Hugging Face
Models
Datasets
Spaces
Buckets
new
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
HelloSun
/
laguna-s-2.1-Q4_K_M_EPQ
Like
0
Text Generation
GGUF
Mixture of Experts
expert-paging
epq
q4_k_m
laguna
cpu-inference
conversational
arxiv:
2602.03921
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
laguna-s-2.1-Q4_K_M_EPQ
/
sdq_cli.cpp
Commit History
Oct 19
3 days ago
21:14
Add top-k ablation: original 10 vs 4 (speed, SSD, PPL)
HelloSun
Verified signature
f050a0c
15:53
EPQ expert-paging port for Laguna-S-2.1 Q4_K_M (source + results)
HelloSun
Verified signature
37c1f39
