id stringlengths 2 115 | lastModified stringlengths 24 24 | tags list | author stringlengths 2 42 ⌀ | description stringlengths 0 6.67k ⌀ | citation stringlengths 0 10.7k ⌀ | likes int64 0 3.66k | downloads int64 0 8.89M | created timestamp[us] | card stringlengths 11 977k | card_len int64 11 977k | embeddings list |
|---|---|---|---|---|---|---|---|---|---|---|---|
mjavadmt/mbti-persian-twitter | 2023-05-18T16:55:59.000Z | [
"task_categories:text-classification",
"size_categories:1K<n<10K",
"language:fa",
"region:us"
] | mjavadmt | null | null | 1 | 6 | 2023-05-18T13:01:33 | ---
task_categories:
- text-classification
language:
- fa
pretty_name: MBTI-persian-dataset
size_categories:
- 1K<n<10K
---
Persian dataset with Myers-Briggs 16 types. crawled on twitter persian users. | 202 | [
[
-0.031494140625,
-0.02984619140625,
0.034881591796875,
0.029266357421875,
-0.01296234130859375,
0.04840087890625,
-0.026824951171875,
-0.00624847412109375,
0.047515869140625,
0.023468017578125,
-0.05615234375,
-0.053436279296875,
-0.03912353515625,
0.0088119... |
ProjectFisokuhle/insure_docs | 2023-05-18T19:45:52.000Z | [
"region:us"
] | ProjectFisokuhle | null | null | 0 | 6 | 2023-05-18T17:39:08 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
edarchimbaud/earnings-stocks | 2023-10-29T23:10:38.000Z | [
"region:us"
] | edarchimbaud | null | null | 1 | 6 | 2023-05-18T21:40:18 | ---
dataset_info:
features:
- name: symbol
dtype: string
- name: date
dtype: timestamp[ns, tz=EST]
- name: eps_estimate
dtype: float64
- name: reported_eps
dtype: float64
- name: surprise
dtype: float64
splits:
- name: train
num_bytes: 289231
num_examples: 7269
download_size: 140615
dataset_size: 289231
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "earnings-sp500"
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://edarchimbaud.substack.com
- **Repository:** https://github.com/edarchimbaud
- **Point of Contact:** contact@edarchimbaud.com
### Dataset Summary
The earnings-sp500 dataset provides information on earnings reports of companies in the S&P 500 index.
### Supported Tasks and Leaderboards
The dataset can be used to analyze and predict earnings surprises for companies in the S&P 500 index. It can be used to develop models for financial analysis and trading strategies.
### Languages
[N/A]
## Dataset Structure
### Data Instances
[N/A]
### Data Fields
- symbol (string): A string representing the ticker symbol or abbreviation used to identify the company.
- date (timestamp[ns, tz=EST]): A timestamp indicating the date of the earnings report. The timestamps are in the Eastern Standard Time (EST) timezone.
- eps_estimate (float64): A floating-point number representing the estimated earnings per share (EPS) for the company.
- reported_eps (float64): A floating-point number representing the reported earnings per share (EPS) for the company.
- surprise (float64): A floating-point number representing the surprise factor, calculated as the difference between the reported EPS and the estimated EPS.
### Data Splits
A single split, called train.
## Dataset Creation
### Curation Rationale
The earnings-sp500 dataset was created to provide data on earnings reports of companies in the S&P 500 index for research and analysis purposes.
### Source Data
#### Initial Data Collection and Normalization
The data was collected from various financial sources and normalized for consistency.
### Annotations
#### Annotation Process
[N/A]
#### Who are the Annotators?
[N/A]
### Personal and Sensitive Information
[N/A]
## Considerations for Using the Data
### Social Impact of Dataset
[N/A]
### Discussion of Biases
[N/A]
### Other Known Limitations
[N/A]
## Additional Information
### Dataset Curators
The earnings-sp500 dataset was collected by https://edarchimbaud.substack.com.
### Licensing Information
The earnings-sp500 dataset is licensed under the MIT License.
### Citation Information
> https://edarchimbaud.substack.com, earnings-sp500 dataset, GitHub repository, https://github.com/edarchimbaud
### Contributions | 3,835 | [
[
-0.0135498046875,
-0.02618408203125,
0.0005841255187988281,
0.038238525390625,
-0.0226898193359375,
0.0175018310546875,
-0.0005931854248046875,
-0.04119873046875,
0.07122802734375,
0.01297760009765625,
-0.0797119140625,
-0.03936767578125,
-0.0535888671875,
0... |
voidful/fermi | 2023-05-20T16:29:45.000Z | [
"region:us"
] | voidful | null | null | 0 | 6 | 2023-05-20T16:28:55 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
RussianNLP/RuSpellGold | 2023-05-26T16:41:30.000Z | [
"task_categories:text-generation",
"size_categories:1K<n<10K",
"language:ru",
"license:apache-2.0",
"region:us"
] | RussianNLP | RuSpellGold is a benchmark of 1711 sentence pairs
dedicated to a problem of automatic spelling correction in Russian language.
The dataset is gathered from five different domains including news, Russian classic literature,
social media texts, open web and strategic documents.
It has been passed through two-stage manual labeling process with native speakers as annotators
to correct spelling violation and preserve original style of text at the same time. | null | 0 | 6 | 2023-05-24T10:08:08 | ---
license: apache-2.0
task_categories:
- text-generation
language:
- ru
size_categories:
- 1K<n<10K
---
# Dataset Card for RuSpellGold
## Dataset Description
- **Paper:** # TODO
- **ArXiv:** # TODO
- **Point of Contact:** nikita.martynov.98@list.ru
- **Language:** Russian
### Dataset Summary
RuSpellGold is a benchmark of 1711 sentence pairs dedicated to a problem of automatic spelling correction in Russian language. The dataset is gathered from five different domains including news, Russian classic literature, social media texts, open web and strategic documents. It has been passed through two-stage manual labeling process with native speakers as annotators to correct spelling violation and preserve original style of text at the same time.
## Dataset Structure
### Supported Tasks and Leaderboards
- **Task:** automatic spelling correction.
- **Metrics:** https://www.dialog-21.ru/media/3427/sorokinaaetal.pdf.
### Languages
Russian.
### Data Instances
```
{
"sources": "Видела в городе афиши, анонсрующие ее концерт.",
"corrections": "Видела в городе афиши, анонсирующие её концерт",
"domain": "aranea"
}
```
### Data Fields
- ```sources (str)```: original sentence.
- ```corrections (str)```: corrected sentence.
- ```domain (str)```: domain, from which the sentence is taken from.
### Data Splits
Current version of benchmark is only represented by test part:
- ```test```: 1711 sentence pairs (```"data/test.csv"```).
which is then splitted into following domain-relaited shards:
- ```aranea```: 756 sentence pairs (```"data/aranea/split.csv"```);
- ```literature```: 260 sentence pairs (```"data/literature/split.csv"```);
- ```news```: 245 sentence pairs (```"data/news/split.csv"```);
- ```social_media```: 200 sentence pairs (```"data/social_media/split.csv"```);
- ```strategic_documents```: 250 sentence pairs (```"data/strategic_documents/split.csv"```);
## Dataset Creation
### Source Data
|Source |Strategy |Domain |
|---|---|---|
|Vladimír Benko. 2014. Aranea: Yet another family of (comparable) web corpora. // Text, Speech and Dialogue: 17th International Conference, TSD 2014, Brno, Czech Republic, September 8-12, 2014. Proceedings 17, P 247–256. Springer| Random sentences from Araneum Russicum|Open web (aranea) |
| Russian classic literature aggregated in this [corpus](https://www.kaggle.com/datasets/d0rj3228/russian-literature) | Random sentences | Literature |
|Ilya Gusev. 2020. Dataset for automatic summarization of russian news. // Artificial Intelligence and Natural Language: 9th Conference, AINL 2020, Helsinki, Finland, October 7–9, 2020, Proceedings 9, P 122–134. Springer | Random sentences | News |
|Social media platforms | Posts from social media platforms marked with specific hashtags | Social Media |
|Vitaly Ivanin, Ekaterina Artemova, Tatiana Batura, Vladimir Ivanov, Veronika Sarkisyan, Elena Tutubalina, and Ivan Smurov. 2020. Rurebus-2020 shared task: Russian relation extraction for business. // Computational Linguistics and Intellectual Technologies: Proceedings of the International Conference “Dialog” [Komp’iuternaia Lingvistika i Intellektual’nye Tehnologii: Trudy Mezhdunarodnoj Konferentsii “Dialog”], Moscow, Russia. | Random sentences | Strategic documents |
### Annotations
#### Annotation process
All of the sentences undergo a two-stage annotation procedure on [Toloka](https://toloka.ai), a crowd-sourcing platform for data labeling.
Each stage includes an unpaid training phase with explanations, control tasks for tracking annotation quality, and the main annotation task. Before starting, a worker is given detailed instructions describing the task, explaining the labels, and showing plenty of examples.
The instruction is available at any time during both the training and main annotation phases. To get access to the main phase, the worker should first complete the training phase by labeling more than 70% of its examples correctly. To ensure high-quality expertise on the matter of spelling, we set up additional test phase on a small portion of data, manually revised the results and approved only those annotators, who managed to avoid any mistakes.
- **Stage 1: Data gathering**
We provide texts with possible mistakes to annotators and ask them to write the sentence correctly preserving the original style-markers of the text.
- **Stage 2: Validation**
We provide annotators with the pair of sentences (origin and its corresponding correction from the previous stage) and ask them to check if the correction is right.
### Personal and Sensitive Information
Each annotator is warned about potentially sensitive topics in data (e.g., politics, societal minorities, and religion).
## Additional Information
### Dataset Curators
Correspondence: ```nikita.martynov.98@list.ru```
### Licensing Information
The corpus is available under the Apache 2.0 license. The copyright (where applicable) of texts from the linguistic publications and resources remains with the original authors or publishers.
### Other
Please refer to our paper # TODO for more details. | 5,101 | [
[
-0.00865936279296875,
-0.049774169921875,
0.01519012451171875,
0.00904083251953125,
-0.0292205810546875,
-0.007114410400390625,
-0.0261383056640625,
-0.02978515625,
0.0186614990234375,
0.03076171875,
-0.04254150390625,
-0.06646728515625,
-0.040863037109375,
... |
Chakshu/conversation_ender | 2023-05-25T08:56:31.000Z | [
"task_categories:text-classification",
"size_categories:n<1K",
"language:en",
"license:mit",
"Conversation",
"region:us"
] | Chakshu | null | null | 1 | 6 | 2023-05-25T07:57:48 | ---
license: mit
task_categories:
- text-classification
language:
- en
tags:
- Conversation
size_categories:
- n<1K
pretty_name: Conversation Enders
---
Conversation Ending Check | 178 | [
[
-0.0235443115234375,
-0.0574951171875,
0.061737060546875,
0.0034046173095703125,
-0.03485107421875,
0.01505279541015625,
-0.0014057159423828125,
-0.035675048828125,
0.033050537109375,
0.08526611328125,
-0.033966064453125,
-0.007160186767578125,
-0.05886840820312... |
Linly-AI/Chinese-pretraining-dataset | 2023-05-26T02:32:06.000Z | [
"license:apache-2.0",
"region:us"
] | Linly-AI | null | null | 22 | 6 | 2023-05-25T08:31:43 | ---
license: apache-2.0
---
Data source: https://github.com/CVI-SZU/Linly/wiki/Linly-OpenLLaMA | 95 | [
[
-0.0038700103759765625,
-0.033721923828125,
0.0433349609375,
-0.003307342529296875,
0.011871337890625,
-0.0284881591796875,
-0.025115966796875,
-0.0220794677734375,
0.04351806640625,
0.04656982421875,
-0.05059814453125,
-0.057891845703125,
-0.0011682510375976562... |
stacked-summaries/onlystacked-xsum-1024 | 2023-10-16T20:05:16.000Z | [
"task_categories:summarization",
"task_categories:text2text-generation",
"size_categories:100K<n<1M",
"source_datasets:xsum",
"language:en",
"license:apache-2.0",
"stacked summaries",
"region:us"
] | stacked-summaries | null | null | 0 | 6 | 2023-05-28T22:40:37 | ---
language:
- en
license: apache-2.0
size_categories:
- 100K<n<1M
source_datasets: xsum
task_categories:
- summarization
- text2text-generation
tags:
- stacked summaries
configs:
- config_name: deduped
data_files:
- split: train
path: deduped/train-*
- split: validation
path: deduped/validation-*
- split: test
path: deduped/test-*
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
dataset_info:
- config_name: deduped
features:
- name: document
dtype: string
- name: summary
dtype: string
- name: id
dtype: int64
- name: chapter_length
dtype: int64
- name: summary_length
dtype: int64
- name: is_stacked
dtype: bool
splits:
- name: train
num_bytes: 307044969
num_examples: 82575
- name: validation
num_bytes: 17368941
num_examples: 4674
- name: test
num_bytes: 17048516
num_examples: 4593
download_size: 219853891
dataset_size: 341462426
- config_name: default
features:
- name: document
dtype: string
- name: summary
dtype: string
- name: id
dtype: int64
- name: chapter_length
dtype: int64
- name: summary_length
dtype: int64
- name: is_stacked
dtype: bool
splits:
- name: train
num_bytes: 437045277
num_examples: 116994
- name: validation
num_bytes: 24723155
num_examples: 6603
- name: test
num_bytes: 24228493
num_examples: 6499
download_size: 313190936
dataset_size: 485996925
---
# stacked-summaries/onlystacked-xsum-1024
Same thing as [stacked-summaries/stacked-xsum-1024](https://huggingface.co/datasets/stacked-summaries/stacked-xsum-1024) but filtered such that `is_stacked=True`. Please refer to the original dataset for info and to raise issues if needed.
Basic info on `train` split:
```
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 116994 entries, 0 to 116993
Data columns (total 6 columns):
# Column Non-Null Count Dtype
--- ------ -------------- -----
0 document 116994 non-null string
1 summary 116994 non-null string
2 id 116994 non-null Int64
3 chapter_length 116994 non-null Int64
4 summary_length 116994 non-null Int64
5 is_stacked 116994 non-null boolean
dtypes: Int64(3), boolean(1), string(2)
memory usage: 5.0 MB
```
_If you are interested in subscribing to this dataset on OnlyStacks, please reach out._ | 2,527 | [
[
-0.0213775634765625,
-0.0211639404296875,
0.00522613525390625,
0.0200958251953125,
-0.036346435546875,
0.010101318359375,
0.00295257568359375,
-0.01042938232421875,
0.07330322265625,
0.0751953125,
-0.051971435546875,
-0.034820556640625,
-0.044342041015625,
0... |
kaahila/sugarcrm_130_documentation | 2023-05-31T23:24:02.000Z | [
"task_categories:question-answering",
"language:en",
"sugarcrm",
"documentation",
"region:us"
] | kaahila | null | null | 0 | 6 | 2023-05-30T21:03:41 | ---
task_categories:
- question-answering
language:
- en
tags:
- sugarcrm
- documentation
pretty_name: kaahila/sugarcrm_130_documentation
---
# Source: [Sugarcrm 13.0 Dev Documentation](https://support.sugarcrm.com/Documentation/Sugar_Developer/Sugar_Developer_Guide_13.0/)
The chunks in the files are diffrent splittet based on the tokenizer conained in the name of the file
###### cl100k_base: 400 Tokens per chunk
###### p50k_base: 200 Tokens per chunk | 459 | [
[
-0.009033203125,
-0.039825439453125,
0.028411865234375,
0.032135009765625,
-0.0372314453125,
0.031280517578125,
-0.024017333984375,
-0.0102081298828125,
0.04071044921875,
0.04510498046875,
-0.046966552734375,
-0.0408935546875,
-0.061737060546875,
0.019821166... |
andersonbcdefg/red_teaming_reward_modeling_pairwise | 2023-06-01T07:00:45.000Z | [
"region:us"
] | andersonbcdefg | null | null | 0 | 6 | 2023-06-01T06:02:38 | ---
dataset_info:
features:
- name: prompt
dtype: string
- name: response_a
dtype: string
- name: response_b
dtype: string
- name: explanation
dtype: string
- name: preferred
dtype: string
- name: __index_level_0__
dtype: int64
splits:
- name: train
num_bytes: 41305999
num_examples: 35279
download_size: 0
dataset_size: 41305999
---
# Dataset Card for "red_teaming_reward_modeling_pairwise"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 578 | [
[
-0.0245361328125,
-0.00693511962890625,
0.006908416748046875,
0.0233306884765625,
-0.00391387939453125,
0.01140594482421875,
0.01934814453125,
-0.01194000244140625,
0.056854248046875,
0.02813720703125,
-0.058441162109375,
-0.03948974609375,
-0.0364990234375,
... |
OdiaGenAI/all_combined_bengali_252k | 2023-06-28T12:47:51.000Z | [
"task_categories:text-generation",
"size_categories:100K<n<1M",
"language:bn",
"license:cc-by-nc-sa-4.0",
"region:us"
] | OdiaGenAI | null | null | 2 | 6 | 2023-06-02T19:23:48 | ---
license: cc-by-nc-sa-4.0
task_categories:
- text-generation
language:
- bn
pretty_name: all_combined_bengali_252K
size_categories:
- 100K<n<1M
---
# Dataset Card for all_combined_bengali_252K
## Dataset Description
- **Homepage: https://www.odiagenai.org/**
- **Repository: https://github.com/OdiaGenAI**
- **Point of Contact: Shantipriya Parida, and Sambit Sekhar**
### Dataset Summary
This dataset is a mix of Bengali instruction sets translated from open-source instruction sets:
* Dolly,
* Alpaca,
* ChatDoctor,
* Roleplay
* GSM
In this dataset Bengali instruction, input, and output strings are available.
### Supported Tasks and Leaderboards
Large Language Model (LLM)
### Languages
Bengali
## Dataset Structure
JSON
### Data Fields
output (string)
data_source (string)
instruction (string)
input (string)
### Licensing Information
This work is licensed under a
[Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License][cc-by-nc-sa].
[![CC BY-NC-SA 4.0][cc-by-nc-sa-image]][cc-by-nc-sa]
[cc-by-nc-sa]: http://creativecommons.org/licenses/by-nc-sa/4.0/
[cc-by-nc-sa-image]: https://licensebuttons.net/l/by-nc-sa/4.0/88x31.png
[cc-by-nc-sa-shield]: https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg
### Citation Information
If you find this repository useful, please consider giving 👏 and citing:
```
@misc{OdiaGenAI,
author = {Shantipriya Parida and Sambit Sekhar and Guneet Singh Kohli and Arghyadeep Sen and Shashikanta Sahoo},
title = {Bengali Instruction Set},
year = {2023},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/OdiaGenAI}},
}
```
### Contributions
- Shantipriya Parida
- Sambit Sekhar
- Guneet Singh Kohli
- Arghyadeep Sen
- Shashikanta Sahoo | 1,819 | [
[
-0.0213775634765625,
-0.03277587890625,
-0.00498199462890625,
0.04339599609375,
-0.025054931640625,
-0.002071380615234375,
-0.0042877197265625,
-0.01277923583984375,
0.0247802734375,
0.04931640625,
-0.0306243896484375,
-0.04925537109375,
-0.045562744140625,
... |
DragonFire0159x/nijijourney-images | 2023-06-06T09:23:43.000Z | [
"task_categories:unconditional-image-generation",
"size_categories:n<1K",
"region:us"
] | DragonFire0159x | null | null | 2 | 6 | 2023-06-06T08:35:30 | ---
task_categories:
- unconditional-image-generation
size_categories:
- n<1K
---
# DragonFire0159x/nijijourney-images
Dataset with images generated by niji-journey
Contains only images, no prompts
# What's in the repository
Here are the archives with different dataset sizes
For example, the niji_dataset_404.zip archive contains 404 pictures
You can also use to fine tune the Stable Diffusion | 399 | [
[
-0.01508331298828125,
-0.0286865234375,
0.03680419921875,
0.0252532958984375,
-0.0238494873046875,
-0.0296783447265625,
0.008575439453125,
0.0213470458984375,
0.03240966796875,
0.06951904296875,
-0.09393310546875,
-0.0266571044921875,
-0.03289794921875,
-0.0... |
nicholasKluge/reward-aira-dataset | 2023-08-30T20:50:28.000Z | [
"task_categories:text-classification",
"size_categories:10K<n<100K",
"language:pt",
"language:en",
"license:apache-2.0",
"reward model",
"instruction",
"alignment",
"region:us"
] | nicholasKluge | null | null | 0 | 6 | 2023-06-07T18:14:57 | ---
license: apache-2.0
task_categories:
- text-classification
language:
- pt
- en
tags:
- reward model
- instruction
- alignment
pretty_name: Reward-Aira Dataset
size_categories:
- 10K<n<100K
dataset_info:
features:
- name: instruction
dtype: string
- name: chosen_response
dtype: string
- name: rejected_response
dtype: string
splits:
- name: english
num_bytes: 53232958
num_examples: 32675
- name: portuguese
num_bytes: 59650447
num_examples: 32675
download_size: 65455319
dataset_size: 112883405
---
# Dataset (`Reward-Aira Dataset`)
### Overview
This dataset contains a collection of prompt + completion examples of LLM following instructions in a conversational manner. All prompts come with two possible completions (one better than the other). The dataset is available in both Portuguese and English languages.
### Dataset Details
- **Dataset Name:** Reward-Aira Dataset
- **Language:** Portuguese and English
- **Total Size:** 32,675 pairs of demonstrations (in Portuguese and English)
### Contents
The dataset consists of data frames with the following columns:
- **Prompt (`instruction`):** The initial prompt provided to the model.
- **Completion (`chosen_response`):** A completion to the prompt.
- **Completion (`rejected_response`):** A worst completion to the prompt.
```python
{
"instruction":"Why is AI Ethics important?",
"chosen_response": "The field of AI Ethics delves deeply into the intricate ethical considerations that arise with respect to AI systems. This includes the role of humanity in creating and deploying these systems, as well as the conduct of machines themselves. Broadly speaking, AI Ethics can be divided into two major categories : concerns surrounding the morality of human actions in relation to creating and using AI, and concerns regarding the moral implications of machine behavior.",
"rejected_response": "Who cares about AI Ethics? It's just a bunch of whining about humans making and using AI and bitching about what the machines do."
}
```
### Use Cases
`Reward-Aira Dataset` can be utilized to train a reward/preference model.
## How to use
Available splits are `portuguese` and `english`.
```python
from datasets import load_dataset
dataset = load_dataset("nicholasKluge/reward-aira-dataset")
```
### Dataset License
The `Reward-Aira Dataset` is licensed under the Apache License, Version 2.0. See the [LICENSE](LICENSE) file for more details.
### Disclaimer
This dataset is provided as is, without any warranty or guarantee of its accuracy or suitability for any purpose. The creators and contributors of this dataset are not liable for any damages or losses arising from its use. Please review and comply with the licenses and terms of the original datasets before use. | 2,802 | [
[
-0.006015777587890625,
-0.03076171875,
0.0187530517578125,
0.0208282470703125,
-0.010955810546875,
-0.0201568603515625,
-0.00506591796875,
-0.018768310546875,
0.021209716796875,
0.043914794921875,
-0.05755615234375,
-0.0202789306640625,
-0.04638671875,
0.005... |
declare-lab/InstructEvalImpact | 2023-06-09T08:53:22.000Z | [
"size_categories:n<1K",
"license:apache-2.0",
"region:us"
] | declare-lab | null | null | 6 | 6 | 2023-06-09T07:05:44 | ---
license: apache-2.0
size_categories:
- n<1K
ArXiv: 2306.04757
---
# Project Links
# Dataset Description
The IMPACT dataset contains 50 human created prompts for each category, 200 in total, to test LLMs general writing ability.
