ZachW/gpt-oss-20b_storygen-prompts-200

该数据集名为openai/gpt-oss-20b on storygen-prompts-200，是来自微创造力推理套件的模型输出。使用的模型是openai/gpt-oss-20b，数据集是storygen-prompts-200，包含200个项目。数据集属于ZachW/llm-creativity-benchmarks集合的一部分，主要用于文本生成任务。数据集包含多个列，如task_id（唯一任务标识符）、input（发送给模型的精确提示）、raw_output（完整的模型输出字符串）、thinking_content（提取的思维链/思维块）、final_answer（去除思维后的最终答案）、finish_reason（完成原因）、prompt_tokens（提示中的令牌数）、completion_tokens（生成的令牌数）、temperature（采样温度）和max_tokens（令牌生成限制）。This dataset, named openai/gpt-oss-20b on storygen-prompts-200, consists of model outputs from the micro-creativity inference suite. The model used is openai/gpt-oss-20b, and the dataset is storygen-prompts-200, containing 200 items. It is part of the ZachW/llm-creativity-benchmarks collection and is primarily used for text-generation tasks. The dataset includes multiple columns such as task_id (unique task identifier), input (the exact prompt sent to the model), raw_output (full model output string), thinking_content (extracted chain-of-thought/thinking block), final_answer (extracted final answer after thinking is removed), finish_reason (completion reason), prompt_tokens (number of tokens in the prompt), completion_tokens (number of tokens generated), temperature (sampling temperature used), and max_tokens (token generation limit).