Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Jul 25, 2025

• Update missing uv dep (#3772)

  lhoestq

  authored
  eee9ec9View commit details

  Copy full SHA for eee9ec9

  Browse repository at this point

• Add uv scripts headers (#3767)

  lhoestq

  authored
  a043fd7View commit details

  Copy full SHA for a043fd7

  Browse repository at this point

• 🤓 [GRPO] Documentation for entropy metric (#3770)

  LeonEricsson

  authored
  d16b960View commit details

  Copy full SHA for d16b960

  Browse repository at this point

• 🌌 [GRPO] Log generation entropy (#3700)

  Show description for daad892
  

  LeonEricsson

  and

  qgallouedec

  authored
  daad892View commit details

  Copy full SHA for daad892

  Browse repository at this point

• 🔠 Support model str in OnlineDPO (#3765)

  Show description for 097d615
  

  kashif

  and

  qgallouedec

  authored
  097d615View commit details

  Copy full SHA for 097d615

  Browse repository at this point

• 🔔 Add deprecation warnings for `AlignPropTrainer` and `DDPOTrainer` (#3755)

  Show description for bc3eebb
  

  qgallouedec

  and

  LeonEricsson

  authored
  bc3eebbView commit details

  Copy full SHA for bc3eebb

  Browse repository at this point

• ✋ Prevent NCCL Device Conflicts Between vLLM Server and Trainers (#3762)

  Show description for 1fb115d
  

  CarlosArguilar

  and

  qgallouedec

  authored
  1fb115dView commit details

  Copy full SHA for 1fb115d

  Browse repository at this point

Commits on Jul 24, 2025

• Add MPO recipe to Community tutorials (#3766)

  sergiopaniego

  authored
  3a40f18View commit details

  Copy full SHA for 3a40f18

  Browse repository at this point

Commits on Jul 23, 2025

• 👁️ [GRPO] Add VLM training capabilities to the trainer (#3072)

  CompN3rd

  authored
  56f4201View commit details

  Copy full SHA for 56f4201

  Browse repository at this point

Commits on Jul 22, 2025

• 👨‍💼 [SFT] Packing with completion_only and assistant_only training (#3749)

  Show description for a50bdc6
  

  LeonEricsson

  and

  qgallouedec

  authored
  a50bdc6View commit details

  Copy full SHA for a50bdc6

  Browse repository at this point

• ⚰️ Remove deprecated (#3704)

  qgallouedec

  authored
  e102ac8View commit details

  Copy full SHA for e102ac8

  Browse repository at this point

Commits on Jul 21, 2025

• 🐙 MPO (#2544)

  Show description for d870230
  

  4 peopleauthored
  d870230View commit details

  Copy full SHA for d870230

  Browse repository at this point

• Add Object detection grounding recipe to Community tutorials (#3752)

  sergiopaniego

  authored
  68ce3a3View commit details

  Copy full SHA for 68ce3a3

  Browse repository at this point

Commits on Jul 20, 2025

• [GRPO] Fix: Processing ref logprobs in batches (#3740)

  Show description for 5787f3b
  

  idanshen

  and

  LeonEricsson

  authored
  5787f3bView commit details

  Copy full SHA for 5787f3b

  Browse repository at this point

Commits on Jul 19, 2025

• 🏗️ Refactor top-entropy in GRPO (#3727)

  qgallouedec

  authored
  116ec49View commit details

  Copy full SHA for 116ec49

  Browse repository at this point

• uses `steps_per_generation` in vllm max_num_seqs (#3747)

  akakakakakaa

  authored
  1b17fa7View commit details

  Copy full SHA for 1b17fa7

  Browse repository at this point

• Add comment for `average_tokens_across_devices` (#3746)

  qgallouedec

  authored
  c389599View commit details

  Copy full SHA for c389599

  Browse repository at this point

Commits on Jul 18, 2025

• Updated missing `processing_class` docs for rest of trainers (#3745)

