Hugging Face
Search models, datasets, users...
Ctrl K
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
๐
Open to Work
104.8
TFLOPS
CK
Chris4K
29
18
1168
Follow
Valentina9502's profile picture
0p71m4lpr1m3's profile picture
PhysiQuanty's profile picture
88 followers
ยท
313 following
zX14_7
ckal
AI & ML interests
Phonetics, Alpha-Beta Pruning, Bayes, Go the game, NLP, Bots
Recent Activity
new
activity
about 11 hours ago
Chris4K/zeroflops-enwik8-lm:
Hard-residual LM line: 0.9756 bits/byte on enwik8 (below 1.0 BPC)
reacted
to
their
post
with ๐
about 11 hours ago
๐ง 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
liked
a model
about 13 hours ago
Chris4K/zeroflops-enwik8-lm
View all activity
Organizations
Chris4K
's datasets
1
Sort:ย Recently updated
Chris4K/connect-four-gf256
Updated
19 days ago
โข
301
โข
1