evalscope 0.5.2__py3-none-any.whl → 0.5.4__py3-none-any.whl

evalscope-0.5.4.dist-info/METADATA

@@ -0,0 +1,399 @@
+Metadata-Version: 2.1
+Name: evalscope
+Version: 0.5.4
+Summary: EvalScope: Lightweight LLMs Evaluation Framework
+Home-page: https://github.com/modelscope/evalscope
+Author: ModelScope team
+Author-email: contact@modelscope.cn
+Keywords: python,llm,evaluation
+Classifier: Development Status :: 4 - Beta
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.8
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+Requires-Dist: torch
+Requires-Dist: absl-py
+Requires-Dist: accelerate
+Requires-Dist: cachetools
+Requires-Dist: datasets (<3.0.0,>=2.18.0)
+Requires-Dist: editdistance
+Requires-Dist: jsonlines
+Requires-Dist: matplotlib
+Requires-Dist: modelscope[framework]
+Requires-Dist: nltk
+Requires-Dist: openai
+Requires-Dist: pandas
+Requires-Dist: plotly
+Requires-Dist: pyarrow
+Requires-Dist: pympler
+Requires-Dist: pyyaml
+Requires-Dist: regex
+Requires-Dist: requests
+Requires-Dist: requests-toolbelt
+Requires-Dist: rouge-score
+Requires-Dist: sacrebleu
+Requires-Dist: scikit-learn
+Requires-Dist: seaborn
+Requires-Dist: sentencepiece
+Requires-Dist: simple-ddl-parser
+Requires-Dist: tabulate
+Requires-Dist: tiktoken
+Requires-Dist: tqdm
+Requires-Dist: transformers (>=4.33)
+Requires-Dist: transformers-stream-generator
+Requires-Dist: jieba
+Requires-Dist: rouge-chinese
+Provides-Extra: all
+Requires-Dist: torch ; extra == 'all'
+Requires-Dist: absl-py ; extra == 'all'
+Requires-Dist: accelerate ; extra == 'all'
+Requires-Dist: cachetools ; extra == 'all'
+Requires-Dist: datasets (<3.0.0,>=2.18.0) ; extra == 'all'
+Requires-Dist: editdistance ; extra == 'all'
+Requires-Dist: jsonlines ; extra == 'all'
+Requires-Dist: matplotlib ; extra == 'all'
+Requires-Dist: modelscope[framework] ; extra == 'all'
+Requires-Dist: nltk ; extra == 'all'
+Requires-Dist: openai ; extra == 'all'
+Requires-Dist: pandas ; extra == 'all'
+Requires-Dist: plotly ; extra == 'all'
+Requires-Dist: pyarrow ; extra == 'all'
+Requires-Dist: pympler ; extra == 'all'
+Requires-Dist: pyyaml ; extra == 'all'
+Requires-Dist: regex ; extra == 'all'
+Requires-Dist: requests ; extra == 'all'
+Requires-Dist: requests-toolbelt ; extra == 'all'
+Requires-Dist: rouge-score ; extra == 'all'
+Requires-Dist: sacrebleu ; extra == 'all'
+Requires-Dist: scikit-learn ; extra == 'all'
+Requires-Dist: seaborn ; extra == 'all'
+Requires-Dist: sentencepiece ; extra == 'all'
+Requires-Dist: simple-ddl-parser ; extra == 'all'
+Requires-Dist: tabulate ; extra == 'all'
+Requires-Dist: tiktoken ; extra == 'all'
+Requires-Dist: tqdm ; extra == 'all'
+Requires-Dist: transformers (>=4.33) ; extra == 'all'
+Requires-Dist: transformers-stream-generator ; extra == 'all'
+Requires-Dist: jieba ; extra == 'all'
+Requires-Dist: rouge-chinese ; extra == 'all'
+Requires-Dist: ms-opencompass (>=0.1.0) ; extra == 'all'
+Requires-Dist: ms-vlmeval (>=0.0.5) ; extra == 'all'
+Provides-Extra: inner
+Requires-Dist: absl-py ; extra == 'inner'
+Requires-Dist: accelerate ; extra == 'inner'
+Requires-Dist: alibaba-itag-sdk ; extra == 'inner'
+Requires-Dist: dashscope ; extra == 'inner'
+Requires-Dist: editdistance ; extra == 'inner'
+Requires-Dist: jsonlines ; extra == 'inner'
+Requires-Dist: nltk ; extra == 'inner'
+Requires-Dist: openai ; extra == 'inner'
+Requires-Dist: pandas (==1.5.3) ; extra == 'inner'
+Requires-Dist: plotly ; extra == 'inner'
+Requires-Dist: pyarrow ; extra == 'inner'
+Requires-Dist: pyodps ; extra == 'inner'
+Requires-Dist: pyyaml ; extra == 'inner'
+Requires-Dist: regex ; extra == 'inner'
+Requires-Dist: requests (==2.28.1) ; extra == 'inner'
+Requires-Dist: requests-toolbelt (==0.10.1) ; extra == 'inner'
+Requires-Dist: rouge-score ; extra == 'inner'
+Requires-Dist: sacrebleu ; extra == 'inner'
+Requires-Dist: scikit-learn ; extra == 'inner'
