Skip to content

WillHeld

Delphi-25B-SimpleRL-Math

Based on marin-community/delphi-1e23-25Bparams-628Btokens

Tags

  • safetensors
  • qwen3
  • math
  • reasoning
  • grpo
  • simplerl
  • base_model:marin-community/delphi-1e23-25Bparams-628Btokens
  • base_model:finetune:marin-community/delphi-1e23-25Bparams-628Btokens
  • region:us
Author
WillHeld
Task
reinforcement-learning
Architecture
qwen3
Base model
marin-community/delphi-1e23-25Bparams-628Btokens
Downloads
9
Likes
0
Delphi-25B-SimpleRL-Math — AI Model — AIMarketly