Understanding R1-Zero-Like Training: A Critical Perspective
Paper • 2503.20783 • Published • 60
Financial Sentiment Dr. GRPO
Fine-tuned with reinforcement learning on Financial PhraseBank (sentences_50agree).
AI League #5 Problem Statement 2 POC.
loss_type=dr_grpo,scale_rewards=False(arXiv:2503.20783 fix)- Verifiable label reward in
<answer>tags - Base model:
unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit
- Downloads last month
- 13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for yashcse21/financial-sentiment-drgrpo-lora
Base model
Qwen/Qwen2.5-0.5B Finetuned
Qwen/Qwen2.5-0.5B-Instruct Quantized
unsloth/Qwen2.5-0.5B-Instruct-bnb-4bit