Research Engineering & Debugging7 / 8
Research Engineering & Debugging
Build a toy post-training stack with intentional bugs, then write tests that catch every one.
seq_logprob(model, ids, prompt_len, mask_bug=False)Implement the function/class skeleton in the editor. Any correct approach is accepted.
import os, torch, torch.nn.functional as F
def seq_logprob(model, ids, prompt_len, mask_bug=False):
raise NotImplementedError
def dpo_loss(policy, ref, chosen, rejected, prompt_len, beta=0.1):
raise NotImplementedError⌘/Ctrl↵to submit
No review yet
Submit your solution for a verdict, a score out of 100 and concrete feedback. Any correct approach passes.
Research Engineering & Debugging
Build a toy post-training stack with intentional bugs, then write tests that catch every one.
seq_logprob(model, ids, prompt_len, mask_bug=False)Implement the function/class skeleton in the editor. Any correct approach is accepted.