zuxler/qwen2.5-1.5b-legal-grpo-reasoning

(Trained with Unsloth)

(Trained with Unsloth)

(Trained with Unsloth)

Unsloth Model Card

(Trained with Unsloth)

(Trained with Unsloth)

(Trained with Unsloth)

(Trained with Unsloth)

Unsloth Model Card

initial commit