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
I wonder if the position id of query is the same with key or is the actual generated context length (this comment is confusing me)?
For example, as mentioned in the toy example, the position id for key of M is 9. What's the position id for q of M? 9 or 12 here? And more , why make this choice?
Looking forward to your response. Thank you.
The text was updated successfully, but these errors were encountered:
We also apply position in the cache to query instead of the position in the actual text. In the toy example, the position ID for the query is also 9. This is because we want to limit position encoding used within the cache size so we can generate text much longer than the pre-training window.
@Guangxuan-Xiao, thanks for replying here. However, the code seems to be different here. I see that query_states is encoded with position_ids while key_states is encoded with key_position_ids, which is the position in cache. Could you please elaborate more? Thank you!
Hello,
I wonder if the position id of query is the same with key or is the actual generated context length (this comment is confusing me)?
For example, as mentioned in the toy example, the position id for key of M is 9. What's the position id for q of M? 9 or 12 here? And more , why make this choice?
Looking forward to your response. Thank you.
The text was updated successfully, but these errors were encountered: