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.

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

Add conversational serving #165

Merged
merged 1 commit into from
Feb 24, 2023
Merged

Add conversational serving #165

merged 1 commit into from
Feb 24, 2023

Conversation

jonatanklosko
Copy link
Member

@jonatanklosko jonatanklosko commented Feb 24, 2023

image

@seanmor5
Copy link
Contributor

I'm not sure, but I think I'm gonna go to sleep

I felt that

Each call to serving returns the conversation history, which can be
fed into the next run to maintain the context.

Note that either `:max_new_tokens` or `:max_length` must be specified.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think max_length is missing from the options below?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's intentional, we do say "Also accepts all the other options of Bumblebee.Text.Generation.build_generate/3" and both :max_new_tokens and :max_length are there. I think :max_new_tokens is common enough that it makes sense to list it here, but it should be preferred over :max_length, and so I didn't include both.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants