Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Oct 24, 2024

• add exps on TWCC

  ariapoy

  committed
  91cd090View commit details

  Copy full SHA for 91cd090

  Browse repository at this point

• Finetune Diffusion models with PickScore by DDPO

  ariapoy

  committed
  e1aa842View commit details

  Copy full SHA for e1aa842

  Browse repository at this point

Commits on Oct 22, 2024

• 🚩 `setup_chat_format`: throw error if there is already a template in base model (#2252)

  Show description for 88be2c0
  

  ngxson

  and

  kashif

  authored
  88be2c0View commit details

  Copy full SHA for 88be2c0

  Browse repository at this point

• Adjust padding in batch generation (#2251)

  Show description for f2349d2
  

  gaetanlop

  and

  kashif

  authored
  f2349d2View commit details

  Copy full SHA for f2349d2

  Browse repository at this point

• Use `processing_class` instead of `tokenizer` in `LogCompletionsCallback` (#2261)

  qgallouedec

  authored
  d843b3dView commit details

  Copy full SHA for d843b3d

  Browse repository at this point

Commits on Oct 21, 2024

• 🧽 Fix typo in dataset format doc (#2259)

  Show description for 84dab85
  cameronphchen

  authored
  84dab85View commit details

  Copy full SHA for 84dab85

  Browse repository at this point

• 🏗️ Refactor DPO data processing (#2209)

  Show description for 92f6d24
  

  qgallouedec

  and

  lewtun

  authored
  92f6d24View commit details

  Copy full SHA for 92f6d24

  Browse repository at this point

Commits on Oct 18, 2024

• 🔀 Rename `get_batch_sample` and add `num_items_in_batch` to `compute_loss` (#2246)

  qgallouedec

  authored
  31b7820View commit details

  Copy full SHA for 31b7820

  Browse repository at this point

• ✨ Enhance log report script: add error handling and logging (#2232)

  Show description for b9aa965
  

  DhruvKadam-git

  and

  qgallouedec

  authored
  b9aa965View commit details

  Copy full SHA for b9aa965

  Browse repository at this point

Commits on Oct 17, 2024

• Update SFT examples (#2244)

  lewtun

  authored
  a67f214View commit details

  Copy full SHA for a67f214

  Browse repository at this point

• [CLI] Setting capture output to `False` (#2239)

  Show description for 494b4af
  

  August-murr

  and

  qgallouedec

  authored
  494b4afView commit details

  Copy full SHA for 494b4af

  Browse repository at this point

Commits on Oct 16, 2024

• DPO support `remove_unused_columns` (#2233)

  qgallouedec

  authored
  02f4e75View commit details

  Copy full SHA for 02f4e75

  Browse repository at this point

Commits on Oct 15, 2024

• Updated ScriptArguments warning messages (#2230)

  sergiopaniego

  authored
  2ba3005View commit details

  Copy full SHA for 2ba3005

  Browse repository at this point

Commits on Oct 14, 2024

• 🎭 Deprecate `[SFT/DPO/Reward]ScriptArguments` in favour of `ScriptArguments` (#2145)

  Show description for 7e394b0
  qgallouedec

  authored
  7e394b0View commit details

  Copy full SHA for 7e394b0

  Browse repository at this point

Commits on Oct 13, 2024

• ✨ Update commands for code linting in contributing guidelines (#2225)

  Show description for 14f3613
  

  Ben-Schneider-code

  and

  qgallouedec

  authored
  14f3613View commit details

  Copy full SHA for 14f3613

  Browse repository at this point

Commits on Oct 11, 2024

• 📒 Fix type/format confusions (#2223)

  qgallouedec

  authored
  5e24101View commit details

  Copy full SHA for 5e24101

  Browse repository at this point

• Add GKD to dataset_formats.mdx (#2222)

  Show description for b81a612
  

  August-murr

  and

  qgallouedec

  authored
  b81a612View commit details

  Copy full SHA for b81a612

  Browse repository at this point

• Add Sequence-Level KD (#2220)

