Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ABaroian
/
Apertus-8B-RLVR-GSM
like
1
Reinforcement Learning
ai2-adapt-dev/rlvr_gsm8k_zs
rlvr
grpo
gsm8k
apertus
arxiv:
2411.15124
arxiv:
2509.14233
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
main
Apertus-8B-RLVR-GSM
/
zero_pp_rank_2_mp_rank_00_model_states.pt
Commit History
Upload folder using huggingface_hub
c2c1bb9
verified
ABaroian
commited on
14 days ago