Actions: huggingface/trl
Actions
1,013 workflow runs
1,013 workflow runs
grpo_trainer.py): Variational Sequence-Level Soft Policy Optim…
Build TRL Docker image
#1380:
Commit 406d406
pushed
by
qgallouedec
vllm_mode to "colocate" and add v0→v1 migration gu…
Build TRL Docker image
#1378:
Commit c0eabc4
pushed
by
qgallouedec
bfd-requeue to bfd_split (#5189)
Build TRL Docker image
#1377:
Commit 6c0fccd
pushed
by
qgallouedec
_generate_single_turn (#5…
Build TRL Docker image
#1365:
Commit a65c830
pushed
by
qgallouedec