Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Oct 31, 2025

• Migrate experimental trl feature docs (#4411)

  ethanknights

  authored
  0aef77bView commit details

  Copy full SHA for 0aef77b

  Browse repository at this point

Commits on Oct 30, 2025

• Fix paper link for "Towards Efficient and Exact Optimization of Language Model Alignment" (#4409)

  qgallouedec

  authored
  519cdf3View commit details

  Copy full SHA for 519cdf3

  Browse repository at this point

• Hotfix CI with dev dependencies: xfail test_prepare_inputs_for_generation (#4372)

  Show description for b3bf53f
  

  albertvillanova

  and

  qgallouedec

  authored
  b3bf53fView commit details

  Copy full SHA for b3bf53f

  Browse repository at this point

• [GOLD] Update code example for GOLD Trainer (#4406)

  cmpatino

  authored
  c26b375View commit details

  Copy full SHA for c26b375

  Browse repository at this point

• [tests] Update rope_scaling configuration for tiny qwen-vl models (#4405)

  Show description for a8f70b0
  

  kashif

  and

  qgallouedec

  authored
  a8f70b0View commit details

  Copy full SHA for a8f70b0

  Browse repository at this point

• Hotfix CI for Python 3.9 by setting test as xfail until transformers release (#4388)

  albertvillanova

  authored
  1c2322eView commit details

  Copy full SHA for 1c2322e

  Browse repository at this point

• Fix typo in GOLD docs (#4394)

  sergiopaniego

  authored
  242de1eView commit details

  Copy full SHA for 242de1e

  Browse repository at this point

• [GOLD] Set teacher tokenizer name if using ULD loss (#4389)

  kashif

  authored
  caaf656View commit details

  Copy full SHA for caaf656

  Browse repository at this point

Commits on Oct 29, 2025

• Support chat_template_kwargs (#4350)

  Show description for 9925469
  

  pramodith

  and

  qgallouedec

  authored
  9925469View commit details

  Copy full SHA for 9925469

  Browse repository at this point

• 👑 [experimental] GOLD Trainer (#4349)

  Show description for 4e9ab9f
  

  kashif

  and

  qgallouedec

  authored
  4e9ab9fView commit details

  Copy full SHA for 4e9ab9f

  Browse repository at this point

• 🔥 docs: Add RapidFire AI integration guide (#4340)

  Show description for b82a8f4
  

  3 peopleauthored
  b82a8f4View commit details

  Copy full SHA for b82a8f4

  Browse repository at this point

• Align make test_experimental with make test (#4371)

  albertvillanova

  authored
  29fb69fView commit details

  Copy full SHA for 29fb69f

  Browse repository at this point

• Fix add_generation_prompt arg for paged transformers in GRPO and RLOO trainers (#4370)

  Show description for ac6cea8
  

  albertvillanova

  and

  qgallouedec

  authored
  ac6cea8View commit details

  Copy full SHA for ac6cea8

  Browse repository at this point

• Add support for Trackio completions logging in GRPOTrainer (#4359)

  Show description for 1e39eb6
  

  taha-yassine

  and

  qgallouedec

  authored
  1e39eb6View commit details

  Copy full SHA for 1e39eb6

  Browse repository at this point

• Replace deprecated list with tuple indexing in PPOTrainer (#4356)

  albertvillanova

  authored
  97830a3View commit details

  Copy full SHA for 97830a3

  Browse repository at this point

• Remove ignored max_length parameter from PRMTrainer data collator (#4355)

  albertvillanova

  authored
  d275418View commit details

  Copy full SHA for d275418

  Browse repository at this point

• Move tests of BCO trainer args to tests/experimental (#4354)

  Show description for 61bf96c
  

  albertvillanova

  and

  qgallouedec

  authored
  61bf96cView commit details

  Copy full SHA for 61bf96c

  Browse repository at this point

• Replace deprecated AutoModelForVision2Seq with AutoModelForImageTextToText (#4353)

  albertvillanova

  authored
  b8f23efView commit details

  Copy full SHA for b8f23ef

  Browse repository at this point

• Implement CI test workflow for experimental module (#4330)

