You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The paper mentions using several datasets, including MT-bench, HumanEval, GSM8K, and Alpaca, to test Eagle’s speedup effect. Would it be possible to provide the specific paths to the complete datasets? I noticed that the eagle/data directory contains several datasets, but most of them have only about 80 samples. Was the speedup effect in the paper tested using only these subsets, or were the full datasets used as well? Thank you!
The text was updated successfully, but these errors were encountered:
The paper mentions using several datasets, including MT-bench, HumanEval, GSM8K, and Alpaca, to test Eagle’s speedup effect. Would it be possible to provide the specific paths to the complete datasets? I noticed that the eagle/data directory contains several datasets, but most of them have only about 80 samples. Was the speedup effect in the paper tested using only these subsets, or were the full datasets used as well? Thank you!
The text was updated successfully, but these errors were encountered: