A python wrapper over NESTFUL data
Project description
NESTFUL
This is the official repository for NESTFUL.
- Paper Title: NESTFUL: A Benchmark for Evaluating LLMs on Nested Sequences of API Calls
- Link: https://arxiv.org/abs/2409.03797v2
- HuggingFace Data Link: https://huggingface.co/datasets/ibm-research/nestful
Data
We have shared the latest NESTFUL evaluation set under data_v2 dir.
nestful_data.jsonl: It has 1861 evaluation data for nested sequencing.executable_functions: Contains the implementation of all the functions in the benchmark.
The data_v1 directory includes the data for the previous version of the paper - link.
executable: contains data and spec with necessary information to execute them through RapidAPI.non-executable: contains the nested sequencing data from SGD and GLAIVE that are hand-picked by human annotators from data synthetically generated using an LLM.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
nestful_wrapper-0.0.4.tar.gz
(94.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file nestful_wrapper-0.0.4.tar.gz.
File metadata
- Download URL: nestful_wrapper-0.0.4.tar.gz
- Upload date:
- Size: 94.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.21
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
54c70cfdb6c125bd68aa04c2abb879d6726c2fb5a340579dbf4ca69432809045
|
|
| MD5 |
1973eb6b87ea2144d494580e5d51bb1a
|
|
| BLAKE2b-256 |
5aaf2a54bc6e82193cf688122a74d133396c52f0c1ad31c2f84c8779505d240f
|
File details
Details for the file nestful_wrapper-0.0.4-py3-none-any.whl.
File metadata
- Download URL: nestful_wrapper-0.0.4-py3-none-any.whl
- Upload date:
- Size: 118.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.9.21
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
048e65dc2682514425c854bf9800d13dd6cbdd7892501f5faf3cf37944d953e8
|
|
| MD5 |
f02457e670e3428ce2631e8e329a714d
|
|
| BLAKE2b-256 |
27383c976b2dfe1e8249942bcfb3352bb1504ef3276cc08cab7c6bba6e58ecfa
|