8000 Tags · sail-sg/oat · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Tags: sail-sg/oat

Tags

v0.1.2

Toggle v0.1.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
feat: fix deps, refactor apis, allow resume training (#39)

* fix deps, refactor apis

* bump version

* updates

* actor identity

* fix ref offload

* training resume

* bump version

v0.1.0

Toggle v0.1.0's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Upgrade to vllm V1 (0.8.4) and use actor api init() (#38)

* updates

* bump version

v0.0.9

Toggle v0.0.9's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Upgrade vllm for more efficient collocation (#34)

* upgrade vllm & adopt collective_rpc

* use .float() for kl & increase timeout to 60m

* speed up minibatch training

* add constant lr scheduler

* update

* updates

* fix non_eos detection

* changes

* minor

* update

* ratio

* updates

v0.0.6

Toggle v0.0.6's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Refactor and add PPO for math reasoning (#25)

* huge refactor to make structure clearer and more extendable

* sync

* fix

* update docs

* bump version

* update logo

* minor

* minor

* fix images

* minor

v0.0.5

Toggle v0.0.5's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
bump version (#23)

v0.0.4

Toggle v0.0.4's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
dump (#12)

v0.0.3

Toggle v0.0.3's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
Fix APL due to vllm upgrade; update package v0.0.3 (#7)

* typo

* fix apl

* minor

* dump version

v0.0.2

Toggle v0.0.2's commit message

Verified

This commit was created on GitHub.com and signed with GitHub’s verified signature.
dump version (#5)

0