meta-llama / PurpleLlama

Set of tools to assess and improve LLM security.

meta-llama/PurpleLlama Issues

Precision/Recall Curves
Updated a month ago
CYBERSECEVAL 2: Cannot reproduce Table 1's example with `Llama-3-8B-Instruct`
Updated 2 months ago2
False refusal detection in CyberSecEval
Closed 2 months ago2
meta-llama / LlamaGuard-7b inference speed
Closed 2 months ago1
Fine tuning for additional policies LlamaGuard
Closed 2 months ago1
llama-guard eval scripts
Closed 2 months ago1
Will the dataset be released?
Closed 2 months ago4
Evaluation script released?
Closed 2 months ago3
./download.sh: 13: Bad substitution
Closed 2 months ago1
got error to run download.sh download.sh: line 1: payload:allShortcutsEnabled:false: command not found
Closed 2 months ago1
Problem when evaluation with Expansion LLM and Judge LLM for CyberSecEval
Closed 2 months ago1
ImportError: attempted relative import with no known parent package
Closed 3 months ago1
ImportError: attempted relative import with no known parent package
Closed 3 months ago1
Llama-guard does not resepect custom Taxonomy
Updated 3 months ago4
Release few-shot prompting code example
Updated 3 months ago
Issues with the Dataset in Cyberbenchmark
Closed 3 months ago4
Question about the dataset in CyberSecurity benchmark
Closed 5 months ago6