Skip to content

Fixes minor typos on keras_hub/getting_started.py #2027

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

Merged
merged 1 commit into from
Jan 13, 2025
Merged

Fixes minor typos on keras_hub/getting_started.py #2027

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
6 changes: 3 additions & 3 deletions guides/keras_hub/getting_started.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,8 +272,8 @@
tokens vary per model and can be hard to track, the [Kaggle model
page](https://www.kaggle.com/models/keras/gemma2/) will contain details such as this.

`CausalLM` come with an extra function called `generate()` which can be used generate
predict tokens in a loop and decode them as a string.
`CausalLM` comes with an extra function called `generate()` which can be used generate
predicted tokens in a loop and decode them as a string.
"""

template = "<start_of_turn>user\n{question}<end_of_turn>\n<start_of_turn>model"
Expand All @@ -285,7 +285,7 @@
"""
Note that on the Jax and TensorFlow backends, this `generate()` function is compiled, so
the second time you call for the same `max_length`, it will actually be much faster.
KerasHub will use Jax an TensorFlow to compute an optimized version of the generation
KerasHub will use Jax and TensorFlow to compute an optimized version of the generation
computational graph that can be reused.
"""

Expand Down
Loading