Previous studies show that more than 85% of the peers have joined multiple torrents in BitTorrent, but theoretical work on multiple files BitTorrent downloading is rare. In this paper, we first consider the scenario of multi-torrent downloading. We present a fluid-model based analysis on the multi-torrent concurrent downloading scheme, which is implicitly adopted in practical applications, and quantitatively compare its performance with an alternative scheme of multi-torrent sequential downloading. We also consider the scenario of multi-file torrent downloading (e.g. multiple files shared within a single torrent), and find that the scheme of multi-file torrent concurrent downloading, which is explicitly engaged in practical applications, is inefficient. A new scheme named collaborative multi-file torrent sequential downloading is proposed, and we show via numerical analysis that the download performance could be improved by collaboration among the peers in different subtorrents. Finally, we propose a self-adaptive mechanism for practically deploying our multi-file torrent downloading scheme in a distributed fashion under situations when correlation among the files and majority peers? behaviors are unknown.