five

carbonteq/rg-knights_knaves-instruct-100k

收藏
Hugging Face2026-04-20 更新2026-04-26 收录
下载链接:
https://hf-mirror.com/datasets/carbonteq/rg-knights_knaves-instruct-100k
下载链接
链接失效反馈
官方服务:
资源简介:
--- license: mit pretty_name: RLVR (verl) dataset --- # RLVR generated dataset Procedural rows from [reasoning-gym](https://github.com/open-thought/reasoning-gym), formatted for [verl](https://github.com/verl-project/verl) GRPO. ## Build metadata ```json { "config": "/home/owais/Projects/rlvr/rlvr/configs/datasets/knights_knaves-instruct.yaml", "template_type": "qwen-instruct", "developer_prompt": null, "data_source": "reasoning_gym", "default_extract": "answer_tag", "train_rows": 100000, "test_rows": 4096, "train_seed": 42, "test_seed": 43, "tasks": { "knights_knaves": { "weight": 1, "config": { "n_people": 4, "depth_constraint": 3, "width_constraint": 3 } } }, "reasoning_gym_version": "0.1.19" } ```
提供机构:
carbonteq
二维码
社区交流群
二维码
科研交流群
商业服务