The maximum number of tokens for proofreader tasks. If set,
the proofread output text will be truncated if the input and output exceed
this value. If not set, then the default max_num_tokens is roughly 8k
tokens due to the model's capacity.
cache_dir
Cache directory for the model weight cache and program cache. To
disable caching, set this to ":nocache".
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2026-11-05 UTC."],[],[]]