Commits

Branch selector

main

User selector

All users

All time

Commit history

Commits on Apr 5, 2025

• diverse grpo

  tarsur909

  committed
  ef08f62View commit details

  Copy full SHA for ef08f62

  Browse repository at this point

• Merge branch 'volcengine:main' into main

  tarsur909

  authored
  49ed933View commit details

  Copy full SHA for 49ed933

  Browse repository at this point

• docker: add verl-sglang dockerfile (#930)

  Show description for cc6dd90
  ocss884

  authored
  cc6dd90View commit details

  Copy full SHA for cc6dd90

  Browse repository at this point

• [math-verify] fix: TimeoutException (#929)

  tongyx361

  authored
  8447937View commit details

  Copy full SHA for 8447937

  Browse repository at this point

• Merge branch 'volcengine:main' into main

  tarsur909

  authored
  f7b2581View commit details

  Copy full SHA for f7b2581

  Browse repository at this point

• add div

  tarsur909

  committed
  7e951e4View commit details

  Copy full SHA for 7e951e4

  Browse repository at this point

• Feat: support REINFORCE++-baseline and add script for REINFORCE++ (#908)

  Show description for 30259d2
  hijkzzz

  authored
  30259d2View commit details

  Copy full SHA for 30259d2

  Browse repository at this point

Commits on Apr 4, 2025

• feat: Add multi-turn SFT support (#195)

  xingyaoww

  authored
  fb03941View commit details

  Copy full SHA for fb03941

  Browse repository at this point

• tool: add diagnosis script (#918)

  Show description for 4f245a3
  eric-haibin-lin

  authored
  4f245a3View commit details

  Copy full SHA for 4f245a3

  Browse repository at this point

• docs: update installation and adoption docs (#921)

  eric-haibin-lin

  authored
  0fc8e77View commit details

  Copy full SHA for 0fc8e77

  Browse repository at this point

• [dataset] refactor: remove unused filter_prompts parameter from RLHFDataset (#889)

  Show description for 0407cad
  0x404

  authored
  0407cadView commit details

  Copy full SHA for 0407cad

  Browse repository at this point

• fix: set gen_batch_size based on config (#909)

  tongyx361

  authored
  d5a1c81View commit details

  Copy full SHA for d5a1c81

  Browse repository at this point

• [dataset] refactor: use hf Dataset instead of pandas DataFrame in RLHFDataset for speedup (#890)

  Show description for 6974bba
  

  0x404

  and

  hiyouga

  authored
  6974bbaView commit details

  Copy full SHA for 6974bba

  Browse repository at this point

• [log] fix: log after generate_sequences (#819)

  tongyx361

  authored
  6d931dfView commit details

  Copy full SHA for 6d931df

  Browse repository at this point

• [algo] misc: remove redundant tile([1, response_length]), efficient broadcast instead (#868)

  Show description for f9256b8
  dirtyDan0

  authored
  f9256b8View commit details

  Copy full SHA for f9256b8

  Browse repository at this point

Commits on Apr 3, 2025

• [recipe] feat: integrate DAPO and provide reproduction script (#623)

  Show description for 3a27a98
  

  tongyx361

  and

  PeterSH6

  authored
  3a27a98View commit details

  Copy full SHA for 3a27a98

  Browse repository at this point

• [dev] feat: default VSCode repo settings to help consistency with CI (#894)

  Show description for cc612db
  tongyx361

  authored
  cc612dbView commit details

  Copy full SHA for cc612db

  Browse repository at this point

• test: update vllm_spmd test for > 0.7.3 (#861)

  Show description for 1a7e53d
  BearBiscuit05

  authored
  1a7e53dView commit details

  Copy full SHA for 1a7e53d

  Browse repository at this point

• reuse GPTModel, try to fix CI issue (#884)

  Show description for 0338805
  ETOgaosion

  authored
  0338805View commit details

  Copy full SHA for 0338805

  Browse repository at this point

• fix: the error is not raised when using both megatron and hf inference (#885)

  Show description for b6dc157
  wkcn

  authored
  b6dc157View commit details

  Copy full SHA for b6dc157

  Browse repository at this point

• docs: add config docs for evaluation.yaml (#886)

  Show description for b0e0ac5
  yyDing1

  authored
  b0e0ac5View commit details

  Copy full SHA for b0e0ac5

  Browse repository at this point

• fix: misleading eos_mask->response_mask (#878)

  Show description for 8cae42d
  dirtyDan0

  authored
  8cae42dView commit details

  Copy full SHA for 8cae42d

  Browse repository at this point

• docs: add megatron grpo qwen2 training logs (#881)

  eric-haibin-lin

  authored
  7895c1fView commit details

  Copy full SHA for 7895c1f

  Browse repository at this point

Commits on Apr 2, 2025

• revert: "Use Mcore GPTModel" (#883)

  Show description for 81a15ed
  eric-haibin-lin

  authored
  81a15edView commit details

  Copy full SHA for 81a15ed

  Browse repository at this point

• [recipe] r1: support R1 Benchmark Evaluation (#777)

  Show description for 233c11c
  yyDing1

  authored
  233c11cView commit details

  Copy full SHA for 233c11c

  Browse repository at this point

• Use Mcore GPTModel (#706)

  Show description for b6cd6b7
  ISEEKYAN

  authored
  b6cd6b7View commit details

  Copy full SHA for b6cd6b7

  Browse repository at this point

• [fix] add dpsk v3 type in config for mfu compute (#872)

  Show description for 4fec38c
  BearBiscuit05

  authored
  4fec38cView commit details

  Copy full SHA for 4fec38c

  Browse repository at this point

• Implement Dual-Clip PPO Algorithm (#784)

  Show description for 6272b8c
  none0663

  authored
  6272b8cView commit details

  Copy full SHA for 6272b8c

  Browse repository at this point

Commits on Apr 1, 2025

• [misc] add trust_remote_code param for loading custom tokenizer (#865)

  BearBiscuit05

  authored
  05bdeadView commit details

  Copy full SHA for 05bdead

  Browse repository at this point

• Docs: add Rec-R1 in Readme (#869)

  linjc16

  authored
  45e02c8View commit details

  Copy full SHA for 45e02c8

  Browse repository at this point

• [sglang] doc: Update the SGLang installation instructions to the latest version. (#867)

  BearBiscuit05

  authored
  437e96bView commit details

  Copy full SHA for 437e96b

  Browse repository at this point

• [critic] fix: normalize mini batch size for critic (#853)

  Show description for 9dcac14
  tongyx361

  authored
  9dcac14View commit details

  Copy full SHA for 9dcac14

  Browse repository at this point

• docs: improve installation and ulysses docs (#854)

  eric-haibin-lin

  authored
  776b0a9View commit details

  Copy full SHA for 776b0a9

  Browse repository at this point

• feat: support no reference model; fix KL issues (#644)

  Show description for 072fc9f
  dirtyDan0

  authored
  072fc9fView commit details

  Copy full SHA for 072fc9f

  Browse repository at this point

Commits on Mar 31, 2025

• [ulysses] fix: repeat kv heads by sp_size//nheads_k if nheads_k is less than sp_size (#850)

  wuxibin89

  authored
  c0621e1View commit details

  Copy full SHA for c0621e1

  Browse repository at this point