rilixai/20260401_purchase_order_sft-20260331_sft_dataset_fixed

--- dataset_info: features: - name: messages list: - name: role dtype: string - name: content list: json - name: extraction_record_id dtype: string - name: thread_id dtype: string - name: message_id dtype: string - name: unique_order_identifier dtype: string - name: gold_candidate_ids struct: - name: customer_id dtype: string - name: carrier_code dtype: string - name: items list: string - name: facility dtype: string - name: task_type dtype: string - name: injected_candidates dtype: string splits: - name: train num_bytes: 8021321654 num_examples: 4731 - name: eval num_bytes: 180015035 num_examples: 249 download_size: 8200657248 dataset_size: 8201336689 configs: - config_name: default data_files: - split: train path: data/train-* - split: eval path: data/eval-* ---