Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Jan 14, 2026

• bump the versions of some packages to those I actually run

  

  M I

  committed
  441b88dView commit details

  Copy full SHA for 441b88d

  Browse repository at this point

• GRPO Trainer: accommodations for reward logging for eval as well as abiulity to not compute eval losses.

  

  M I

  committed
  67582f2View commit details

  Copy full SHA for 67582f2

  Browse repository at this point

Commits on Oct 23, 2025

• factor out the logps and importance calcualtions from _generate_and_score to _compute_importances

  

  M I

  committed
  be1ea63View commit details

  Copy full SHA for be1ea63

  Browse repository at this point

Commits on Oct 22, 2025

• Merge remote-tracking branch 'upstream/v0.24-release'

  

  M I

  committed
  1f7209bView commit details

  Copy full SHA for 1f7209b

  Browse repository at this point

• fix a typo

  

  M I

  committed
  ef32cb1View commit details

  Copy full SHA for ef32cb1

  Browse repository at this point

Commits on Oct 16, 2025

• Release: v0.24 (#4292)

  qgallouedec

  authored
  04fd120View commit details

  Copy full SHA for 04fd120

  Browse repository at this point

• Deprecate `BestOfNSampler` (#4291)

  Show description for 19d2f97
  

  qgallouedec

  and

  behroozazarkhalili

  authored
  19d2f97View commit details

  Copy full SHA for 19d2f97

  Browse repository at this point

• Remove unused commands directory (#4258)

  Show description for 31caf64
  behroozazarkhalili

  authored
  31caf64View commit details

  Copy full SHA for 31caf64

  Browse repository at this point

• Add accuracy reward (#4270)

  Show description for 8e2d551
  

  pramodith

  and

  qgallouedec

  authored
  8e2d551View commit details

  Copy full SHA for 8e2d551

  Browse repository at this point

Commits on Oct 15, 2025

• Remove how_to_train.md: outdated training FAQ (#4267)

  Show description for 94aac4a
  behroozazarkhalili

  authored
  94aac4aView commit details

  Copy full SHA for 94aac4a

  Browse repository at this point

• Add support for `token_type_ids` in `DPOTrainer` (#4285)

  Show description for 26b7c25
  

  aweers

  and

  qgallouedec

  authored
  26b7c25View commit details

  Copy full SHA for 26b7c25

  Browse repository at this point

• Remove using_llama_models.md: outdated Llama2-specific documentation (#4268)

  Show description for aa25c26
  behroozazarkhalili

  authored
  aa25c26View commit details

  Copy full SHA for aa25c26

  Browse repository at this point

• Remove logging.md: trainer-specific metrics documentation (#4269)

  Show description for 93c7d88
  behroozazarkhalili

  authored
  93c7d88View commit details

  Copy full SHA for 93c7d88

  Browse repository at this point

• Fix CI slow tests: ImportError: vLLM is not installed (#4287)

  albertvillanova

  authored
  c7c041eView commit details

  Copy full SHA for c7c041e

  Browse repository at this point

• Replace unittest skipTest with pytest.skip (#4263)

  albertvillanova

  authored
  ef40c04View commit details

  Copy full SHA for ef40c04

  Browse repository at this point

• Fix CI dev test TypeError: unexpected keyword argument 'load_in_4bit' (#4262)

  albertvillanova

  authored
  7e0adbcView commit details

  Copy full SHA for 7e0adbc

  Browse repository at this point

• 💰 `RichProgressCallback` enhancement (#4245)

  qgallouedec

  authored
  773afd9View commit details

  Copy full SHA for 773afd9

  Browse repository at this point

• Fix CI slow test OSError: You are trying to access a gated repo (#4283)

  albertvillanova

  authored
  966b397View commit details

  Copy full SHA for 966b397

  Browse repository at this point

• Fix docstrings with Sphinx 'deprecated' directive (#4279)

  albertvillanova

  authored
  927cf6bView commit details

  Copy full SHA for 927cf6b

  Browse repository at this point

Commits on Oct 14, 2025

• Fix typo in Colab link (#4276)

  sergiopaniego

  authored
  56cb6ccView commit details

  Copy full SHA for 56cb6cc

  Browse repository at this point

• Add Qwen3-VL notebooks (SFT, GRPO) (#4275)

  Show description for 49c8f14
  

  sergiopaniego

  and

  Copilot

  authored
  49c8f14View commit details

  Copy full SHA for 49c8f14

  Browse repository at this point

• Fix style with make precommit (#4265)

  albertvillanova

  authored
  cefbacbView commit details

  Copy full SHA for cefbacb

  Browse repository at this point

• Use FutureWarning instead of DeprecationWarning (#4266)

  albertvillanova

  authored
  fae245aView commit details

  Copy full SHA for fae245a

  Browse repository at this point

Commits on Oct 13, 2025

• Fix docstring interlinks (#4221)

  albertvillanova

  authored
  2aa9506View commit details

  Copy full SHA for 2aa9506

  Browse repository at this point

• Raise deprecation warning for Python 3.9 (#4226)

  albertvillanova

  authored
  d6eeb29View commit details

  Copy full SHA for d6eeb29

  Browse repository at this point

Commits on Oct 10, 2025

• Fix Python version check for skipping tests on Python 3.13.8 (#4246)

  albertvillanova

  authored
  1684ef2View commit details

  Copy full SHA for 1684ef2

  Browse repository at this point

• Include `chat_template_kwargs` in `apply_chat_template` (#4233)

  Show description for aab21eb
  

  cmpatino

  and

  qgallouedec

  authored
  aab21ebView commit details

  Copy full SHA for aab21eb

  Browse repository at this point

• [Online-DPO] fix the completion_len == max_new_tokens crash (#4193)

  Show description for b997a31
  

  3 peopleauthored
  b997a31View commit details

  Copy full SHA for b997a31

  Browse repository at this point

• Fix CI slow test AttributeError: 'TestSFTTrainerSlow' object has no attribute 'addCleanup' (#4255)

  albertvillanova

  authored
  86d1963View commit details

  Copy full SHA for 86d1963

  Browse repository at this point

• Deprecate unused dataset_formatting module (#4242)

  Show description for 039d526
  

  behroozazarkhalili

  and

  qgallouedec

  authored
  039d526View commit details

  Copy full SHA for 039d526

  Browse repository at this point

• Remove obsolete research_projects directory (#4243)

  Show description for bcd059a
  

  behroozazarkhalili

  and

  qgallouedec

  authored
  bcd059aView commit details

  Copy full SHA for bcd059a

  Browse repository at this point

• 🧺 [3/N] Refactor `_generate` in GRPO/RLOO: Rely on generator for prompt truncation (#4153)

  qgallouedec

  authored
  0e57b4aView commit details

  Copy full SHA for 0e57b4a

  Browse repository at this point

• Fix CI slow test ValueError: Unknown loss type: dapo (#4254)

  albertvillanova

  authored
  98488e0View commit details

  Copy full SHA for 98488e0

  Browse repository at this point

• Fix CI ImportError for 'require_torch_gpu_if_bnb_not_multi_backend_enabled' (#4253)

  albertvillanova

  authored
  f45e865View commit details

  Copy full SHA for f45e865

  Browse repository at this point

• Install peft from main for CI tests with dev dependencies (#4250)

  albertvillanova

  authored
  f582792View commit details

  Copy full SHA for f582792

  Browse repository at this point