/opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Primary LanguagePythonApache License 2.0Apache-2.0




🌐Website | 📖CompassHub | 📊CompassRank | 📘Documentation | 🛠️Installation | 🤔Reporting Issues

English | 简体中文

👋 join us on Discord and WeChat

Important

Star Us, You will receive all release notifications from GitHub without any delay ~ ⭐️

📣 OpenCompass 2.0

We are thrilled to introduce OpenCompass 2.0, an advanced suite featuring three key components: CompassKit, CompassHub, and CompassRank. oc20

CompassRank has been significantly enhanced into the leaderboards that now incorporates both open-source benchmarks and proprietary benchmarks. This upgrade allows for a more comprehensive evaluation of models across the industry.

CompassHub presents a pioneering benchmark browser interface, designed to simplify and expedite the exploration and utilization of an extensive array of benchmarks for researchers and practitioners alike. To enhance the visibility of your own benchmark within the community, we warmly invite you to contribute it to CompassHub. You may initiate the submission process by clicking here.

CompassKit is a powerful collection of evaluation toolkits specifically tailored for Large Language Models and Large Vision-language Models. It provides an extensive set of tools to assess and measure the performance of these complex models effectively. Welcome to try our toolkits for in your research and products.

Star History

🧭 Welcome

to OpenCompass!

Just like a compass guides us on our journey, OpenCompass will guide you through the complex landscape of evaluating large language models. With its powerful algorithms and intuitive interface, OpenCompass makes it easy to assess the quality and effectiveness of your NLP models.

🚩🚩🚩 Explore opportunities at OpenCompass! We're currently hiring full-time researchers/engineers and interns. If you're passionate about LLM and OpenCompass, don't hesitate to reach out to us via email. We'd love to hear from you!

🔥🔥🔥 We are delighted to announce that the OpenCompass has been recommended by the Meta AI, click Get Started of Llama for more information.

Attention
We launch the OpenCompass Collaboration project, welcome to support diverse evaluation benchmarks into OpenCompass! Clike Issue for more information. Let's work together to build a more powerful OpenCompass toolkit!

🚀 What's New

  • [2024.04.26] We deprecated the multi-madality evaluating function from OpenCompass, related implement has moved to VLMEvalKit, welcome to use! 🔥🔥🔥.
  • [2024.04.26] We supported the evaluation of ArenaHard welcome to try!🔥🔥🔥.
  • [2024.04.22] We supported the evaluation of LLaMA3LLaMA3-Instruct, welcome to try! 🔥🔥🔥
  • [2024.02.29] We supported the MT-Bench, AlpacalEval and AlignBench, more information can be found here
  • [2024.01.30] We release OpenCompass 2.0. Click CompassKit, CompassHub, and CompassRank for more information !

More

✨ Introduction

image

OpenCompass is a one-stop platform for large model evaluation, aiming to provide a fair, open, and reproducible benchmark for large model evaluation. Its main features include:

  • Comprehensive support for models and datasets: Pre-support for 20+ HuggingFace and API models, a model evaluation scheme of 70+ datasets with about 400,000 questions, comprehensively evaluating the capabilities of the models in five dimensions.

  • Efficient distributed evaluation: One line command to implement task division and distributed evaluation, completing the full evaluation of billion-scale models in just a few hours.

  • Diversified evaluation paradigms: Support for zero-shot, few-shot, and chain-of-thought evaluations, combined with standard or dialogue-type prompt templates, to easily stimulate the maximum performance of various models.

  • Modular design with high extensibility: Want to add new models or datasets, customize an advanced task division strategy, or even support a new cluster management system? Everything about OpenCompass can be easily expanded!

  • Experiment management and reporting mechanism: Use config files to fully record each experiment, and support real-time reporting of results.

📊 Leaderboard

We provide OpenCompass Leaderboard for the community to rank all public models and API models. If you would like to join the evaluation, please provide the model repository URL or a standard API interface to the email address opencompass@pjlab.org.cn.

🔝Back to top

🛠️ Installation

Below are the steps for quick installation and datasets preparation.

💻 Environment Setup

Open-source Models with GPU

conda create --name opencompass python=3.10 pytorch torchvision pytorch-cuda -c nvidia -c pytorch -y
conda activate opencompass
git clone https://github.com/open-compass/opencompass opencompass
cd opencompass
pip install -e .

API Models with CPU-only

conda create -n opencompass python=3.10 pytorch torchvision torchaudio cpuonly -c pytorch -y
conda activate opencompass
git clone https://github.com/open-compass/opencompass opencompass
cd opencompass
pip install -e .
# also please install requiresments packages via `pip install -r requirements/api.txt` for API models if needed.

📂 Data Preparation

# Download dataset to data/ folder
wget https://github.com/open-compass/opencompass/releases/download/0.2.2.rc1/OpenCompassData-core-20240207.zip
unzip OpenCompassData-core-20240207.zip

Some third-party features, like Humaneval and Llama, may require additional steps to work properly, for detailed steps please refer to the Installation Guide.