+Requires-Dist: seaborn ; extra == 'inner'
+Requires-Dist: simple-ddl-parser ; extra == 'inner'
+Requires-Dist: streamlit ; extra == 'inner'
+Requires-Dist: tqdm ; extra == 'inner'
+Requires-Dist: transformers (<4.43,>=4.33) ; extra == 'inner'
+Requires-Dist: transformers-stream-generator ; extra == 'inner'
+Provides-Extra: opencompass
+Requires-Dist: ms-opencompass (>=0.1.0) ; extra == 'opencompass'
+Provides-Extra: vlmeval
+Requires-Dist: ms-vlmeval (>=0.0.5) ; extra == 'vlmeval'
+
+English | [简体中文](README_zh.md)
+
+
+![](docs/en/_static/images/evalscope_logo.png)
+
+<p align="center">
+<a href="https://badge.fury.io/py/evalscope"><img src="https://badge.fury.io/py/evalscope.svg" alt="PyPI version" height="18"></a>
+<a href="https://pypi.org/project/evalscope"><img alt="PyPI - Downloads" src="https://static.pepy.tech/badge/evalscope">
+</a>
+<a href='https://evalscope.readthedocs.io/en/latest/?badge=latest'>
+    <img src='https://readthedocs.org/projects/evalscope-en/badge/?version=latest' alt='Documentation Status' />
+</a>
+<br>
+ <a href="https://evalscope.readthedocs.io/en/latest/"><span style="font-size: 16px;">📖 Documents</span></a> &nbsp | &nbsp<a href="https://evalscope.readthedocs.io/zh-cn/latest/"><span style="font-size: 16px;"> 📖  中文文档</span></a>
+<p>
+
+
+## 📋 Table of Contents
+- [Introduction](#introduction)
+- [News](#News)
+- [Installation](#installation)
+- [Quick Start](#quick-start)
+- [Evaluation Backend](#evaluation-backend)
+- [Custom Dataset Evaluation](#custom-dataset-evaluation)
+- [Offline Evaluation](#offline-evaluation)
+- [Arena Mode](#arena-mode)
+- [Model Serving Performance Evaluation](#Model-Serving-Performance-Evaluation)
+- [Leaderboard](#leaderboard)
+
+## 📝 Introduction
+
+Large Model (including Large Language Models, Multi-modal Large Language Models) evaluation has become a critical process for assessing and improving LLMs. To better support the evaluation of large models, we propose the EvalScope framework.
+
+### Framework Features
+- **Benchmark Datasets**: Preloaded with several commonly used test benchmarks, including MMLU, CMMLU, C-Eval, GSM8K, ARC, HellaSwag, TruthfulQA, MATH, HumanEval, etc.
+- **Evaluation Metrics**: Implements various commonly used evaluation metrics.
+- **Model Access**: A unified model access mechanism that is compatible with the Generate and Chat interfaces of multiple model families.
+- **Automated Evaluation**: Includes automatic evaluation of objective questions and complex task evaluation using expert models.
+- **Evaluation Reports**: Automatically generates evaluation reports.
+- **Arena Mode**: Used for comparisons between models and objective evaluation of models, supporting various evaluation modes, including:
+  - **Single mode**: Scoring a single model.
+  - **Pairwise-baseline mode**: Comparing against a baseline model.
+  - **Pairwise (all) mode**: Pairwise comparison among all models.
+- **Visualization Tools**: Provides intuitive displays of evaluation results.
+- **Model Performance Evaluation**: Offers a performance testing tool for model inference services and detailed statistics, see [Model Performance Evaluation Documentation](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test.html).
+- **OpenCompass Integration**: Supports OpenCompass as the evaluation backend, providing advanced encapsulation and task simplification, allowing for easier task submission for evaluation.
+- **VLMEvalKit Integration**: Supports VLMEvalKit as the evaluation backend, facilitating the initiation of multi-modal evaluation tasks, supporting various multi-modal models and datasets.
+- **Full-Link Support**: Through seamless integration with the [ms-swift](https://github.com/modelscope/ms-swift) training framework, provides a one-stop development process for model training, model deployment, model evaluation, and report viewing, enhancing user development efficiency.
