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
In Figure 5 of the technical report (which illustrates the length extrapolation capability of Qwen2-VL-72B on Video-MME Medium Video), the inference sequence length is scaled into 80K. However, the max_position_embeddings in the config is only 32768.
Could the authors share with us how did the length extrapolation perform?
The text was updated successfully, but these errors were encountered:
In Figure 5 of the technical report (which illustrates the length extrapolation capability of Qwen2-VL-72B on Video-MME Medium Video), the inference sequence length is scaled into
80K
. However, themax_position_embeddings
in the config is only32768
.Could the authors share with us how did the length extrapolation perform?
The text was updated successfully, but these errors were encountered: