Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
jadohu
/
Qwen2.5-32B-MASA-efficient
like
0
Reinforcement Learning
Safetensors
agentica-org/DeepScaleR-Preview-Dataset
qwen2
arxiv:
2510.03259
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
main
Qwen2.5-32B-MASA-efficient
/
tokenizer.json
Commit History
Upload folder using huggingface_hub
4f33f73
verified
jadohu
commited on
Nov 25, 2025
jadohu
commited on
