togethercomputer / OpenChatKit

Apache License 2.0
9.01k stars 1.01k forks source link

LOST in the MIDDLE #164

Open eyuansu62 opened 1 year ago

eyuansu62 commented 1 year ago

hi, i'm curious about the experiment that togetherAI reproduced of paper: LOST in the MIDDLE. It seems that llama-2 and llama2-32K does not have the "U-shape performance" in the long-context QA. Did togetherAI use the same setting with LOST in the MIDDLE?