Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
zen-E
/
SSA-1B
like
0
Safetensors
EleutherAI/SmolLM2-135M-100B
English
llama-nsa
sparse_attention
pretrain
custom_code
arxiv:
2511.20102
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
main
SSA-1B
Commit History
Update README.md
e613e4b
verified
zen-E
commited on
5 days ago
Delete training_args.bin
ec5d310
verified
zen-E
commited on
5 days ago
Delete trainer_state.json
f73d1a0
verified
zen-E
commited on
5 days ago
Update configuration_llama_nsa.py
4c774c9
verified
zen-E
commited on
10 days ago
Update modeling_llama_nsa.py
91d7770
verified
zen-E
commited on
10 days ago
Update README.md
5d22a99
verified
zen-E
commited on
10 days ago
Create README.md
cf38879
verified
zen-E
commited on
10 days ago
Upload 10 files
acb48fb
verified
zen-E
commited on
10 days ago
initial commit
a06b937
verified
zen-E
commited on
10 days ago