Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
real-jiakai
/
gemma3-4b-thinking
like
2
Transformers
Safetensors
Generated from Trainer
trl
grpo
reasoning
math
step-by-step-thinking
arxiv:
2402.03300
Model card
Files
Files and versions
Community
Train
Deploy
Use this model
main
gemma3-4b-thinking
Commit History
Update README.md
75449fb
verified
real-jiakai
commited on
20 days ago
Update README.md
d6eefb8
verified
real-jiakai
commited on
20 days ago
real-jiakai/gemma3-4b-thinking
2f55483
verified
real-jiakai
commited on
20 days ago
initial commit
1857c10
verified
real-jiakai
commited on
20 days ago
real-jiakai
commited on
