GNU social JP
  • FAQ
  • Login
GNU social JPは日本のGNU socialサーバーです。
Usage/ToS/admin/test/Pleroma FE

  • Public

    • Public
    • Network
    • Groups
    • Featured
    • Popular
    • People

Embed Notice

HTML Code

Corresponding Notice

  1. Embed this notice
    Jan Wildeboer 😷:krulorange: (jwildeboer@social.wildeboer.net)'s status on Tuesday, 28-Jan-2025 19:51:05 JSTJan Wildeboer 😷:krulorange:Jan Wildeboer 😷:krulorange:
    in reply to
    • Eva Wolfangel
    • tante
    • Florian 'floe' Echtler
    • Lars Weisbrod
    • Kris

    @floe Ja, kan man auf Modelleben machen. Siehe z.B. https://arxiv.org/abs/2403.01081

    In der Praxis z.B. mit Instructlab https://docs.instructlab.ai
    @isotopp @evawolfangel @larsweisbrod @tante

    In conversationabout 4 months ago from social.wildeboer.netpermalink

    Attachments

    1. Domain not in remote thumbnail source whitelist: arxiv.org
      LAB: Large-Scale Alignment for ChatBots
      This work introduces LAB (Large-scale Alignment for chatBots), a novel methodology designed to overcome the scalability challenges in the instruction-tuning phase of large language model (LLM) training. Leveraging a taxonomy-guided synthetic data generation process and a multi-phase tuning framework, LAB significantly reduces reliance on expensive human annotations and proprietary models like GPT-4. We demonstrate that LAB-trained models can achieve competitive performance across several benchmarks compared to models trained with traditional human-annotated or GPT-4 generated synthetic data. Thus offering a scalable, cost-effective solution for enhancing LLM capabilities and instruction-following behaviors without the drawbacks of catastrophic forgetting, marking a step forward in the efficient training of LLMs for a wide range of applications.
    2. Domain not in remote thumbnail source whitelist: docs.instructlab.ai
      Welcome to InstructLab! - docs.instructlab.ai
      The overview of 🐶 InstructLab.
  • Help
  • About
  • FAQ
  • TOS
  • Privacy
  • Source
  • Version
  • Contact

GNU social JP is a social network, courtesy of GNU social JP管理人. It runs on GNU social, version 2.0.2-dev, available under the GNU Affero General Public License.

Creative Commons Attribution 3.0 All GNU social JP content and data are available under the Creative Commons Attribution 3.0 license.