Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Add missing word #40

Merged
merged 1 commit into from
Nov 19, 2024
Merged

Add missing word #40

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion crates/bpe/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,7 +243,7 @@ This type of algorithm is interesting for use cases where a certain token budget
This benchmark shows the runtime for the appending encoder when a text is encoded byte-by-byte.
For comparison we show the runtime of the backtracking encoder when it encodes the whole text at once.

The benchmark measured the runtime of encoding of slices of lengths 10, 100, 1000, and 10000 from a random 20000 token original using the o200k token set.
The benchmark measured the runtime of encoding of slices of lengths 10, 100, 1000, and 10000 from a random 20000 token original text using the o200k token set.

The graph below shows encoding runtime vs slice length.
The overall runtime of byte-by-byte incremental encoder for encoding the full text is comparable to the runtime of the backtracking encoder, with only a constant factor overhead.
Expand Down