2.2 KiB
Welcome to EvalScope Tutorial!
Getting Started Guide
To help users get started quickly, we recommend the following process:
- For users who want to use EvalScope, we recommend reading the Quick Start section first to set up the environment and launch a mini experiment to familiarize yourself with the process.
- For basic usage, we suggest users read the Tutorial section, including How to Use Arena Mode for Evaluation, How to Use Other Evaluation Backends, and How to Use Model Service Stress Testing Tool.
- If you want to customize more modules, such as adding datasets and models, we provide Advanced Tutorials.
- In addition, we provide Third-party Tools to help users quickly evaluate models, such as using ToolBench for evaluation.
- Finally, we provide Best Practices to help users conduct evaluations, such as how to use Swift for evaluation.
We always welcome users' PRs and Issues to improve EvalScope.
:::{toctree} :hidden: :caption: 🚀 Quick Start
get_started/introduction.md get_started/installation.md get_started/basic_usage.md get_started/visualization.md get_started/parameters.md get_started/supported_dataset/index.md get_started/faq.md :::
:::{toctree} :hidden: :caption: 🔧 Tutorials user_guides/backend/index.md user_guides/stress_test/index.md user_guides/aigc/index.md user_guides/arena.md user_guides/sandbox.md user_guides/agent/index.md user_guides/service.md :::
:::{toctree} :hidden: :caption: 🛠️ Advanced Tutorials advanced_guides/collection/index.md advanced_guides/custom_dataset/index.md advanced_guides/custom_model.md advanced_guides/add_benchmark.md advanced_guides/sandbox.md :::
:::{toctree} :hidden: :caption: 🧰 Extended Benchmarks
third_party/index.md :::
:::{toctree} :hidden: :caption: 📖 Best Practices
best_practice/index.md :::
:::{toctree} :hidden: :caption: 🧪 Benchmark Results experiments/benchmark/index.md experiments/speed_benchmark/index.md :::
:::{toctree} :hidden: :caption: 🌟 Blog blog/index.md :::