Nexusflow/NexusRaven_API_evaluation

---
dataset_info:
- config_name: outputs_in_toolllm_format
features:
- name: response
list:
- name: function_call
dtype: string
- name: query
dtype: string
- name: task_id
dtype: int64
- name: timestamp
dtype: float64
splits:
- name: train
num_bytes: 303376
num_examples: 348
download_size: 83053
dataset_size: 303376
- config_name: raw_api_list
features:
- name: dataset
dtype: string
- name: name
dtype: string
- name: description
dtype: string
- name: args_dicts
list:
- name: default
dtype: 'null'
- name: description
dtype: string
- name: name
dtype: string
- name: required
dtype: bool
- name: type
dtype: string
splits:
- name: train
num_bytes: 22276
num_examples: 2
download_size: 10949
dataset_size: 22276
- config_name: raw_queries
features:
- name: dataset
dtype: string
- name: query_dict
dtype: string
splits:
- name: train
num_bytes: 466227
num_examples: 339
download_size: 98527
dataset_size: 466227
- config_name: standardized_api_list
features:
- name: dataset
dtype: string
- name: name
dtype: string
- name: description
dtype: string
- name: args_dicts
list:
- name: default
dtype: string
- name: description
dtype: string
- name: name
dtype: string
- name: required
dtype: bool
- name: type
dtype: string
splits:
- name: train
num_bytes: 47776
num_examples: 65
download_size: 27751
dataset_size: 47776
- config_name: standardized_queries
features:
- name: dataset
dtype: string
- name: prompt
dtype: string
- name: python_function_name
dtype: string
- name: python_args_dict
dtype: string
- name: context_functions
sequence: string
splits:
- name: train
num_bytes: 153860
num_examples: 318
download_size: 36721
dataset_size: 153860
configs:
- config_name: outputs_in_toolllm_format
data_files:
- split: train
path: outputs_in_toolllm_format/train-*
- config_name: raw_queries
data_files:
- split: train
path: raw_queries/train-*
- config_name: standardized_api_list
data_files:
- split: train
path: standardized_api_list/train-*
- config_name: standardized_queries
data_files:
- split: train
path: standardized_queries/train-*
---

# NexusRaven API Evaluation dataset
Please see [blog post](http://nexusflow.ai/blog) or [NexusRaven Github repo](https://github.com/nexusflowai/NexusRaven) for more information.

## License
The evaluation data in this repository consists primarily of our own curated evaluation data that only uses open source commercializable models. However, we include general domain data from the ToolLLM and ToolAlpaca papers. Since the data in the ToolLLM and ToolAlpaca works use OpenAI's GPT models for the generated content, the data is not commercially licensable, even if our own data is. As a result, the evaluation data used here is strictly non-commercial under [CC-BY-NC-4.0](https://creativecommons.org/licenses/by-nc/4.0/). Thank you for understanding!

## References
We thank the following authors and entities for their evaluation data, which we leveraged to produce the results contained in this repository. Their citations can be found below

1. ToolAlpaca team
2. ToolLLM team

```
@misc{tang2023toolalpaca,
title={ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases},
author={Qiaoyu Tang and Ziliang Deng and Hongyu Lin and Xianpei Han and Qiao Liang and Boxi Cao and Le Sun},
year={2023},
eprint={2306.05301},
archivePrefix={arXiv},
primaryClass={cs.CL}
}

@misc{qin2023toolllm,
title={ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs},
author={Yujia Qin and Shihao Liang and Yining Ye and Kunlun Zhu and Lan Yan and Yaxi Lu and Yankai Lin and Xin Cong and Xiangru Tang and Bill Qian and Sihan Zhao and Runchu Tian and Ruobing Xie and Jie Zhou and Mark Gerstein and Dahai Li and Zhiyuan Liu and Maosong Sun},
year={2023},
eprint={2307.16789},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```

## Citation
```
@misc{nexusraven,
title={NexusRaven: Surpassing the state-of-the-art in open-source function calling LLMs},
author={Nexusflow.ai team},
year={2023},
url={http://nexusflow.ai/blog}
}
```

## Contact
Please reach out to [e-mail] for any questions!

原始信息汇总

数据集概述

数据集信息

• 获取更多信息：请参考博客文章或NexusRaven的GitHub仓库。