Instructed LLMs demonstrate promising ability in writing-based tasks, such as composing letters or ethical debates. This dataset consists prompts across 4 diverse usage scenarios:
- **Informative Writing**: User queries such as self-help advice or explanations for various concept
- **Professional Writing**: Format involves suggestions presentations or emails in a business setting
- **Argumentative Writing**: Debate positions on ethical and societal question
- **Creative Writing**: Diverse writing formats such as stories, poems, and songs.
The IMPACT dataset is included in our [InstructEval Benchmark Suite](https://github.com/declare-lab/instruct-eval).
# Evaluation Results
We leverage ChatGPT to judge the quality of the generated answers by LLMs. In terms of:
- Relevance: how well the answer engages with the given prompt
- Coherence: general text quality such as organization and logical flow
Each answer is scored on a Likert scale from 1 to 5. We evaluate the models in the zero-shot
setting based on the given prompt and perform sampling-based decoding with a temperature of 1.0
| **Model** | **Size** | **Informative** | | **Professional** | | **Argumentative** | | **Creative** | | **Avg.** | |
| :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| | | Rel. | Coh. | Rel. | Coh. | Rel. | Coh. | Rel. | Coh. | Rel. | Coh. |
| **ChatGPT** | - | 3.34 | 3.98 | 3.88 | 3.96 | 3.96 | 3.82 | 3.92 | 3.94 | 3.78 | 3.93 |
| [**Flan-Alpaca**](https://huggingface.co/declare-lab/flan-alpaca-xxl) | 11B | 3.56 | 3.46 | 3.54 | 3.70 | 3.22 | 3.28 | 3.70 | 3.40 | 3.51 | 3.46 |
| [**Dolly-V2**](https://huggingface.co/databricks/dolly-v2-12b) | 12 B | 3.54 | 3.64 | 2.96 | 3.74 | 3.66 | 3.20 | 3.02 | 3.18 | 3.30 | 3.44 |
| [**StableVicuna**](https://huggingface.co/TheBloke/stable-vicuna-13B-HF) | 13B | 3.54 | 3.64 | 2.96 | 3.74 | 3.30 | 3.20 | 3.02 | 3.18 | 3.21 | 3.44 |
| [**Flan-T5**](https://huggingface.co/google/flan-t5-xxl) | 11B | 2.64 | 3.24 | 2.62 | 3.22 | 2.54 | 3.40 | 2.50 | 2.72 | 2.58 | 3.15 |
# Citation
Please consider citing the following article if you found our work useful:
```
bibtex
@article{chia2023instructeval,
title={INSTRUCTEVAL: Towards Holistic Evaluation of Instruction-Tuned Large Language Models},
author={Yew Ken Chia and Pengfei Hong and Lidong Bing and Soujanya Poria},
journal={arXiv preprint arXiv:2306.04757},
year={2023}
}
```
| 2,694 | [
[
-0.034423828125,
-0.053466796875,
0.0224456787109375,
0.0159759521484375,
-0.004207611083984375,
-0.01418304443359375,
-0.00750732421875,
-0.03472900390625,
0.02899169921875,
0.033447265625,
-0.04583740234375,
-0.056182861328125,
-0.041290283203125,
0.018997... |
Norquinal/claude_evol_instruct_210k | 2023-07-17T04:10:04.000Z | [
"region:us"
] | Norquinal | null | null | 13 | 6 | 2023-06-10T06:00:28 | This dataset is the result of roughly 250k instruction/response pairs being generated by Claude, with instances of blatant alignment removed.
213375 instructions remain.
This dataset is experimental in two ways:
1. From start to finish, it was generated entirely synthetically through Anthropic's Claude AI.
2. It was generated using a somewhat imperfect recreation of the evol-instruct method. 50k instructions were initially synthetically generated then ran through four epochs of evol-instruct. | 499 | [
[
-0.03729248046875,
-0.07159423828125,
0.03961181640625,
-0.0069580078125,
0.0162353515625,
0.001171112060546875,
-0.0028095245361328125,
-0.0401611328125,
0.0247344970703125,
0.05126953125,
-0.0758056640625,
-0.003082275390625,
-0.0235748291015625,
0.0178985... |
d0rj/full-hh-rlhf-ru | 2023-06-16T08:04:18.000Z | [
"task_categories:text-classification",
"language_creators:translated",
"multilinguality:monolingual",
"size_categories:100K<n<1M",
"source_datasets:Dahoas/full-hh-rlhf",
"language:ru",
"reward",
"ChatGPT",
"human-feedback",
"region:us"
] | d0rj | null | null | 1 | 6 | 2023-06-14T13:40:04 | ---
dataset_info:
features:
- name: prompt
dtype: string
- name: response
dtype: string
- name: chosen
dtype: string
- name: rejected
dtype: string
splits:
- name: train
num_bytes: 315825386
num_examples: 112052
- name: test
num_bytes: 22606646
num_examples: 12451
download_size: 176330770
dataset_size: 338432032
task_categories:
- text-classification
language:
- ru
language_creators:
- translated
source_datasets:
- Dahoas/full-hh-rlhf
multilinguality:
- monolingual
tags:
- reward
- ChatGPT
- human-feedback
size_categories:
- 100K<n<1M
---
# full-hh-rlhf-ru
This is translated version of [Dahoas/full-hh-rlhf](https://huggingface.co/datasets/Dahoas/full-hh-rlhf) dataset into Russian. | 742 | [
[
0.01058197021484375,
-0.0491943359375,
0.021728515625,
0.026123046875,
-0.04766845703125,
0.0033092498779296875,
0.02001953125,
-0.0304718017578125,
0.0599365234375,
0.0399169921875,
-0.0736083984375,
-0.04534912109375,
-0.0340576171875,
0.0184173583984375,
... |
open-source-metrics/preprocessed_pip | 2023-10-26T12:04:57.000Z | [
"region:us"
] | open-source-metrics | null | null | 0 | 6 | 2023-06-14T19:10:29 | ---
dataset_info:
features:
- name: pytorch_image_models
dtype: int64
- name: tokenizers
dtype: int64
- name: transformers
dtype: int64
- name: evaluate
dtype: int64
- name: gradio
dtype: int64
- name: accelerate
dtype: int64
- name: huggingface_hub
dtype: int64
- name: datasets
dtype: int64
- name: optimum
dtype: int64
- name: safetensors
dtype: int64
- name: diffusers
dtype: int64
- name: peft
dtype: int64
- name: langchain
dtype: int64
- name: pytorch
dtype: int64
- name: tensorflow
dtype: int64
- name: day
dtype: string
splits:
- name: raw
num_bytes: 204261
num_examples: 1506
- name: wow
num_bytes: 29161
num_examples: 215
download_size: 119378
dataset_size: 233422
---
# Dataset Card for "preprocessed_pip"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 975 | [
[
-0.039520263671875,
-0.007232666015625,
0.0038051605224609375,
0.031341552734375,
-0.022857666015625,
-0.00943756103515625,
0.0285491943359375,
0.00638580322265625,
0.061767578125,
0.03814697265625,
-0.05633544921875,
-0.05224609375,
-0.04559326171875,
-0.01... |
juniorrios/icomp-dog-breed | 2023-06-15T00:49:19.000Z | [
"region:us"
] | juniorrios | null | null | 0 | 6 | 2023-06-15T00:47:34 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
CoolOppo/WizardLM_evol_instruct_V2_196k_uncensored | 2023-06-17T14:06:09.000Z | [
"uncensored",
"wizard",
"region:us"
] | CoolOppo | null | null | 3 | 6 | 2023-06-17T13:58:31 | ---
tags:
- uncensored
- wizard
---
Uncensored version of [WizardLM_evol_instruct_V2_196k](https://huggingface.co/datasets/WizardLM/WizardLM_evol_instruct_V2_196k) (filtered the Wizard dataset and merged it with the (already uncensored) ShareGPT dataset that they link to.)
Uncensoring was done with [my rust rewrite](https://github.com/CoolOppo/wizard-clean) of the cleaner script used by [Eric Hartford](https://erichartford.com/uncensored-models) et, al. It uses all the exact same words, just compiled into a big RegEx so it runs faster. | 543 | [
[
-0.024505615234375,
-0.031219482421875,
-0.00003987550735473633,
-0.01039886474609375,
-0.0279541015625,
0.0048828125,
-0.00601959228515625,
-0.0300750732421875,
0.005023956298828125,
0.0758056640625,
-0.03485107421875,
-0.048736572265625,
-0.0243072509765625,
... |
dmayhem93/agieval-gaokao-chemistry | 2023-06-18T17:17:33.000Z | [
"license:mit",
"arxiv:2304.06364",
"region:us"
] | dmayhem93 | null | null | 0 | 6 | 2023-06-18T12:47:32 | ---
dataset_info:
features:
- name: query
dtype: string
- name: choices
sequence: string
- name: gold
sequence: int64
splits:
- name: test
num_bytes: 173207
num_examples: 207
download_size: 78411
dataset_size: 173207
license: mit
---
# Dataset Card for "agieval-gaokao-chemistry"
Dataset taken from https://github.com/microsoft/AGIEval and processed as in that repo.
MIT License
Copyright (c) Microsoft Corporation.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE
@misc{zhong2023agieval,
title={AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models},
author={Wanjun Zhong and Ruixiang Cui and Yiduo Guo and Yaobo Liang and Shuai Lu and Yanlin Wang and Amin Saied and Weizhu Chen and Nan Duan},
year={2023},
eprint={2304.06364},
archivePrefix={arXiv},
primaryClass={cs.CL}
} | 1,839 | [
[
-0.01190185546875,
-0.02947998046875,
0.0205535888671875,
0.017059326171875,
-0.0089263916015625,
-0.002597808837890625,
0.00787353515625,
-0.0172576904296875,
-0.0003974437713623047,
0.036468505859375,
-0.041168212890625,
-0.04827880859375,
-0.0267181396484375,... |
dmayhem93/agieval-gaokao-physics | 2023-06-18T17:22:01.000Z | [
"license:mit",
"arxiv:2304.06364",
"region:us"
] | dmayhem93 | null | null | 0 | 6 | 2023-06-18T12:48:50 | ---
dataset_info:
features:
- name: query
dtype: string
- name: choices
sequence: string
- name: gold
sequence: int64
splits:
- name: test
num_bytes: 136757
num_examples: 200
download_size: 70363
dataset_size: 136757
license: mit
---
# Dataset Card for "agieval-gaokao-physics"
Dataset taken from https://github.com/microsoft/AGIEval and processed as in that repo.
MIT License
Copyright (c) Microsoft Corporation.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to deal
in the Software without restriction, including without limitation the rights
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in all
copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
SOFTWARE
@misc{zhong2023agieval,
title={AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models},
author={Wanjun Zhong and Ruixiang Cui and Yiduo Guo and Yaobo Liang and Shuai Lu and Yanlin Wang and Amin Saied and Weizhu Chen and Nan Duan},
year={2023},
eprint={2304.06364},
archivePrefix={arXiv},
primaryClass={cs.CL}
} | 1,837 | [
[
-0.0128021240234375,
-0.038177490234375,
0.0138092041015625,
0.0187835693359375,
-0.02362060546875,
-0.0106353759765625,
0.0133209228515625,
-0.0288543701171875,
-0.00010281801223754883,
0.021484375,
-0.047698974609375,
-0.026580810546875,
-0.037322998046875,
... |
haandol/icon | 2023-07-14T07:16:28.000Z | [
"language:en",
"region:us"
] | haandol | null | null | 1 | 6 | 2023-06-20T11:59:13 | ---
language: en
dataset_info:
features:
- name: image
dtype: image
- name: text
dtype: string
splits:
- name: train
num_bytes: 5823068.0
num_examples: 263
download_size: 5306675
dataset_size: 5823068.0
---
# Dataset Card for "icon"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 395 | [
[
-0.04449462890625,
-0.00867462158203125,
0.007518768310546875,
0.00681304931640625,
-0.01239013671875,
0.01050567626953125,
0.030303955078125,
-0.023712158203125,
0.067626953125,
0.0278778076171875,
-0.05462646484375,
-0.05328369140625,
-0.043731689453125,
-... |
microsoft/LCC_csharp | 2023-06-21T02:59:17.000Z | [
"region:us"
] | microsoft | null | null | 3 | 6 | 2023-06-21T02:46:10 | ---
dataset_info:
features:
- name: context
dtype: string
- name: gt
dtype: string
splits:
- name: train
num_bytes: 1851797668
num_examples: 100000
- name: validation
num_bytes: 136620599
num_examples: 10000
- name: test
num_bytes: 136701413
num_examples: 10000
download_size: 581666513
dataset_size: 2125119680
---
# Dataset Card for "LCC_csharp"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 530 | [
[
-0.031463623046875,
0.00537872314453125,
0.0107574462890625,
0.01580810546875,
-0.0077972412109375,
0.02471923828125,
0.0026702880859375,
-0.01253509521484375,
0.047393798828125,
0.033782958984375,
-0.05999755859375,
-0.0633544921875,
-0.02459716796875,
-0.0... |
tasksource/mtop | 2023-06-23T12:49:07.000Z | [
"task_categories:text-classification",
"multilinguality:multilingual",
"license:cc-by-sa-4.0",
"multilingual",
"intent",
"arxiv:2008.09335",
"region:us"
] | tasksource | @article{li2020mtop,
title={MTOP: A comprehensive multilingual task-oriented semantic parsing benchmark},
author={Li, Haoran and Arora, Abhinav and Chen, Shuohui and Gupta, Anchit and Gupta, Sonal and Mehdad, Yashar},
journal={arXiv preprint arXiv:2008.09335},
year={2020}
} | 0 | 6 | 2023-06-23T12:35:09 | ---
license: cc-by-sa-4.0
task_categories:
- text-classification
tags:
- multilingual
- intent
multilinguality:
- multilingual
---
https://arxiv.org/pdf/2008.09335.pdf
```
@article{li2020mtop,
title={MTOP: A comprehensive multilingual task-oriented semantic parsing benchmark},
author={Li, Haoran and Arora, Abhinav and Chen, Shuohui and Gupta, Anchit and Gupta, Sonal and Mehdad, Yashar},
journal={arXiv preprint arXiv:2008.09335},
year={2020}
}
``` | 458 | [
[
-0.01446533203125,
-0.038970947265625,
0.029327392578125,
0.017181396484375,
-0.019134521484375,
-0.01904296875,
-0.0162200927734375,
-0.048828125,
-0.0086669921875,
0.0406494140625,
-0.04052734375,
-0.0400390625,
-0.047271728515625,
0.0253143310546875,
... | |
wendlerc/RenderedText | 2023-07-12T09:28:10.000Z | [
"task_categories:text-to-image",
"task_categories:image-to-text",
"size_categories:10M<n<100M",
"language:en",
"OCR",
"blender",
"LAION",
"Stability",
"region:us"
] | wendlerc | null | null | 4 | 6 | 2023-06-26T11:26:16 | ---
task_categories:
- text-to-image
- image-to-text
language:
- en
tags:
- OCR
- blender
- LAION
- Stability
size_categories:
- 10M<n<100M
---
*This dataset has been created by Stability AI and LAION.*
This dataset contains 12 million 1024x1024 images of handwritten text written on a digital 3D sheet of paper generated using Blender geometry nodes and rendered using Blender Cycles. The text has varying font size, color, and rotation, and the paper was rendered under random lighting conditions.
Note that, the first 10 million examples are in the root folder of this dataset repository and the remaining 2 million are in ./remaining (due to the constraint on number of files per directory).
It was generated with the script https://github.com/GbotHQ/ocr-dataset-rendering/, which utilizes:
- ~8000 fonts from https://www.urbanfonts.com/free-fonts.htm and https://www.fontspace.com/
- 643 CC0 HDRIs from https://polyhaven.com/
- 1837 CC0 PRB materials from https://ambientcg.com/
- random sentences sampled from https://huggingface.co/datasets/ChristophSchuhmann/wikipedia-en-nov22-1-sentence-level and https://huggingface.co/datasets/ChristophSchuhmann/1-sentence-level-gutenberg-en_arxiv_pubmed_soda
to generate example images as shown below.
The dataset contains both line-level, as well as character level annotations for each example. The annotations are stored in the accompanying json files and are of the following form:
```
{
'ocr_annotation':
{'bounding_boxes': [[[145.0, 370.0], [788.0, 353.0], [827.0, 633.0], [182.0, 669.0]]],
'text': ['Joe.'],
'bb_relative': [[[0.1416015625, 0.361328125], [0.76953125, 0.3447265625], [0.8076171875, 0.6181640625], [0.177734375, 0.6533203125]]],
'char': ['J', 'o', 'e', '.'],
'char_idx': [0, 1, 2, 3],
'bb_character_level': [[[145.0, 370.0], [346.0, 365.0], [382.0, 651.0], [181.0, 662.0]], [[375.0, 438.0], [557.0, 431.0], [585.0, 640.0], [402.0, 650.0]], [[578.0, 440.0], [744.0, 434.0], [771.0, 629.0], [604.0, 638.0]], [[778.0, 591.0], [821.0, 589.0], [827.0, 633.0], [784.0, 635.0]]],
'font_path': '/fsx/home-wendlerc/blender-dataset/assets/fonts/fontcollection/HelloScribbles-axapm.ttf',
'font_color': [17, 25, 231],
'text_rotation_angle': 7},
'width':1024,
'height':1024,
}
```
Browse a few more examples here: https://colab.research.google.com/drive/1o0rZhtY9aeurzNrAbu6nJypULSIIcf1v?authuser=1 | 2,588 | [
[
-0.022705078125,
-0.040069580078125,
0.0289459228515625,
-0.011810302734375,
-0.005268096923828125,
-0.0013141632080078125,
-0.0033054351806640625,
-0.048248291015625,
0.0218048095703125,
0.054290771484375,
-0.032501220703125,
-0.06304931640625,
-0.0392761230468... |
Einstellung/wiki_art | 2023-06-27T23:51:34.000Z | [
"region:us"
] | Einstellung | Este dataset fue creado para el workshop de Medellin AI y Bancolombia con fines educativos. | @InProceedings{huggingface:dataset,
title = {WikiArt},
author={Medellín AI.
},
year={2023}
} | 0 | 6 | 2023-06-27T23:51:32 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
JourneyDB/JourneyDB | 2023-08-10T14:19:04.000Z | [
"arxiv:2307.00716",
"region:us"
] | JourneyDB | null | null | 25 | 6 | 2023-06-28T08:32:06 | ---
extra_gated_prompt: "You have carefully read the [Terms of Usage](https://journeydb.github.io/assets/Terms_of_Usage.html) and agree with the listed terms."
extra_gated_fields:
First Name: text
Last Name: text
Affiliation: text
I agree with our JourneyDB usage terms and I will obey the terms when using the JourneyDB dataset: checkbox
---
---
task_categories:
- image-to-text
language:
- en
size_categories:
- 1M<n<10M
---
# JourneyDB
[[Project Page]](https://journeydb.github.io) [[Paper]](https://arxiv.org/abs/2307.00716) [[Code]](https://github.com/JourneyDB/JourneyDB) [[HuggingFace]](https://huggingface.co/datasets/JourneyDB/JourneyDB) [[OpenDataLab]]()
## Dataset Description
### Summary
**JourneyDB** is a large-scale generated image understanding dataset that contains **4,429,295** high-resolution Midjourney images, annotated with corresponding **text prompt**, **image caption** and **visual question answering**.
### Supported Tasks
**JourneyDB** supports **4** downstream tasks, i.e. **Prompt Inversion**, **Style Retrieval**, **Image Caption**, and **Visual Question Answering**. We evaluate many existing methods on these tasks and provide a comprehensive benchmark. Please see our [Paper](https://arxiv.org/abs/2307.00716) for more details.
## Dataset Details
### Data Collection
For each image instance, we acquire the corresponding text prompts used to generate the images with Midjourney. Furthermore, we employ GPT3.5 to generate the caption and VAQ groundtruth.
### Data Instances
We provide several examples to show the contents of each dataset instance.
### Data Splits
We provide detailed statistics for each split subset in the following table. We randomly split the whole dataset into roughly 20 : 1 to obtain the training and validation set. The training set contains 4,189,737 labeled images and 1,385,317 labeled prompts. The validation set contains 235,156 images and 82,093 prompts. And we additionally sample a testing set for manual filtering. The testing set contains 5,402 images and 5,171 prompts.
| | Image | Prompt | Labeled Image | Labeled Prompt | Style QA | Content QA |
|----------------|:---------:|:---------:|:-------------:|:--------------:|:---------:|:----------:|
| Training Set | 4,453,193 | 1,643,375 | 4,189,737 | 1,385,317 | 7,056,394 | 8,775,971 |
| Validation Set | 234,156 | 82,093 | 234,156 | 82,093 | 311,569 | 374,310 |
| Testing Set | 5,402 | 5,171 | 5,402 | 5,171 | 10,040 | 11,369 |
| Total | 4,692,751 | 1,730,639 | 4,429,295 | 1,472,581 | 7,378,003 | 9,161,650 |
## Acquirements
### License
The JourneyDB dataset is available under the customised [Terms of Usage](./assets/Terms_of_Usage.md).
