Actions: huggingface/trl
Actions
445 workflow runs
445 workflow runs
PreferenceCollator
to ` DataCollatorForPreference…
Slow tests (on push)
#444:
Commit 99451b4
pushed
by
qgallouedec
disable_dropout
(#2511)
Slow tests (on push)
#443:
Commit 5239b94
pushed
by
qgallouedec
model_args
(#2442)
Slow tests (on push)
#433:
Commit 460e780
pushed
by
qgallouedec
ref_model
in OnlineDPOTrainer
(#2417)
Slow tests (on push)
#432:
Commit 7ba118a
pushed
by
qgallouedec
max_steps
calculation in RLOOTrainer
(#2433)
Slow tests (on push)
#430:
Commit 52201d3
pushed
by
qgallouedec
DPOTrainer
(#2413)
Slow tests (on push)
#426:
Commit 8d9cfaa
pushed
by
qgallouedec
AutoModelForCausalLMWithValueHead
(#2398)
Slow tests (on push)
#425:
Commit 94e4135
pushed
by
qgallouedec
SmolVLM
models via standalone script `sft_…
Slow tests (on push)
#424:
Commit e1d7813
pushed
by
qgallouedec