Actions: huggingface/trl
Actions
735 workflow runs
735 workflow runs
max_length
from RewardDataCollatorWithPadding
(#2119)
Build documentation
#850:
Commit fb1b48f
pushed
by
qgallouedec
BCOTrainer
conversational dataset support (#2107)
Build documentation
#847:
Commit 44a06fc
pushed
by
qgallouedec
0.11.0
-> 0.11.1
Build documentation
#846:
Commit 86ad7a7
pushed
by
qgallouedec
RewardTrainer
] Tokenize inputs within trainer (#2102)
Build documentation
#841:
Commit cc23b51
pushed
by
qgallouedec
trl env
for printing system info (#2104)
Build documentation
#840:
Commit 2cad48d
pushed
by
qgallouedec
training_args
for all TrainingArguments
(#2082)
Build documentation
#833:
Commit 10c2f63
pushed
by
qgallouedec
PPOv2Trainer.save
(#2080)
Build documentation
#829:
Commit cc80ac6
pushed
by
lewtun
PPOv2Trainer.save
(#2080)
Build documentation
#828:
Commit cc80ac6
pushed
by
qgallouedec