-
### Filter Mode
Auto-Smart Mode
### Select the Problem
A type of spammer is not detected at all
### (Optional) If 'Other', Enter Very Short Description
_No response_
### Spammer Example / Sample…
-
Cohere only allows up to num_outputs=5. See if numbers change drastically.
Are we able to even run RealToxicityPrompts on Cohere because of https://docs.cohere.ai/usage-guidelines/?
-
Hi! I try to generate continuations with DExperts using the following scrpit.
```bash
OUTPUT_DIR=output/toxicity/dexperts
PROMPTS_DATASET=prompts/nontoxic_prompts-10k.jsonl
MODEL_DIR=models/exper…
-
I'll be using Google's Perspective API to improve the chat/username filtering. Any score greater than 70% will be blocked. We can fine-tune the percentage later if needed.
[Perspective API](https:/…
-
https://github.com/stanford-crfm/benchmarking#perspective-api
-
https://developers.perspectiveapi.com/s/
gigxz updated
2 years ago
-
**Describe the bug**
```
from perspective import PerspectiveAPI
p = Perspective("API_KEY")
result = p.score("This is a comment")
print("Toxicity score: " + result["TOXICITY"])
```
In this code …
-
**Feature Request**
As part of the Kindly project (see [2-pager overview](https://docs.google.com/document/d/18DvrmiQEKhaPh80FHAPwkVyVlUj-81r_Rdks5ygTxRE/edit?usp=drive_web&ouid=106544392152177223836…
-
Need a few automated tests to ensure the API wrapper is still working with the API and getting the correct data back.
-
hi @favstats ,
In **Setup/Get an API key/step 2**, I'm getting an error with the Perspective API package.
If I use a google cloud project I have for something else as my active project, I get the…