Ujjwal Karn

Results 6 comments of 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...

@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)