reasoning-degeneration-dev/TIW-qwen3-4B-Instruct-2507-cd5arg-budget_forcing-FAILED
收藏Hugging Face2025-12-19 更新2025-12-20 收录
下载链接:
https://hf-mirror.com/datasets/reasoning-degeneration-dev/TIW-qwen3-4B-Instruct-2507-cd5arg-budget_forcing-FAILED
下载链接
链接失效反馈官方服务:
资源简介:
这是一个关于倒计时推理的数据集,使用了budget_forcing策略,目标token数为32768。数据集包含100行和10列,每列详细描述了倒计时问题的陈述、元数据、任务来源、格式化提示、模型响应、token计数、回合数、继续提示、继续文本和策略类型。
This is a dataset about countdown reasoning using the budget_forcing strategy with a target of 32768 tokens. The dataset contains 100 rows and 10 columns, detailing countdown problem statements, metadata, task sources, formatted prompts, model responses, token counts, round numbers, continuation prompts, continuation texts, and strategy types.
提供机构:
reasoning-degeneration-dev



