intuit/foresight-rl-core: a config-driven library for reinforcement-learning fine-tuning; one YAML file trains with GRPO, DPO, or SFT on local GPU, SageMaker, or HyperPod, and runs evaluation, optimization, and load tests

Original headline: "intuit/foresight-rl-core: A config-driven library for reinforcement-learning fine-tuning. One YAML file trains with GRPO, DPO, or SFT on a local GPU, SageMaker, or HyperPod, and runs evaluation, optimization, and load tests."