  Show description for 7f0d246
  

  3 peopleauthored
  7f0d246View commit details

  Copy full SHA for 7f0d246

  Browse repository at this point

• 🕊️ Migration `PPOv2` -> `PPO` (#2174)

  Show description for 70036bf
  

  3 peopleauthored
  70036bfView commit details

  Copy full SHA for 70036bf

  Browse repository at this point

• Conversational dataset support for `ORPOTrainer` (#2184)

  Show description for d0aa421
  qgallouedec

  authored
  d0aa421View commit details

  Copy full SHA for d0aa421

  Browse repository at this point

• `trl env` report all cuda devices (#2216)

  qgallouedec

  authored
  5375d71View commit details

  Copy full SHA for 5375d71

  Browse repository at this point

• Updated README.md with CLI examples and additional usage instructions (#2199)

  Show description for 6004e03
  

  4 peopleauthored
  6004e03View commit details

  Copy full SHA for 6004e03

  Browse repository at this point

• Update README.md (#2180)

  Show description for f436c3e
  

  4 peopleauthored
  f436c3eView commit details

  Copy full SHA for f436c3e

  Browse repository at this point

• [Judges] Soft judges for PairRM (#2221)

  Show description for cd1aa6b
  kashif

  authored
  cd1aa6bView commit details

  Copy full SHA for cd1aa6b

  Browse repository at this point

Commits on Oct 10, 2024

• Report to `"none"` in GKD test (#2214)

  qgallouedec

  authored
  b3f93f0View commit details

  Copy full SHA for b3f93f0

  Browse repository at this point

• ✨ Improve slack reporting (#2182)

  Show description for 6c32c8b
  

  DhruvKadam-git

  and

  qgallouedec

  authored
  6c32c8bView commit details

  Copy full SHA for 6c32c8b

  Browse repository at this point

• Update incorrect data processing in DataCollatorForChatML (#2172)

  Show description for 3107a40
  

  4 peopleauthored
  3107a40View commit details

  Copy full SHA for 3107a40

  Browse repository at this point

• Drop `decoder_input_ids` in `DPOTrainer` (#2208)

  qgallouedec

  authored
  4197916View commit details

  Copy full SHA for 4197916

  Browse repository at this point

Commits on Oct 9, 2024

• [GKD] interpolate in prob. space (#2204)

  Show description for 7e5924d
  kashif

  authored
  7e5924dView commit details

  Copy full SHA for 7e5924d

  Browse repository at this point

Commits on Oct 8, 2024

• [DPO] Adding weighted preference optimization (WPO) (#2141)

  Show description for ed9ea74
  

  gaetanlop

  and

  kashif

  authored
  ed9ea74View commit details

  Copy full SHA for ed9ea74

  Browse repository at this point

• Get the `aux_loss_coef` at `BCOTrainer`, `CPOTrainer`, `KTOTrainer`, and `ORPOTrainer` initialization (#2201)

  Show description for 511c92c
  muupan

  authored
  511c92cView commit details

  Copy full SHA for 511c92c

  Browse repository at this point

• Get the `aux_loss_coef` at `DPOTrainer` initialization (#2200)

  muupan

  authored
  c6cb635View commit details

  Copy full SHA for c6cb635

  Browse repository at this point

• ♾️ [CI] Use transformers from source in "tests_no_optional_dep" (#2198)

  qgallouedec

  authored
  adb3e05View commit details

  Copy full SHA for adb3e05

  Browse repository at this point

Commits on Oct 7, 2024

• `skip_prompt=True` in `TextIteratorStreamer` (#2193)

  Show description for adf58d8
  

  qgallouedec

  and

  kashif

  authored
  adf58d8View commit details

  Copy full SHA for adf58d8

  Browse repository at this point

• Update README.md (#2186)

  Show description for 9aa0225
  

  3 peopleauthored
  9aa0225View commit details

  Copy full SHA for 9aa0225

  Browse repository at this point