Ujjwal Karn
Ujjwal Karn
Hi, we leverage the human preference data from Anthropic to collect the prompts. At this point, we are unable to share the dataset that was used, but more details about...
Hi, if you're looking for Llama Guard evaluation, Llama recipes has a [script for running inference](https://github.com/meta-llama/llama-recipes/blob/main/recipes/responsible_ai/llama_guard/inference.py). We then use sklearn's precision_score, recall_score, f1_score, average_precision_score to compute the metrics. Is this...
Could you check if the solutions in #394 or #593 help?
cc: @osanseviero in case you can help here.
@samhforbes sure I can take this up!
@groklab @Jiang22s @Snigdha08 @ziyue-101 would you be willing to review this submission to JOSS? We carry out our checklist-driven reviews here in GitHub issues and follow these guidelines: [https://joss.readthedocs.io/en/latest/review_criteria.htm](https://joss.readthedocs.io/en/latest/review_criteria.html)