Commits

Branch selector

main

User selector

dirtyDan0

All time

Commit history

Commits on Jun 17, 2025

• [data] fix: multimodal overlong prompt length filtering (#2063)

  Show description for 992ac06
  dirtyDan0

  authored
  992ac06View commit details

  Copy full SHA for 992ac06

  Browse repository at this point

Commits on May 13, 2025

• [doc] Clarifying `gpu_memory_utilization` for different engines (#1491)

  Show description for 9a956c0
  dirtyDan0

  authored
  9a956c0View commit details

  Copy full SHA for 9a956c0

  Browse repository at this point

Commits on Apr 16, 2025

• fix: missed loss_agg_mode in dp_actor (#945)

  Show description for 3e3d937
  dirtyDan0

  authored
  3e3d937View commit details

  Copy full SHA for 3e3d937

  Browse repository at this point

Commits on Apr 8, 2025

• fix: wrong pg_clipfrac_lower (#972)

  Show description for 88db554
  dirtyDan0

  authored
  88db554View commit details

  Copy full SHA for 88db554

  Browse repository at this point

Commits on Apr 4, 2025

• [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

• 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

Commits on Apr 1, 2025

• 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 22, 2025

• fix: support transformers==4.50.0 (#704)

  Show description for 3f6d45d
  dirtyDan0

  authored
  3f6d45dView commit details

  Copy full SHA for 3f6d45d

  Browse repository at this point

Commits on Mar 14, 2025

• misc: remove redundant .to(device) (#565)

  Show description for d2db725
  dirtyDan0

  authored
  d2db725View commit details

  Copy full SHA for d2db725

  Browse repository at this point

Commits on Mar 8, 2025

• feat: support loading reward function from an external file (#452)

  dirtyDan0

  authored
  13a87c7View commit details

  Copy full SHA for 13a87c7

  Browse repository at this point

Commits on Mar 6, 2025

• fix: (1) skipped last step (2) redundant validation and logging (#409)

  Show description for 3165d98
  dirtyDan0

  authored
  3165d98View commit details

  Copy full SHA for 3165d98

  Browse repository at this point

Commits on Mar 1, 2025

• fix: 2 typos (#435)

  dirtyDan0

  authored
  99fb2ddView commit details

  Copy full SHA for 99fb2dd

  Browse repository at this point