+
+
+<details><summary>Overall Architecture</summary>
+
+<p align="center">
+  <img src="docs/en/_static/images/evalscope_framework.png" width="70%">
+  <br>Fig 1. EvalScope Framework.
+</p>
+
+The architecture includes the following modules:
+1. **Model Adapter**: The model adapter is used to convert the outputs of specific models into the format required by the framework, supporting both API call models and locally run models.
+2. **Data Adapter**: The data adapter is responsible for converting and processing input data to meet various evaluation needs and formats.
+3. **Evaluation Backend**: 
+    - **Native**: EvalScope’s own **default evaluation framework**, supporting various evaluation modes, including single model evaluation, arena mode, baseline model comparison mode, etc.
+    - **OpenCompass**: Supports [OpenCompass](https://github.com/open-compass/opencompass) as the evaluation backend, providing advanced encapsulation and task simplification, allowing you to submit tasks for evaluation more easily.
+    - **VLMEvalKit**: Supports [VLMEvalKit](https://github.com/open-compass/VLMEvalKit) as the evaluation backend, enabling easy initiation of multi-modal evaluation tasks, supporting various multi-modal models and datasets.
+    - **ThirdParty**: Other third-party evaluation tasks, such as ToolBench.
+4. **Performance Evaluator**: Model performance evaluation, responsible for measuring model inference service performance, including performance testing, stress testing, performance report generation, and visualization.
+5. **Evaluation Report**: The final generated evaluation report summarizes the model's performance, which can be used for decision-making and further model optimization.
+6. **Visualization**: Visualization results help users intuitively understand evaluation results, facilitating analysis and comparison of different model performances.
+</details>
+
+
+## 🎉 News
+- 🔥 **[2024.09.18]** Our documentation has been updated to include a blog module, featuring some technical research and discussions related to evaluations. We invite you to [📖 read it](https://evalscope.readthedocs.io/en/refact_readme/blog/index.html).
+- 🔥 **[2024.09.12]** Support for LongWriter evaluation, which supports 10,000+ word generation. You can use the benchmark [LongBench-Write](evalscope/third_party/longbench_write/README.md) to measure the long output quality as well as the output length.
+- 🔥 **[2024.08.30]** Support for custom dataset evaluations, including text datasets and multimodal image-text datasets.
+- 🔥 **[2024.08.20]** Updated the official documentation, including getting started guides, best practices, and FAQs. Feel free to [📖read it here](https://evalscope.readthedocs.io/en/latest/)!
+- 🔥 **[2024.08.09]** Simplified the installation process, allowing for pypi installation of vlmeval dependencies; optimized the multimodal model evaluation experience, achieving up to 10x acceleration based on the OpenAI API evaluation chain.
+- 🔥 **[2024.07.31]** Important change: The package name `llmuses` has been changed to `evalscope`. Please update your code accordingly.
+- 🔥 **[2024.07.26]** Support for **VLMEvalKit** as a third-party evaluation framework to initiate multimodal model evaluation tasks.
+- 🔥 **[2024.06.29]** Support for **OpenCompass** as a third-party evaluation framework, which we have encapsulated at a higher level, supporting pip installation and simplifying evaluation task configuration.
+- 🔥 **[2024.06.13]** EvalScope seamlessly integrates with the fine-tuning framework SWIFT, providing full-chain support from LLM training to evaluation.
+- 🔥 **[2024.06.13]** Integrated the Agent evaluation dataset ToolBench.
+
+
+
+## 🛠️ Installation
+### Method 1: Install Using pip
+We recommend using conda to manage your environment and installing dependencies with pip:
+
+1. Create a conda environment (optional)
+   ```shell
+   # It is recommended to use Python 3.10
+   conda create -n evalscope python=3.10
+   # Activate the conda environment
+   conda activate evalscope
+   ```
+
+2. Install dependencies using pip
+   ```shell
+   pip install evalscope                # Install Native backend (default)
+   # Additional options
+   pip install evalscope[opencompass]   # Install OpenCompass backend
+   pip install evalscope[vlmeval]       # Install VLMEvalKit backend
+   pip install evalscope[all]           # Install all backends (Native, OpenCompass, VLMEvalKit)
+   ```
+
+> [!WARNING]
+> As the project has been renamed to `evalscope`, for versions `v0.4.3` or earlier, you can install using the following command:
+> ```shell
+> pip install llmuses<=0.4.3
+> ```
+> To import relevant dependencies using `llmuses`:
+> ``` python
+> from llmuses import ...
