Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Posts
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up
sail 's Collections
πŸš€ Active PRM
🌾Oat-Zero: Understanding R1-Zero-Like Training
πŸ”± Sailor2 Language Models
🧬 RegMix: Data Mixture as Regression
πŸ“ˆ Scaling Laws with Vocabulary
πŸ’‘ DICE
βš“οΈ Sailor Language Models

πŸ’‘ DICE

updated Jul 28, 2024

Self-alignment with DPO Implicit Rewards

Upvote
9

  • Bootstrapping Language Models with DPO Implicit Rewards

    Paper β€’ 2406.09760 β€’ Published Jun 14, 2024 β€’ 41

  • sail/Llama-3-Base-8B-DICE-Iter1

    Text Generation β€’ Updated Mar 11 β€’ 11 β€’ 2

  • sail/Llama-3-Base-8B-DICE-Iter2

    Text Generation β€’ Updated Mar 11 β€’ 12 β€’ 3

  • sail/Zephyr-7B-DICE-Iter1

    Text Generation β€’ Updated Mar 11 β€’ 5

  • sail/Zephyr-7B-DICE-Iter2

    Text Generation β€’ Updated Mar 11 β€’ 11 β€’ 2
Upvote
9
  • Collection guide
  • Browse collections
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs