Skip to content

Actions: huggingface/trl

Build documentation

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
723 workflow runs
723 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[GKD] interpolate in prob. space (#2204)
Build documentation #895: Commit 1661bc2 pushed by qgallouedec
October 10, 2024 12:41 3m 27s v0.11-release
October 10, 2024 12:41 3m 27s
Version 0.11.2 -> 0.11.3
Build documentation #894: Commit fdbcaae pushed by qgallouedec
October 10, 2024 12:30 3m 31s v0.11-release
October 10, 2024 12:30 3m 31s
Update incorrect data processing in DataCollatorForChatML (#2172)
Build documentation #893: Commit 22567cd pushed by qgallouedec
October 10, 2024 12:28 3m 33s v0.11-release
October 10, 2024 12:28 3m 33s
Update incorrect data processing in DataCollatorForChatML (#2172)
Build documentation #892: Commit 3107a40 pushed by kashif
October 10, 2024 10:49 3m 5s main
October 10, 2024 10:49 3m 5s
Drop decoder_input_ids in DPOTrainer (#2208)
Build documentation #891: Commit 4197916 pushed by qgallouedec
October 10, 2024 08:20 3m 7s main
October 10, 2024 08:20 3m 7s
[GKD] interpolate in prob. space (#2204)
Build documentation #890: Commit 7e5924d pushed by kashif
October 9, 2024 10:13 3m 16s main
October 9, 2024 10:13 3m 16s
[DPO] Adding weighted preference optimization (WPO) (#2141)
Build documentation #889: Commit ed9ea74 pushed by kashif
October 8, 2024 17:52 3m 55s main
October 8, 2024 17:52 3m 55s
Get the aux_loss_coef at BCOTrainer, CPOTrainer, KTOTrainer
Build documentation #888: Commit 511c92c pushed by qgallouedec
October 8, 2024 14:17 4m 8s main
October 8, 2024 14:17 4m 8s
Get the aux_loss_coef at DPOTrainer initialization (#2200)
Build documentation #887: Commit c6cb635 pushed by qgallouedec
October 8, 2024 14:06 4m 2s main
October 8, 2024 14:06 4m 2s
♾️ [CI] Use transformers from source in "tests_no_optional_dep" (#2198)
Build documentation #886: Commit adb3e05 pushed by qgallouedec
October 8, 2024 10:19 3m 8s main
October 8, 2024 10:19 3m 8s
Version 0.11.1 -> 0.11.2
Build documentation #885: Commit 01142bb pushed by qgallouedec
October 7, 2024 15:59 3m 49s v0.11-release
October 7, 2024 15:59 3m 49s
Fix RLOO checkpointing (#2114)
Build documentation #884: Commit d3fb486 pushed by qgallouedec
October 7, 2024 15:57 3m 54s v0.11-release
October 7, 2024 15:57 3m 54s
skip_prompt=True in TextIteratorStreamer (#2193)
Build documentation #883: Commit adf58d8 pushed by qgallouedec
October 7, 2024 15:38 3m 23s main
October 7, 2024 15:38 3m 23s
Update README.md (#2186)
Build documentation #882: Commit 9aa0225 pushed by qgallouedec
October 7, 2024 12:30 3m 11s main
October 7, 2024 12:30 3m 11s
Fix RLOO checkpointing (#2114)
Build documentation #881: Commit 82ad390 pushed by qgallouedec
October 7, 2024 11:11 3m 2s main
October 7, 2024 11:11 3m 2s
Update CONTRIBUTING.md (#2181)
Build documentation #880: Commit ac038ef pushed by lewtun
October 7, 2024 10:56 2m 58s main
October 7, 2024 10:56 2m 58s
[CI] fix dpo gpu ci tests (#2189)
Build documentation #879: Commit 51ca76b pushed by kashif
October 7, 2024 08:59 2m 56s main
October 7, 2024 08:59 2m 56s
🃏 Model card: "unsloth" tag (#2173)
Build documentation #878: Commit 7005ab4 pushed by qgallouedec
October 7, 2024 08:57 3m 1s main
October 7, 2024 08:57 3m 1s
Update documentation CLI Chat (#2191)
Build documentation #877: Commit ffb1ab7 pushed by qgallouedec
October 7, 2024 08:33 3m 23s main
October 7, 2024 08:33 3m 23s
Rename trainer arg tokenizer to processing_class (#2162)
Build documentation #876: Commit 47d08a9 pushed by qgallouedec
October 7, 2024 07:39 2m 58s main
October 7, 2024 07:39 2m 58s
add trl to tag for models (#2178)
Build documentation #875: Commit 70327c1 pushed by qgallouedec
October 7, 2024 06:12 4m 20s main
October 7, 2024 06:12 4m 20s
minor KTO setting changes + KL batch size (#2153)
Build documentation #874: Commit f05c3fa pushed by kashif
October 6, 2024 11:13 2m 55s main
October 6, 2024 11:13 2m 55s
Capybara replaced with ultrafeedback_binarized (#2183)
Build documentation #873: Commit 4799ba4 pushed by qgallouedec
October 5, 2024 16:49 3m 2s main
October 5, 2024 16:49 3m 2s
Conversational dataset support for CPOTrainer (#2144)
Build documentation #872: Commit d45c86e pushed by qgallouedec
October 4, 2024 16:01 3m 17s main
October 4, 2024 16:01 3m 17s
🗑️ Set deprecation version for DPO and SFT arguments to version 0.13 …
Build documentation #871: Commit c6b0d13 pushed by qgallouedec
October 4, 2024 15:46 3m 4s main
October 4, 2024 15:46 3m 4s