+> ```
+
+### Method 2: Install from Source
+1. Download the source code
+   ```shell
+   git clone https://github.com/modelscope/evalscope.git
+   ```
+
+2. Install dependencies
+   ```shell
+   cd evalscope/
+   pip install -e .                  # Install Native backend
+   # Additional options
+   pip install -e '.[opencompass]'   # Install OpenCompass backend
+   pip install -e '.[vlmeval]'       # Install VLMEvalKit backend
+   pip install -e '.[all]'           # Install all backends (Native, OpenCompass, VLMEvalKit)
+   ```
+
+
+## 🚀 Quick Start
+
+### 1. Simple Evaluation
+To evaluate a model using default settings on specified datasets, follow the process below:
+
+#### Install using pip
+You can execute this command from any directory:
+```bash
+python -m evalscope.run \
+ --model qwen/Qwen2-0.5B-Instruct \
+ --template-type qwen \
+ --datasets arc 
+```
+
+#### Install from source
+Execute this command in the `evalscope` directory:
+```bash
+python evalscope/run.py \
+ --model qwen/Qwen2-0.5B-Instruct \
+ --template-type qwen \
+ --datasets arc
+```
+
+If prompted with `Do you wish to run the custom code? [y/N]`, please type `y`.
+
+
+#### Basic Parameter Descriptions
+- `--model`: Specifies the `model_id` of the model on [ModelScope](https://modelscope.cn/), allowing automatic download. For example, see the [Qwen2-0.5B-Instruct model link](https://modelscope.cn/models/qwen/Qwen2-0.5B-Instruct/summary); you can also use a local path, such as `/path/to/model`.
+- `--template-type`: Specifies the template type corresponding to the model. Refer to the `Default Template` field in the [template table](https://swift.readthedocs.io/en/latest/Instruction/Supported-models-datasets.html#llm) for filling in this field.
+- `--datasets`: The dataset name, allowing multiple datasets to be specified, separated by spaces; these datasets will be automatically downloaded. Refer to the [supported datasets list](https://evalscope.readthedocs.io/en/latest/get_started/supported_dataset.html) for available options.
+
+### 2. Parameterized Evaluation
+If you wish to conduct a more customized evaluation, such as modifying model parameters or dataset parameters, you can use the following commands:
+
+**Example 1:**
+```shell
+python evalscope/run.py \
+ --model qwen/Qwen2-0.5B-Instruct \
+ --template-type qwen \
+ --model-args revision=master,precision=torch.float16,device_map=auto \
+ --datasets gsm8k ceval \
+ --use-cache true \
+ --limit 10
+```
+
+**Example 2:**
+```shell
+python evalscope/run.py \
+ --model qwen/Qwen2-0.5B-Instruct \
+ --template-type qwen \
+ --generation-config do_sample=false,temperature=0.0 \
+ --datasets ceval \
+ --dataset-args '{"ceval": {"few_shot_num": 0, "few_shot_random": false}}' \
+ --limit 10
+```
+
+#### Parameter Descriptions
+In addition to the three [basic parameters](#basic-parameter-descriptions), the other parameters are as follows:
+- `--model-args`: Model loading parameters, separated by commas, in `key=value` format.
+- `--generation-config`: Generation parameters, separated by commas, in `key=value` format.
+  - `do_sample`: Whether to use sampling, default is `false`.
+  - `max_new_tokens`: Maximum generation length, default is 1024.
+  - `temperature`: Sampling temperature.
+  - `top_p`: Sampling threshold.
+  - `top_k`: Sampling threshold.
+- `--use-cache`: Whether to use local cache, default is `false`. If set to `true`, previously evaluated model and dataset combinations will not be evaluated again, and will be read directly from the local cache.
+- `--dataset-args`: Evaluation dataset configuration parameters, provided in JSON format, where the key is the dataset name and the value is the parameter; note that these must correspond one-to-one with the values in `--datasets`.
+  - `--few_shot_num`: Number of few-shot examples.
+  - `--few_shot_random`: Whether to randomly sample few-shot data; if not specified, defaults to `true`.
+- `--limit`: Maximum number of evaluation samples per dataset; if not specified, all will be evaluated, which is useful for quick validation.
+
+### 3. Use the run_task Function to Submit an Evaluation Task
+Using the `run_task` function to submit an evaluation task requires the same parameters as the command line. You need to pass a dictionary as the parameter, which includes the following fields:
+
+#### 1. Configuration Task Dictionary Parameters
+```python
+import torch
+from evalscope.constants import DEFAULT_ROOT_CACHE_DIR
+
+# Example
+your_task_cfg = {
+        'model_args': {'revision': None, 'precision': torch.float16, 'device_map': 'auto'},
+        'generation_config': {'do_sample': False, 'repetition_penalty': 1.0, 'max_new_tokens': 512},
+        'dataset_args': {},
+        'dry_run': False,
+        'model': 'qwen/Qwen2-0.5B-Instruct',
+        'template_type': 'qwen',
+        'datasets': ['arc', 'hellaswag'],
+        'work_dir': DEFAULT_ROOT_CACHE_DIR,
+        'outputs': DEFAULT_ROOT_CACHE_DIR,
+        'mem_cache': False,
+        'dataset_hub': 'ModelScope',
+        'dataset_dir': DEFAULT_ROOT_CACHE_DIR,
+        'limit': 10,
+        'debug': False
+    }
+```
+Here, `DEFAULT_ROOT_CACHE_DIR` is set to `'~/.cache/evalscope'`.
