← 트렌딩

Tangerine Index는 ChatGPT 이후 나온 프로덕트와 사람들의 반응을 싣습니다.

xtuner

github.com

A Next-Generation Training Engine Built for Ultra-Large MoE Models

오픈소스

github.com 방문외부 사이트GitHub5,222 스타외부 사이트

반응 (1)

비슷한 프로덕트

설명이 비슷한 순

  1. We trained an MoE LLM built for developer tasks

    Introducing Interfaze Hybrid Architecture: A unified transformer and DNN architecture that shares the same vector space and context window, allowing for seamless switching between modalities and specialized tasks.

    interfaze.ai최근 반응

    Hacker News
    5점
    GitHub
    반응 없음

  2. Model Training Memory Simulator

    Zhéyuán Chén's homepage

    czheo.github.io최근 반응

    Hacker News
    10점
    GitHub
    반응 없음

  3. Yi

    A series of large language models trained from scratch by developers @01-ai

    github.com오픈소스최근 반응

    Hacker News
    반응 없음
    GitHub
    스타 7,833

  4. verl

    verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

    github.com라이브러리오픈소스최근 반응

    Hacker News
    반응 없음
    GitHub
    스타 24,162

  5. BELLE

    BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）

    github.com오픈소스최근 반응

    Hacker News
    반응 없음
    GitHub
    스타 8,261