Skip to content

Activity

Deleted branch

lkevinzcdeleted refactor • 
8 days ago

Deleted branch

lkevinzcdeleted lkevinzc-patch-1 • 
8 days ago

chore: update deepspeed.py (#30)

Pull request merge
lkevinzcpushed 1 commit to main • fa662b1…4540740 • 
9 days ago

Update README.md (#29)

Pull request merge
lkevinzcpushed 1 commit to main • 56b9b57…fa662b1 • 
11 days ago

Update README.md

lkevinzccreated lkevinzc-patch-1 • 2f331cf • 
11 days ago

Deleted branch

lkevinzcdeleted r1-like • 
15 days ago

Use a toy task to test R1-zero like training behaviors (#28)

Pull request merge
lkevinzcpushed 1 commit to main • d000304…56b9b57 • 
15 days ago

minor

lkevinzcpushed 1 commit to r1-like • 5da02fa…0613e78 • 
15 days ago

update

lkevinzcpushed 1 commit to r1-like • ac8d518…5da02fa • 
15 days ago

use count down to test r1-zero like training behavior

lkevinzccreated r1-like • ac8d518 • 
15 days ago

Deleted branch

lkevinzcdeleted fix • 
18 days ago

minor fix for offline sft (#27)

Pull request merge
lkevinzcpushed 1 commit to main • f778278…d000304 • 
18 days ago

minor fix for offline sft

lkevinzccreated fix • 247ea83 • 
18 days ago

Deleted branch

lkevinzcdeleted grpo • 
21 days ago

add grpo (#26)

Pull request merge
lkevinzcpushed 1 commit to main • b966394…f778278 • 
21 days ago

add grpo

lkevinzccreated grpo • e95a37c • 
21 days ago

Refactor and add PPO for math reasoning (#25)

Pull request merge
lkevinzcpushed 1 commit to main • 37becae…b966394 • 
21 days ago

minor

lkevinzcpushed 1 commit to refactor • 82b1fbd…fc043b5 • 
21 days ago

fix images

lkevinzcpushed 1 commit to refactor • e852eec…82b1fbd • 
21 days ago

minor

lkevinzcpushed 1 commit to refactor • 3baab9d…e852eec • 
21 days ago

minor

lkevinzcpushed 1 commit to refactor • 72145c8…3baab9d • 
21 days ago

update logo

lkevinzcpushed 1 commit to refactor • e09b47c…72145c8 • 
21 days ago

bump version

lkevinzcpushed 1 commit to refactor • c470ccb…e09b47c • 
21 days ago

update docs

lkevinzccreated refactor • c470ccb • 
21 days ago

Deleted branch

lkevinzcdeleted ae2 • 
on Dec 22, 2024

Deleted branch

lkevinzcdeleted len-norm • 
on Dec 21, 2024

implement length-regularized DPO (#24)

Pull request merge
lkevinzcpushed 1 commit to main • ed7d3b1…37becae • 
on Dec 21, 2024

implement length-regularized DPO

lkevinzccreated len-norm • cf22844 • 
on Dec 21, 2024

Deleted branch

lkevinzcdeleted update-v • 
on Dec 17, 2024

bump version (#23)

Pull request merge
lkevinzcpushed 1 commit to main • c638ce4…ed7d3b1 • 
on Dec 17, 2024