Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
martineden
/
gemma-3-4b-it-reasoning
like
0
Transformers
Safetensors
Generated from Trainer
trl
grpo
arxiv:
2402.03300
Model card
Files
Files and versions
xet
Community
Train
Deploy
Use this model
6d321b1
gemma-3-4b-it-reasoning
/
added_tokens.json
martineden
martineden/gemma3-4b-thinking
ff6603c
verified
8 months ago
raw
Copy download link
history
blame
Safe
35 Bytes
{
"<image_soft_token>"
:
262144
}