Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up
mX7pf <img src=x onerror=window.__pf1=1>'s picture

mX7pf <img src=x onerror=window.__pf1=1>

jdjsjsj28828
1
Chris4K's profile picture jdjdje8383's profile picture
ยท
https://example.com/

AI & ML interests

None yet

Recent Activity

reacted to Chris4K's post with ๐Ÿ˜Ž about 7 hours ago
๐Ÿง  Zero-FLOP Memory Can a small transformer do more by remembering differently? 39.5M parameters + discrete count tables + document cache. 1.017 BPC on enwik8. No gradient updates needed to build the memory. Exploring a different way to scale language modeling: not just more parameters, but better memory. Paper & code follows ... if someones interested
repliedto Chris4K's post about 7 hours ago
๐Ÿง  Zero-FLOP Memory Can a small transformer do more by remembering differently? 39.5M parameters + discrete count tables + document cache. 1.017 BPC on enwik8. No gradient updates needed to build the memory. Exploring a different way to scale language modeling: not just more parameters, but better memory. Paper & code follows ... if someones interested
published a bucket about 16 hours ago
jdjsjsj28828/bkprobe
View all activity

Organizations

mX7s1 <img src=x onerror=window.__o1=1>'s profile picture

jdjsjsj28828 's models 2

jdjsjsj28828/mx7n

Updated about 16 hours ago

jdjsjsj28828/tcprobe

Token Classification โ€ข Updated about 16 hours ago
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs