Skip to content

CodCodingCode

Qwen2-0.5B-GRPO-test

Based on Qwen/Qwen2-0.5B-Instruct

Tags

  • tensorboard
  • safetensors
  • generated_from_trainer
  • trl
  • grpo
  • dataset:AGBonnet/augmented-clinical-notes
  • arxiv:2402.03300
  • base_model:Qwen/Qwen2-0.5B-Instruct
  • base_model:finetune:Qwen/Qwen2-0.5B-Instruct
  • endpoints_compatible
  • region:us
Author
CodCodingCode
Library
transformers
Base model
Qwen/Qwen2-0.5B-Instruct
Downloads
0
Likes
0
Qwen2-0.5B-GRPO-test — AI Model — AIMarketly