  Show description for f8073cb
  

  albertvillanova

  and

  qgallouedec

  authored
  f8073cbView commit details

  Copy full SHA for f8073cb

  Browse repository at this point

• Move tests of experimental GRPO with replay buffer to tests/experimental (#4329)

  Show description for 55854c8
  

  albertvillanova

  and

  qgallouedec

  authored
  55854c8View commit details

  Copy full SHA for 55854c8

  Browse repository at this point

• Use explicit tiny-Qwen2_5_VL model_id parameter in CI tests (#4325)

  Show description for 4352074
  

  albertvillanova

  and

  qgallouedec

  authored
  4352074View commit details

  Copy full SHA for 4352074

  Browse repository at this point

• Fix: `add_generation_prompt=True` for conversational only (#4362)

  qgallouedec

  authored
  928f589View commit details

  Copy full SHA for 928f589

  Browse repository at this point

• Add `add_generation_prompt` to processor_kwargs in GRPO and RLOO trainer (#4361)

  qgallouedec

  authored
  b0889d2View commit details

  Copy full SHA for b0889d2

  Browse repository at this point

Commits on Oct 28, 2025

• fix CI issue for vlm_gemma_3n model (#4278)

  Show description for a9d33d0
  

  3 peopleauthored
  a9d33d0View commit details

  Copy full SHA for a9d33d0

  Browse repository at this point

• Fixed links inside Tips in docs (#4360)

  Show description for 34fdb61
  

  sergiopaniego

  and

  qgallouedec

  authored
  34fdb61View commit details

  Copy full SHA for 34fdb61

  Browse repository at this point

• Add missing license in `tests/experimental/__init__.py`

  qgallouedec

  committed
  a23e91cView commit details

  Copy full SHA for a23e91c

  Browse repository at this point

Commits on Oct 27, 2025

• Fix GRPO and RLOO trainers for continuous batching (#4348)

  albertvillanova

  authored
  5e691d1View commit details

  Copy full SHA for 5e691d1

  Browse repository at this point

• [vllm] update comment about communication group host ip (#4337)

  kashif

  authored
  fa644b1View commit details

  Copy full SHA for fa644b1

  Browse repository at this point

• Added custom `prepare_model_for_kbit_training` to save VRAM (#4335)

  Show description for fda88c6
  

  sergiopaniego

  and

  kashif

  authored
  fda88c6View commit details

  Copy full SHA for fda88c6

  Browse repository at this point

• Update Reducing Memory Consumption guide with more details (#4332)

  Show description for 2a138c7
  

  sergiopaniego

  and

  kashif

  authored
  2a138c7View commit details

  Copy full SHA for 2a138c7

  Browse repository at this point

Commits on Oct 24, 2025

• 🗞️ Update "What's New" (#4338)

  qgallouedec

  authored
  05a1febView commit details

  Copy full SHA for 05a1feb

  Browse repository at this point

• Add OpenEnv blog to landing (#4333)

  sergiopaniego

  authored
  d8543c0View commit details

  Copy full SHA for d8543c0

  Browse repository at this point

• Hotfix: Fall back to config.text_config._name_or_path if missing config._name_or_path (#4324)

  albertvillanova

  authored
  23c0062View commit details

  Copy full SHA for 23c0062

  Browse repository at this point

Commits on Oct 23, 2025

• Move BCO tests to tests/experimental (#4326)

  albertvillanova

  authored
  47b1aa7View commit details

  Copy full SHA for 47b1aa7

  Browse repository at this point

• Update OpenEnv docs (#4328)

  sergiopaniego

  authored
  a4872d9View commit details

  Copy full SHA for a4872d9

  Browse repository at this point