+
+#### 2. Execute Task with run_task
+```python
+from evalscope.run import run_task
+run_task(task_cfg=your_task_cfg)
+```
+
+
+## Evaluation Backend
+EvalScope supports using third-party evaluation frameworks to initiate evaluation tasks, which we call Evaluation Backend. Currently supported Evaluation Backend includes:
+- **Native**: EvalScope's own **default evaluation framework**, supporting various evaluation modes including single model evaluation, arena mode, and baseline model comparison mode.
+- [OpenCompass](https://github.com/open-compass/opencompass): Initiate OpenCompass evaluation tasks through EvalScope. Lightweight, easy to customize, supports seamless integration with the LLM fine-tuning framework ms-swift. [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/opencompass_backend.html)
+- [VLMEvalKit](https://github.com/open-compass/VLMEvalKit): Initiate VLMEvalKit multimodal evaluation tasks through EvalScope. Supports various multimodal models and datasets, and offers seamless integration with the LLM fine-tuning framework ms-swift. [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/vlmevalkit_backend.html)
+- **ThirdParty**: The third-party task, e.g. [ToolBench](https://evalscope.readthedocs.io/en/latest/third_party/toolbench.html), you can contribute your own evaluation task to EvalScope as third-party backend.
+
+## Custom Dataset Evaluation
+EvalScope supports custom dataset evaluation. For detailed information, please refer to the Custom Dataset Evaluation [📖User Guide](https://evalscope.readthedocs.io/en/latest/advanced_guides/custom_dataset.html)
+
+## Offline Evaluation
+You can use local dataset to evaluate the model without internet connection. 
+
+Refer to: Offline Evaluation [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/offline_evaluation.html)
+
+
+## Arena Mode
+The Arena mode allows multiple candidate models to be evaluated through pairwise battles, and can choose to use the AI Enhanced Auto-Reviewer (AAR) automatic evaluation process or manual evaluation to obtain the evaluation report. 
+
+Refer to: Arena Mode [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/arena.html)
+
+## Model Serving Performance Evaluation
+A stress testing tool that focuses on large language models and can be customized to support various data set formats and different API protocol formats.
+
+Refer to : Model Serving Performance Evaluation [📖 User Guide](https://evalscope.readthedocs.io/en/latest/user_guides/stress_test.html)
+
+
+## Leaderboard
+The LLM Leaderboard aims to provide an objective and comprehensive evaluation standard and platform to help researchers and developers understand and compare the performance of models on various tasks on ModelScope.
+
+Refer to : [Leaderboard](https://modelscope.cn/leaderboard/58/ranking?type=free)
+
+
+## TO-DO List
+- [x] Agents evaluation
+- [x] vLLM
+- [ ] Distributed evaluating
+- [x] Multi-modal evaluation
+- [ ] Benchmarks
+  - [ ] GAIA
+  - [ ] GPQA
+  - [x] MBPP
+- [ ] Auto-reviewer
