mzio/tw-sft-treasure-hunter-medium-hi
收藏资源简介:
--- dataset_info: features: - name: state list: - name: content dtype: string - name: role dtype: string - name: action struct: - name: content dtype: string - name: role dtype: string - name: next_obs list: - name: content dtype: string - name: role dtype: string - name: done dtype: bool - name: reward dtype: float64 - name: is_train dtype: bool - name: tools list: - name: description dtype: string - name: name dtype: string - name: parameters struct: - name: properties struct: - name: container struct: - name: description dtype: string - name: type dtype: string - name: direction struct: - name: description dtype: string - name: enum list: string - name: type dtype: string - name: item struct: - name: description dtype: string - name: type dtype: string - name: key struct: - name: description dtype: string - name: type dtype: string - name: source struct: - name: description dtype: string - name: type dtype: string - name: supporter struct: - name: description dtype: string - name: type dtype: string - name: target struct: - name: description dtype: string - name: type dtype: string - name: required list: string - name: type dtype: string - name: type dtype: string - name: system_prompt dtype: string - name: unique_data_sample_id dtype: int64 - name: timestep dtype: int64 - name: generation_id dtype: int64 - name: return_ dtype: float64 - name: advantage dtype: float64 - name: split dtype: string splits: - name: train num_bytes: 2011447 num_examples: 244 download_size: 1687239 dataset_size: 2011447 configs: - config_name: default data_files: - split: train path: data/train-* ---