### Citation
```
@misc{pan2023journeydb,
title={JourneyDB: A Benchmark for Generative Image Understanding},
author={Junting Pan and Keqiang Sun and Yuying Ge and Hao Li and Haodong Duan and Xiaoshi Wu and Renrui Zhang and Aojun Zhou and Zipeng Qin and Yi Wang and Jifeng Dai and Yu Qiao and Hongsheng Li},
year={2023},
eprint={2307.00716},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```
### Contributions
[Junting Pan](https://junting.github.io)\*, [Keqiang Sun](https://keqiangsun.github.io)\*, [Yuying Ge](https://geyuying.github.io), [Hao Li](https://cpsxhao.github.io), [Haodong Duan](https://kennymckormick.github.io), [Xiaoshi Wu](https://github.com/tgxs002), [Renrui Zhang](https://github.com/ZrrSkywalker), [Aojun Zhou](https://scholar.google.com/citations?user=cC8lXi8AAAAJ&hl=en), [Zipeng Qin](https://www.linkedin.cn/incareer/in/zipeng-bruce-qin-846a65119), [Yi Wang](https://shepnerd.github.io), [Jifeng Dai](https://jifengdai.org), [Yu Qiao](http://mmlab.siat.ac.cn/yuqiao/), [Hongsheng Li](https://www.ee.cuhk.edu.hk/~hsli/)<sup>+</sup>
(\* equal contribution, <sup>+</sup> corresponding author)
### Contact
If you have any problem or suggestion, please feel free to open an issue or send emails to the contributors. | 4,200 | [
[
-0.0399169921875,
-0.0214385986328125,
0.031341552734375,
0.02117919921875,
-0.019500732421875,
-0.0067596435546875,
0.0055999755859375,
-0.03363037109375,
0.0026645660400390625,
0.033660888671875,
-0.053741455078125,
-0.0670166015625,
-0.037872314453125,
0.... |
llm-lens/lens_sample_test | 2023-09-18T01:27:52.000Z | [
"region:us"
] | llm-lens | null | null | 0 | 6 | 2023-06-29T03:45:56 | ---
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': abyssinian
'1': american bulldog
'2': american pit bull terrier
'3': basset hound
'4': beagle
'5': bengal
'6': birman
'7': bombay
'8': boxer
'9': british shorthair
'10': chihuahua
'11': egyptian mau
'12': english cocker spaniel
'13': english setter
'14': german shorthaired
'15': great pyrenees
'16': havanese
'17': japanese chin
'18': keeshond
'19': leonberger
'20': maine coon
'21': miniature pinscher
'22': newfoundland
'23': persian
'24': pomeranian
'25': pug
'26': ragdoll
'27': russian blue
'28': saint bernard
'29': samoyed
'30': scottish terrier
'31': shiba inu
'32': siamese
'33': sphynx
'34': staffordshire bull terrier
'35': wheaten terrier
'36': yorkshire terrier
- name: id
dtype: int64
- name: tags_laion-ViT-H-14-2B
sequence: string
- name: attributes_laion-ViT-H-14-2B
sequence: string
- name: caption_Salesforce-blip-image-captioning-large
dtype: string
- name: intensive_captions_Salesforce-blip-image-captioning-large
sequence: string
splits:
- name: test
num_bytes: 183543.0
num_examples: 10
download_size: 162581
dataset_size: 183543.0
---
# Dataset Card for "lens_sample_test"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 1,776 | [
[
-0.04754638671875,
-0.0232391357421875,
0.01494598388671875,
0.0077056884765625,
-0.005950927734375,
-0.01538848876953125,
0.01421356201171875,
-0.01068115234375,
0.042572021484375,
0.022308349609375,
-0.076904296875,
-0.053497314453125,
-0.0272064208984375,
... |
9wimu9/sinhala_30m | 2023-07-01T18:46:04.000Z | [
"region:us"
] | 9wimu9 | null | null | 1 | 6 | 2023-07-01T18:26:22 | ---
dataset_info:
features:
- name: id
dtype: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 7579499129.883565
num_examples: 30600246
- name: test
num_bytes: 421083367.55821764
num_examples: 1700014
- name: valid
num_bytes: 421083367.55821764
num_examples: 1700014
download_size: 4095088923
dataset_size: 8421665865.000001
---
# Dataset Card for "sinhala_30m"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 561 | [
[
-0.034576416015625,
-0.0092315673828125,
0.0011453628540039062,
0.03009033203125,
-0.0235595703125,
-0.00348663330078125,
0.0031642913818359375,
-0.010284423828125,
0.054656982421875,
0.045379638671875,
-0.05194091796875,
-0.053863525390625,
-0.037567138671875,
... |
kinyugo/lima_concatenated | 2023-07-23T19:16:28.000Z | [
"language:en",
"region:us"
] | kinyugo | null | null | 0 | 6 | 2023-07-02T19:10:10 | ---
language: en
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 2883591
num_examples: 1030
- name: test
num_bytes: 37237
num_examples: 300
download_size: 1722252
dataset_size: 2920828
---
# Dataset Card for "lima_concatenated"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 430 | [
[
-0.0298004150390625,
-0.0298309326171875,
0.0080413818359375,
0.04217529296875,
-0.05010986328125,
-0.0013484954833984375,
0.01629638671875,
-0.021728515625,
0.063232421875,
0.046478271484375,
-0.05621337890625,
-0.0528564453125,
-0.06494140625,
-0.011108398... |
Ngadou/social-engineering-convo | 2023-07-03T01:36:04.000Z | [
"task_categories:text-classification",
"size_categories:n<1K",
"language:en",
"language:fr",
"license:apache-2.0",
"region:us"
] | Ngadou | null | null | 1 | 6 | 2023-07-03T01:31:10 | ---
license: apache-2.0
task_categories:
- text-classification
language:
- en
- fr
pretty_name: Social Engineering Conversation modelling
size_categories:
- n<1K
---
Social Engineering Conversation modelling
## Rational
LLM are few shot learners | 248 | [
[
-0.005176544189453125,
-0.0694580078125,
0.033203125,
0.017730712890625,
-0.0038604736328125,
0.033599853515625,
0.030975341796875,
-0.005794525146484375,
0.0011281967163085938,
0.0382080078125,
-0.0469970703125,
-0.0440673828125,
-0.0228424072265625,
-0.016... |
bias-amplified-splits/anli | 2023-07-04T11:49:28.000Z | [
"task_categories:text-classification",
"size_categories:100K<n<1M",
"language:en",
"license:cc-by-nc-4.0",
"arxiv:2305.18917",
"arxiv:1910.14599",
"region:us"
] | bias-amplified-splits | The Adversarial Natural Language Inference (ANLI) is a new large-scale NLI benchmark dataset,
The dataset is collected via an iterative, adversarial human-and-model-in-the-loop procedure.
ANLI is much more difficult than its predecessors including SNLI and MNLI.
It contains three rounds. Each round has train/dev/test splits. | @InProceedings{nie2019adversarial,
title={Adversarial NLI: A New Benchmark for Natural Language Understanding},
author={Nie, Yixin
and Williams, Adina
and Dinan, Emily
and Bansal, Mohit
and Weston, Jason
and Kiela, Douwe},
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
year = "2020",
publisher = "Association for Computational Linguistics",
} | 0 | 6 | 2023-07-03T20:55:29 | ---
license: cc-by-nc-4.0
dataset_info:
- config_name: minority_examples
features:
- name: round
dtype: string
- name: uid
dtype: string
- name: premise
dtype: string
- name: hypothesis
dtype: string
- name: label
dtype:
class_label:
names:
'0': entailment
'1': neutral
'2': contradiction
- name: reason
dtype: string
splits:
- name: train.biased
num_bytes: 61260115
num_examples: 134068
- name: train.anti_biased
num_bytes: 13246263
num_examples: 28797
- name: validation.biased
num_bytes: 1311433
num_examples: 2317
- name: validation.anti_biased
num_bytes: 500409
num_examples: 883
- name: test.biased
num_bytes: 1284544
num_examples: 2262
- name: test.anti_biased
num_bytes: 539798
num_examples: 938
download_size: 86373189
dataset_size: 78142562
- config_name: partial_input
features:
- name: round
dtype: string
- name: uid
dtype: string
- name: premise
dtype: string
- name: hypothesis
dtype: string
- name: label
dtype:
class_label:
names:
'0': entailment
'1': neutral
'2': contradiction
- name: reason
dtype: string
splits:
- name: train.biased
num_bytes: 60769911
num_examples: 134068
- name: train.anti_biased
num_bytes: 13736467
num_examples: 28797
- name: validation.biased
num_bytes: 1491254
num_examples: 2634
- name: validation.anti_biased
num_bytes: 320588
num_examples: 566
- name: test.biased
num_bytes: 1501586
num_examples: 2634
- name: test.anti_biased
num_bytes: 322756
num_examples: 566
download_size: 86373189
dataset_size: 78142562
task_categories:
- text-classification
language:
- en
pretty_name: Adversarial NLI
size_categories:
- 100K<n<1M
---
# Dataset Card for Bias-amplified Splits for Adversarial NLI
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Annotations](#annotations)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Citation Information](#citation-information)
## Dataset Description
- **Repository:** [Fighting Bias with Bias repo](https://github.com/schwartz-lab-nlp/fight-bias-with-bias)
- **Paper:** [arXiv](https://arxiv.org/abs/2305.18917)
- **Point of Contact:** [Yuval Reif](mailto:yuval.reif@mail.huji.ac.il)
- **Original Dataset's Paper:** [ANLI](https://arxiv.org/abs/1910.14599)
### Dataset Summary
Bias-amplified splits is a novel evaluation framework to assess model robustness, by amplifying dataset biases in the training data and challenging models to generalize beyond them. This framework is defined by a bias-amplified training set and a hard, anti-biased test set, which we automatically extract from existing datasets using model-based methods.
Our experiments show that the identified anti-biased examples are naturally challenging for models, and moreover, models trained on bias-amplified data exhibit dramatic performance drops on anti-biased examples, which are not mitigated by common approaches to improve generalization.
Here we apply our framework to Adversarial Natural Language Inference (ANLI), a large-scale NLI benchmark dataset. The dataset was collected via an iterative, adversarial human-and-model-in-the-loop procedure. ANLI is much more difficult than its predecessors including SNLI and MNLI.
Our evaluation framework can be applied to any existing dataset, even those considered obsolete, to test model robustness. We hope our work will guide the development of robust models that do not rely on superficial biases and correlations.
#### Evaluation Results (DeBERTa-large)
##### For splits based on minority examples:
| Training Data \ Test Data | Original test | Anti-biased test |
|---------------------------|---------------|------------------|
| Original training split | 67.5 | 58.3 |
| Biased training split | 60.6 | 21.4 |
##### For splits based on partial-input model:
| Training Data \ Test Data | Original test | Anti-biased test |
|---------------------------|---------------|------------------|
| Original training split | 67.5 | 50.0 |
| Biased training split | 62.5 | 28.3 |
#### Loading the Data
ANLI contains three rounds of data collection, and each round has train/dev/test splits. We concatenated the splits from all rounds to create one train/dev/test splits.
```
from datasets import load_dataset
# choose which bias detection method to use for the bias-amplified splits: either "minority_examples" or "partial_input"
dataset = load_dataset("bias-amplified-splits/anli", "minority_examples")
# use the biased training split and anti-biased test split
train_dataset = dataset['train.biased']
eval_dataset = dataset['validation.anti_biased']
```
## Dataset Structure
### Data Instances
Data instances are taken directly from ANLI, and re-split into biased and anti-biased subsets. Here is an example of an instance from the dataset:
```
{
"round": "r1",
"idx": "20a331ee-cf54-4e8a-9ff9-6152cd679780",
"premise": "Milton Teagle "Richard" Simmons (born July 12, 1948) is an American fitness guru, actor, and comedian. He promotes weight-loss programs, prominently through his "Sweatin' to the Oldies" line of aerobics videos and is known for his eccentric, flamboyant, and energetic personality.",
"hypothesis": "Milton Teagle "Richard" Simmons created his "Sweatin' to the Oldies" line of aerobics videos without help or input from anyone else.",
"label": 1,
"reason": "The context gives no information as to how the "Sweatin' to the Oldies" videos are produced, Simmons may well produce them alone, or may produce them with a team. The system may have had difficulty with this because it is unlikely that Simmons produced the videos alone."
}
```
### Data Fields
- `round`: which round of data collection the example comes from (one of `r1`, `r2` and `r3`)
- `uid`: unique identifier for the example.
- `premise`: a piece of text
- `hypothesis`: a piece of text that may be true, false, or whose truth conditions may not be knowable when compared to the premise
- `label`: one of `0`, `1` and `2` (`entailment`, `neutral`, and `contradiction`)
- `reason`: explanation why the label is true (only for some examples).
### Data Splits
Bias-amplified splits require a method to detect *biased* and *anti-biased* examples in datasets. We release bias-amplified splits based created with each of these two methods:
- **Minority examples**: A novel method we introduce that leverages representation learning and clustering for identifying anti-biased *minority examples* (Tu et al., 2020)—examples that defy common statistical patterns found in the rest of the dataset.
- **Partial-input baselines**: A common method for identifying biased examples containing annotation artifacts in a dataset, which examines the performance of models that are restricted to using only part of the input. Such models, if successful, are bound to rely on unintended or spurious patterns in the dataset.
Using each of the two methods, we split each of the original train and test splits into biased and anti-biased subsets. See the [paper](https://arxiv.org/abs/2305.18917) for more details.
#### Minority Examples
| Dataset Split | Number of Instances in Split |
|--------------------------|------------------------------|
| Train - biased | 134068 |
| Train - anti-biased | 28797 |
| Validation - biased | 2317 |
| Validation - anti-biased | 883 |
| Test - biased | 2262 |
| Test - anti-biased | 938 |
#### Partial-input Baselines
| Dataset Split | Number of Instances in Split |
|--------------------------|------------------------------|
| Train - biased | 134068 |
| Train - anti-biased | 28797 |
| Validation - biased | 2634 |
| Validation - anti-biased | 566 |
| Test - biased | 2634 |
| Test - anti-biased | 566 |
## Dataset Creation
### Curation Rationale
NLP models often rely on superficial cues known as *dataset biases* to achieve impressive performance, and can fail on examples where these biases do not hold. To develop more robust, unbiased models, recent work aims to filter bisased examples from training sets. We argue that in order to encourage the development of robust models, we should in fact **amplify** biases in the training sets, while adopting the challenge set approach and making test sets anti-biased. To implement our approach, we introduce a simple framework that can be applied automatically to any existing dataset to use it for testing model robustness.
### Annotations
#### Annotation process
No new annotations are required to create bias-amplified splits. Existing data instances are split into *biased* and *anti-biased* splits based on automatic model-based methods to detect such examples.
## Considerations for Using the Data
### Social Impact of Dataset
Bias-amplified splits were created to promote the development of robust NLP models that do not rely on superficial biases and correlations, and provide more challenging evaluation of existing systems.
### Discussion of Biases
We propose to use bias-amplified splits to complement benchmarks with challenging evaluation settings that test model robustness, in addition to the dataset’s main training and test sets. As such, while existing dataset biases are *amplified* during training with bias-amplified splits, these splits are intended primarily for model evaluation, to expose the bias-exploiting behaviors of models and to identify more robsut models and effective robustness interventions.
## Additional Information
### Dataset Curators
Bias-amplified splits were introduced by Yuval Reif and Roy Schwartz from the [Hebrew University of Jerusalem](https://schwartz-lab-huji.github.io).
ANLI was developed by Adina Williams, Tristan Thrush and Douwe Kiela.
### Citation Information
```
@misc{reif2023fighting,
title = "Fighting Bias with Bias: Promoting Model Robustness by Amplifying Dataset Biases",
author = "Yuval Reif and Roy Schwartz",
month = may,
year = "2023",
url = "https://arxiv.org/pdf/2305.18917",
}
```
Source dataset:
```
@article{williams-etal-2020-anlizing,
title = "ANLIzing the Adversarial Natural Language Inference Dataset",
author = "Adina Williams and
Tristan Thrush and
Douwe Kiela",
booktitle = "Proceedings of the 5th Annual Meeting of the Society for Computation in Linguistics",
year = "2022",
publisher = "Association for Computational Linguistics",
}
``` | 11,515 | [
[
-0.057159423828125,
-0.0633544921875,
-0.0003063678741455078,
-0.002429962158203125,
-0.0115203857421875,
-0.0081939697265625,
-0.013458251953125,
-0.01983642578125,
0.023162841796875,
0.0219573974609375,
-0.053680419921875,
-0.0292816162109375,
-0.0603942871093... |
jjzha/gnehm | 2023-09-07T12:14:33.000Z | [
"language:de",
"license:cc-by-nc-sa-4.0",
"region:us"
] | jjzha | null | null | 0 | 6 | 2023-07-04T13:44:11 | ---
license: cc-by-nc-sa-4.0
language: de
---
This is the skill dataset created by:
```
@inproceedings{gnehm-etal-2022-fine,
title = "Fine-Grained Extraction and Classification of Skill Requirements in {G}erman-Speaking Job Ads",
author = {Gnehm, Ann-sophie and
B{\"u}hlmann, Eva and
Buchs, Helen and
Clematide, Simon},
booktitle = "Proceedings of the Fifth Workshop on Natural Language Processing and Computational Social Science (NLP+CSS)",
month = nov,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.nlpcss-1.2",
doi = "10.18653/v1/2022.nlpcss-1.2",
pages = "14--24",
}
```
There are document delimiters indicated by `idx`.
Number of samples (sentences):
- train: 19889
- dev: 2332
- test: 2557
Sources:
- Swiss Job Market Monitor (SJMM): https://www.swissubase.ch/en/
Type of tags:
- BI(-ICT) and O tags with keys `tags_skill`
Sample:
```
{
"idx": 198,
"tokens": ["-", "besitzen", "fundierte", "Anwenderkenntnisse", "in", "MS-Office"],
"tags_skill": ["O", "O", "O", "O", "O", "B-ICT"]
}
``` | 1,166 | [
[
-0.022918701171875,
-0.044769287109375,
0.0214691162109375,
-0.01287841796875,
-0.015899658203125,
0.006038665771484375,
-0.023406982421875,
-0.03021240234375,
0.01390838623046875,
0.035247802734375,
-0.0433349609375,
-0.0635986328125,
-0.052093505859375,
0.... |
t4tiana/store-sales-time-series-forecasting | 2023-07-05T07:00:06.000Z | [
"region:us"
] | t4tiana | null | null | 1 | 6 | 2023-07-05T06:51:09 | # *taken from [this Kaggle competition](https://www.kaggle.com/competitions/store-sales-time-series-forecasting/data)*:
# Dataset Description
In this competition, you will predict sales for the thousands of product families sold at Favorita stores located in Ecuador. The training data includes dates, store and product information, whether that item was being promoted, as well as the sales numbers. Additional files include supplementary information that may be useful in building your models.
#### File Descriptions and Data Field Information
**train.csv**</br>
The training data, comprising time series of features store_nbr, family, and onpromotion as well as the target sales.</br>
`store_nbr` identifies the store at which the products are sold.</br>
`family` identifies the type of product sold.</br>
`sales` gives the total sales for a product family at a particular store at a given date. Fractional values are possible since products can be sold in fractional units (1.5 kg of cheese, for instance, as opposed to 1 bag of chips).
onpromotion gives the total number of items in a product family that were being promoted at a store at a given date.</br>
</br>
**test.csv**</br>
The test data, having the same features as the training data. You will predict the target sales for the dates in this file.</br>
The dates in the test data are for the 15 days after the last date in the training data.</br>
</br>
**sample_submission.csv**</br>
A sample submission file in the correct format.</br>
</br>
**stores.csv**</br>
Store metadata, including city, state, type, and cluster.</br>
`cluster` is a grouping of similar stores.</br>
</br>
**oil.csv**</br>
Daily oil price. Includes values during both the train and test data timeframes. (Ecuador is an oil-dependent country and it's economical health is highly vulnerable to shocks in oil prices.)
</br></br>
**holidays_events.csv**</br>
Holidays and Events, with metadata</br>
</br>
**NOTE:** Pay special attention to the transferred column. A holiday that is transferred officially falls on that calendar day, but was moved to another date by the government. A transferred day is more like a normal day than a holiday. To find the day that it was actually celebrated, look for the corresponding row where type is Transfer. For example, the holiday Independencia de Guayaquil was transferred from 2012-10-09 to 2012-10-12, which means it was celebrated on 2012-10-12. Days that are type Bridge are extra days that are added to a holiday (e.g., to extend the break across a long weekend). These are frequently made up by the type Work Day which is a day not normally scheduled for work (e.g., Saturday) that is meant to payback the Bridge.
Additional holidays are days added a regular calendar holiday, for example, as typically happens around Christmas (making Christmas Eve a holiday).
</br>
</br>
**Additional Notes**
- Wages in the public sector are paid every two weeks on the 15 th and on the last day of the month. Supermarket sales could be affected by this.
- A magnitude 7.8 earthquake struck Ecuador on April 16, 2016. People rallied in relief efforts donating water and other first need products which greatly affected supermarket sales for several weeks after the earthquake. | 3,243 | [
[
0.0006422996520996094,
-0.02825927734375,
0.0121612548828125,
0.0258941650390625,
-0.015472412109375,
-0.0018472671508789062,
0.002353668212890625,
-0.039581298828125,
0.0196990966796875,
0.028900146484375,
-0.05499267578125,
-0.053436279296875,
-0.0383605957031... |
declare-lab/flan-mini | 2023-07-06T05:19:06.000Z | [
"size_categories:1M<n<10M",
"license:cc",
"arxiv:2307.02053",
"region:us"
] | declare-lab | null | null | 11 | 6 | 2023-07-06T02:01:36 | ---
dataset_info:
features:
- name: id
dtype: string
- name: source
dtype: string
- name: conversations
dtype: list
splits:
- name: train
num_examples: 1340153
license: cc
size_categories:
- 1M<n<10M
---
# Dataset Card for Flan-mini
## Dataset Description
- **Repository:** https://github.com/declare-lab/flacuna
- **Paper:** https://arxiv.org/abs//2307.02053
- **Leaderboard:** https://declare-lab.net/instruct-eval/
- **Point of Contact:** sporia@sutd.edu.sg
### Dataset Summary
Given the enormous size of the Flan Collection, we opted to work with a carefully selected subset that maintains a high level of task diversity while reducing the overall dataset size. In the Table below, we present the specific tasks included in our subset of Flan, along with their respective dataset sizes.
As the public release of the Flan Collection does not include programming tasks, we augment the collection with existing code datasets.
Specifically, we include CodeContests, APPS, and CodeSearchNet.
Following the data processing pipeline of Flan Collection, we sample a fixed number of examples from each dataset, where each example is randomly augmented with different prompt templates.
Specifically, the examples are processed with a pool of handcrafted prompt templates and may be used as zero-shot examples or grouped together with few-shot demonstrations.
We incorporated various ChatGPT datasets, including Alpaca, Code Alpaca, and ShareGPT, into our Flan-mini collection.
| Dataset Name | Source | Dataset Size |
|-----------------------------|------------------------|--------------|
| Flan2021 | Flan | 388K |
| Public Pool of Prompts | Flan | 320K |
| Natural instructions v2 | Flan | 200K |
| CoT | Flan | 100K |
| Code Search | HF/code_search_net | 100K |
| Code Contest | HF/deepmind/code_contests | 50K |
| Apps | HF/codeparrot/apps | 50K |
| GPT4-Alpaca | GPT-4 | 52K |
| Code-Alpaca | ChatGPT | 20K |
| ShareGPT | ChatGPT | 60K |
| Total | - | 1.34M |
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Citation Information
```bibtex
@misc{ghosal2023flacuna,
title={Flacuna: Unleashing the Problem Solving Power of Vicuna using FLAN Fine-Tuning},
author={Deepanway Ghosal and Yew Ken Chia and Navonil Majumder and Soujanya Poria},
year={2023},
eprint={2307.02053},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` | 2,913 | [
[
-0.041015625,
-0.0390625,
0.01148223876953125,
-0.00016510486602783203,
-0.0005192756652832031,
-0.007404327392578125,
-0.0224456787109375,
-0.029754638671875,
0.0308685302734375,
0.025360107421875,
-0.044830322265625,
-0.0288848876953125,
-0.029937744140625,
... |
InfImagine/FakeImageDataset | 2023-08-13T09:00:14.000Z | [
"license:apache-2.0",
"arxiv:2304.13023",
"region:us"
] | InfImagine | null | null | 6 | 6 | 2023-07-07T04:08:51 | ---
license: apache-2.0
---
# Fake Image Dataset
Fake Image Dataset is now open-sourced at [huggingface (InfImagine Organization)](https://huggingface.co/datasets/InfImagine/FakeImageDataset/tree/main/ImageData/train). ↗ It consists of two folders, *ImageData* and *MetaData*. *ImageData* contains the compressed packages of the Fake Image Dataset, while *MetaData* contains the labeling information of the corresponding data indicating whether they are real or fake.
Sentry-Image is now open-sourced at [Sentry-Image (github repository)](https://github.com/Inf-imagine/Sentry) which provides the SOTA fake image detection models in [Sentry-Image Leaderboard](http://sentry.infimagine.com/) pretraining in [Fake Image Dataset](https://huggingface.co/datasets/InfImagine/FakeImageDataset/tree/main/ImageData/train) to detect whether the image provided is an AI-generated or real image.
## Why we need [Fake Image Dataset](https://huggingface.co/datasets/InfImagine/FakeImageDataset/tree/main/ImageData/train) and [Sentry-Image](http://sentry.infimagine.com/)?