+  - [ ] Qwen-max
+

{evalscope-0.5.2.dist-info → evalscope-0.5.4.dist-info}/RECORD

@@ -1,24 +1,25 @@
 evalscope/__init__.py,sha256=3eLMMrjkAIAs3vGluXNZn5-xTSbO_vfba9yNPbkVtg8,105
 evalscope/cache.py,sha256=zpGjL9JMosqjk_dkODVwvIGiUC0WAMmMTHDNJOvBQU8,3288
-evalscope/config.py,sha256=LfVLET3k7UvZ5nISZJ0uigZetZlvKvaYPfj04dGDblQ,6916
+evalscope/config.py,sha256=G_rpSn5Kd1aPlFJO6asnZu5FUggZmwcYdAxxpuq0yDs,6972
 evalscope/constants.py,sha256=g8lGYlpA4Wk88HwtqId1-jJX_z8Lr2k02gWLsyofyj0,2670
 evalscope/run.py,sha256=T-2zoJpBx6YxLnLJH-iFF3UxUGYTU36PMV_DQ9e8tSM,18484
-evalscope/run_arena.py,sha256=_LL8fqeKUEMUg985TENYzcnH5_Q8sqPxM68eZk-jhLA,8793
+evalscope/run_arena.py,sha256=BCWCAiX0BQ9pLMIq08svEcd-IoFr75gFShpV88robIY,8963
 evalscope/run_ms.py,sha256=UtJoGnah64SXigTawJQWTi_TEGjr7Td0rjCTaO-htL8,6028
-evalscope/summarizer.py,sha256=Ie1kwPETpz3x2yROLMGqC0UwEj6OKJuKwEcUqxUx5fM,6358
-evalscope/version.py,sha256=Bo14bi3CEm4GSQOqlmyUKrRQLg4TS8hCNrE-bnYDI28,118
+evalscope/summarizer.py,sha256=rIyML8HpjQxIpXg8KvQ0CzOS6xMS-JHZh6kUZzkaRsk,6640
+evalscope/version.py,sha256=yeILiwZ11YPUOCKr-BHfiOuKFIWppiHTIqg22wbfo_g,118
 evalscope/backend/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
 evalscope/backend/base.py,sha256=5BLrDNNwxsGp35zorD-kphmN15tlBbkuuqwkz8jWZq0,876
 evalscope/backend/opencompass/__init__.py,sha256=UP_TW5KBq6V_Nvqkeb7PGvGGX3rVYussT43npwCwDgE,135
 evalscope/backend/opencompass/api_meta_template.py,sha256=sBW0XbVDOKeJ7mVUDLhmcG4e0yClw3eluazdp_8wtgQ,1753
-evalscope/backend/opencompass/backend_manager.py,sha256=Rr8eFFDUXTxI8AMcrbFW9LZuSQVZ7tsgHcZ1veNhfWM,10190
+evalscope/backend/opencompass/backend_manager.py,sha256=_eg82FLAVxQ6t5e1OqlyuxZcngqD8rxvI5EijLUh_zI,10294
 evalscope/backend/opencompass/tasks/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/backend/opencompass/tasks/eval_api.py,sha256=12lrgDpMzZ1XBRboq5TEOovDPCMDwwGCJoRT78Ox_yo,1108
-evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=DWwKcQGGSkkh65H1d-oKN8Jow0Q0cHJJzDC75inycFM,5186
+evalscope/backend/opencompass/tasks/eval_datasets.py,sha256=EizugDMt-ontWsTOaM61XGLUkx-S9rzdLf2Ssfmw3Yc,5263
 evalscope/backend/vlm_eval_kit/__init__.py,sha256=xTgHM95lWzh4s0W7zxLwYkgUbPAZfAb0UoGGmyyBXrs,83
-evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=PQ9n2jdfPj7s5Ma6_5nNuOMM4La9JBdxKbLf4Oa17NI,6055
+evalscope/backend/vlm_eval_kit/backend_manager.py,sha256=k52qTUqkp1kJivKn8bVrKoF8cng4xYTQLUmjnH_CWPM,6080
+evalscope/backend/vlm_eval_kit/custom_dataset.py,sha256=zC40Jw9bIqcGKuWS9oKPAlQdBARc-zY3sJlSiU-u-sI,1625
 evalscope/benchmarks/__init__.py,sha256=6TKP35wfKf7R_h870fsEtcIlIAgomKOcukNL9M-5I1Y,162
-evalscope/benchmarks/benchmark.py,sha256=e7rA8Y_vo6q5BhlUbZGWfZ1-SfJnU2IFRg62pnjQtDk,2157
+evalscope/benchmarks/benchmark.py,sha256=EmwYyFdrAHBGMkSbsMZQOR_62Q0CSKl8zeLlr7xvJdQ,2159
 evalscope/benchmarks/data_adapter.py,sha256=eVQvOQYQOQbIl8UlvOEUqRThL3FP3aUD6DSlqF1bqO0,10395
 evalscope/benchmarks/arc/__init__.py,sha256=7k2jFDUCHpEKDdQZ3Bmq59YmImFg9RyIfZQIsGebhE8,314
