Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Jul 4, 2025

• Merge branch 'main' into main

  jannisborn

  authored
  b768224View commit details

  Copy full SHA for b768224

  Browse repository at this point

Commits on Jul 3, 2025

• Fix non-serializable torch.dtype bug in VLLM weight sync (#3690)

  Show description for 686cd35
  

  CarlosArguilar

  and

  kashif

  authored
  686cd35View commit details

  Copy full SHA for 686cd35

  Browse repository at this point

• Update steps_per_generation default description grpo_config.py (#3685)

  wa008

  authored
  601a256View commit details

  Copy full SHA for 601a256

  Browse repository at this point

• Support datasets 4 (#3688)

  Show description for d42188b
  

  lhoestq

  and

  Quentin Lhoest

  authored
  d42188bView commit details

  Copy full SHA for d42188b

  Browse repository at this point

• Merge branch 'main' into main

  jannisborn

  authored
  72966bdView commit details

  Copy full SHA for 72966bd

  Browse repository at this point

• Faster `position_ids` computation for FFD packing (#3649)

  Show description for 4ccc5ca
  

  mariosasko

  and

  shirinyamani

  authored
  4ccc5caView commit details

  Copy full SHA for 4ccc5ca

  Browse repository at this point

• [SFT] drop attention_mask if we have position ids for fa2 (#3673)

  Show description for d1e116c
  

  kashif

  and

  shirinyamani

  authored
  d1e116cView commit details

  Copy full SHA for d1e116c

  Browse repository at this point

Commits on Jul 2, 2025

• 🖼️ Add mlflow support for generate_during_eval DPOTrainer (#3660)

  Show description for 90cdf96
  

  dhruvmullick

  and

  shirinyamani

  authored
  90cdf96View commit details

  Copy full SHA for 90cdf96

  Browse repository at this point

• Enable completion-only loss in SFTTrainer when using Liger Kernel (#3674)

  Show description for b520378
  

  3 peopleauthored
  b520378View commit details

  Copy full SHA for b520378

  Browse repository at this point

• format

  jannisborn

  committed
  9089d78View commit details

  Copy full SHA for 9089d78

  Browse repository at this point

• format

  jannisborn

  committed
  3bda286View commit details

  Copy full SHA for 3bda286

  Browse repository at this point

• Update trl/trainer/sft_trainer.py

  Show description for 9dbdb6c
  

  jannisborn

  and

  kashif

  authored
  9dbdb6cView commit details

  Copy full SHA for 9dbdb6c

  Browse repository at this point

• Merge branch 'main' into main

  jannisborn

  authored
  9b3b284View commit details

  Copy full SHA for 9b3b284

  Browse repository at this point

Commits on Jul 1, 2025

• feat: Pass trainer state to reward functions (#3669)

  Show description for e04f7eb
  

  seungduk-yanolja

  and

  kashif

  authored
  e04f7ebView commit details

  Copy full SHA for e04f7eb

  Browse repository at this point

• Add support for CB with native transformers (#3471)

  Show description for 02cce41
  

  3 peopleauthored
  02cce41View commit details

  Copy full SHA for 02cce41

  Browse repository at this point

• fix: support dict access in SFT Trainer

  jannisborn

  committed
  4665f8eView commit details

  Copy full SHA for 4665f8e

  Browse repository at this point

Commits on Jun 28, 2025

• Add paranthesis to correct the check. (#3658)

  pramodith

  authored
  6a6d434View commit details

  Copy full SHA for 6a6d434

  Browse repository at this point

Commits on Jun 26, 2025

• [GRPO] Make sure special tokens aren't lost when truncating prompt. (#3651)

  pramodith

  authored
  79ec242View commit details

  Copy full SHA for 79ec242

  Browse repository at this point

Commits on Jun 25, 2025

• Add entropy based filtering inside the GRPOTrainer. (#3563)

  Show description for 7e8ef86
  

  3 peopleauthored
  7e8ef86View commit details

  Copy full SHA for 7e8ef86

  Browse repository at this point

• 🤝 validate gradient_accumulation_steps vs steps_per_generation for on-policy GRPO (#3493)

  Show description for 32df093
  

  HarryHsing

  and

  shirinyamani

  authored
  32df093View commit details

  Copy full SHA for 32df093

  Browse repository at this point

• ☕️ GRPO script reward_funcs error (#3639)

  Show description for 0336e4b
  

  tcapelle

  and

  shirinyamani

  authored
  0336e4bView commit details

  Copy full SHA for 0336e4b

  Browse repository at this point

Commits on Jun 24, 2025

• Update dpo_vlm.py (#3629)

  Show description for ab331bf
  

  Clement25

  and

  shirinyamani

  authored
  ab331bfView commit details

  Copy full SHA for ab331bf

  Browse repository at this point

• env var for vllm colocate exp added (#3638)

  shirinyamani

  authored
  84d7b5bView commit details

  Copy full SHA for 84d7b5b

  Browse repository at this point

• fixing num_processes (#3637)

  shirinyamani

  authored
  b40c959View commit details

  Copy full SHA for b40c959

  Browse repository at this point

• 🐛 fix grpo generation_kwargs (#3634)

  Show description for 34fa6b9
  

  ahatamiz

  and

  kashif

  authored
  34fa6b9View commit details

  Copy full SHA for 34fa6b9

  Browse repository at this point

Commits on Jun 22, 2025

• Revert "🔍 Add guidance on choosing `max_length` value and include visualization tool"

  Show description for eef7a43
  qgallouedec

  committed
  eef7a43View commit details

  Copy full SHA for eef7a43

  Browse repository at this point

• 🔍 Add guidance on choosing `max_length` value and include visualization tool

  qgallouedec

  committed
  89c699fView commit details

  Copy full SHA for 89c699f

  Browse repository at this point

Commits on Jun 20, 2025

• ⬆️ Bump dev version (#3626)

  qgallouedec

  authored
  559a99fView commit details

  Copy full SHA for 559a99f

  Browse repository at this point

• Release: v0.19 (#3625)

  qgallouedec

  authored
  5b3ea9dView commit details

  Copy full SHA for 5b3ea9d

  Browse repository at this point

• 🧰 [SFT] Tool support (#3597)

  Show description for c262674
  

  qgallouedec

  and

  kashif

  authored
  c262674View commit details

  Copy full SHA for c262674

  Browse repository at this point

• 🔍 Add test to verify chat template consistency (#3624)

  qgallouedec

  authored
  5c3dd3aView commit details

  Copy full SHA for 5c3dd3a

  Browse repository at this point

• ⚔️ Fix bf16 fp16 config conflict issue (#3598)

  Show description for 4c92de0
  

  yao-matrix

  and

  qgallouedec

  authored
  4c92de0View commit details

  Copy full SHA for 4c92de0

  Browse repository at this point

• 📜 Add `chat_template_path` parameter to `SFTConfig` (#3599)

  qgallouedec

  authored
  67f17f7View commit details

  Copy full SHA for 67f17f7

  Browse repository at this point

• 🧬 Add `generation_kwargs` as a property of `GRPOConfig` to support additional generation arguments. (#3617)

  Show description for 37a71e8
  

  pramodith

  and

  qgallouedec

  authored
  37a71e8View commit details

  Copy full SHA for 37a71e8

  Browse repository at this point

• [GRPO] Fix prompt truncation (`max_prompt_length`) with vLLM. (#3601)

  Show description for b0958c6
  

  LeonEricsson

  and

  qgallouedec

  authored
  b0958c6View commit details

  Copy full SHA for b0958c6

  Browse repository at this point