LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

  • Markets
  • Builders
  • Research
  • Ecosystems
  • Launchpads
  • Search
Ecosystems

Python

trl

Train transformer language models with reinforcement learning.

PythonEmerging
GitHubWebsite
Stars
—
Forks
—
Contributors
8
Last push
15mo ago

Recent commits

Latest commits.

  • updating use_cache
    ae10482max-kaufmann15mo ago
  • updating the chain
    24fb30bmax-kaufmann15mo ago
  • 🕊️ Padding-free for SFT (#3076)
    9f7755dQuentin Gallouédec15mo ago
  • ⛔ Add EOS token to processed input in SFT (#3091)
    5cb390cQuentin Gallouédec15mo ago
  • 🫣 [GRPO] add cache_implementation option in GRPO (#3075)
    fc4dae2Kashif Rasul15mo ago
💎 Gemma 3 SFT example on Codeforces dataset (#3070)
e4e5671Quentin Gallouédec15mo ago
  • 🎭 Minor spelling fix in documentation (caracteres -> characters) (#3074)
    aad18efEd Snible15mo ago
  • Fixing JSD loss computation as per definition (#3043)
    b55d9f0Abhinav Goyal15mo ago

    • Top contributors

    Builders behind this project.

    qgallouedec
    246 commits
    younesbelkada
    241 commits
    kashif
    75 commits
    lewtun
    75 commits
    vwxyzjn
    53 commits
    lvwerra
    46 commits
    edbeeching
    42 commits
    mnoukhov
    15 commits