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

Embedder Service v0 with FlashBert #385

Open
wants to merge 18 commits into
base: main
Choose a base branch
from
Open

Conversation

magdyksaleh
Copy link
Collaborator

No description provided.

@magdyksaleh
Copy link
Collaborator Author

curl 127.0.0.1:8080/embed
-X POST
-d '{
"inputs": "[INST] Natalia sold clips to 48 of her friends in April, and then she sold half as many clips in May. How many clips did Natalia sell altogether in April and May? [/INST]"
}'
-H 'Content-Type: application/json'

;)

@magdyksaleh magdyksaleh changed the title [WIP] Embedder Service Inner Embedder Service v0 with FlashBert Apr 12, 2024
@magdyksaleh magdyksaleh marked this pull request as ready for review April 12, 2024 19:43
Copy link
Contributor

@tgaddair tgaddair left a comment

Choose a reason for hiding this comment

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

Looks great! Couple minor questions.


class EmbedResponse(BaseModel):
# Embeddings
embeddings: Optional[List[float]]
Copy link
Contributor

Choose a reason for hiding this comment

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

Is this optional for embedding responses, or required?

server/lorax_server/models/__init__.py Outdated Show resolved Hide resolved
server/lorax_server/models/types.py Outdated Show resolved Hide resolved
@@ -86,6 +86,10 @@ def info(self) -> InfoResponse:
@property
def sliding_window_blocks(self) -> Optional[int]:
return None

@property
def supports_embeddings(self) -> bool:
Copy link
Contributor

Choose a reason for hiding this comment

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

Conversely, what happens when someone tries to use the BERT model for text generation?

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

2 participants