1. "My jobs on Talapas are crashing immediately, what's wrong??"
By default, users are assigned one core at a time, and a chunk of memory (~4GB RAM) associated with that core. For many applications, this may not be enough memory. To get around this, one can reserve more cores:
[user@ln1 ~]$ srun -n28 --pty bash
This will reserve all 28 cores on a basic node, which should suffice for most applications. Alternatively, if you just want to reserve more memory, do:
[user@ln1 ~]$ srun --mem=50G --pty bash
This will reserve 1 core but 32GB RAM on a node. It may be useful to try reserving a full node and determine how much RAM is needed for your application, then future jobs can be adjusted accordingly.