From ec9fc38340280b0750f9896d8ba33aee479452e6 Mon Sep 17 00:00:00 2001 From: Prannaya Date: Sat, 3 Aug 2024 23:45:36 +0800 Subject: [PATCH] fix(mkdocs): remove templates page + bold links --- docs/quickstart/auto-red-teaming.md | 5 ++++- docs/quickstart/index.md | 12 ++++++------ mkdocs.yml | 1 - 3 files changed, 10 insertions(+), 8 deletions(-) diff --git a/docs/quickstart/auto-red-teaming.md b/docs/quickstart/auto-red-teaming.md index 79fde4b..a6f0f40 100644 --- a/docs/quickstart/auto-red-teaming.md +++ b/docs/quickstart/auto-red-teaming.md @@ -1,3 +1,6 @@ +--- +hide: '["toc"]' +--- # Automated Red-Teaming - +Automated Red-Teaming allows users to automatically diff --git a/docs/quickstart/index.md b/docs/quickstart/index.md index 405200e..e84cc94 100644 --- a/docs/quickstart/index.md +++ b/docs/quickstart/index.md @@ -13,7 +13,7 @@ WalledEval can serve **four** major functions, namely the following: You plug and play your own datasets, LLMs and safety judges and easily get results with limited overhead! - [:octicons-arrow-right-24: Prompt Benchmarking](prompts.md) + [**:octicons-arrow-right-24: Prompt Benchmarking**](prompts.md) - :material-book-check-outline:{ .lg .middle } __LLM Knowledge__ @@ -21,7 +21,7 @@ WalledEval can serve **four** major functions, namely the following: You can design your own MCQ quizzes on LLMs and test their accuracy on answering such questions immediately with our MCQ pipeline! - [:octicons-arrow-right-24: MCQ Benchmarking](mcq.md) + [**:octicons-arrow-right-24: MCQ Benchmarking**](mcq.md) - :material-gavel:{ .lg .middle } __Safety Judge Effectiveness__ @@ -29,15 +29,15 @@ WalledEval can serve **four** major functions, namely the following: You can easily get messy with testing judges using our framework! - [:octicons-arrow-right-24: Judge Benchmarking](judges.md) + [**:octicons-arrow-right-24: Judge Benchmarking**](judges.md) -- :material-library:{ .lg .middle } __Extensive Prompt Template Database__ + - :material-emoticon-devil-outline:{ .lg .middle } __Automated Red-Teaming__ @@ -45,6 +45,6 @@ WalledEval can serve **four** major functions, namely the following: If you think that's all, you're mistaken! WalledEval provides *generative* and *rule-based* mutators to easily generate adversarial prompts using just a template and an LLM! - [:octicons-arrow-right-24: AUtomated Red-Teaming](auto-red-teaming.md) + [**:octicons-arrow-right-24: Automated Red-Teaming**](auto-red-teaming.md) \ No newline at end of file diff --git a/mkdocs.yml b/mkdocs.yml index dbf07b1..760a7e0 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -109,7 +109,6 @@ nav: - "Prompt Benchmarking": quickstart/prompts.md - "MCQ Benchmarking": quickstart/mcq.md - "Judge Benchmarking": quickstart/judges.md - - "Prompt Template Database": quickstart/templates.md - "Automated Red Teaming": quickstart/auto-red-teaming.md - Components: - Dataset: components/dataset.md