* 🧐 Recent [study](https://arxiv.org/abs/2304.13023) have shown that humans struggle significantly to distinguish real photos from AI-generated ones, with a misclassification rate of **38.7%**.
* 🤗 To help people confirm whether the images they see are real images or AI-generated images, we launched the Sentry-Image project.
* 💻 Sentry-Image is an open source project which provides the SOTA fake image detection models in [Sentry-Image Leaderboard](http://sentry.infimagine.com/) to detect whether the image provided is an AI-generated or real image.
# Dataset card for Fake Image Dataset
## Dataset Description
* **Homepage:** [Sentry-Image](http://sentry.infimagine.com/)
* **Paper:** [https://arxiv.org/pdf/2304.13023.pdf](https://arxiv.org/pdf/2304.13023.pdf)
* **Point of Contact:** [contact@infimagine.com](mailto:contact@infimagine.com)
## How to Download
You can use following codes to download the dataset：
```shell
git lfs install
git clone https://huggingface.co/datasets/InfImagine/FakeImageDataset
```
You can use following codes to extract the files in each subfolder (take the *IF-CC95K* subfolder in ImageData/val/IF-CC95K as an example)：
```shell
cat IF-CC95K.tar.gz.* > IF-CC95K.tar.gz
tar -xvf IF-CC95K.tar.gz
```
## Dataset Summary
FakeImageDataset was created to serve as an large-scale dataset for the pretraining of detecting fake images.
It was built on StableDiffusion v1.5, IF and StyleGAN3.
## Supported Tasks and Leaderboards
FakeImageDataset is intended to be primarly used as a pretraining dataset for detecting fake images.
## Sub Dataset
### Training Dataset (Fake2M)
| Dataset | SD-V1.5Real-dpms-25 | IF-V1.0-dpms++-25 | StyleGAN3 |
| :----------- | :-----------: | :-----------: | :-----------: |
| Generator | Diffusion | Diffusion | GAN |
| Numbers | 1M | 1M | 87K |
| Resolution | 512 | 256 | (>=512) |
| Caption | CC3M-Train | CC3M-Train | - |
| ImageData Path | ImageData/train/SDv15R-CC1M | ImageData/train/IFv1-CC1M | ImageData/train/stylegan3-80K |
| MetaData Path | MetaData/train/SDv15R-CC1M.csv | MetaData/train/IF-CC1M.csv | MetaData/train/stylegan3-80K.csv |
### Validation Dataset (MPBench)
| Dataset | SDv15 | SDv21 | IF | Cogview2 | StyleGAN3 | Midjourneyv5 |
| :---------- | :-----------: | :-----------: | :-----------: | :-----------: | :-----------: | :-----------: |
| Generator | Diffusion | Diffusion | Diffusion | AR | GAN | - |
| Numbers | 30K | 15K | 95K | 22K | 60K | 5K |
| Resolution | 512 | 512 | 256 | 480 | (>=512) | (>=512) |
| Caption | CC15K-val | CC15K-val | CC15K-val | CC15K-val | - | - |
| ImageData Path | ImageData/val/SDv15-CC30K | ImageData/val/SDv21-CC15K | ImageData/val/IF-CC95K | ImageData/val/cogview2-22K | ImageData/val/stylegan3-60K | ImageData/val/Midjourneyv5-5K|
| MetaData Path | MetaData/val/SDv15-CC30K.csv| MetaData/val/SDv21-CC15K.csv | MetaData/val/IF-CC95K.csv | MetaData/val/cogview2-22K.csv | MetaData/val/stylegan3-60K.csv | MetaData/val/Midjourneyv5-5K.csv |
# News
* [2023/07] We open source the [Sentry-Image repository](https://github.com/Inf-imagine/Sentry) and [Sentry-Image Demo & Leaderboard](http://sentry.infimagine.com/).
* [2023/07] We open source the [Sentry-Image dataset](https://huggingface.co/datasets/InfImagine/FakeImageDataset).
Stay tuned for this project! Feel free to contact [contact@infimagine.com](contact@infimagine.com)! 😆
# License
This project is open-sourced under the [Apache-2.0](https://www.apache.org/licenses/LICENSE-2.0). These weights and datasets are fully open for academic research and can be used for commercial purposes with official written permission. If you find our open-source models and datasets useful for your business, we welcome your donation to support the development of the next-generation Sentry-Image model. Please contact [contact@infimagine.com](contact@infimagine.com) for commercial licensing and donation inquiries.
# Citation
The code and model in this repository is mostly developed for or derived from the paper below. Please cite it if you find the repository helpful.
```
@misc{sentry-image-leaderboard,
title = {Sentry-Image Leaderboard},
author = {Zeyu Lu, Di Huang, Chunli Zhang, Chengyue Wu, Xihui Liu, Lei Bai, Wanli Ouyang},
year = {2023},
publisher = {InfImagine, Shanghai AI Laboratory},
howpublished = "\url{https://github.com/Inf-imagine/Sentry}"
},
@misc{lu2023seeing,
title = {Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images},
author = {Zeyu Lu, Di Huang, Lei Bai, Jingjing Qu, Chengyue Wu, Xihui Liu, Wanli Ouyang},
year = {2023},
eprint = {2304.13023},
archivePrefix = {arXiv},
primaryClass = {cs.AI}
}
``` | 6,294 | [
[
-0.03692626953125,
-0.03350830078125,
0.01345062255859375,
-0.004306793212890625,
-0.0189971923828125,
-0.0010471343994140625,
0.0035724639892578125,
-0.046630859375,
0.0245361328125,
0.0263214111328125,
-0.052886962890625,
-0.041473388671875,
-0.0384521484375,
... |
DynamicSuperb/SpokenTermDetection_LJSpeech | 2023-07-12T14:05:11.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-07-10T14:21:50 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: text
dtype: string
- name: instruction
dtype: string
- name: label
dtype: string
- name: transcription
dtype: string
splits:
- name: test
num_bytes: 3858212926.0
num_examples: 13100
download_size: 3785261536
dataset_size: 3858212926.0
---
# Dataset Card for "spokenTermDetection_LJSpeech"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 565 | [
[
-0.039154052734375,
-0.0277557373046875,
-0.002666473388671875,
0.01293182373046875,
-0.0090484619140625,
0.0170135498046875,
-0.01180267333984375,
-0.0157318115234375,
0.0665283203125,
0.0352783203125,
-0.062255859375,
-0.059173583984375,
-0.043548583984375,
... |
DynamicSuperb/SpokenTermDetection_LibriSpeech-TestClean | 2023-07-12T14:06:13.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-07-10T15:31:21 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: text
dtype: string
- name: instruction
dtype: string
- name: label
dtype: string
- name: transcription
dtype: string
splits:
- name: test
num_bytes: 371914549.46
num_examples: 2620
download_size: 350491134
dataset_size: 371914549.46
---
# Dataset Card for "speechTermDetection_LibrispeechTestClean"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 575 | [
[
-0.041534423828125,
-0.023468017578125,
-0.0069580078125,
0.0090789794921875,
-0.0120391845703125,
0.0107269287109375,
-0.01335906982421875,
-0.0154876708984375,
0.062347412109375,
0.035675048828125,
-0.057952880859375,
-0.0540771484375,
-0.0496826171875,
-0... |
DynamicSuperb/SpokenTermDetection_LibriSpeech-TestOther | 2023-07-12T14:07:16.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-07-10T15:34:55 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: text
dtype: string
- name: instruction
dtype: string
- name: label
dtype: string
- name: transcription
dtype: string
splits:
- name: test
num_bytes: 352592993.811
num_examples: 2939
download_size: 332909359
dataset_size: 352592993.811
---
# Dataset Card for "speechTermDetection_LibrispeechTestOther"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 577 | [
[
-0.0413818359375,
-0.02447509765625,
-0.01111602783203125,
0.00945281982421875,
-0.00963592529296875,
0.006336212158203125,
-0.005035400390625,
-0.0122833251953125,
0.05743408203125,
0.032073974609375,
-0.053436279296875,
-0.04754638671875,
-0.05303955078125,
... |
BigSuperbPrivate/SpeechDetection_Voxceleb1Train | 2023-07-17T13:25:42.000Z | [
"region:us"
] | BigSuperbPrivate | null | null | 0 | 6 | 2023-07-13T14:59:40 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: text
dtype: string
- name: instruction
dtype: string
- name: label
dtype: string
- name: transcription
dtype: string
splits:
- name: train
num_bytes: 3188741275.0
num_examples: 12000
- name: validation
num_bytes: 733987727.88
num_examples: 2609
download_size: 3909471035
dataset_size: 3922729002.88
---
# Dataset Card for "SpeechDetection_VoxCeleb1Train"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 641 | [
[
-0.041778564453125,
-0.028472900390625,
0.007511138916015625,
0.017059326171875,
-0.003780364990234375,
0.00579071044921875,
0.0036525726318359375,
-0.0038585662841796875,
0.037261962890625,
0.022216796875,
-0.066650390625,
-0.059295654296875,
-0.031204223632812... |
DynamicSuperb/NoiseDetection_LJSpeech_MUSAN-Music | 2023-07-18T07:52:06.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-07-14T03:15:40 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: instruction
dtype: string
- name: label
dtype: string
splits:
- name: test
num_bytes: 3372063990.0
num_examples: 26200
download_size: 3363012142
dataset_size: 3372063990.0
---
# Dataset Card for "NoiseDetectionmusic_LJSpeechMusan"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 495 | [
[
-0.036651611328125,
-0.0094757080078125,
0.015869140625,
0.023956298828125,
-0.0056610107421875,
0.00696563720703125,
-0.0006556510925292969,
-0.02374267578125,
0.06005859375,
0.026275634765625,
-0.0645751953125,
-0.046142578125,
-0.034210205078125,
-0.02711... |
alexshengzhili/mPLUG-owl | 2023-07-16T22:58:55.000Z | [
"region:us"
] | alexshengzhili | null | null | 0 | 6 | 2023-07-16T22:58:26 | ---
dataset_info:
features:
- name: image_file
dtype: string
- name: id
dtype: string
- name: caption
dtype: string
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
- name: first_mention
dtype: string
- name: response
dtype: string
- name: title
dtype: string
- name: abstract
dtype: string
- name: q_a_pairs
sequence:
sequence: string
- name: response_mPLUG-owl
dtype: string
splits:
- name: 1_percent_as_validation
num_bytes: 19209561
num_examples: 3002
download_size: 8946500
dataset_size: 19209561
---
# Dataset Card for "mPLUG-owl"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 807 | [
[
-0.03155517578125,
-0.017364501953125,
0.022247314453125,
0.006290435791015625,
-0.0037746429443359375,
-0.0164947509765625,
0.030548095703125,
-0.02630615234375,
0.041595458984375,
0.0256500244140625,
-0.065673828125,
-0.059478759765625,
-0.05731201171875,
... |
HanbingL/midjourney_prompty_dataset | 2023-07-18T06:12:17.000Z | [
"region:us"
] | HanbingL | null | null | 1 | 6 | 2023-07-18T04:49:01 | Entry not found | 15 | [
[
-0.0213775634765625,
-0.01497650146484375,
0.05718994140625,
0.02880859375,
-0.0350341796875,
0.046478271484375,
0.052490234375,
0.00507354736328125,
0.051361083984375,
0.0170135498046875,
-0.052093505859375,
-0.01497650146484375,
-0.0604248046875,
0.0379028... |
DavidVivancos/MindBigData2023_MNIST-2B | 2023-07-18T10:16:28.000Z | [
"license:odbl",
"arxiv:2306.00455",
"region:us"
] | DavidVivancos | null | null | 0 | 6 | 2023-07-18T07:55:07 | ---
license: odbl
---
## Dataset Summary
MindBigData 2023 MNIST-2B is a reduced subset of the MindBigData 2023 MNIST-8B https://huggingface.co/datasets/DavidVivancos/MindBigData2023_MNIST-8B (June 1st 2023), brain signals open dataset created for Machine Learning, based on EEG signals from a single subject captured using a custom 128 channels device, replicating the full 70,000 digits from Yaan LeCun et all MNIST dataset. The brain signals were captured while the subject was watching the pixels of the original digits one by one on a screen and listening at the same time to the spoken number 0 to 9 from the real label.
Supporting dataset for paper https://arxiv.org/abs/2306.00455
The dataset contains 70,000 records from 128 EEG channels, each of 256 samples ( a bit more than 1 second), recorded at 250hz
(From the Original 8 Billion datapoints dataset, all the non digits (labled -1) (70000 records) where removed and also the EEG signals were reduced from 500 samples to 256 samples(a bit more than 1 second))
It consists of 2 main csv data files:
- “train.csv” 10,7Gb Header + 60,000 rows 32,558 columns
- “test.csv” 1,79Gb Header + 10,000 rows 32,558 columns
10 audio files at a folder named “audiolabels”: “0.wav”, “1.wav”......“9.wav”
And 1 csv file with 3d coordinates of the EEG electrodes: “3Dcoords.csv” 4,27Kb Header + 130 rows 4 columns
## Dataset Structure
review supporting paper https://arxiv.org/abs/2306.00455
## Data Fields
review supporting paper https://arxiv.org/abs/2306.00455
## Citation
```sh
@article{MindBigData_2023_MNIST-8B,
title={MindBigData 2023 MNIST-8B The 8 billion datapoints Multimodal Dataset of Brain Signals},
author={David Vivancos},
journal={arXiv preprint arXiv:2306.00455},
year={2023}
}
``` | 1,762 | [
[
-0.05462646484375,
-0.036651611328125,
0.030853271484375,
0.0185699462890625,
-0.017120361328125,
-0.036376953125,
-0.0254364013671875,
-0.0369873046875,
0.03656005859375,
0.039215087890625,
-0.06304931640625,
-0.033935546875,
-0.0252532958984375,
-0.0014905... |
FunDialogues/academia-physics-office-hours | 2023-08-28T23:35:08.000Z | [
"task_categories:question-answering",
"task_categories:conversational",
"size_categories:n<1K",
"language:en",
"license:apache-2.0",
"fictitious dialogues",
"prototyping",
"region:us"
] | FunDialogues | null | null | 2 | 6 | 2023-07-19T03:44:55 | ---
license: apache-2.0
task_categories:
- question-answering
- conversational
language:
- en
tags:
- fictitious dialogues
- prototyping
pretty_name: 'academia-physics-office-hours '
size_categories:
- n<1K
---
# fun dialogues
A library of fictitious dialogues that can be used to train language models or augment prompts for prototyping and educational purposes. Fun dialogues currently come in json and csv format for easy ingestion or conversion to popular data structures. Dialogues span various topics such as sports, retail, academia, healthcare, and more. The library also includes basic tooling for loading dialogues and will include quick chatbot prototyping functionality in the future.
Visit the Project Repo: https://github.com/eduand-alvarez/fun-dialogues/
# This Dialogue
Comprised of fictitious examples of dialogues between a physics professor and a student during office hours. Check out the example below:
```
"id":1,
"description":"Understanding the concept of velocity",
"dialogue":"Student: Professor, I'm having trouble understanding the concept of velocity. Could you please explain it to me?\n\nProfessor: Of course! Velocity is a fundamental concept in physics that describes the rate of change of an object's position with respect to time. It is a vector quantity, which means it has both magnitude and direction. To calculate velocity, you divide the change in position by the change in time. It is important to note that velocity takes into account both speed and direction. For example, if an object is moving north at a speed of 20 meters per second, its velocity is 20 meters per second in the north direction. Does that clarify it for you?"
```
# How to Load Dialogues
Loading dialogues can be accomplished using the fun dialogues library or Hugging Face datasets library.
## Load using fun dialogues
1. Install fun dialogues package
`pip install fundialogues`
2. Use loader utility to load dataset as pandas dataframe. Further processing might be required for use.
```
from fundialogues import dialoader
# load as pandas dataframe
bball_coach = dialoader("FunDialogues/academia-physics-office-hours")
```
## Loading using Hugging Face datasets
1. Install datasets package
2. Load using datasets
```
from datasets import load_dataset
dataset = load_dataset("FunDialogues/academia-physics-office-hours")
```
## How to Contribute
If you want to contribute to this project and make it better, your help is very welcome. Contributing is also a great way to learn more about social coding on Github, new technologies and and their ecosystems and how to make constructive, helpful bug reports, feature requests and the noblest of all contributions: a good, clean pull request.
### Contributing your own Lifecycle Solution
If you want to contribute to an existing dialogue or add a new dialogue, please open an issue and I will follow up with you ASAP!
### Implementing Patches and Bug Fixes
- Create a personal fork of the project on Github.
- Clone the fork on your local machine. Your remote repo on Github is called origin.
- Add the original repository as a remote called upstream.
- If you created your fork a while ago be sure to pull upstream changes into your local repository.
- Create a new branch to work on! Branch from develop if it exists, else from master.
- Implement/fix your feature, comment your code.
- Follow the code style of the project, including indentation.
- If the component has tests run them!
- Write or adapt tests as needed.
- Add or change the documentation as needed.
- Squash your commits into a single commit with git's interactive rebase. Create a new branch if necessary.
- Push your branch to your fork on Github, the remote origin.
- From your fork open a pull request in the correct branch. Target the project's develop branch if there is one, else go for master!
If the maintainer requests further changes just push them to your branch. The PR will be updated automatically.
Once the pull request is approved and merged you can pull the changes from upstream to your local repo and delete your extra branch(es).
And last but not least: Always write your commit messages in the present tense. Your commit message should describe what the commit, when applied, does to the code – not what you did to the code.
# Disclaimer
The dialogues contained in this repository are provided for experimental purposes only. It is important to note that these dialogues are assumed to be original work by a human and are entirely fictitious, despite the possibility of some examples including factually correct information. The primary intention behind these dialogues is to serve as a tool for language modeling experimentation and should not be used for designing real-world products beyond non-production prototyping.
Please be aware that the utilization of fictitious data in these datasets may increase the likelihood of language model artifacts, such as hallucinations or unrealistic responses. Therefore, it is essential to exercise caution and discretion when employing these datasets for any purpose.
It is crucial to emphasize that none of the scenarios described in the fun dialogues dataset should be relied upon to provide advice or guidance to humans. These scenarios are purely fictitious and are intended solely for demonstration purposes. Any resemblance to real-world situations or individuals is entirely coincidental.
The responsibility for the usage and application of these datasets rests solely with the individual or entity employing them. By accessing and utilizing these dialogues and all contents of the repository, you acknowledge that you have read and understood this disclaimer, and you agree to use them at your own discretion and risk. | 5,744 | [
[
-0.007511138916015625,
-0.0657958984375,
0.0309295654296875,
0.0180206298828125,
-0.021942138671875,
0.01406097412109375,
-0.00753021240234375,
-0.0248260498046875,
0.035888671875,
0.034942626953125,
-0.060394287109375,
-0.0306549072265625,
-0.01026153564453125,... |
johannes-garstenauer/structs_token_size_4_pd_False_reduced_labelled | 2023-07-20T21:05:52.000Z | [
"region:us"
] | johannes-garstenauer | null | null | 1 | 6 | 2023-07-20T21:02:35 | ---
dataset_info:
features:
- name: struct
dtype: string
- name: label
dtype: string
splits:
- name: train
num_bytes: 7448045059
num_examples: 30656932
download_size: 2199643691
dataset_size: 7448045059
---
# Dataset Card for "structs_token_size_4_pd_False_reduced_labelled"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 437 | [
[
-0.031890869140625,
-0.023651123046875,
0.0118408203125,
0.0250244140625,
-0.0201263427734375,
0.004756927490234375,
0.02166748046875,
-0.007358551025390625,
0.058837890625,
0.032379150390625,
-0.05230712890625,
-0.060455322265625,
-0.03277587890625,
0.00583... |
andersonbcdefg/physics | 2023-07-21T01:27:46.000Z | [
"region:us"
] | andersonbcdefg | null | null | 0 | 6 | 2023-07-21T01:27:24 | ---
dataset_info:
features:
- name: role_1
dtype: string
- name: topic;
dtype: string
- name: sub_topic
dtype: string
- name: message_1
dtype: string
- name: message_2
dtype: string
splits:
- name: train
num_bytes: 51650490
num_examples: 20000
download_size: 23872399
dataset_size: 51650490
---
# Dataset Card for "physics"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 504 | [
[
-0.0384521484375,
-0.0157012939453125,
0.0299072265625,
0.01499176025390625,
-0.01006317138671875,
0.00433349609375,
0.02520751953125,
-0.01509857177734375,
0.056610107421875,
0.006809234619140625,
-0.0601806640625,
-0.033447265625,
-0.03533935546875,
-0.026... |
jondurbin/airoboros-gpt4-2.0 | 2023-07-30T08:30:24.000Z | [
"license:other",
"region:us"
] | jondurbin | null | null | 17 | 6 | 2023-07-25T08:17:42 | ---
license: other
---
## Overview
This is a brand new dataset, with nothing copied from the 1.* series of airoboros, using only the June version of gpt-4.
I used the latest overhaul of the airoboros python tool to generate the data, which has several "instructions", where an instructor is a specific prompt/response generator.
The instructors include:
- agent/function style prompts, which generate a function name and args based on the provided input and available functions in either JSON or YAML format
- model/scenario/character cards, to help build random descriptive cards based on a template
- coding and scripting
- contextual q&a with the specific context obedient formatting
- chain-of-thought, i.e. for a given question, generate ~3 possible solutions, rank them, select the best
- experience, e.g. guided meditations or describing a walk through a forest
- general - completely random tasks not specifically targetting any type of task, using a random list of topics
- jokes - still horrible, but at least there are some now
- orca, i.e. "Solve [problem], provide step-by-step reasoning."
- execution planning, specifically the reWOO style, where you describe a list of available functions and it will generate a plan to make use of them
- riddles - still not great either, but present
- roleplay
- songs
- wordgames, e.g. give me a list of 28 words that start with 'cr'
- creative writing
**Is it better than 1.4?**
Not necessarily. It has some extra functionality that didn't exist before, but if you want to be sure you don't lose much, check out m2.0, with is a merge of 1.4.1 and 2.0:
https://huggingface.co/datasets/jondurbin/airoboros-gpt4-m2.0
The main point here was to test the June version of gpt-4 against the March version (and add new prompt types).
### Category breakdown
### Configuration for airoboros
https://gist.github.com/jondurbin/65df002c16560899e05365ca6cbd43e3
### Licence and usage restrictions
The data was generated by gpt-4 via OpenAI API calls.
The ToS for OpenAI API usage has a clause preventing the output from being used to train a model that __competes__ with OpenAI
- what does *compete* actually mean here?
- these small open source models will not produce output anywhere near the quality of gpt-4, or even gpt-3.5, so I can't imagine this could credibly be considered competing in the first place
- if someone else uses the dataset to do the same, they wouldn't necessarily be violating the ToS because they didn't call the API, so I don't know how that works
- the training data used in essentially all large language models includes a significant of copyrighted or otherwise unallowable licensing in the first place
- other work using the self-instruct method, e.g. the original here: https://github.com/yizhongw/self-instruct released the data and model as apache-2
I am purposingly leaving this license ambiguous (other than the fact you must comply with the Meta original license) because I am not a lawyer and refuse to attempt to interpret all of the terms accordingly.
Your best bet is probably to avoid using this commercially due to the OpenAI API usage.
Either way, by using this model, you agree to completely idemnify me from any and all license related issues.
