Skip to content

Drogsin

Qwen2.5-Math-1.5B-Open-R1-GRPO

Tags

  • safetensors
  • qwen2
  • generated_from_trainer
  • open-r1
  • trl
  • grpo
  • conversational
  • dataset:DigitalLearningGmbH/MATH-lighteval
  • arxiv:2402.03300
  • text-generation-inference
  • endpoints_compatible
  • region:us
Author
Drogsin
Task
text-generation
Library
transformers
Architecture
qwen2
Downloads
18
Likes
0
Qwen2.5-Math-1.5B-Open-R1-GRPO — AI Model — AIMarketly