Actions: huggingface/trl
Actions
6,456 workflow runs
6,456 workflow runs
grpo_trainer.py): Variational Sequence-Level Soft Policy Optimization (VESPO)
Build PR Documentation
#14501:
Pull request #5199
synchronize
by
qgallouedec
grpo_trainer.py): Variational Sequence-Level Soft Policy Optimization (VESPO)
Build PR Documentation
#14500:
Pull request #5199
synchronize
by
qgallouedec
vllm_mode to "colocate" and add v0→v1 migration guide
Build PR Documentation
#14492:
Pull request #5255
synchronize
by
qgallouedec
vllm_mode to "colocate" and add v0→v1 migration guide
Build PR Documentation
#14491:
Pull request #5255
synchronize
by
qgallouedec
AGENTS.md
Build PR Documentation
#14490:
Pull request #5280
synchronize
by
qgallouedec
bfd-requeue to bfd_split
Build PR Documentation
#14488:
Pull request #5189
synchronize
by
qgallouedec
bfd-requeue to bfd_split
Build PR Documentation
#14486:
Pull request #5189
synchronize
by
qgallouedec
bfd-requeue to bfd_split
Build PR Documentation
#14483:
Pull request #5189
synchronize
by
qgallouedec
bfd-requeue to bfd_split
Build PR Documentation
#14482:
Pull request #5189
synchronize
by
mariosasko
.ai
Build PR Documentation
#14481:
Pull request #5268
synchronize
by
qgallouedec
.ai
Build PR Documentation
#14480:
Pull request #5268
synchronize
by
qgallouedec
environment_factory
Build PR Documentation
#14477:
Pull request #5235
synchronize
by
sergiopaniego
environment_factory
Build PR Documentation
#14476:
Pull request #5235
synchronize
by
sergiopaniego
environment_factory
Build PR Documentation
#14475:
Pull request #5235
synchronize
by
sergiopaniego
environment_factory
Build PR Documentation
#14474:
Pull request #5235
synchronize
by
sergiopaniego