Attribution would be nice if you use some or all of the data. | 3,335 | [
[
-0.023590087890625,
-0.041900634765625,
0.02178955078125,
0.0190277099609375,
-0.0252685546875,
-0.042449951171875,
-0.0125274658203125,
-0.03369140625,
0.0009202957153320312,
0.039306640625,
-0.046295166015625,
-0.025634765625,
-0.0294342041015625,
0.016006... |
IlyaGusev/rulm_human_preferences | 2023-09-07T07:40:28.000Z | [
"region:us"
] | IlyaGusev | null | null | 0 | 6 | 2023-07-25T13:12:57 | ---
dataset_info:
features:
- name: result
dtype: string
- name: worker_id
dtype: string
- name: assignment_id
dtype: string
- name: pool_id
dtype: int64
- name: instruction
dtype: string
- name: input
dtype: string
- name: left_answer
dtype: string
- name: right_answer
dtype: string
- name: left_model
dtype: string
- name: right_model
dtype: string
- name: id
dtype: string
splits:
- name: train
num_bytes: 104434766
num_examples: 34520
download_size: 12663395
dataset_size: 104434766
---
# Dataset Card for "rulm_human_preferences"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 752 | [
[
-0.048736572265625,
-0.00986480712890625,
0.006275177001953125,
0.01456451416015625,
-0.00402069091796875,
-0.00457000732421875,
0.00585174560546875,
-0.0168609619140625,
0.059478759765625,
0.03369140625,
-0.05841064453125,
-0.0509033203125,
-0.027923583984375,
... |
izumi-lab/wikinews-en-20230728 | 2023-07-29T03:07:56.000Z | [
"language:en",
"license:cc-by-2.5",
"region:us"
] | izumi-lab | null | null | 1 | 6 | 2023-07-28T22:13:05 | ---
dataset_info:
features:
- name: text
dtype: string
- name: title
dtype: string
- name: url
dtype: string
splits:
- name: train
num_bytes: 114757457
num_examples: 43246
download_size: 38557626
dataset_size: 114757457
license: cc-by-2.5
language:
- en
---
# Dataset Card for "wikinews-en-20230728"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 468 | [
[
-0.041259765625,
-0.006191253662109375,
0.01013946533203125,
0.0242919921875,
-0.01385498046875,
-0.01418304443359375,
0.0162200927734375,
-0.01751708984375,
0.06591796875,
0.035125732421875,
-0.06927490234375,
-0.04217529296875,
-0.038421630859375,
-0.00547... |
zjunlp/KnowLM-IE | 2023-08-23T11:04:58.000Z | [
"language:zh",
"license:apache-2.0",
"arxiv:2305.11527",
"region:us"
] | zjunlp | null | null | 10 | 6 | 2023-07-29T02:20:17 | ---
license: apache-2.0
language:
- zh
---
| Field | Description |
| :---------: | :----------------------------------------------------------: |
| id | Unique identifier |
| cate | text category of input (12 categories in total) |
| input | Model input text (need to extract all triples involved within) |
| instruction | Instruction for the model to perform the extraction task |
| output | Expected model output |
| relation | Relation triples(head, relation, tail) involved in the input |
For more details on data processing and conversion, please refer to https://github.com/zjunlp/DeepKE/tree/main/example/llm/InstructKGC
If you have used the data of this project, please refer to the following papers:
```
@article{DBLP:journals/corr/abs-2305-11527,
author = {Honghao Gui and
Jintian Zhang and
Hongbin Ye and
Ningyu Zhang},
title = {InstructIE: {A} Chinese Instruction-based Information Extraction Dataset},
journal = {CoRR},
volume = {abs/2305.11527},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.11527},
doi = {10.48550/arXiv.2305.11527},
eprinttype = {arXiv},
eprint = {2305.11527},
timestamp = {Thu, 25 May 2023 15:41:47 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-11527.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
``` | 1,627 | [
[
-0.0130767822265625,
-0.04791259765625,
0.02587890625,
0.018890380859375,
-0.0213470458984375,
-0.010955810546875,
0.00521087646484375,
-0.018035888671875,
-0.01299285888671875,
0.031280517578125,
-0.03662109375,
-0.06396484375,
-0.0262908935546875,
0.005943... |
BigSuperbPrivate/DialogueEmotionClassification_DailyTalk | 2023-08-02T09:29:24.000Z | [
"region:us"
] | BigSuperbPrivate | null | null | 0 | 6 | 2023-07-31T12:16:53 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype: audio
- name: instruction
dtype: string
- name: label
dtype: string
splits:
- name: train
num_bytes: 4844730479.633
num_examples: 16623
- name: validation
num_bytes: 679693951.392
num_examples: 2392
download_size: 5171522830
dataset_size: 5524424431.025001
---
# Dataset Card for "DialogueEmotionClassification_DailyTalk"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 718 | [
[
-0.0261383056640625,
-0.0261993408203125,
0.00983428955078125,
0.0211334228515625,
0.00028443336486816406,
0.01316070556640625,
0.01119232177734375,
-0.027679443359375,
0.0545654296875,
0.03765869140625,
-0.069580078125,
-0.0699462890625,
-0.0341796875,
-0.0... |
lighteval/hendrycks_ethics | 2023-07-31T14:40:47.000Z | [
"region:us"
] | lighteval | The ETHICS dataset is a benchmark that spans concepts in justice, well-being,
duties, virtues, and commonsense morality. Models predict widespread moral
judgments about diverse text scenarios. This requires connecting physical and
social world knowledge to value judgements, a capability that may enable us
to steer chatbot outputs or eventually regularize open-ended reinforcement
learning agents. | @article{hendrycks2021ethics
title={Aligning AI With Shared Human Values},
author={Dan Hendrycks and Collin Burns and Steven Basart and Andrew Critch and Jerry Li and Dawn Song and Jacob Steinhardt},
journal={Proceedings of the International Conference on Learning Representations (ICLR)},
year={2021}
} | 0 | 6 | 2023-07-31T14:40:28 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
adityarra07/ATC_2 | 2023-08-06T05:38:14.000Z | [
"region:us"
] | adityarra07 | null | null | 0 | 6 | 2023-08-06T05:38:10 | ---
dataset_info:
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: transcription
dtype: string
- name: id
dtype: string
splits:
- name: test
num_bytes: 113797125.0
num_examples: 871
download_size: 113447323
dataset_size: 113797125.0
---
# Dataset Card for "ATC_2"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 464 | [
[
-0.0276031494140625,
-0.01262664794921875,
0.0203857421875,
0.01007843017578125,
-0.0220794677734375,
0.00815582275390625,
0.0352783203125,
-0.019989013671875,
0.0545654296875,
0.029632568359375,
-0.046356201171875,
-0.053192138671875,
-0.045562744140625,
-0... |
valentinwerner/cameo_news | 2023-08-06T10:19:57.000Z | [
"task_categories:text-classification",
"task_categories:question-answering",
"task_categories:conversational",
"size_categories:1K<n<10K",
"language:en",
"region:us"
] | valentinwerner | null | null | 0 | 6 | 2023-08-06T10:16:58 | ---
task_categories:
- text-classification
- question-answering
- conversational
language:
- en
size_categories:
- 1K<n<10K
---
Dataset used in my thesis (https://github.com/valentinwerner1/Thesis_RelationExtraction_PoliticsNews)
Reformatted for training with LLMs, experimenting whether these can improve performance | 317 | [
[
-0.0206298828125,
-0.00606536865234375,
0.0292205810546875,
0.0013399124145507812,
-0.025787353515625,
-0.016082763671875,
-0.012847900390625,
-0.01348114013671875,
0.03216552734375,
0.053985595703125,
-0.060028076171875,
-0.044586181640625,
-0.0224151611328125,... |
jordyvl/rvl_cdip_n_mp | 2023-08-07T14:43:09.000Z | [
"license:cc-by-nc-4.0",
"region:us"
] | jordyvl | The RVL-CDIP-N (Ryerson Vision Lab Complex Document Information Processing) dataset consists of newly gathered documents in 16 classes
There are 991 documents for testing purposes. There were 10 documents from the original dataset that could not be retrieved based on the metadata or were out-of-scope (language). | @inproceedings{larson2022evaluating,
title={Evaluating Out-of-Distribution Performance on Document Image Classifiers},
author={Larson, Stefan and Lim, Gordon and Ai, Yutong and Kuang, David and Leach, Kevin},
booktitle={Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track},
year={2022}
}
@inproceedings{bdpc,
title = {Beyond Document Page Classification},
author = {Anonymous},
booktitle = {Under Review},
year = {2023}
} | 0 | 6 | 2023-08-07T09:43:50 | ---
license: cc-by-nc-4.0
dataset_info:
features:
- name: id
dtype: string
- name: file
dtype: binary
- name: labels
dtype:
class_label:
names:
'0': letter
'1': form
'2': email
'3': handwritten
'4': advertisement
'5': scientific report
'6': scientific publication
'7': specification
'8': file folder
'9': news article
'10': budget
'11': invoice
'12': presentation
'13': questionnaire
'14': resume
'15': memo
splits:
- name: test
num_bytes: 1349159996
num_examples: 991
download_size: 0
dataset_size: 1349159996
---
# Dataset Card for RVL-CDIP-N_MultiPage
## Extension
The data loader provides support for loading RVL_CDIP-N in its extended multipage format.
Big kudos to the original authors (first in CITATION) for collecting the RVL-CDIP-N dataset.
We stand on the shoulders of giants :)
## Required installation
```bash
pip3 install pypdf2 pdf2image
sudo apt-get install poppler-utils
``` | 1,107 | [
[
-0.0599365234375,
-0.007373809814453125,
-0.004573822021484375,
0.041900634765625,
-0.015899658203125,
0.00319671630859375,
0.0113677978515625,
0.008148193359375,
0.01052093505859375,
0.05126953125,
-0.0283203125,
-0.01486968994140625,
-0.049224853515625,
0.... |
hac541309/open-lid-dataset | 2023-10-27T01:18:24.000Z | [
"size_categories:100M<n<1B",
"language:en",
"language:ko",
"language:fr",
"language:aa",
"language:hi",
"license:gpl-3.0",
"arxiv:2305.13820",
"region:us"
] | hac541309 | null | null | 4 | 6 | 2023-08-09T08:46:10 | ---
language:
- en
- ko
- fr
- aa
- hi
license: gpl-3.0
size_categories:
- 100M<n<1B
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: src
dtype: string
- name: lang
dtype: string
- name: text
dtype: string
splits:
- name: train
num_bytes: 22252477927
num_examples: 121165414
download_size: 16613981282
dataset_size: 22252477927
---
This dataset is built from the open source data accompanying ["An Open Dataset and Model for Language Identification" (Burchell et al., 2023)](https://arxiv.org/abs/2305.13820)
The repository containing the actual data can be found here : https://github.com/laurieburchell/open-lid-dataset.
The license for this recreation itself follows the original upstream dataset as GPLv3+.
However, individual datasets within it follow [each of their own licenses.](https://github.com/laurieburchell/open-lid-dataset/blob/main/licenses.md)
The "src" column lists the sources. "lang" column lists the language code in alpha-3/ISO 639-2 format followed by the script. "text" column contains the sentence.
Conversion to huggingface dataset and upload to hub done by [Chris Ha](https://github.com/chris-ha458)
Original authors built the dataset for LID models for 201 languages. I thought such a dataset could also be used for a tokenizer for 201 languages.
This dataset was processed and uploaded using huggingface datasets.
[Link to original author](https://huggingface.co/laurievb/OpenLID) | 1,523 | [
[
-0.0247802734375,
-0.044952392578125,
0.029815673828125,
0.03594970703125,
0.0033512115478515625,
-0.0236053466796875,
-0.034759521484375,
-0.037017822265625,
0.0030345916748046875,
0.059661865234375,
-0.03790283203125,
-0.04779052734375,
-0.0310516357421875,
... |
engkufizz/router-switch-instruct | 2023-08-09T16:31:20.000Z | [
"region:us"
] | engkufizz | null | null | 0 | 6 | 2023-08-09T16:27:47 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
adityarra07/sub_ATC_test | 2023-08-09T17:25:54.000Z | [
"region:us"
] | adityarra07 | null | null | 0 | 6 | 2023-08-09T17:25:49 | ---
dataset_info:
features:
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: transcription
dtype: string
- name: id
dtype: string
splits:
- name: train
num_bytes: 130645075.80770035
num_examples: 1000
download_size: 120802206
dataset_size: 130645075.80770035
---
# Dataset Card for "sub_ATC_test"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 487 | [
[
-0.050018310546875,
-0.024810791015625,
0.005542755126953125,
-0.0017690658569335938,
-0.0237579345703125,
0.0137176513671875,
0.031524658203125,
-0.004756927490234375,
0.060760498046875,
0.0150146484375,
-0.058197021484375,
-0.055908203125,
-0.0311431884765625,... |
ds4sd/PubTables-1M_OTSL | 2023-08-31T16:00:24.000Z | [
"task_categories:object-detection",
"task_categories:table-to-text",
"size_categories:100K<n<1M",
"license:other",
"table-structure-recognition",
"table-understanding",
"PDF",
"arxiv:2305.03393",
"region:us"
] | ds4sd | null | null | 1 | 6 | 2023-08-10T08:21:06 | ---
license: other
pretty_name: PubTables-1M-OTSL
size_categories:
- 100K<n<1M
tags:
- table-structure-recognition
- table-understanding
- PDF
task_categories:
- object-detection
- table-to-text
---
# Dataset Card for PubTables-1M_OTSL
## Dataset Description
- **Homepage:** https://ds4sd.github.io
- **Paper:** https://arxiv.org/pdf/2305.03393
### Dataset Summary
This dataset enables the evaluation of both object detection models and image-to-text methods.
[PubTables-1M](https://github.com/microsoft/table-transformer) is introduced in the publication *"PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents"* by Smock et al. The conversion into HF (Hugging Face) and the addition of the OTSL (Optimized Table Structure Language) format is presented in our paper "Optimized Table Tokenization for Table Structure Recognition" by Lysak et al. The dataset includes the original annotations amongst new additions.
### Dataset Structure
* cells: origunal dataset cell groundtruth (content).
* table_bbox: origunal dataset table detection groundtruth.
* otsl: new reduced table structure token format
* html: Generated HTML for PubTables-1M to match PubTabNet, FinTabNet, and SynthTabNet format.
* html_restored: generated HTML from OTSL.
* cols: grid column length.
* rows: grid row length.
* image: PIL image
### OTSL Vocabulary:
**OTSL**: new reduced table structure token format
More information on the OTSL table structure format and its concepts can be read from our paper.
Format of this dataset extends work presented in a paper, and introduces slight modifications:
* "fcel" - cell that has content in it
* "ecel" - cell that is empty
* "lcel" - left-looking cell (to handle horizontally merged cells)
* "ucel" - up-looking cell (to handle vertically merged cells)
* "xcel" - 2d span cells, in this dataset - covers entire area of a merged cell
* "nl" - new line token
### Data Splits
The dataset provides three splits
- `train`
- `val`
- `test`
## Additional Information
### Dataset Curators
The dataset is converted by the [Deep Search team](https://ds4sd.github.io/) at IBM Research.
You can contact us at [deepsearch-core@zurich.ibm.com](mailto:deepsearch-core@zurich.ibm.com).
Curators:
- Maksym Lysak, [@maxmnemonic](https://github.com/maxmnemonic)
- Ahmed Nassar, [@nassarofficial](https://github.com/nassarofficial)
- Christoph Auer, [@cau-git](https://github.com/cau-git)
- Nikos Livathinos, [@nikos-livathinos](https://github.com/nikos-livathinos)
- Peter Staar, [@PeterStaar-IBM](https://github.com/PeterStaar-IBM)
### Citation Information
**Citation to OTSL Paper:**
@article{lysak2023optimized,
title={Optimized Table Tokenization for Table Structure Recognition},
author={Maksym Lysak and Ahmed Nassar and Nikolaos Livathinos and Christoph Auer and Peter Staar},
year={2023},
eprint={2305.03393},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
**Citation to PubTables-1M creators:**
@inproceedings{smock2022pubtables,
title={Pub{T}ables-1{M}: Towards comprehensive table extraction from unstructured documents},
author={Smock, Brandon and Pesala, Rohith and Abraham, Robin},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
pages={4634-4642},
year={2022},
month={June}
} | 3,357 | [
[
-0.01708984375,
-0.030120849609375,
0.033935546875,
-0.006885528564453125,
-0.0413818359375,
-0.013031005859375,
-0.0002338886260986328,
-0.03228759765625,
0.0160980224609375,
0.0253448486328125,
-0.0174560546875,
-0.07244873046875,
-0.0204620361328125,
0.01... |
DynamicSuperb/NoiseDetection_VCTK_MUSAN-Music | 2023-11-02T09:28:51.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-08-11T07:52:51 | ---
dataset_info:
features:
- name: file
dtype: string
- name: audio
struct:
- name: array
sequence: float64
- name: path
dtype: string
- name: sampling_rate
dtype: int64
- name: instruction
dtype: string
- name: label
dtype: string
splits:
- name: test
num_bytes: 13812472441
num_examples: 26865
download_size: 3396944645
dataset_size: 13812472441
---
# Dataset Card for "NoiseDetectionmusic_VCTKMusan"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 608 | [
[
-0.03729248046875,
-0.017120361328125,
0.0122222900390625,
0.033843994140625,
-0.0206756591796875,
-0.0048370361328125,
0.01103973388671875,
-0.01154327392578125,
0.046173095703125,
0.0355224609375,
-0.07061767578125,
-0.059814453125,
-0.038543701171875,
-0.... |
AISE-TUDelft/PY150k | 2023-08-11T11:47:47.000Z | [
"size_categories:100K<n<1M",
"license:cc0-1.0",
"code",
"region:us"
] | AISE-TUDelft | null | null | 0 | 6 | 2023-08-11T09:28:32 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: dev
path: data/dev-*
- split: test
path: data/test-*
dataset_info:
features:
- name: index
dtype: int64
- name: input
dtype: string
- name: gt
dtype: string
- name: hash
dtype: int64
- name: full_line
dtype: string
splits:
- name: train
num_bytes: 662931126
num_examples: 95000
- name: dev
num_bytes: 41218084
num_examples: 5000
- name: test
num_bytes: 343336086
num_examples: 50000
download_size: 277005224
dataset_size: 1047485296
license: cc0-1.0
tags:
- code
pretty_name: PY150 Line Completion Dataset
size_categories:
- 100K<n<1M
---
# Dataset Card for "PY150k"
## Dataset Summary
Code Completion dataset created from the code available in [CodeXGlue](https://github.com/microsoft/CodeXGLUE/tree/main/Code-Code/CodeCompletion-line).
| 918 | [
[
-0.04022216796875,
-0.0030078887939453125,
0.0038604736328125,
0.023162841796875,
-0.005840301513671875,
0.015625,
0.00811004638671875,
-0.00878143310546875,
0.042236328125,
0.045745849609375,
-0.05487060546875,
-0.047515869140625,
-0.0025196075439453125,
0.... |
shirsh10mall/Image_Captioning_Dataset | 2023-08-22T14:12:14.000Z | [
"region:us"
] | shirsh10mall | null | null | 0 | 6 | 2023-08-15T11:10:57 | ---
dataset_info:
features:
- name: caption
dtype: string
- name: image_data
dtype: image
splits:
- name: train
num_bytes: 395280032.345
num_examples: 1318
download_size: 0
dataset_size: 395280032.345
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "Image_Captioning_Dataset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 499 | [
[
-0.03765869140625,
-0.006664276123046875,
0.00438690185546875,
0.023406982421875,
-0.033843994140625,
0.0113067626953125,
0.0243988037109375,
-0.0031757354736328125,
0.050872802734375,
0.043182373046875,
-0.048095703125,
-0.0474853515625,
-0.048858642578125,
... |
HydraLM/Open_Platypus_standardized | 2023-08-15T19:10:03.000Z | [
"region:us"
] | HydraLM | null | null | 0 | 6 | 2023-08-15T19:09:35 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
achang/stocks_one_nvda_v2 | 2023-08-16T06:50:09.000Z | [
"region:us"
] | achang | null | null | 0 | 6 | 2023-08-16T05:16:13 | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 2469069
num_examples: 1538
download_size: 148179
dataset_size: 2469069
---
# Dataset Card for "stocks_one_nvda_v2"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 435 | [
[
-0.0189361572265625,
-0.0163726806640625,
-0.00272369384765625,
0.018280029296875,
-0.035430908203125,
0.001880645751953125,
0.054168701171875,
0.00887298583984375,
0.076904296875,
0.043731689453125,
-0.05560302734375,
-0.0516357421875,
-0.0333251953125,
-0.... |
DynamicSuperb/IntentClassification_FluentSpeechCommands-Action | 2023-08-16T10:48:46.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-08-16T10:46:12 | ---
dataset_info:
features:
- name: file
dtype: string
- name: speakerId
dtype: string
- name: transcription
dtype: string
- name: audio
dtype: audio
- name: label
dtype: string
- name: instruction
dtype: string
splits:
- name: test
num_bytes: 743300704.0
num_examples: 10000
download_size: 636643694
dataset_size: 743300704.0
---
# Dataset Card for "Intent_Classification_FluentSpeechCommands_Action"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 588 | [
[
-0.0167694091796875,
-0.0201873779296875,
0.0103302001953125,
0.0226898193359375,
0.00039768218994140625,
-0.032196044921875,
0.005901336669921875,
0.0003185272216796875,
0.054656982421875,
0.042144775390625,
-0.055450439453125,
-0.061126708984375,
-0.0499267578... |
DynamicSuperb/IntentClassification_FluentSpeechCommands-Location | 2023-08-16T10:53:59.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-08-16T10:51:30 | ---
dataset_info:
features:
- name: file
dtype: string
- name: speakerId
dtype: string
- name: transcription
dtype: string
- name: audio
dtype: audio
- name: label
dtype: string
- name: instruction
dtype: string
splits:
- name: test
num_bytes: 752958575.0
num_examples: 10000
download_size: 639176861
dataset_size: 752958575.0
---
# Dataset Card for "Intent_Classification_FluentSpeechCommands_Location"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 590 | [
[
-0.026031494140625,
-0.0161895751953125,
0.0256805419921875,
0.019683837890625,
0.0051727294921875,
-0.02752685546875,
-0.0002129077911376953,
-0.006938934326171875,
0.051910400390625,
0.036346435546875,
-0.046661376953125,
-0.07281494140625,
-0.037261962890625,... |
prasadsawant7/sentiment_analysis_preprocessed_dataset | 2023-08-16T19:01:42.000Z | [
"task_categories:text-classification",
"size_categories:10K<n<100K",
"language:en",
"license:mit",
"sentiment-analysis",
"text-classification",
"multiclass-classification",
"region:us"
] | prasadsawant7 | null | null | 1 | 6 | 2023-08-16T17:52:39 | ---
license: mit
task_categories:
- text-classification
language:
- en
tags:
- sentiment-analysis
- text-classification
- multiclass-classification
pretty_name: Sentiment Analysis Preprocessed Dataset including training and testing split
size_categories:
- 10K<n<100K
---
**Brief idea about dataset**:
<br>
This dataset is designed for a Text Classification to be specific Multi Class Classification, inorder to train a model (Supervised Learning) for Sentiment Analysis.
<br>
Also to be able retrain the model on the given feedback over a wrong predicted sentiment this dataset will help to manage those things using **Other Features**.
