Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Log In
Sign Up
fraQtl
/
TinyLlama-1.1B-optimized
like
0
Follow
fraQtl AI Research
2
Safetensors
llama
fraqtl
kv-cache-optimized
inference
arxiv:
2604.11501
License:
other
Model card
Files
Files and versions
xet
Community
main
TinyLlama-1.1B-optimized
Commit History
Add arXiv paper link
7681719
verified
Zenalyze
commited on
4 days ago
Clarify: KV cache optimized, not smaller file
2141b55
verified
Zenalyze
commited on
5 days ago
Update model card with runtime comparison
29875f7
verified
Zenalyze
commited on
8 days ago
fraQtl compressed: k=16 INT3, delta=+0.3533
22cfe1d
verified
Zenalyze
commited on
8 days ago
initial commit
49ec424
verified
Zenalyze
commited on
8 days ago