Aug 27, 2025
[CI] Modify tests to handle device allocation for models (#3962)
kashif
authored
515e9eb
View commit details
Copy full SHA for 515e9eb
View code at this point
Browse repository at this point
Commits on Aug 25, 2025
🤸 [SFT] Drop entropy calculation when using liger (#3947)
qgallouedec
authored
38fc1f6
View commit details
Copy full SHA for 38fc1f6
View code at this point
Browse repository at this point
Commits on Aug 24, 2025
[GKD] add liger loss (#3946)
Show description for 39cc9a8
kashif
and
qgallouedec
authored
39cc9a8
View commit details
Copy full SHA for 39cc9a8
View code at this point
Browse repository at this point
[DPO] Adding support for different losses which are now supported by Liger (#3815)
Show description for 1f15f18
3 people
authored
1f15f18
View commit details
Copy full SHA for 1f15f18
View code at this point
Browse repository at this point
Commits on Aug 22, 2025
🏌️ DAPO loss type (#3938)
qgallouedec
authored
2324245
View commit details
Copy full SHA for 2324245
View code at this point
Browse repository at this point
Commits on Aug 21, 2025
🪶 [GRPO] PPO Lite: Scale rewards by Std of Batch (#3935)
Show description for fe44806
pramodith
and
qgallouedec
authored
fe44806
View commit details
Copy full SHA for fe44806
View code at this point
Browse repository at this point
🗞 bugfix 'TrainerState' object is not subscriptable (#3936)
Show description for e2eaa23
ErezYosef
and
qgallouedec
authored
e2eaa23
View commit details
Copy full SHA for e2eaa23
View code at this point
Browse repository at this point
Commits on Aug 20, 2025
🗑️ Deprecate `setup_chat_format` (#3929)
qgallouedec
authored
48d7ecc
View commit details
Copy full SHA for 48d7ecc
View code at this point
Browse repository at this point
♻️ Reuse multimodal message preparation from `SFTTrainer` in `GRPOTrainer` (#3919)
Show description for 85ead75
MengAiDev
and
qgallouedec
authored
85ead75
View commit details
Copy full SHA for 85ead75
View code at this point
Browse repository at this point
🧾 Use `logger.warning` instead of `warnings.warn` (#3923)
Show description for 8793a46
qgallouedec
and
kashif
authored
8793a46
View commit details
Copy full SHA for 8793a46
View code at this point
Browse repository at this point
🧹 Clean SFT tests (#3922)
qgallouedec
authored
7233b98
View commit details
Copy full SHA for 7233b98
View code at this point
Browse repository at this point
Commits on Aug 19, 2025
✏️ Fix typos (#3921)
Show description for 18836f0
cyyever
and
qgallouedec
authored
18836f0
View commit details
Copy full SHA for 18836f0
View code at this point
Browse repository at this point
Commits on Aug 18, 2025
🌓 SFTTrainer for VLM: Support for prompt-completion data (#3907)
qgallouedec
authored
0227d68
View commit details
Copy full SHA for 0227d68
View code at this point
Browse repository at this point
♻️ `use_cache` should be set in the forward pass (#3891)
qgallouedec
authored
b08bc7f
View commit details
Copy full SHA for b08bc7f
View code at this point
Browse repository at this point
Commits on Aug 17, 2025
🗳️ Extend BCO Trainer dataset format support (#3134)
reihig-ut
authored
d15049b
View commit details
Copy full SHA for d15049b
View code at this point
Browse repository at this point
🗿 [CPO] Add AlphaPO method via CPOTrainer (#3824)
Show description for b971844
kashif
and
qgallouedec
authored
b971844
View commit details
Copy full SHA for b971844
View code at this point
Browse repository at this point
🌳 Enhance segment tree implementation for non-power-of-2 values (#3888)
Show description for c99cd23
3 people
authored
c99cd23
View commit details
Copy full SHA for c99cd23
View code at this point
Browse repository at this point
Add tests for get_position_ids_from_packed_seq_lengths (#3883)
pramodith
authored
6893796
View commit details
Copy full SHA for 6893796
View code at this point
Browse repository at this point
Commits on Aug 15, 2025
✏️ Fix SFTTrainer token accuracy computation with PromptEncoder (#3821)
zk-quantum
authored
485e7d1
View commit details
Copy full SHA for 485e7d1
View code at this point
Browse repository at this point
👔 HF Doc Builder style (#3498)
qgallouedec
authored
7ee8f79
View commit details
Copy full SHA for 7ee8f79
View code at this point
Browse repository at this point
Previous
Next
You can’t perform that action at this time.