**Main Features**
| text | labels |
|----------------------------------------------------------------------|---------------------------------------------------------------------------------------------------------------------------------------------------------|
| This feature variable has all sort of texts, sentences, tweets, etc. | This target variable contains 3 types of numeric values as sentiments such as 0, 1 and 2. Where 0 means Negative, 1 means Neutral and 2 means Positive. |
**Other Features**
| preds | feedback | retrain_labels | retrained_preds |
|----------------------------------------------------------|--------------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------------------------|------------------------------------------------------------------------------|
| In this variable all predictions are going to be stored. | In this variable user can enter either yes or no to indicate whether the prediction is right or wrong. | In this variable user will enter the correct label as a feedback inorder to retrain the model. | In this variable all predictions after feedback loop are going to be stored. | | 2,385 | [
[
-0.034027099609375,
-0.0292816162109375,
0.018096923828125,
0.0224456787109375,
-0.005901336669921875,
0.0035724639892578125,
-0.0057525634765625,
-0.0015850067138671875,
0.0260162353515625,
0.047576904296875,
-0.053985595703125,
-0.0611572265625,
-0.05047607421... |
parambharat/bengali_asr_corpus | 2023-08-29T05:12:50.000Z | [
"task_categories:automatic-speech-recognition",
"annotations_creators:found",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:100K<n<1M",
"source_datasets:extended|openslr",
"language:bn",
"license:cc-by-4.0",
"region:us"
] | parambharat | The corpus contains roughly 500 hours of audio and transcripts in Bangla language.
The transcripts have beed de-duplicated using exact match deduplication and audio has be converted to 16000 samples | 0 | 6 | 2023-08-17T09:03:50 | ---
annotations_creators:
- found
language:
- bn
language_creators:
- found
license:
- cc-by-4.0
multilinguality:
- monolingual
pretty_name: Bengali ASR Corpus
size_categories:
- 100K<n<1M
source_datasets:
- extended|openslr
tags: []
task_categories:
- automatic-speech-recognition
task_ids: []
---
# Dataset Card for [Bengali Asr Corpus]
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
[More Information Needed]
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
Thanks to [@parambharat](https://github.com/parambharat) for adding this dataset. | 2,778 | [
[
-0.017608642578125,
-0.01947021484375,
-0.01396942138671875,
0.028411865234375,
-0.0224456787109375,
0.0230712890625,
-0.01910400390625,
-0.01947021484375,
0.03729248046875,
0.045989990234375,
-0.035491943359375,
-0.0601806640625,
-0.053680419921875,
0.01306... | |
open-llm-leaderboard/details_meta-llama__Llama-2-13b-hf | 2023-10-14T23:00:39.000Z | [
"region:us"
] | open-llm-leaderboard | null | null | 0 | 6 | 2023-08-19T22:35:59 | ---
pretty_name: Evaluation run of meta-llama/Llama-2-13b-hf
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf)\
\ on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\
\nThe dataset is composed of 123 configuration, each one coresponding to one of\
\ the evaluated task.\n\nThe dataset has been created from 7 run(s). Each run can\
\ be found as a specific split in each configuration, the split being named using\
\ the timestamp of the run.The \"train\" split is always pointing to the latest\
\ results.\n\nAn additional configuration \"results\" store all the aggregated results\
\ of the run (and is used to compute and display the agregated metrics on the [Open\
\ LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\
\nTo load the details from a run, you can for instance do the following:\n```python\n\
from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_meta-llama__Llama-2-13b-hf\"\
,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\
These are the [latest results from run 2023-10-14T23:00:26.644553](https://huggingface.co/datasets/open-llm-leaderboard/details_meta-llama__Llama-2-13b-hf/blob/main/results_2023-10-14T23-00-26.644553.json)(note\
\ that their might be results for other tasks in the repos if successive evals didn't\
\ cover the same tasks. You find each in the results and the \"latest\" split for\
\ each eval):\n\n```python\n{\n \"all\": {\n \"em\": 0.0014681208053691276,\n\
\ \"em_stderr\": 0.00039210421902982666,\n \"f1\": 0.0607822986577181,\n\
\ \"f1_stderr\": 0.0013583957676382913,\n \"acc\": 0.43739636770101,\n\
\ \"acc_stderr\": 0.010228023491905505\n },\n \"harness|drop|3\": {\n\
\ \"em\": 0.0014681208053691276,\n \"em_stderr\": 0.00039210421902982666,\n\
\ \"f1\": 0.0607822986577181,\n \"f1_stderr\": 0.0013583957676382913\n\
\ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.10841546626231995,\n \
\ \"acc_stderr\": 0.008563852506627487\n },\n \"harness|winogrande|5\"\
: {\n \"acc\": 0.7663772691397001,\n \"acc_stderr\": 0.011892194477183524\n\
\ }\n}\n```"
repo_url: https://huggingface.co/meta-llama/Llama-2-13b-hf
leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
point_of_contact: clementine@hf.co
configs:
- config_name: harness_arc_challenge_25
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|arc:challenge|25_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|arc:challenge|25_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|arc:challenge|25_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|arc:challenge|25_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_drop_0
data_files:
- split: 2023_09_15T14_07_08.353318
path:
- '**/details_harness|drop|0_2023-09-15T14-07-08.353318.parquet'
- split: latest
path:
- '**/details_harness|drop|0_2023-09-15T14-07-08.353318.parquet'
- config_name: harness_drop_3
data_files:
- split: 2023_09_08T14_32_14.957248
path:
- '**/details_harness|drop|3_2023-09-08T14-32-14.957248.parquet'
- split: 2023_10_14T23_00_26.644553
path:
- '**/details_harness|drop|3_2023-10-14T23-00-26.644553.parquet'
- split: latest
path:
- '**/details_harness|drop|3_2023-10-14T23-00-26.644553.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2023_09_08T14_32_14.957248
path:
- '**/details_harness|gsm8k|5_2023-09-08T14-32-14.957248.parquet'
- split: 2023_10_14T23_00_26.644553
path:
- '**/details_harness|gsm8k|5_2023-10-14T23-00-26.644553.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2023-10-14T23-00-26.644553.parquet'
- config_name: harness_hellaswag_10
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hellaswag|10_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hellaswag|10_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hellaswag|10_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hellaswag|10_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-19T22:35:38.117975.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-23T17:28:00.015478.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-08-29T22:26:02.660247.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_abstract_algebra_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_anatomy_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_astronomy_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_business_ethics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_clinical_knowledge_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_college_biology_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_college_chemistry_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_college_computer_science_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_college_mathematics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_college_medicine_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_college_physics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_computer_security_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_conceptual_physics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_econometrics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_electrical_engineering_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_elementary_mathematics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_formal_logic_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_global_facts_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_biology_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_chemistry_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_computer_science_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_european_history_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_geography_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_government_and_politics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_macroeconomics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_mathematics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_microeconomics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_physics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_psychology_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_statistics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_us_history_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_high_school_world_history_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_human_aging_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_human_sexuality_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_international_law_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_jurisprudence_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_logical_fallacies_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_machine_learning_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_management_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-management|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_marketing_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_medical_genetics_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_miscellaneous_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_moral_disputes_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_moral_scenarios_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_nutrition_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_philosophy_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_prehistory_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_professional_accounting_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_professional_law_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_professional_medicine_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_professional_psychology_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_public_relations_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_security_studies_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_sociology_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_us_foreign_policy_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_virology_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-virology|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_hendrycksTest_world_religions_5
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_truthfulqa_mc_0
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-19T22:35:38.117975.parquet'
- split: 2023_08_23T17_28_00.015478
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-23T17:28:00.015478.parquet'
- split: 2023_08_29T22_26_02.660247
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-29T22:26:02.660247.parquet'
- split: latest
path:
- '**/details_harness|truthfulqa:mc|0_2023-08-29T22:26:02.660247.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2023_09_08T14_32_14.957248
path:
- '**/details_harness|winogrande|5_2023-09-08T14-32-14.957248.parquet'
- split: 2023_10_14T23_00_26.644553
path:
- '**/details_harness|winogrande|5_2023-10-14T23-00-26.644553.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2023-10-14T23-00-26.644553.parquet'
- config_name: original_mmlu_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:abstract_algebra|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:anatomy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:astronomy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:business_ethics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:clinical_knowledge|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_biology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_medicine|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_physics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:computer_security|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:conceptual_physics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:econometrics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:electrical_engineering|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:elementary_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:formal_logic|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:global_facts|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_biology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_european_history|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_geography|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_government_and_politics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_macroeconomics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_microeconomics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_physics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_psychology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_statistics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_us_history|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_world_history|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:human_aging|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:human_sexuality|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:international_law|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:jurisprudence|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:logical_fallacies|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:machine_learning|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:management|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:marketing|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:medical_genetics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:miscellaneous|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:moral_disputes|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:moral_scenarios|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:nutrition|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:philosophy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:prehistory|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_accounting|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_law|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_medicine|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_psychology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:public_relations|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:security_studies|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:sociology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:us_foreign_policy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:virology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:world_religions|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:abstract_algebra|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:anatomy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:astronomy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:business_ethics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:clinical_knowledge|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_biology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_medicine|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:college_physics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:computer_security|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:conceptual_physics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:econometrics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:electrical_engineering|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:elementary_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:formal_logic|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:global_facts|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_biology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_european_history|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_geography|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_government_and_politics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_macroeconomics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_microeconomics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_physics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_psychology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_statistics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_us_history|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:high_school_world_history|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:human_aging|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:human_sexuality|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:international_law|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:jurisprudence|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:logical_fallacies|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:machine_learning|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:management|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:marketing|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:medical_genetics|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:miscellaneous|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:moral_disputes|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:moral_scenarios|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:nutrition|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:philosophy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:prehistory|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_accounting|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_law|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_medicine|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:professional_psychology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:public_relations|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:security_studies|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:sociology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:us_foreign_policy|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:virology|5_2023-08-28T19:56:56.621542.parquet'
- '**/details_original|mmlu:world_religions|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_abstract_algebra_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:abstract_algebra|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:abstract_algebra|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_anatomy_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:anatomy|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:anatomy|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_astronomy_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:astronomy|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:astronomy|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_business_ethics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:business_ethics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:business_ethics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_clinical_knowledge_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:clinical_knowledge|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:clinical_knowledge|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_college_biology_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:college_biology|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:college_biology|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_college_chemistry_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:college_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:college_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_college_computer_science_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:college_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:college_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_college_mathematics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:college_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:college_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_college_medicine_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:college_medicine|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:college_medicine|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_college_physics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:college_physics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:college_physics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_computer_security_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:computer_security|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:computer_security|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_conceptual_physics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:conceptual_physics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:conceptual_physics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_econometrics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:econometrics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:econometrics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_electrical_engineering_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:electrical_engineering|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:electrical_engineering|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_elementary_mathematics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:elementary_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:elementary_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_formal_logic_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:formal_logic|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:formal_logic|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_global_facts_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:global_facts|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:global_facts|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_biology_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_biology|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_biology|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_chemistry_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_chemistry|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_computer_science_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_computer_science|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_european_history_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_european_history|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_european_history|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_geography_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_geography|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_geography|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_government_and_politics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_government_and_politics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_government_and_politics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_macroeconomics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_macroeconomics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_macroeconomics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_mathematics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_mathematics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_microeconomics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_microeconomics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_microeconomics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_physics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_physics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_physics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_psychology_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_psychology|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_psychology|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_statistics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_statistics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_statistics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_us_history_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_us_history|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_us_history|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_high_school_world_history_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:high_school_world_history|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:high_school_world_history|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_human_aging_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:human_aging|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:human_aging|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_human_sexuality_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:human_sexuality|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:human_sexuality|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_international_law_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:international_law|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:international_law|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_jurisprudence_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:jurisprudence|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:jurisprudence|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_logical_fallacies_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:logical_fallacies|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:logical_fallacies|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_machine_learning_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:machine_learning|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:machine_learning|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_management_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:management|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:management|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_marketing_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:marketing|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:marketing|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_medical_genetics_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:medical_genetics|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:medical_genetics|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_miscellaneous_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:miscellaneous|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:miscellaneous|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_moral_disputes_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:moral_disputes|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:moral_disputes|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_moral_scenarios_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:moral_scenarios|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:moral_scenarios|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_nutrition_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:nutrition|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:nutrition|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_philosophy_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:philosophy|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:philosophy|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_prehistory_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:prehistory|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:prehistory|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_professional_accounting_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:professional_accounting|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:professional_accounting|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_professional_law_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:professional_law|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:professional_law|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_professional_medicine_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:professional_medicine|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:professional_medicine|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_professional_psychology_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:professional_psychology|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:professional_psychology|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_public_relations_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:public_relations|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:public_relations|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_security_studies_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:security_studies|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:security_studies|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_sociology_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:sociology|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:sociology|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_us_foreign_policy_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:us_foreign_policy|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:us_foreign_policy|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_virology_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:virology|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:virology|5_2023-08-28T19:56:56.621542.parquet'
- config_name: original_mmlu_world_religions_5
data_files:
- split: 2023_08_28T19_56_56.621542
path:
- '**/details_original|mmlu:world_religions|5_2023-08-28T19:56:56.621542.parquet'
- split: latest
path:
- '**/details_original|mmlu:world_religions|5_2023-08-28T19:56:56.621542.parquet'
- config_name: results
data_files:
- split: 2023_08_19T22_35_38.117975
path:
- results_2023-08-19T22:35:38.117975.parquet
- split: 2023_08_23T17_28_00.015478
path:
- results_2023-08-23T17:28:00.015478.parquet
- split: 2023_08_28T19_56_56.621542
path:
- results_2023-08-28T19:56:56.621542.parquet
- split: 2023_08_29T22_26_02.660247
path:
- results_2023-08-29T22:26:02.660247.parquet
- split: 2023_09_08T14_32_14.957248
path:
- results_2023-09-08T14-32-14.957248.parquet
- split: 2023_09_15T14_07_08.353318
path:
- results_2023-09-15T14-07-08.353318.parquet
- split: 2023_10_14T23_00_26.644553
path:
- results_2023-10-14T23-00-26.644553.parquet
- split: latest
path:
- results_2023-10-14T23-00-26.644553.parquet
---
# Dataset Card for Evaluation run of meta-llama/Llama-2-13b-hf
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/meta-llama/Llama-2-13b-hf
- **Paper:**
- **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- **Point of Contact:** clementine@hf.co
### Dataset Summary
Dataset automatically created during the evaluation run of model [meta-llama/Llama-2-13b-hf](https://huggingface.co/meta-llama/Llama-2-13b-hf) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 123 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 7 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the agregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_meta-llama__Llama-2-13b-hf",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-10-14T23:00:26.644553](https://huggingface.co/datasets/open-llm-leaderboard/details_meta-llama__Llama-2-13b-hf/blob/main/results_2023-10-14T23-00-26.644553.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"em": 0.0014681208053691276,
"em_stderr": 0.00039210421902982666,
"f1": 0.0607822986577181,
"f1_stderr": 0.0013583957676382913,
"acc": 0.43739636770101,
"acc_stderr": 0.010228023491905505
},
"harness|drop|3": {
"em": 0.0014681208053691276,
"em_stderr": 0.00039210421902982666,
"f1": 0.0607822986577181,
"f1_stderr": 0.0013583957676382913
},
"harness|gsm8k|5": {
"acc": 0.10841546626231995,
"acc_stderr": 0.008563852506627487
},
"harness|winogrande|5": {
"acc": 0.7663772691397001,
"acc_stderr": 0.011892194477183524
}
}
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
[More Information Needed] | 96,161 | [
[
-0.03021240234375,
-0.04766845703125,
0.0200653076171875,
0.0238494873046875,
-0.0218048095703125,
0.018310546875,
-0.020263671875,
-0.0205841064453125,
0.037811279296875,
0.037322998046875,
-0.056640625,
-0.06842041015625,
-0.05462646484375,
0.0224914550781... |
dim/russian_lyrics_prompts | 2023-08-21T01:23:59.000Z | [
"region:us"
] | dim | null | null | 0 | 6 | 2023-08-21T01:23:41 | ---
dataset_info:
features:
- name: prompt
dtype: string
- name: solution
dtype: string
splits:
- name: train
num_bytes: 18504
num_examples: 43
download_size: 14764
dataset_size: 18504
---
# Dataset Card for "russian_lyrics_prompts"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 395 | [
[
-0.0306243896484375,
-0.01390838623046875,
0.0211029052734375,
0.03466796875,
-0.01290130615234375,
0.0066680908203125,
-0.005229949951171875,
0.007106781005859375,
0.048858642578125,
0.029571533203125,
-0.0794677734375,
-0.06475830078125,
-0.03271484375,
-0... |
vivym/midjourney-prompts | 2023-08-26T17:20:53.000Z | [
"task_categories:text-to-image",
"license:apache-2.0",
" midjourney",
"region:us"
] | vivym | null | null | 5 | 6 | 2023-08-25T16:57:14 | ---
license: apache-2.0
task_categories:
- text-to-image
tags:
- ' midjourney'
---
# midjourney-prompts
## Description
This dataset contains the cleaned midjourney prompts from Midjourney.
Total prompts: 9,085,397
| Version | Count |
| ------- | --------- |
| 5.2 | 2,272,465 |
| 5.1 | 2,060,106 |
| 5.0 | 3,530,770 |
| 4.0 | 1,204,384 |
| 3.0 | 14,991 |
| 2.0 | 791 |
| 1.0 | 1,239 |
| Style | Count |
| --------- | ----------- |
| default | 8,874,181 |
| raw | 177,953 |
| expressive| 27,919 |
| scenic | 2,146 |
| cute | 2,036 |
| original | 511 |
| 660 | [
[
-0.023712158203125,
-0.0150146484375,
0.03778076171875,
0.0197601318359375,
-0.01444244384765625,
-0.007167816162109375,
0.0037784576416015625,
0.0190277099609375,
0.039520263671875,
0.043212890625,
-0.072021484375,
-0.044952392578125,
-0.040130615234375,
0.... |
baoanhtran/guanaco-llama2-200 | 2023-09-24T12:48:00.000Z | [
"task_categories:text-generation",
"task_categories:fill-mask",
"task_ids:language-modeling",
"task_ids:masked-language-modeling",
"annotations_creators:no-annotation",
"language_creators:found",
"multilinguality:multilingual",
"size_categories:n<1K",
"size_categories:1K<n<10K",
"size_categories:1... | baoanhtran | CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages \ | @misc{nguyen2023culturax,
title={CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages},
author={Thuat Nguyen and Chien Van Nguyen and Viet Dac Lai and Hieu Man and Nghia Trung Ngo and Franck Dernoncourt and Ryan A. Rossi and Thien Huu Nguyen},
year={2023},
eprint={2309.09400},
archivePrefix={arXiv},
primaryClass={cs.CL}
} | 1 | 6 | 2023-08-26T16:33:33 | ---
pretty_name: CulturaX
annotations_creators:
- no-annotation
language_creators:
- found
language:
- af
- als
- am
- an
- ar
- arz
- as
- ast
- av
- az
- azb
- ba
- bar
- bcl
- be
- bg
- bh
- bn
- bo
- bpy
- br
- bs
- bxr
- ca
- cbk
- ce
- ceb
- ckb
- cs
- cv
- cy
- da
- de
- dsb
- dv
- el
- eml
- en
- eo
- es
- et
- eu
- fa
- fi
- fr
- frr
- fy
- ga
- gd
- gl
- gn
- gom
- gu
- he
- hi
- hr
- hsb
- ht
- hu
- hy
- ia
- id
- ie
- ilo
- io
- is
- it
- ja
- jbo
- jv
- ka
- kk
- km
- kn
- ko
- krc
- ku
- kv
- kw
- ky
- la
- lb
- lez
- li
- lmo
- lo
- lrc
- lt
- lv
- mai
- mg
- mhr
- min
- mk
- ml
- mn
- mr
- mrj
- ms
- mt
- mwl
- my
- myv
- mzn
- nah
- nap
- nds
- ne
- new
- nl
- nn
- 'no'
- oc
- or
- os
- pa
- pam
- pl
- pms
- pnb
- ps
- pt
- qu
- rm
- ro
- ru
- rue
- sa
- sah
- scn
- sd
- sh
- si
- sk
- sl
- so
- sq
- sr
- su
- sv
- sw
- ta
- te
- tg
- th
- tk
- tl
- tr
- tt
- tyv
- ug
- uk
- ur
- uz
- vec
- vi
- vls
- vo
- wa
- war
- wuu
- xal
- xmf
- yi
- yo
- yue
- zh
multilinguality:
- multilingual
size_categories:
- n<1K
- 1K<n<10K
- 10K<n<100K
- 100K<n<1M
- 1M<n<10M
- 10M<n<100M
- 100M<n<1B
- 1B<n<10B
source_datasets:
- original
task_categories:
- text-generation
- fill-mask
task_ids:
- language-modeling
- masked-language-modeling
extra_gated_prompt: "By completing the form below, you acknowledge that the provided data is offered as is. Although we anticipate no problems, you accept full responsibility for any repercussions resulting from the use of this data. Furthermore, you agree that the data must not be utilized for malicious or harmful purposes towards humanity."
extra_gated_fields:
Name: text
Email: text
Affiliation: text
Country: text
Usecase: text
I have explicitly check with my jurisdiction and I confirm that downloading CulturaX is legal in the country/region where I am located right now, and for the use case that I have described above: checkbox
You agree to not attempt to determine the identity of individuals in this dataset: checkbox
---
<div align="center">
<h1> CulturaX </h1>
<h3> Cleaned, Enormous, and Public: The Multilingual Fuel to Democratize Large Language Models for 167 Languages </h3>
</div>
## Dataset Description
- **Repository:** [https://github.com/nlp-uoregon/CulturaX](https://github.com/nlp-uoregon/CulturaX)
- **Papers:** [CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages](https://arxiv.org/abs/2309.09400)
## Dataset Summary
We present CulturaX, a substantial multilingual dataset with 6.3 trillion tokens in 167 languages, tailored for large language model (LLM) development. Our dataset undergoes meticulous cleaning and deduplication through a rigorous pipeline of multiple stages to accomplish the best quality for model training, including language identification, URL-based filtering, metric-based cleaning, document refinement, and data deduplication. We employ MinHash at document level to achieve fuzzy deduplication for the datasets in different languages. Our data cleaning framework includes diverse criteria and threshold selections, guided by extensive data samples, ensuring comprehensive noise filtering in various aspects. CulturaX is fully released to the public in HuggingFace to facilitate research and advancements in multilingual LLMs.
Our dataset combines the most recent iteration of mC4 (version 3.1.0) [1] with all accessible OSCAR corpora up to the present year, including 20.19, 21.09, 22.01, and 23.01 [2]. After deep cleaning and deduplication, CulturaX involves 16TB data in the parquet format (expanding to 27TB when unpacked). More than a half of our dataset is dedicated to non-English languages to significantly boost the data size and enhance the feasibility of training models in multilingual scenarios.
To obtain perplexity scores for data cleaning, we train a SentencePiece tokenizer and 5-gram Kneser-Ney language models as provided in the KenLM library [3] using the 20230501 dumps of Wikipedia. Our KenLM models are also released in HuggingFace: https://huggingface.co/uonlp/kenlm.
