ysramen

finance-rl-investigation-v1-grpo

ysramen/finance-rl-investigation-v1-grpo

finance-rl-investigation-v1-grpo is a reinforcement learning model from ysramen. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.

Qwen3-8B checkpoint for a finance tool-calling agent trained with SFT plus GRPO repair on investigation and true multi-turn finance tasks.