Hugging Face's logo

wzx111
/
Qwen3-1.7B-MATH-GDPO

Text Generation
Transformers
Safetensors
qwen3
Generated from Trainer
open-r1
trl
gdpo
conversational
text-generation-inference
Model card Files
xet
 Community
1
New discussion

Which post-training method was actually used for this model, GDPO or GRPO?

1
#1 opened 4 months ago by
roseblooming