  sergiopaniego

  authored
  e333da8View commit details

  Copy full SHA for e333da8

  Browse repository at this point

Commits on Jul 16, 2025

• Updated `processing_class` docs for trainers (#3737)

  sergiopaniego

  authored
  c8347b4View commit details

  Copy full SHA for c8347b4

  Browse repository at this point

• 🕸 Use `wandb.run.url` instead of `wandb.run.get_url()` (deprecated) (#3726)

  qgallouedec

  authored
  8684cb4View commit details

  Copy full SHA for 8684cb4

  Browse repository at this point

Commits on Jul 15, 2025

• 🔧 Fix GRPO sampling logic (#3725)

  qgallouedec

  authored
  508d551View commit details

  Copy full SHA for 508d551

  Browse repository at this point

• [GRPO] remove common activation offloading substring in all cases (#3738)

  winglian

  authored
  569d60eView commit details

  Copy full SHA for 569d60e

  Browse repository at this point

Commits on Jul 12, 2025

• 📥 Set environment variables for vLLM distributed training in GRPOTrainer (#3723)

  qgallouedec

  authored
  640a9f3View commit details

  Copy full SHA for 640a9f3

  Browse repository at this point

• ↔️ Fix CB in GRPO (#3722)

  Show description for 5a2b04a
  

  qgallouedec

  and

  shirinyamani

  authored
  5a2b04aView commit details

  Copy full SHA for 5a2b04a

  Browse repository at this point

• 👋 Remove `--bf16` flag from training scripts (#3724)

  Show description for dffd1ac
  

  qgallouedec

  and

  shirinyamani

  authored
  dffd1acView commit details

  Copy full SHA for dffd1ac

  Browse repository at this point

Commits on Jul 11, 2025

• Remove deprecated `processor.tokenizer` (#3720)

  Tavish9

  authored
  43e6b24View commit details

  Copy full SHA for 43e6b24

  Browse repository at this point

• [Online DPO] Safeguard logit slice against empty prompt (#3719)

  LeonEricsson

  authored
  2ae43f8View commit details

  Copy full SHA for 2ae43f8

  Browse repository at this point

Commits on Jul 10, 2025

• Fix ORPOTrainer loss scaling with gradient accumulation (#3716)

  Aratako

  authored
  c949b66View commit details

  Copy full SHA for c949b66

  Browse repository at this point

• BUG: Disregard pad token entropies for entropy threshold calculation (#3715)

  pramodith

  authored
  9708553View commit details

  Copy full SHA for 9708553

  Browse repository at this point

Commits on Jul 9, 2025

• ⚗️ Tiny MoE for test (#3712)

  qgallouedec

  authored
  68ed863View commit details

  Copy full SHA for 68ed863

  Browse repository at this point

Commits on Jul 8, 2025

• [SFT] Add `seq_lengths` to signature columns (#3699)

  Show description for 0462dd7
  

  LeonEricsson

  and

  kashif

  authored
  0462dd7View commit details

  Copy full SHA for 0462dd7

  Browse repository at this point

• 🔭 Fix package discovery configuration in setup.cfg (#3703)

  qgallouedec

  authored
  68db24eView commit details

  Copy full SHA for 68db24e

  Browse repository at this point

Commits on Jul 7, 2025

• 📣 Use explicit version for checking datasets version (#3702)

  qgallouedec

  authored
  2d086f2View commit details

  Copy full SHA for 2d086f2

  Browse repository at this point

• ✂️ [BUG when vllm and prompt_truncation are used]: Strip out pad tokens in truncated prompt text (#3698)

  Show description for b674989
  

  4 peopleauthored
  b674989View commit details

  Copy full SHA for b674989

  Browse repository at this point

• Fix mislabeling: "First-fit decreasing" is actually "Best-fit-decreasing" (#3696)

  Show description for 0353d67
  

  LeonEricsson

  and

  shirinyamani

  authored
  0353d67View commit details

  Copy full SHA for 0353d67

  Browse repository at this point