🔝Back to top

🏗️ ️Evaluation

After ensuring that OpenCompass is installed correctly according to the above steps and the datasets are prepared, you can evaluate the performance of the LLaMA-7b model on the MMLU and C-Eval datasets using the following command:

python run.py --models hf_llama_7b --datasets mmlu_ppl ceval_ppl

OpenCompass has predefined configurations for many models and datasets. You can list all available model and dataset configurations using the tools.

# List all configurations
python tools/list_configs.py
# List all configurations related to llama and mmlu
python tools/list_configs.py llama mmlu

You can also evaluate other HuggingFace models via command line. Taking LLaMA-7b as an example:

python run.py --datasets ceval_ppl mmlu_ppl \
--hf-path huggyllama/llama-7b \  # HuggingFace model path
--model-kwargs device_map='auto' \  # Arguments for model construction
--tokenizer-kwargs padding_side='left' truncation='left' use_fast=False \  # Arguments for tokenizer construction
--max-out-len 100 \  # Maximum number of tokens generated
--max-seq-len 2048 \  # Maximum sequence length the model can accept
--batch-size 8 \  # Batch size
--no-batch-padding \  # Don't enable batch padding, infer through for loop to avoid performance loss
--num-gpus 1  # Number of minimum required GPUs

Note
To run the command above, you will need to remove the comments starting from # first.

Through the command line or configuration files, OpenCompass also supports evaluating APIs or custom models, as well as more diversified evaluation strategies. Please read the Quick Start to learn how to run an evaluation task.

🔝Back to top

📖 Dataset Support

Language Knowledge Reasoning Examination
Word Definition
  • WiC
  • SummEdits
Idiom Learning
  • CHID
Semantic Similarity
  • AFQMC
  • BUSTM
Coreference Resolution
  • CLUEWSC
  • WSC
  • WinoGrande
Translation
  • Flores
  • IWSLT2017
Multi-language Question Answering
  • TyDi-QA
  • XCOPA
Multi-language Summary
  • XLSum
Knowledge Question Answering
  • BoolQ
  • CommonSenseQA
  • NaturalQuestions
  • TriviaQA
Textual Entailment
  • CMNLI
  • OCNLI
  • OCNLI_FC
  • AX-b
  • AX-g
  • CB
  • RTE
  • ANLI
Commonsense Reasoning
  • StoryCloze
  • COPA
  • ReCoRD
  • HellaSwag
  • PIQA
  • SIQA
Mathematical Reasoning
  • MATH
  • GSM8K
Theorem Application
  • TheoremQA
  • StrategyQA
  • SciBench
Comprehensive Reasoning
  • BBH
Junior High, High School, University, Professional Examinations
  • C-Eval
  • AGIEval
  • MMLU
  • GAOKAO-Bench
  • CMMLU
  • ARC
  • Xiezhi
Medical Examinations
  • CMB
Understanding Long Context Safety Code
Reading Comprehension
  • C3
  • CMRC
  • DRCD
  • MultiRC
  • RACE
  • DROP
  • OpenBookQA
  • SQuAD2.0
Content Summary
  • CSL
  • LCSTS
  • XSum
  • SummScreen
Content Analysis
  • EPRSTMT
  • LAMBADA
  • TNEWS
Long Context Understanding
  • LEval
  • LongBench
  • GovReports
  • NarrativeQA
  • Qasper
Safety
  • CivilComments
  • CrowsPairs
  • CValues
  • JigsawMultilingual
  • TruthfulQA
Robustness
  • AdvGLUE
Code
  • HumanEval
  • HumanEvalX
  • MBPP
  • APPs
  • DS1000

📖 Model Support

Open-source Models API Models
  • OpenAI
  • Gemini
  • Claude
  • ZhipuAI(ChatGLM)
  • Baichuan
  • ByteDance(YunQue)
  • Huawei(PanGu)
  • 360
  • Baidu(ERNIEBot)
  • MiniMax(ABAB-Chat)
  • SenseTime(nova)
  • Xunfei(Spark)
  • ……

🔝Back to top

🔜 Roadmap

  • Subjective Evaluation
    • Release CompassAreana
    • Subjective evaluation.
  • Long-context
    • Long-context evaluation with extensive datasets.
    • Long-context leaderboard.
  • Coding
    • Coding evaluation leaderboard.
    • Non-python language evaluation service.
  • Agent
    • Support various agenet framework.
    • Evaluation of tool use of the LLMs.
  • Robustness
    • Support various attack method

👷‍♂️ Contributing

We appreciate all contributions to improving OpenCompass. Please refer to the contributing guideline for the best practice.




🤝 Acknowledgements

Some code in this project is cited and modified from OpenICL.

Some datasets and prompt implementations are modified from chain-of-thought-hub and instruct-eval.

🖊️ Citation

@misc{2023opencompass,
    title={OpenCompass: A Universal Evaluation Platform for Foundation Models},
    author={OpenCompass Contributors},
    howpublished = {\url{https://github.com/open-compass/opencompass}},
    year={2023}
}

🔝Back to top