SIGN IN SIGN UP
unslothai / unsloth UNCLAIMED

Unsloth Studio is a web UI for training and running open models like Qwen, DeepSeek, gpt-oss and Gemma locally.

0 0 99 Python

[RL] make sync weights conditional (#4925)

* make sync weights conditional

* Also conditionalise vllm creation

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* guard sync for weight sharing

* Guard self.llm access in VLLMGeneration sync_weights and generate patches for PR #4925

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Daniel Han <danielhanchen@gmail.com>
D
Datta Nimmaturi committed
88391182689754c251c1013973657a3b2bbc73db
Parent: 131fa4f
Committed by GitHub <noreply@github.com> on 5/27/2026, 12:53:26 PM