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

Fix samplers documentation #980

Merged
merged 2 commits into from
Jun 18, 2024
Merged

Fix samplers documentation #980

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a869f7f
Fix for samplers isinstance oddity in the generate api
jrinder42 Jun 16, 2024
ce93c8c
modified greedy variable in docs to show correct usage
jrinder42 Jun 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
4 changes: 2 additions & 2 deletions docs/cookbook/classification.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ Outlines provides a shortcut to do multi-label classification, using the `outlin
```python
from outlines.samplers import greedy

generator = outlines.generate.choice(model, ["URGENT", "STANDARD"], sampler=greedy)
generator = outlines.generate.choice(model, ["URGENT", "STANDARD"], sampler=greedy())
```
Outlines supports batched requests, so we will pass two requests to the model:

Expand Down Expand Up @@ -96,7 +96,7 @@ class Classification(BaseModel):
and we can use `generate.json` by passing this Pydantic model we just defined, and call the generator:

```python
generator = outlines.generate.json(model, Classification, sampler=greedy)
generator = outlines.generate.json(model, Classification, sampler=greedy())
labels = generator(prompts)
print(labels)
# [Classification(label=<Label.urgent: 'URGENT'>), Classification(label=<Label.standard: 'STANDARD'>)]
Expand Down