 evalscope/benchmarks/arc/ai2_arc.py,sha256=Wim8JsH094og7d0eLCEI0kUwDP_0x7AT117oTRPdiAI,5608
@@ -90,7 +91,7 @@ evalscope/cli/cli.py,sha256=uZ-qC8WBsLd5-Hn94d43sSGg0UC_12RebSD4ToKjypg,844
 evalscope/cli/start_perf.py,sha256=TL6bMXYl3ln-tfs5uBmzb9x94uxz6f3PBFIt1l7g3VA,994
 evalscope/cli/start_server.py,sha256=ATGLP2TE0aImJNicpehdzBuFlNb50F7KhyL4A_ZSoGU,3885
 evalscope/evaluator/__init__.py,sha256=S6MU1O_iiNAaKxNIhO9MEmdW-BSNf_YH2l6NQ9lxVNo,103
-evalscope/evaluator/evaluator.py,sha256=sWaJ2zkPFkSNuRAGdfhTqgF8nbtL1y55NQYHeBK8MG0,30715
+evalscope/evaluator/evaluator.py,sha256=gB408byOpu269Psh6MjYC9-a_uv9GvThoT7t07Oqh6w,30712
 evalscope/evaluator/rating_eval.py,sha256=cJbkyXIuwFUZoe7ZJZM6eUskNd9zlORgndckuon2OQ8,5768
 evalscope/evaluator/reviewer/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
 evalscope/evaluator/reviewer/auto_reviewer.py,sha256=JycPYti9h1j_8DRcu_rc5U0wkEASHYg-XBqrUUoiO-Q,17054
@@ -104,9 +105,11 @@ evalscope/metrics/bundled_rouge_score/rouge_scorer.py,sha256=xSLis-zx1hnHuj_9JI7
 evalscope/models/__init__.py,sha256=zG27J2HSeKPGiAIUE7QLPHEPLyXLsfaDwYI_TDXjpCg,145
 evalscope/models/dummy_chat_model.py,sha256=xE8wcFVSCkvizEJ-B8ojX0Ir01Q5KrN5mapjMQaQtbg,1325
 evalscope/models/model.py,sha256=ZzzVzZHVzuzdt5F1r-rEBT44ZfW9B7R1spsrV-T8nSw,3020
-evalscope/models/model_adapter.py,sha256=_Q3_0d1dMBnS1HxaAjpz-Q7gnzSRQH1hklB608DNct8,22488
+evalscope/models/model_adapter.py,sha256=Cgs68ajRwTETEo1eU-OhFiFGuSx4eS1p7-JT3jOpcOk,22740
 evalscope/models/openai_model.py,sha256=PoQS1FIiWIxp1xBJPV7Bq81LFD9FIT3vAHUvNa22DCc,3452
 evalscope/models/template.py,sha256=Yk7-QnvjiLD0zchSZcaDSLmpW8onIeFpngSwtUOYVPk,56035
+evalscope/models/api/__init__.py,sha256=0c75K78O1KaV02BqqtEp-hhtSSClXLawb8E0c2iqN_A,105
+evalscope/models/api/openai_api.py,sha256=o-FVJFSvfk5mFJm4egXcKfR5ya1fduo5b-uqTkeRu9A,7871
 evalscope/models/custom/__init__.py,sha256=K4Ewo7Qrs73-jBuPq4ffxd8hMnttKhic-Zj0amH3wiU,103
 evalscope/models/custom/custom_model.py,sha256=2ivxfGQs5V5HDnQEhTBi5v8KNBxJDbzPVJdNOGo3iSg,1566
 evalscope/perf/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -116,7 +119,7 @@ evalscope/perf/custom_api.py,sha256=H2IgM-LMjqXxVhbrtkXuiREb-p14zwMmllgl26a-jgw,
 evalscope/perf/dashscope_api.py,sha256=_XUF3czkYdPdVgtP7nqzRxROKxlqDjWs4DQnTyocNvM,3410
 evalscope/perf/dataset_plugin_base.py,sha256=6veUTyZ38W1Iig65vxNV9SfmqrsR8ID_UHgNiUO9Bv4,1814
 evalscope/perf/how_to_analysis_result.py,sha256=UVd_aYJ_7N5hl_wK9oIZig1vSwfgzodxW7XC6IWqbdg,1044
-evalscope/perf/http_client.py,sha256=y5t_LPqrxtYS315iz43-4Wu8wZgkftRgC3UlseSVKR0,34540
+evalscope/perf/http_client.py,sha256=WYHuGY_BCeeh8vHi1fm9zrAndOKpVQp4h21j1kKnM64,34535
 evalscope/perf/openai_api.py,sha256=XrH6jg8VlO9Wu0vGwZna_bHq65XMAlCfCEyqMjs8w1c,5970
 evalscope/perf/plugin_registry.py,sha256=D2MG2AXDBScjuKxB4g_Hg026pSRO752dBimonYtaAzM,782
 evalscope/perf/query_parameters.py,sha256=HfGRZJSzRMVfPezWTvbWhYeprCetGNPX_M_paoDtuOY,1346
@@ -141,6 +144,18 @@ evalscope/registry/tasks/gsm8k.yaml,sha256=KYLK-xtv_3qtgCZiwwP4-rP_ftc_qUmtsl1Tf
