SafeAILab
Is there a script to calculate the average acceptance length?
Hi, thanks for you great work! When I used the EAGLE-llama2-chat-7B you provided for testing, the average acceptance length I measured was lower than the value in the paper. The way I obtained it was to get all the accept_lengths and divide them by the total number of inferences, and finally add 1, which is the token of the last sample of the large model.
You may refer to the link below.
https://github.com/SafeAILab/EAGLE/issues/153#issuecomment-2454707075
Hi, thanks for you great work! When I used the EAGLE-llama2-chat-7B you provided for testing, the average acceptance length I measured was lower than the value in the paper. The way I obtained it was to get all the accept_lengths and divide them by the total number of inferences, and finally add 1, which is the token of the last sample of the large model.
@Lyn-Lucy My approach is the same as yours, and indeed it is on the low side.
