Hugging Face's logo

Timusgeorge
/
SynthAudit-Qwen2.5-3B-GRPO

Text Generation
PEFT
Safetensors
English
medical
clinical-trial
oversight
grpo
reinforcement-learning
lora
qwen2.5
openenv
multi-agent
conversational
Model card Files
xet
 Community
SynthAudit-Qwen2.5-3B-GRPO / tokenizer.json

Commit History

feat: GRPO-trained Qwen2.5-3B for clinical trial auditing (50 steps, T4)
6d6953a
verified

Timusgeorge commited on