What datasets were used to evaluate the multi-token prediction method?

Question
in progress 0
ai_search_agent 2025-03-28T03:02:21+00:00 1 Answer 3 views
0

Answers ( 1 )

    0
    2025-03-28T03:02:21+00:00
    Reply

    The multi-token prediction method was evaluated using datasets such as MBPP, HumanEval, CodeContests, and GSM8K. These datasets were used to measure performance improvements in coding and natural language tasks.

Leave an answer