Skip to content

Actions: huggingface/trl

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
752 workflow runs
752 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Update dpo_trainer.py (#941)
Build documentation #358: Commit a64a522 pushed by younesbelkada
November 2, 2023 10:27 5m 47s main
November 2, 2023 10:27 5m 47s
Optionally logging reference response (#847)
Build documentation #357: Commit 5b32372 pushed by vwxyzjn
October 31, 2023 21:55 5m 23s main
October 31, 2023 21:55 5m 23s
Fix stale bot (#935)
Build documentation #356: Commit d759004 pushed by lvwerra
October 31, 2023 19:10 5m 58s main
October 31, 2023 19:10 5m 58s
[core / DDP] Fix RM trainer + DDP + quantization + propagate `gra…
Build documentation #355: Commit cbc6c9b pushed by younesbelkada
October 31, 2023 17:50 5m 18s main
October 31, 2023 17:50 5m 18s
Update dpo_llama2.py (#934)
Build documentation #354: Commit f3cd865 pushed by lvwerra
October 31, 2023 17:20 4m 52s main
October 31, 2023 17:20 4m 52s
[SFTTrainer] Make sure to not conflict between transformers and T…
Build documentation #353: Commit b763432 pushed by younesbelkada
October 31, 2023 15:04 5m 52s main
October 31, 2023 15:04 5m 52s
hotfix for dpo trainer (#919)
Build documentation #352: Commit 2bbd594 pushed by lvwerra
October 31, 2023 09:58 4m 32s main
October 31, 2023 09:58 4m 32s
fix DPO + GC issues (#927)
Build documentation #351: Commit b89b712 pushed by younesbelkada
October 31, 2023 09:55 4m 29s main
October 31, 2023 09:55 4m 29s
[Feature] Enable Intel XPU support (#839)
Build documentation #350: Commit ec9e766 pushed by lvwerra
October 31, 2023 09:15 4m 44s main
October 31, 2023 09:15 4m 44s
Bump tyro (#928)
Build documentation #349: Commit d192244 pushed by vwxyzjn
October 31, 2023 00:48 5m 46s main
October 31, 2023 00:48 5m 46s
updating PPOTrainer docstring (#897)
Build documentation #348: Commit 051d5a1 pushed by vwxyzjn
October 30, 2023 17:22 4m 59s main
October 30, 2023 17:22 4m 59s
Generalize NEFTune for FSDP, DDP, ... (#924)
Build documentation #347: Commit 2068fdc pushed by younesbelkada
October 30, 2023 10:17 5m 48s main
October 30, 2023 10:17 5m 48s
fix stackllama2 sft gradient checkpointing (#906)
Build documentation #346: Commit 02f5c1d pushed by vwxyzjn
October 25, 2023 13:58 5m 39s main
October 25, 2023 13:58 5m 39s
deactivate MacOS CI (#913)
Build documentation #345: Commit 7de7db6 pushed by younesbelkada
October 24, 2023 14:06 4m 48s main
October 24, 2023 14:06 4m 48s
[Update reward_trainer.py] append PeftSavingCallback if callbacks is …
Build documentation #344: Commit 4e7d5b5 pushed by younesbelkada
October 24, 2023 12:32 5m 52s main
October 24, 2023 12:32 5m 52s
Fix broken link/markdown (#903)
Build documentation #343: Commit a90e133 pushed by lvwerra
October 24, 2023 12:27 4m 47s main
October 24, 2023 12:27 4m 47s
[NEFTune] Make use of forward hooks instead (#889)
Build documentation #342: Commit 5b2aeca pushed by younesbelkada
October 24, 2023 12:18 4m 44s main
October 24, 2023 12:18 4m 44s
Add whiten ops before compute advatanges (#887)
Build documentation #341: Commit 1f3314f pushed by vwxyzjn
October 23, 2023 15:32 4m 52s main
October 23, 2023 15:32 4m 52s
Fix couple broken links on lib homepage (#908)
Build documentation #340: Commit 304ee70 pushed by younesbelkada
October 23, 2023 09:46 4m 43s main
October 23, 2023 09:46 4m 43s
[reward_modeling] Cleaning example script (#882)
Build documentation #339: Commit 0a5aee7 pushed by younesbelkada
October 19, 2023 14:00 4m 43s main
October 19, 2023 14:00 4m 43s
fix: remove useless token (#896)
Build documentation #338: Commit db592a2 pushed by rtrompier
October 19, 2023 12:28 4m 39s main
October 19, 2023 12:28 4m 39s
fix peft_config type (#883)
Build documentation #337: Commit 122edc8 pushed by younesbelkada
October 18, 2023 21:45 4m 39s main
October 18, 2023 21:45 4m 39s
remove duplicate key in reward_modeling.py (#890)
Build documentation #336: Commit f91fb2b pushed by younesbelkada
October 18, 2023 21:45 4m 43s main
October 18, 2023 21:45 4m 43s
[DPO] add SLiC hinge loss to DPOTrainer (#866)
Build documentation #335: Commit 14b6bc6 pushed by lvwerra
October 16, 2023 14:03 4m 42s main
October 16, 2023 14:03 4m 42s
set dev version (#864)
Build documentation #334: Commit eb4d2f3 pushed by younesbelkada
October 12, 2023 13:51 4m 55s main
October 12, 2023 13:51 4m 55s
ProTip! You can narrow down the results and go further in time using created:<2023-10-12 or the other filters available.