Actions: huggingface/trl
Actions
513 workflow runs
513 workflow runs
_generate
in GRPO/RLOO: list of ints instead of te…
Build TRL Docker image
#694:
Commit ea66a9e
pushed
by
qgallouedec
RewardTrainer
refactor (#4093)
Build TRL Docker image
#693:
Commit da209f8
pushed
by
qgallouedec
clone_chat_template
(#…
Build TRL Docker image
#691:
Commit 70e2017
pushed
by
qgallouedec
require_bitsandbytes
(#4137)
Build TRL Docker image
#690:
Commit 4368f54
pushed
by
qgallouedec
<Tip>
with new markdown syntax (#4161)
Build TRL Docker image
#679:
Commit 8a5bfec
pushed
by
qgallouedec
_generate
for GRPO with replay buff…
Build TRL Docker image
#676:
Commit f397a61
pushed
by
qgallouedec
image_split_sizes
in favour of image_grid_thw
(#4156)
Build TRL Docker image
#674:
Commit 79c774a
pushed
by
qgallouedec
_generate
(#4114)
Build TRL Docker image
#673:
Commit 9603b41
pushed
by
qgallouedec