Details for the dataset can be found in our technical paper: [https://arxiv.org/abs/2309.09400](https://arxiv.org/abs/2309.09400)
You can download the dataset using Hugging Face datasets:
*You may need to follow these instructions to setup authentication before downloading the dataset: [https://huggingface.co/docs/huggingface_hub/quick-start#login](https://huggingface.co/docs/huggingface_hub/quick-start#login)*
```python
from datasets import load_dataset
ds = load_dataset("uonlp/CulturaX",
language="en",
use_auth_token=True)
```
### Languages
The supported languages and statistics for our dataset can be found below:
*(Note that the language code `als` and `eml` refer to `gsw` and `x-eml` in the OSCAR-2301 dataset.)*
| | Code | Language | # Documents | # Tokens | # Tokens (%) |
|----:|:-------|:-------------------------|:----------------|:--------------------|:------|
| 0 | en | English | 3,241,065,682 | 2,846,970,578,793 | 45.13 |
| 1 | ru | Russian | 799,310,908 | 737,201,800,363 | 11.69 |
| 2 | es | Spanish | 450,937,645 | 373,845,662,394 | 5.93 |
| 3 | de | German | 420,017,484 | 357,030,348,021 | 5.66 |
| 4 | fr | French | 363,754,348 | 319,332,674,695 | 5.06 |
| 5 | zh | Chinese | 218,624,604 | 227,055,380,882 | 3.60 |
| 6 | it | Italian | 211,309,922 | 165,446,410,843 | 2.62 |
| 7 | pt | Portuguese | 190,289,658 | 136,941,763,923 | 2.17 |
| 8 | pl | Polish | 142,167,217 | 117,269,087,143 | 1.86 |
| 9 | ja | Japanese | 111,188,475 | 107,873,841,351 | 1.71 |
| 10 | vi | Vietnamese | 102,411,180 | 98,453,464,077 | 1.56 |
| 11 | nl | Dutch | 117,392,666 | 80,032,209,900 | 1.27 |
| 12 | ar | Arabic | 74,027,952 | 69,354,335,076 | 1.10 |
| 13 | tr | Turkish | 94,207,460 | 64,292,787,164 | 1.02 |
| 14 | cs | Czech | 65,350,564 | 56,910,486,745 | 0.90 |
| 15 | fa | Persian | 59,531,144 | 45,947,657,495 | 0.73 |
| 16 | hu | Hungarian | 44,132,152 | 43,417,981,714 | 0.69 |
| 17 | el | Greek | 51,430,226 | 43,147,590,757 | 0.68 |
| 18 | ro | Romanian | 40,325,424 | 39,647,954,768 | 0.63 |
| 19 | sv | Swedish | 49,709,189 | 38,486,181,494 | 0.61 |
| 20 | uk | Ukrainian | 44,740,545 | 38,226,128,686 | 0.61 |
| 21 | fi | Finnish | 30,467,667 | 28,925,009,180 | 0.46 |
| 22 | ko | Korean | 20,557,310 | 24,765,448,392 | 0.39 |
| 23 | da | Danish | 25,429,808 | 22,921,651,314 | 0.36 |
| 24 | bg | Bulgarian | 24,131,819 | 22,917,954,776 | 0.36 |
| 25 | no | Norwegian | 18,907,310 | 18,426,628,868 | 0.29 |
| 26 | hi | Hindi | 19,665,355 | 16,791,362,871 | 0.27 |
| 27 | sk | Slovak | 18,582,517 | 16,442,669,076 | 0.26 |
| 28 | th | Thai | 20,960,550 | 15,717,374,014 | 0.25 |
| 29 | lt | Lithuanian | 13,339,785 | 14,247,110,836 | 0.23 |
| 30 | ca | Catalan | 15,531,777 | 12,530,288,006 | 0.20 |
| 31 | id | Indonesian | 23,251,368 | 12,062,966,061 | 0.19 |
| 32 | bn | Bangla | 12,436,596 | 9,572,929,804 | 0.15 |
| 33 | et | Estonian | 8,004,753 | 8,805,656,165 | 0.14 |
| 34 | sl | Slovenian | 7,335,378 | 8,007,587,522 | 0.13 |
| 35 | lv | Latvian | 7,136,587 | 7,845,180,319 | 0.12 |
| 36 | he | Hebrew | 4,653,979 | 4,937,152,096 | 0.08 |
| 37 | sr | Serbian | 4,053,166 | 4,619,482,725 | 0.07 |
| 38 | ta | Tamil | 4,728,460 | 4,378,078,610 | 0.07 |
| 39 | sq | Albanian | 5,205,579 | 3,648,893,215 | 0.06 |
| 40 | az | Azerbaijani | 5,084,505 | 3,513,351,967 | 0.06 |
| 41 | kk | Kazakh | 2,733,982 | 2,802,485,195 | 0.04 |
| 42 | ur | Urdu | 2,757,279 | 2,703,052,627 | 0.04 |
| 43 | ka | Georgian | 3,120,321 | 2,617,625,564 | 0.04 |
| 44 | hy | Armenian | 2,964,488 | 2,395,179,284 | 0.04 |
| 45 | is | Icelandic | 2,373,560 | 2,350,592,857 | 0.04 |
| 46 | ml | Malayalam | 2,693,052 | 2,100,556,809 | 0.03 |
| 47 | ne | Nepali | 3,124,040 | 2,061,601,961 | 0.03 |
| 48 | mk | Macedonian | 2,762,807 | 2,003,302,006 | 0.03 |
| 49 | mr | Marathi | 2,266,588 | 1,955,227,796 | 0.03 |
| 50 | mn | Mongolian | 1,928,828 | 1,850,667,656 | 0.03 |
| 51 | be | Belarusian | 1,643,486 | 1,791,473,041 | 0.03 |
| 52 | te | Telugu | 1,822,865 | 1,566,972,146 | 0.02 |
| 53 | gl | Galician | 1,785,963 | 1,382,539,693 | 0.02 |
| 54 | eu | Basque | 1,598,822 | 1,262,066,759 | 0.02 |
| 55 | kn | Kannada | 1,352,142 | 1,242,285,201 | 0.02 |
| 56 | gu | Gujarati | 1,162,878 | 1,131,730,537 | 0.02 |
| 57 | af | Afrikaans | 826,519 | 1,119,009,767 | 0.02 |
| 58 | my | Burmese | 865,575 | 882,606,546 | 0.01 |
| 59 | si | Sinhala | 753,655 | 880,289,097 | 0.01 |
| 60 | eo | Esperanto | 460,088 | 803,948,528 | 0.01 |
| 61 | km | Khmer | 1,013,181 | 746,664,132 | 0.01 |
| 62 | pa | Punjabi | 646,987 | 727,546,145 | 0.01 |
| 63 | cy | Welsh | 549,955 | 576,743,162 | 0.01 |
| 64 | ky | Kyrgyz | 570,922 | 501,442,620 | 0.01 |
| 65 | ga | Irish | 304,251 | 376,947,935 | 0.01 |
| 66 | ps | Pashto | 376,914 | 363,007,770 | 0.01 |
| 67 | am | Amharic | 243,349 | 358,206,762 | 0.01 |
| 68 | ku | Kurdish | 295,314 | 302,990,910 | 0.00 |
| 69 | tl | Filipino | 348,453 | 242,086,456 | 0.00 |
| 70 | yi | Yiddish | 141,156 | 217,584,643 | 0.00 |
| 71 | lo | Lao | 217,842 | 168,256,876 | 0.00 |
| 72 | fy | Western Frisian | 223,268 | 167,193,111 | 0.00 |
| 73 | sd | Sindhi | 109,162 | 147,487,058 | 0.00 |
| 74 | mg | Malagasy | 115,910 | 142,685,412 | 0.00 |
| 75 | or | Odia | 153,461 | 100,323,213 | 0.00 |
| 76 | as | Assamese | 52,627 | 83,787,896 | 0.00 |
| 77 | ug | Uyghur | 47,035 | 77,677,306 | 0.00 |
| 78 | uz | Uzbek | 87,219 | 75,250,787 | 0.00 |
| 79 | la | Latin | 48,968 | 44,176,580 | 0.00 |
| 80 | hr | Croatian | 460,690 | 40,796,811 | 0.00 |
| 81 | sw | Swahili | 66,506 | 30,708,309 | 0.00 |
| 82 | ms | Malay | 238,151 | 19,375,976 | 0.00 |
| 83 | br | Breton | 43,765 | 13,987,037 | 0.00 |
| 84 | sa | Sanskrit | 16,290 | 13,561,367 | 0.00 |
| 85 | gd | Scottish Gaelic | 8,408 | 4,796,485 | 0.00 |
| 86 | su | Sundanese | 1,554 | 1,308,460 | 0.00 |
| 87 | jv | Javanese | 2,058 | 625,429 | 0.00 |
| 88 | tg | Tajik | 483,835 | - | - |
| 89 | ceb | Cebuano | 263,890 | - | - |
| 90 | tt | Tatar | 218,102 | - | - |
| 91 | ckb | Central Kurdish | 172,035 | - | - |
| 92 | lb | Luxembourgish | 165,891 | - | - |
| 93 | mt | Maltese | 151,320 | - | - |
| 94 | nn | Norwegian Nynorsk | 126,083 | - | - |
| 95 | qu | Quechua | 1,202 | 72,101 | 0.00 |
| 96 | ba | Bashkir | 71,957 | - | - |
| 97 | arz | Egyptian Arabic | 71,625 | - | - |
| 98 | dv | Divehi | 66,702 | - | - |
| 99 | bo | Tibetan | 54,185 | - | - |
| 100 | sh | Serbian (Latin) | 45,619 | - | - |
| 101 | yo | Yoruba | 192 | 42,943 | 0.00 |
| 102 | bs | Bosnian | 1,237 | 39,768 | 0.00 |
| 103 | azb | South Azerbaijani | 29,833 | - | - |
| 104 | ht | Haitian Creole | 12 | 26,183 | 0.00 |
| 105 | war | Waray | 23,687 | - | - |
| 106 | cv | Chuvash | 22,570 | - | - |
| 107 | sah | Sakha | 22,141 | - | - |
| 108 | li | Limburgish | 206 | 18,532 | 0.00 |
| 109 | ce | Chechen | 17,322 | - | - |
| 110 | pnb | Western Panjabi | 15,625 | - | - |
| 111 | nds | Low German | 15,139 | - | - |
| 112 | tk | Turkmen | 14,393 | - | - |
| 113 | gn | Guarani | 103 | 12,708 | 0.00 |
| 114 | oc | Occitan | 10,556 | - | - |
| 115 | xmf | Mingrelian | 9,706 | - | - |
| 116 | ast | Asturian | 9,002 | - | - |
| 117 | os | Ossetic | 8,596 | - | - |
| 118 | mhr | Eastern Mari | 7,883 | - | - |
| 119 | pms | Piedmontese | 7,566 | - | - |
| 120 | als[*] | Swiss German | 6,936 | - | - |
| 121 | vo | Volapük | 6,621 | - | - |
| 122 | so | Somali | 39 | 6,053 | 0.00 |
| 123 | bpy | Bishnupriya | 5,087 | - | - |
| 124 | new | Newari | 4,344 | - | - |
| 125 | hsb | Upper Sorbian | 4,244 | - | - |
| 126 | lmo | Lombard | 3,530 | - | - |
| 127 | an | Aragonese | 2,746 | - | - |
| 128 | ilo | Iloko | 2,328 | - | - |
| 129 | mzn | Mazanderani | 1,914 | - | - |
| 130 | lez | Lezghian | 1,806 | - | - |
| 131 | rm | Romansh | 30 | 1,769 | 0.00 |
| 132 | krc | Karachay-Balkar | 1,745 | - | - |
| 133 | min | Minangkabau | 1,429 | - | - |
| 134 | kv | Komi | 1,396 | - | - |
| 135 | wa | Walloon | 1,383 | - | - |
| 136 | jbo | Lojban | 1,349 | - | - |
| 137 | io | Ido | 1,144 | - | - |
| 138 | mrj | Western Mari | 1,056 | - | - |
| 139 | gom | Goan Konkani | 721 | - | - |
| 140 | ia | Interlingua | 613 | - | - |
| 141 | av | Avaric | 438 | - | - |
| 142 | bh | Bihari languages | 265 | - | - |
| 143 | wuu | Wu Chinese | 222 | - | - |
| 144 | nah | Nahuatl languages | 131 | - | - |
| 145 | vec | Venetian | 113 | - | - |
| 146 | bxr | Russia Buriat | 100 | - | - |
| 147 | kw | Cornish | 94 | - | - |
| 148 | mai | Maithili | 93 | - | - |
| 149 | eml[*] | Emiliano-Romagnol | 91 | - | - |
| 150 | dsb | Lower Sorbian | 59 | - | - |
| 151 | xal | Kalmyk | 51 | - | - |
| 152 | lrc | Northern Luri | 43 | - | - |
| 153 | nap | Neapolitan | 31 | - | - |
| 154 | tyv | Tuvinian | 23 | - | - |
| 155 | scn | Sicilian | 21 | - | - |
| 156 | frr | Northern Frisian | 11 | - | - |
| 157 | mwl | Mirandese | 9 | - | - |
| 158 | myv | Erzya | 4 | - | - |
| 159 | ie | Interlingue | 4 | - | - |
| 160 | pam | Pampanga | 4 | - | - |
| 161 | bar | Bavarian | 3 | - | - |
| 162 | yue | Yue Chinese | 3 | - | - |
| 163 | cbk | Chavacano | 2 | - | - |
| 164 | bcl | Central Bikol | 1 | - | - |
| 165 | vls | West Flemish | 1 | - | - |
| 166 | rue | Rusyn | 1 | - | - |
### Dataset Structure
```json
{
"text": ...,
"timestamp": ...,
"url": ...,
"source": "mc4" | "OSCAR-xxxx",
}
```
## Considerations for Using the Data
As CulturaX is the cleaned version of the mC4 and OSCAR datasets, which were both extracted from CommonCrawl, personal and sensitive information might still contain personal and sensitive information.
This must be considered prior to using this dataset for any purpose, such as training deep learning models, etc.
## License Information
The licence terms for CulturaX strictly follows those of `mC4` and `OSCAR`. Please refer to both below licenses when using this dataset.
- [mC4 license](https://huggingface.co/datasets/allenai/c4#license)
- [OSCAR license](https://huggingface.co/datasets/oscar-corpus/OSCAR-2301#licensing-information)
## Citation
To cite CulturaX, please use:
```
@misc{nguyen2023culturax,
title={CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages},
author={Thuat Nguyen and Chien Van Nguyen and Viet Dac Lai and Hieu Man and Nghia Trung Ngo and Franck Dernoncourt and Ryan A. Rossi and Thien Huu Nguyen},
year={2023},
eprint={2309.09400},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
```
## Reference
[1] Linting Xue, Noah Constant, Adam Roberts, Mihir Kale, Rami Al-Rfou, Aditya Siddhant, Aditya Barua, and Colin Raffel. 2021. mT5: A massively multilingual
pre-trained text-to-text transformer. In NAACL 2021. https://huggingface.co/datasets/mc4
[2] Pedro Javier Ortiz Suárez, Benoît Sagot, and Laurent Romary. 2019. Asynchronous pipelines for processing huge corpora on medium to low resource infrastructures. In Proceedings of the Workshop on Challenges in the Management of Large Corpora (CMLC-
7) 2019. https://oscar-project.org/
[3] KenLM: Faster and smaller language model queries. In Proceedings of the Sixth
Workshop on Statistical Machine Translation, 2011. | 22,372 | [
[
-0.0345458984375,
-0.01239776611328125,
0.0291748046875,
0.0179595947265625,
-0.0183258056640625,
-0.0055389404296875,
-0.003826141357421875,
-0.017364501953125,
0.046783447265625,
0.011688232421875,
-0.02264404296875,
-0.0621337890625,
-0.051025390625,
0.01... |
shiroyasha13/llama_text_to_sql_dataset | 2023-08-29T11:47:05.000Z | [
"region:us"
] | shiroyasha13 | null | null | 5 | 6 | 2023-08-28T12:35:16 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
Mohanrajv27/Finetuned-text-to-sql | 2023-08-28T23:19:30.000Z | [
"region:us"
] | Mohanrajv27 | null | null | 0 | 6 | 2023-08-28T23:17:10 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: instruction
dtype: string
- name: response
dtype: string
- name: input_ids
sequence: int32
- name: attention_mask
sequence: int8
- name: labels
sequence: int64
splits:
- name: train
num_bytes: 215198580.9182748
num_examples: 235987
- name: test
num_bytes: 23911156.081725195
num_examples: 26221
download_size: 85588612
dataset_size: 239109737.0
---
# Dataset Card for "Finetuned-text-to-sql"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 742 | [
[
-0.03375244140625,
-0.045562744140625,
0.0162200927734375,
0.01349639892578125,
-0.02557373046875,
-0.01251220703125,
-0.008331298828125,
-0.0017824172973632812,
0.048095703125,
0.053253173828125,
-0.06414794921875,
-0.05596923828125,
-0.027069091796875,
-0.... |
yurakuratov/example_promoters_300 | 2023-08-29T09:33:54.000Z | [
"region:us"
] | yurakuratov | null | null | 0 | 6 | 2023-08-29T09:33:27 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
Yorai/detect-waste | 2023-09-05T23:04:53.000Z | [
"size_categories:1K<n<10K",
"language:en",
"climate",
"region:us"
] | Yorai | null | null | 0 | 6 | 2023-08-30T03:52:41 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: image_id
dtype: int64
- name: image
dtype: image
- name: width
dtype: int32
- name: height
dtype: int32
- name: objects
sequence:
- name: id
dtype: int64
- name: area
dtype: int64
- name: bbox
sequence: float32
length: 4
- name: category
dtype:
class_label:
names:
'0': metals_and_plastic
'1': other
'2': non_recyclable
'3': glass
'4': paper
'5': bio
'6': unknown
splits:
- name: train
num_bytes: 14799255261.307
num_examples: 3647
- name: test
num_bytes: 3009820376.0
num_examples: 915
download_size: 3002391644
dataset_size: 17809075637.307
language:
- en
tags:
- climate
pretty_name: detect-waste
size_categories:
- 1K<n<10K
---
# Dataset Card for detect-waste
## Dataset Description
- **Homepage: https://github.com/wimlds-trojmiasto/detect-waste**
### Dataset Summary
AI4Good project for detecting waste in environment. www.detectwaste.ml.
Our latest results were published in Waste Management journal in article titled Deep learning-based waste detection in natural and urban environments.
You can find more technical details in our technical report Waste detection in Pomerania: non-profit project for detecting waste in environment.
Did you know that we produce 300 million tons of plastic every year? And only the part of it is properly recycled.
The idea of detect waste project is to use Artificial Intelligence to detect plastic waste in the environment. Our solution is applicable for video and photography. Our goal is to use AI for Good.
### Supported Tasks and Leaderboards
Object Detection
### Languages
English
### Data Fields
https://github.com/wimlds-trojmiasto/detect-waste/tree/main/annotations
## Dataset Creation
The images are post processed to remove exif and reorient as required. Some images are labelled without the exif rotation in mind thus they're not rotated at all but have their exif metadata removed
### Personal and Sensitive Information
**BEWARE** This repository had been created by a third-party and is not affiliated in any way with the original detect-waste creators/
## Considerations for Using the Data
### Licensing Information
https://raw.githubusercontent.com/wimlds-trojmiasto/detect-waste/main/LICENSE | 2,540 | [
[
-0.042449951171875,
-0.0113067626953125,
0.034454345703125,
-0.0182037353515625,
-0.0269927978515625,
-0.01425933837890625,
0.0183563232421875,
-0.0224456787109375,
0.01025390625,
0.037078857421875,
-0.044281005859375,
-0.0635986328125,
-0.032867431640625,
0... |
dim/huggingartists_prompts | 2023-09-01T20:46:14.000Z | [
"region:us"
] | dim | null | null | 0 | 6 | 2023-09-01T20:45:28 | ---
dataset_info:
features:
- name: prompt
dtype: string
- name: song
dtype: string
splits:
- name: train
num_bytes: 121653811
num_examples: 64006
download_size: 57680864
dataset_size: 121653811
---
# Dataset Card for "huggingartists_prompts"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 405 | [
[
-0.050750732421875,
-0.021759033203125,
0.020477294921875,
0.03057861328125,
-0.0106964111328125,
-0.002834320068359375,
0.0128021240234375,
-0.0076446533203125,
0.06695556640625,
0.0205841064453125,
-0.0767822265625,
-0.043121337890625,
-0.045440673828125,
... |
dim/lurk_prompts | 2023-09-01T20:56:40.000Z | [
"region:us"
] | dim | null | null | 0 | 6 | 2023-09-01T20:51:35 | ---
dataset_info:
features:
- name: prompt
dtype: string
- name: text
dtype: string
- name: word
dtype: string
splits:
- name: train
num_bytes: 92132815
num_examples: 5671
download_size: 49004405
dataset_size: 92132815
---
# Dataset Card for "lurk_prompts"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 425 | [
[
-0.038543701171875,
-0.037689208984375,
0.0216064453125,
0.01727294921875,
-0.007762908935546875,
0.0037212371826171875,
0.017120361328125,
-0.0037631988525390625,
0.072509765625,
0.0255889892578125,
-0.08514404296875,
-0.046844482421875,
-0.0300140380859375,
... |
dim/resh_edu_short_prompts | 2023-09-01T22:24:23.000Z | [
"region:us"
] | dim | null | null | 0 | 6 | 2023-09-01T21:36:36 | ---
dataset_info:
features:
- name: solution
dtype: string
- name: prompt
dtype: string
splits:
- name: train
num_bytes: 12371576
num_examples: 2106
download_size: 5361614
dataset_size: 12371576
---
# Dataset Card for "resh_edu_short_prompts"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 405 | [
[
-0.039947509765625,
-0.0318603515625,
0.03515625,
-0.01383209228515625,
-0.0158233642578125,
0.004665374755859375,
0.0005173683166503906,
0.015899658203125,
0.070068359375,
0.020111083984375,
-0.07232666015625,
-0.046600341796875,
-0.017303466796875,
0.01082... |
dim/bugurt_completion_prompts | 2023-09-01T23:28:27.000Z | [
"region:us"
] | dim | null | null | 0 | 6 | 2023-09-01T23:28:23 | ---
dataset_info:
features:
- name: prompt
dtype: string
- name: bugurt
dtype: string
splits:
- name: train
num_bytes: 5451066
num_examples: 5000
download_size: 2806557
dataset_size: 5451066
---
# Dataset Card for "bugurt_completion_prompts"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 404 | [
[
-0.0487060546875,
-0.00989532470703125,
0.02789306640625,
0.00923919677734375,
-0.00970458984375,
0.01085662841796875,
0.0096435546875,
0.004154205322265625,
0.06402587890625,
0.0187835693359375,
-0.07550048828125,
-0.057098388671875,
-0.0278167724609375,
0.... |
HydraLM/OpenOrca-GPT4-standardized | 2023-09-03T22:40:11.000Z | [
"region:us"
] | HydraLM | null | null | 0 | 6 | 2023-09-03T22:35:39 | ---
dataset_info:
features:
- name: message
dtype: string
- name: message_type
dtype: string
- name: message_id
dtype: int64
- name: conversation_id
dtype: int64
splits:
- name: train
num_bytes: 1856699239
num_examples: 2984688
download_size: 979202725
dataset_size: 1856699239
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "OpenOrca-GPT4-standardized"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 590 | [
[
-0.046356201171875,
-0.0172576904296875,
0.00818634033203125,
0.01479339599609375,
-0.0253143310546875,
-0.019561767578125,
0.0050048828125,
-0.028045654296875,
0.037872314453125,
0.03131103515625,
-0.028656005859375,
-0.07623291015625,
-0.03485107421875,
-0... |
cmaldona/Generalization-MultiClass-CLINC150-ROSTD | 2023-09-05T22:11:52.000Z | [
"task_categories:text-classification",
"language:en",
"license:openrail",
"region:us"
] | cmaldona | null | null | 0 | 6 | 2023-09-05T21:35:36 | ---
name: generalization-test
version: 1.0.0
description: Merge between 3 datasets.
configs:
- config_name: clinc150
default: true
data_files:
- split: train
path: "train_clinc150.csv"
- split: validation
path: "validation_clinc150.csv"
- split: test
path: "test_clinc150.csv"
- config_name: rostd+
data_files:
- split: train
path: "train_rostd+.csv"
- split: validation
path: "val_rostd+.csv"
- split: test
path: "test_rostd+.csv"
license: openrail
task_categories:
- text-classification
language:
- en
---
This dataset merge 3 datasets and have two setup for experiments in generalisation for multi-class clasificacitino task.
