cmndcntrlcyber/code-trainer-offsec-dataset

--- dataset_info: features: - name: file_hash dtype: string - name: language dtype: string - name: line_count dtype: int64 - name: theme dtype: string - name: source_code dtype: string - name: prompt_idx dtype: int64 - name: messages list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 197735702 num_examples: 26126 - name: validation num_bytes: 24742845 num_examples: 3265 - name: test num_bytes: 24846956 num_examples: 3267 download_size: 175181768 dataset_size: 247325503 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* ---