LoreonLabsPlatform
DocsHome
  • Overview

Intelligence

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

Python

Trinity-RFT

Trinity-RFT is a general-purpose, flexible and scalable framework designed for reinforcement fine-tuning (RFT) of large language models (LLM).

PythonEmerging
GitHubWebsite
Stars
—
Forks
—
Contributors
8
Last push
9mo ago

Recent commits

Latest commits.

  • Enhance support for multi-modal models (#298)
    90d65caXuchen Pan9mo ago
  • Add LoRA mode (#291)
    564caf1Yuchang Sun9mo ago
  • Fix absmethod in workflow (#297)
    4132f0cchenyushuo9mo ago
  • Explorer provides OpenAI API compatible inference service (#289)
    6ad5429Xuchen Pan9mo ago
  • Add `loss-agg-mode` for policy loss (#294)
    e295092Yuchang Sun9mo ago
Improvement in config (#288)
8da44d0chenyushuo9mo ago
  • Update data-juicer version in toml (#286)
    3294803chenyushuo9mo ago
  • Add enable_activation_offload configuration option (#281)
    d911e9eNikolai Karpov9mo ago
  • Top contributors

    Builders behind this project.

    pan-x-c
    107 commits
    hiyuchang
    45 commits
    chenyushuo
    45 commits
    garyzhang99
    18 commits
    yanxi-chen
    9 commits
    HYLcool
    8 commits
    yaochaorui
    4 commits
    shiweijiezero
    3 commits