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

  • Log In
  • Sign Up
haoranli-ml 's Collections
inference
VF
CoPE

CoPE

updated 1 day ago

CoPE is a drop-in enhancement of RoPE that delivers consistent gains within the training context and during long-context extrapoaltion.

Upvote
1

  • haoranli-ml/Llama-3-8B-CoPE-64k-Instruct

    Text Generation • 8B • Updated about 4 hours ago • 99

  • haoranli-ml/Llama-3-8B-RoPE-64k-Instruct

    Text Generation • 8B • Updated about 4 hours ago • 93

  • haoranli-ml/Llama-3-8B-CoPE-64k-Base

    8B • Updated about 4 hours ago • 20

  • haoranli-ml/Llama-3-8B-RoPE-64k-Base

    8B • Updated about 4 hours ago • 20

  • haoranli-ml/Llama-3-8B-HardClip-64k-Instruct

    8B • Updated about 4 hours ago • 42

  • haoranli-ml/Llama-3-8B-HardClip-64k-Base

    8B • Updated about 4 hours ago • 34

  • haoranli-ml/prolong-ultrachat-64K

    Updated 1 day ago

  • haoranli-ml/prolong-data-64K

    Updated 1 day ago
Upvote
1
  • Collection guide
  • Browse collections
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs