Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
vincenzodentamaro
/
wersa
like
1
Transformers
English
wersa
causal-lm
qwen
long-context
arxiv:
2507.08637
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Use this model
main
wersa
90.4 kB
2 contributors
History:
12 commits
vincenzodentamaro
Update wersa/modeling_wersa.py
e2b3703
verified
about 2 months ago
wersa
Update wersa/modeling_wersa.py
about 2 months ago
.gitattributes
Safe
1.52 kB
initial commit
2 months ago
README.md
Safe
4.47 kB
Update README.md
2 months ago
setup.py
Safe
565 Bytes
Initial release of WERSA source code
2 months ago
train_and_generate_0.6b.py
Safe
5.05 kB
Create train_and_generate_0.6b.py
2 months ago
train_and_generate_8b.py
Safe
5.02 kB
Create train_and_generate_8b.py
2 months ago
train_wersa_single_gpu.py
18.2 kB
Upload 2 files
about 2 months ago
watch_and_test.py
14.2 kB
Upload 2 files
about 2 months ago