 evalscope/registry/tasks/mmlu.yaml,sha256=504yhHVfi9pvUBk_SGPs-Yx7R2hx_2_-nAFiGIiFGx4,726
 evalscope/registry/tasks/mmlu_mini.yaml,sha256=wVbosZ5Tm9pwLG5nCphalezXilIjcq5j33nz3MR7_BE,778
 evalscope/third_party/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
+evalscope/third_party/longbench_write/__init__.py,sha256=GNbBDc7HAh_V2Hfy5HhND_u7z6OI79czoBlP8lX4PVo,126
+evalscope/third_party/longbench_write/eval.py,sha256=_fwV3f-Yq0qrkuZ6LBXvBiXnM6lpz6sOqd7BfYxEU80,11163
+evalscope/third_party/longbench_write/infer.py,sha256=MB0MdSM1qDx15FyrPSU6BXPbSGnBjxuTWqrcHAgbj9o,8318
+evalscope/third_party/longbench_write/longbench_write.py,sha256=MQzlIzv3sGlNgxgX0FPHtDIuAmgwThfBkMeKNcsR3U8,3926
+evalscope/third_party/longbench_write/utils.py,sha256=l6q9cNZLFVRvG9qYbxFxobuQkcMyteU9Y6NxyMU4tmQ,816
+evalscope/third_party/longbench_write/resources/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
+evalscope/third_party/longbench_write/resources/judge.txt,sha256=LEI86IoOtqYUgvQnmXo8A8S8Ef6GEQKJXcrEWSauHVc,1884
+evalscope/third_party/longbench_write/resources/longbench_write.jsonl,sha256=H26ZSXzCTWWJTWXgFAYvOYupRuvdJUt_izOeSNOrV3k,54155
+evalscope/third_party/longbench_write/resources/longbench_write_en.jsonl,sha256=h4AJJ3YfNA5IiZ5N9dR_tyEa1JNqY0INv6l5ZgQUJZ8,24235
+evalscope/third_party/longbench_write/resources/longwrite_ruler.jsonl,sha256=odTr8N8PoWAFZ2kdEcmlLeMDfEo3KXDtLo9S8oieCmI,5718
+evalscope/third_party/longbench_write/tools/__init__.py,sha256=I_ANdxdcIHpkIzIXc1yKOlWwzb4oY0FwTPq1kYtgzQw,50
+evalscope/third_party/longbench_write/tools/data_etl.py,sha256=fSc4iT7_bdTvW20TbjlWme-k1pLqj_e2wXV8z831_Yw,5963
 evalscope/third_party/toolbench_static/__init__.py,sha256=BO936RxwodHr4OEpV6W3S_keC91OfOd41_msIJ2d0fs,128
 evalscope/third_party/toolbench_static/eval.py,sha256=TqjMuuYePnD3bGRhQe1_9bIOlAW41kiFSztaEuppRLM,8237
 evalscope/third_party/toolbench_static/infer.py,sha256=WogwVXqDabdcsJ4uftZxAwR2wncp6HYpkS-fACEvjT4,9331
@@ -158,8 +173,8 @@ evalscope/utils/logger.py,sha256=Ycd0W17Z_oiByPuPX3_umNrOCHjT9O_e_Kws7ZWUSvU,185
 evalscope/utils/task_cfg_parser.py,sha256=LiNQ2X8lbZU0cODpaY_PbKyUhNoxZIC495UsLJigX64,138
 evalscope/utils/task_utils.py,sha256=Mv_u_f4Z91zcUeko6acZCmnOAPRfk61kf_dliLzG5Yk,459
 evalscope/utils/utils.py,sha256=zHo9hfxGBUVKE2xNMR7lDoEvfRnk4V4946DEfXQhlq4,20509
-evalscope-0.5.2.dist-info/METADATA,sha256=F0YWg7gyenErvz-Kq1X5Z2Ngr1TYh3H-KpCX5zBLnog,27866
-evalscope-0.5.2.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
-evalscope-0.5.2.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
-evalscope-0.5.2.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
-evalscope-0.5.2.dist-info/RECORD,,
+evalscope-0.5.4.dist-info/METADATA,sha256=WRfHi_dmJzaF5WXqB2vPz_HhciWfNZ8Su5j_dxbiKQE,20705
+evalscope-0.5.4.dist-info/WHEEL,sha256=2wepM1nk4DS4eFpYrW1TTqPcoGNfHhhO_i5m4cOimbo,92
+evalscope-0.5.4.dist-info/entry_points.txt,sha256=Qr4oTgGhg_K-iUtKwVH6lWUhFHDUiH9trIqydHGTEug,56
+evalscope-0.5.4.dist-info/top_level.txt,sha256=jNR-HMn3TR8Atolq7_4rW8IWVX6GhvYV5_1Y_KbJKlY,10
+evalscope-0.5.4.dist-info/RECORD,,