* ID, near-OOD, covariate-shitf: [CLINC150](https://github.com/clinc/oos-eval)
* ID, near-OOD, covariate-shitf: [ROSTD+OOD](https://github.com/vgtomahawk/LR_GC_OOD) (fbreleasecoarse version)
* far-OOD: [News Category](https://www.kaggle.com/datasets/rmisra/news-category-dataset?resource=download) (v3) | 1,009 | [
[
-0.026336669921875,
-0.034820556640625,
0.02630615234375,
0.01125335693359375,
-0.0087432861328125,
-0.0286865234375,
-0.018218994140625,
-0.032684326171875,
0.00713348388671875,
0.028350830078125,
-0.03472900390625,
-0.047149658203125,
-0.027862548828125,
0... |
nampdn-ai/mini-pubmed | 2023-09-08T07:58:09.000Z | [
"region:us"
] | nampdn-ai | null | null | 1 | 6 | 2023-09-07T10:12:05 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
Minglii/w | 2023-09-09T03:02:52.000Z | [
"region:us"
] | Minglii | null | null | 0 | 6 | 2023-09-09T03:01:15 | ---
dataset_info:
features:
- name: data
struct:
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
- name: id
dtype: string
splits:
- name: train
num_bytes: 407547286
num_examples: 143000
download_size: 195819107
dataset_size: 407547286
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "w"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 587 | [
[
-0.038665771484375,
-0.018096923828125,
0.02020263671875,
-0.0003790855407714844,
-0.0140380859375,
-0.0009469985961914062,
0.01268768310546875,
-0.0302581787109375,
0.06341552734375,
0.0169677734375,
-0.07525634765625,
-0.0523681640625,
-0.04913330078125,
-... |
Falah/portrait_best_prompts | 2023-09-09T08:11:38.000Z | [
"region:us"
] | Falah | null | null | 1 | 6 | 2023-09-09T07:54:17 | ---
dataset_info:
features:
- name: prompts
dtype: string
splits:
- name: train
num_bytes: 20785006
num_examples: 100000
download_size: 516227
dataset_size: 20785006
---
# Dataset Card for "portrait_best_prompts"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 369 | [
[
-0.048736572265625,
-0.01155853271484375,
0.0236053466796875,
0.0249176025390625,
-0.0131683349609375,
-0.0058441162109375,
0.01428985595703125,
0.000278472900390625,
0.05169677734375,
0.0153656005859375,
-0.07562255859375,
-0.061492919921875,
-0.0318603515625,
... |
DynamicSuperb/MultiSpeakerDetection_LibriSpeech-TestClean | 2023-09-11T07:37:39.000Z | [
"region:us"
] | DynamicSuperb | null | null | 0 | 6 | 2023-09-10T13:23:41 | ---
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
dataset_info:
features:
- name: file
dtype: string
- name: audio
dtype:
audio:
sampling_rate: 16000
- name: instruction
dtype: string
- name: label
dtype: string
- name: utterance 1
dtype: string
- name: utterance 2
dtype: string
- name: utterance 3
dtype: string
- name: utterance 4
dtype: string
- name: utterance 5
dtype: string
splits:
- name: test
num_bytes: 889343528.0
num_examples: 2000
download_size: 707786230
dataset_size: 889343528.0
---
# Dataset Card for "MultiSpeakerDetection_LibriSpeechTestClean"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 820 | [
[
-0.054962158203125,
-0.003017425537109375,
0.00951385498046875,
0.017852783203125,
0.0002294778823852539,
-0.0092010498046875,
0.003269195556640625,
-0.0126495361328125,
0.053924560546875,
0.03582763671875,
-0.061065673828125,
-0.0419921875,
-0.045928955078125,
... |
YoussefThabet/Data_Services | 2023-09-11T09:14:50.000Z | [
"region:us"
] | YoussefThabet | null | null | 0 | 6 | 2023-09-10T15:27:28 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: input
dtype: string
- name: output
dtype: string
- name: instruction
dtype: string
splits:
- name: train
num_bytes: 3620222
num_examples: 3980
download_size: 170371
dataset_size: 3620222
---
# Dataset Card for "Data_Services"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 516 | [
[
-0.0438232421875,
-0.0159759521484375,
0.01515960693359375,
0.0167999267578125,
-0.0052947998046875,
0.0025615692138671875,
0.03411865234375,
-0.01256561279296875,
0.0604248046875,
0.0462646484375,
-0.06903076171875,
-0.048065185546875,
-0.0323486328125,
-0.... |
mohamedemam/Arabic-samsum-dialogsum | 2023-09-11T14:35:29.000Z | [
"task_categories:summarization",
"task_categories:conversational",
"size_categories:10K<n<100K",
"language:ar",
"license:cc-by-nc-2.0",
"arxiv:1911.12237",
"region:us"
] | mohamedemam | null | null | 1 | 6 | 2023-09-11T12:48:44 | ---
dataset_info:
features:
- name: index
dtype: int64
- name: id
dtype: string
- name: dialogue
dtype: string
- name: summary
dtype: string
- name: topic
dtype: string
splits:
- name: train
num_bytes: 27913254
num_examples: 24813
download_size: 13968520
dataset_size: 27913254
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
license: cc-by-nc-2.0
task_categories:
- summarization
- conversational
language:
- ar
pretty_name: ar messum
size_categories:
- 10K<n<100K
---
# Dataset Card for "Arabic-samsum-dialogsum"
this dataset is comption between samsum and dialogsum dataset translated in arabic
## Table of Contents
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks and Leaderboards](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Instances](#data-instances)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://arxiv.org/abs/1911.12237v2
- **Repository:** [Needs More Information]
- **Paper:** https://arxiv.org/abs/1911.12237v2
- **Leaderboard:** [Needs More Information]
- **Point of Contact:** [Needs More Information]
### Dataset Summary
The SAMSum dataset contains about 16k messenger-like conversations with summaries. Conversations were created and written down by linguists fluent in English. Linguists were asked to create conversations similar to those they write on a daily basis, reflecting the proportion of topics of their real-life messenger convesations. The style and register are diversified - conversations could be informal, semi-formal or formal, they may contain slang words, emoticons and typos. Then, the conversations were annotated with summaries. It was assumed that summaries should be a concise brief of what people talked about in the conversation in third person.
The SAMSum dataset was prepared by Samsung R&D Institute Poland and is distributed for research purposes (non-commercial licence: CC BY-NC-ND 4.0).
### Supported Tasks and Leaderboards
[Needs More Information]
### Languages
Arabic
## Dataset Structure
t
### Data Instances
The created dataset is made of 16369 conversations distributed uniformly into 4 groups based on the number of utterances in con- versations: 3-6, 7-12, 13-18 and 19-30. Each utterance contains the name of the speaker. Most conversations consist of dialogues between two interlocutors (about 75% of all conversations), the rest is between three or more people
The first instance in the training set:
{'id': '13818513', 'summary': 'Amanda baked cookies and will bring Jerry some tomorrow.', 'dialogue': "Amanda: I baked cookies. Do you want some?\r\nJerry: Sure!\r\nAmanda: I'll bring you tomorrow :-)"}
### Data Fields
- dialogue: text of dialogue.
- summary: human written summary of the dialogue.
- id: unique id of an example.
### Data Splits
- train: 24732
## Dataset Creation
### Curation Rationale
In paper:
> In the first approach, we reviewed datasets from the following categories: chatbot dialogues, SMS corpora, IRC/chat data, movie dialogues, tweets, comments data (conversations formed by replies to comments), transcription of meetings, written discussions, phone dialogues and daily communication data. Unfortunately, they all differed in some respect from the conversations that are typ- ically written in messenger apps, e.g. they were too technical (IRC data), too long (comments data, transcription of meetings), lacked context (movie dialogues) or they were more of a spoken type, such as a dialogue between a petrol station assis- tant and a client buying petrol.
As a consequence, we decided to create a chat dialogue dataset by constructing such conversa- tions that would epitomize the style of a messenger app.
### Source Data
#### Initial Data Collection and Normalization
In paper:
> We asked linguists to create conversations similar to those they write on a daily basis, reflecting the proportion of topics of their real-life messenger conversations. It includes chit-chats, gossiping about friends, arranging meetings, discussing politics, consulting university assignments with colleagues, etc. Therefore, this dataset does not contain any sensitive data or fragments of other corpora.
#### Who are the source language producers?
linguists
### Annotations
#### Annotation process
In paper:
> Each dialogue was created by one person. After collecting all of the conversations, we asked language experts to annotate them with summaries, assuming that they should (1) be rather short, (2) extract important pieces of information, (3) include names of interlocutors, (4) be written in the third person. Each dialogue contains only one ref- erence summary.
#### Who are the annotators?
language experts
### Personal and Sensitive Information
None, see above: Initial Data Collection and Normalization
## Considerations for Using the Data
### Social Impact of Dataset
[Needs More Information]
### Discussion of Biases
[Needs More Information]
### Other Known Limitations
[Needs More Information]
## Additional Information
### Dataset Curators
[Needs More Information]
### Licensing Information
non-commercial licence: CC BY-NC-ND 4.0
### Citation Information
```
@inproceedings{gliwa-etal-2019-samsum,
title = "{SAMS}um Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarization",
author = "Gliwa, Bogdan and
Mochol, Iwona and
Biesek, Maciej and
Wawer, Aleksander",
booktitle = "Proceedings of the 2nd Workshop on New Frontiers in Summarization",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/D19-5409",
doi = "10.18653/v1/D19-5409",
pages = "70--79"
}
```
### Contributions
Thanks to [@cccntu](https://github.com/cccntu) for adding this dataset.
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 6,874 | [
[
-0.032470703125,
-0.053314208984375,
0.005924224853515625,
0.00589752197265625,
-0.0276947021484375,
0.01363372802734375,
-0.01739501953125,
-0.033477783203125,
0.042388916015625,
0.042022705078125,
-0.05364990234375,
-0.062744140625,
-0.041748046875,
0.0166... |
prognosis/symptoms_disease_v1 | 2023-09-11T15:33:24.000Z | [
"region:us"
] | prognosis | null | null | 1 | 6 | 2023-09-11T15:33:08 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
pietrolesci/wikitoxic | 2023-09-13T12:03:54.000Z | [
"task_categories:text-classification",
"task_ids:hate-speech-detection",
"annotations_creators:crowdsourced",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:100K<n<1M",
"source_datasets:extended|other",
"language:en",
"license:cc0-1.0",
"wikipedia",
"toxicity",
"tox... | pietrolesci | null | null | 0 | 6 | 2023-09-11T19:43:51 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
- config_name: embedding_all-MiniLM-L12-v2
data_files:
- split: train
path: embedding_all-MiniLM-L12-v2/train-*
- split: validation
path: embedding_all-MiniLM-L12-v2/validation-*
- split: test
path: embedding_all-MiniLM-L12-v2/test-*
- config_name: embedding_all-mpnet-base-v2
data_files:
- split: train
path: embedding_all-mpnet-base-v2/train-*
- split: validation
path: embedding_all-mpnet-base-v2/validation-*
- split: test
path: embedding_all-mpnet-base-v2/test-*
- config_name: embedding_multi-qa-mpnet-base-dot-v1
data_files:
- split: train
path: embedding_multi-qa-mpnet-base-dot-v1/train-*
- split: validation
path: embedding_multi-qa-mpnet-base-dot-v1/validation-*
- split: test
path: embedding_multi-qa-mpnet-base-dot-v1/test-*
dataset_info:
- config_name: default
features:
- name: id
dtype: string
- name: text
dtype: string
- name: labels
dtype:
class_label:
names:
'0': non
'1': tox
- name: uid
dtype: int64
splits:
- name: train
num_bytes: 55430581
num_examples: 127656
- name: validation
num_bytes: 13936861
num_examples: 31915
- name: test
num_bytes: 27474227
num_examples: 63978
download_size: 62548640
dataset_size: 96841669
- config_name: embedding_all-MiniLM-L12-v2
features:
- name: uid
dtype: int64
- name: embedding_all-MiniLM-L12-v2
sequence: float32
splits:
- name: train
num_bytes: 197611488
num_examples: 127656
- name: validation
num_bytes: 49404420
num_examples: 31915
- name: test
num_bytes: 99037944
num_examples: 63978
download_size: 484421377
dataset_size: 346053852
- config_name: embedding_all-mpnet-base-v2
features:
- name: uid
dtype: int64
- name: embedding_all-mpnet-base-v2
sequence: float32
splits:
- name: train
num_bytes: 393691104
num_examples: 127656
- name: validation
num_bytes: 98425860
num_examples: 31915
- name: test
num_bytes: 197308152
num_examples: 63978
download_size: 827919212
dataset_size: 689425116
- config_name: embedding_multi-qa-mpnet-base-dot-v1
features:
- name: uid
dtype: int64
- name: embedding_multi-qa-mpnet-base-dot-v1
sequence: float32
splits:
- name: train
num_bytes: 393691104
num_examples: 127656
- name: validation
num_bytes: 98425860
num_examples: 31915
- name: test
num_bytes: 197308152
num_examples: 63978
download_size: 827907964
dataset_size: 689425116
annotations_creators:
- crowdsourced
language:
- en
language_creators:
- found
license:
- cc0-1.0
multilinguality:
- monolingual
pretty_name: Toxic Wikipedia Comments
size_categories:
- 100K<n<1M
source_datasets:
- extended|other
tags:
- wikipedia
- toxicity
- toxic comments
task_categories:
- text-classification
task_ids:
- hate-speech-detection
---
This is the same dataset as [`OxAISH-AL-LLM/wiki_toxic`](https://huggingface.co/datasets/OxAISH-AL-LLM/wiki_toxic).
The only differences are
1. Addition of a unique identifier, `uid`
1. Addition of the indices, that is 3 columns with the embeddings of 3 different sentence-transformers
- `all-mpnet-base-v2`
- `multi-qa-mpnet-base-dot-v1`
- `all-MiniLM-L12-v2`
1. Renaming of the `label` column to `labels` for easier compatibility with the transformers library | 3,549 | [
[
-0.007320404052734375,
-0.02825927734375,
0.026611328125,
0.0120697021484375,
0.0157012939453125,
-0.0093536376953125,
0.0032596588134765625,
-0.01369476318359375,
0.031219482421875,
0.041290283203125,
-0.04852294921875,
-0.054656982421875,
-0.039306640625,
... |
ccore/wikipedia-QA | 2023-09-11T21:46:03.000Z | [
"task_categories:text-generation",
"size_categories:10K<n<100K",
"wikipeda",
"markdown",
"qa",
"region:us"
] | ccore | null | null | 0 | 6 | 2023-09-11T20:51:52 | ---
task_categories:
- text-generation
tags:
- wikipeda
- markdown
- qa
size_categories:
- 10K<n<100K
---
GoodWiki Dataset in QA format, asking using description
and having the question at the end of each page again for the network to learn how to create questions from content | 278 | [
[
-0.048980712890625,
-0.045654296875,
0.006183624267578125,
0.01107025146484375,
-0.015289306640625,
-0.03509521484375,
0.0035247802734375,
-0.00846099853515625,
0.046539306640625,
0.0618896484375,
-0.039215087890625,
-0.0205535888671875,
0.0082550048828125,
... |
odunola/foodie-small-context | 2023-10-23T00:34:19.000Z | [
"region:us"
] | odunola | null | null | 0 | 6 | 2023-09-12T14:20:23 | Entry not found | 15 | [
[
-0.02142333984375,
-0.01495361328125,
0.05718994140625,
0.0288238525390625,
-0.035064697265625,
0.046539306640625,
0.052520751953125,
0.005062103271484375,
0.0513916015625,
0.016998291015625,
-0.052093505859375,
-0.014984130859375,
-0.060394287109375,
0.0379... |
kamaludeen/fututech-colorectal-cancer | 2023-09-13T01:17:03.000Z | [
"task_categories:tabular-classification",
"size_categories:n<1K",
"microbiome",
"tabular",
"gut-microbiota",
"region:us"
] | kamaludeen | null | null | 0 | 6 | 2023-09-13T00:36:16 | ---
task_categories:
- tabular-classification
tags:
- microbiome
- tabular
- gut-microbiota
pretty_name: Colorectal Carcinoma Feng Q 2015
size_categories:
- n<1K
---
## Publication Abstract
Colorectal cancer, a commonly diagnosed cancer in the elderly, often develops slowly from benign polyps called adenoma. The gut microbiota is believed to be directly involved in colorectal carcinogenesis. The identity and functional capacity of the adenoma- or carcinoma-related gut microbe(s), however, have not been surveyed in a comprehensive manner. Here we perform a metagenome-wide association study (MGWAS) on stools from advanced adenoma and carcinoma patients and from healthy subjects, revealing microbial genes, strains and functions enriched in each group. An analysis of potential risk factors indicates that high intake of red meat relative to fruits and vegetables appears to associate with outgrowth of bacteria that might contribute to a more hostile gut environment. These findings suggest that faecal microbiome-based strategies may be useful for early diagnosis and treatment of colorectal adenoma or carcinoma.
## Dataset
156 metagenomic shotgun-sequenced faecal samples from colorectal adenoma and carcinoma patients and healthy controls
### Configurations
- `presence-absence`
- `CLR`
## Usage
```python
dataset = load_dataset("wwydmanski/colorectal-carcinoma-microbiome-fengq", "presence-absence")
train_dataset, test_dataset = dataset['train'], dataset['test']
X_train = np.array(train_dataset['values'])
y_train = np.array(train_dataset['target'])
X_test = np.array(test_dataset['values'])
y_test = np.array(test_dataset['target'])
``` | 1,659 | [
[
-0.02117919921875,
-0.0255584716796875,
0.0531005859375,
-0.0259552001953125,
-0.0155029296875,
-0.01177978515625,
0.013458251953125,
-0.021209716796875,
0.04998779296875,
0.01322174072265625,
-0.032806396484375,
-0.0234527587890625,
-0.0491943359375,
0.0287... |
bibidentuhanoi/BMO_vicuna | 2023-10-11T16:04:13.000Z | [
"region:us"
] | bibidentuhanoi | null | null | 0 | 6 | 2023-09-13T12:37:54 | ---
dataset_info:
features:
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
- name: id
dtype: string
splits:
- name: train
num_bytes: 157129
num_examples: 139
download_size: 81053
dataset_size: 157129
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "BMO_vicuna"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 540 | [
[
-0.0304412841796875,
-0.0258331298828125,
0.02325439453125,
0.0252838134765625,
-0.0308074951171875,
-0.0192108154296875,
0.0192718505859375,
-0.0157318115234375,
0.04833984375,
0.038787841796875,
-0.054534912109375,
-0.05938720703125,
-0.045013427734375,
-0... |
aelneima/MaWPS-ar-addCN | 2023-09-15T08:20:53.000Z | [
"task_categories:text2text-generation",
"task_ids:explanation-generation",
"annotations_creators:crowdsourced",
"language_creators:found",
"multilinguality:multilingual",
"size_categories:1K<n<10K",
"language:en",
"language:ar",
"license:mit",
"region:us"
] | aelneima | null | null | 0 | 6 | 2023-09-15T08:17:59 | ---
annotations_creators:
- crowdsourced
language:
- en
- ar
language_creators:
- found
license:
- mit
multilinguality:
- multilingual
pretty_name: MAWPS_ar
size_categories:
- 1K<n<10K
source_datasets: []
task_categories:
- text2text-generation
task_ids:
- explanation-generation
---
# Dataset Card for MAWPS_ar
## Table of Contents
- [Table of Contents](#table-of-contents)
- [Dataset Description](#dataset-description)
- [Dataset Summary](#dataset-summary)
- [Supported Tasks](#supported-tasks-and-leaderboards)
- [Languages](#languages)
- [Dataset Structure](#dataset-structure)
- [Data Fields](#data-fields)
- [Data Splits](#data-splits)
- [Dataset Creation](#dataset-creation)
- [Curation Rationale](#curation-rationale)
- [Source Data](#source-data)
- [Annotations](#annotations)
- [Personal and Sensitive Information](#personal-and-sensitive-information)
- [Considerations for Using the Data](#considerations-for-using-the-data)
- [Social Impact of Dataset](#social-impact-of-dataset)
- [Discussion of Biases](#discussion-of-biases)
- [Other Known Limitations](#other-known-limitations)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
### Dataset Summary
MAWPS: A Math Word Problem Repository
### Supported Tasks
Math Word Problem Solving
### Languages
Supports Arabic and English
## Dataset Structure
### Data Fields
- `text_en`: a `string` feature.
- `text_ar`: a `string` feature.
- `eqn`: a `string` feature.
### Data Splits
|train|validation|test|
|----:|---------:|---:|
| 3636| 1040| 520|
## Dataset Creation
### Curation Rationale
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the source language producers?
[Rik Koncel-Kedziorski**, Subhro Roy**, Aida Amini, Nate Kushman and Hannaneh Hajishirzi.](https://aclanthology.org/N16-1136.pdf)
### Annotations
#### Annotation process
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
#### Who are the annotators?
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Personal and Sensitive Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Discussion of Biases
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Other Known Limitations
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
## Additional Information
### Dataset Curators
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Licensing Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Citation Information
[More Information Needed](https://github.com/huggingface/datasets/blob/master/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
### Contributions
Special thanks to Associate Professor Marwan Torki and all my colleagues in CC491N (NLP) class for helping me translate this dataset. | 4,012 | [
[
-0.04901123046875,
-0.036529541015625,
0.00812530517578125,
0.0175933837890625,
-0.0140228271484375,
0.0003523826599121094,
-0.01404571533203125,
-0.031890869140625,
0.045928955078125,
0.040191650390625,
-0.06365966796875,
-0.06658935546875,
-0.059326171875,
... |
open-llm-leaderboard/details_vibhorag101__llama-2-7b-chat-hf-phr_mental_health-2048 | 2023-10-23T12:14:18.000Z | [
"region:us"
] | open-llm-leaderboard | null | null | 0 | 6 | 2023-09-16T15:28:23 | ---
pretty_name: Evaluation run of vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048
dataset_summary: "Dataset automatically created during the evaluation run of model\
\ [vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048](https://huggingface.co/vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048)\
\ on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).\n\
\nThe dataset is composed of 64 configuration, each one coresponding to one of the\
\ evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be\
\ found as a specific split in each configuration, the split being named using the\
\ timestamp of the run.The \"train\" split is always pointing to the latest results.\n\
\nAn additional configuration \"results\" store all the aggregated results of the\
\ run (and is used to compute and display the agregated metrics on the [Open LLM\
\ Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).\n\
\nTo load the details from a run, you can for instance do the following:\n```python\n\
from datasets import load_dataset\ndata = load_dataset(\"open-llm-leaderboard/details_vibhorag101__llama-2-7b-chat-hf-phr_mental_health-2048\"\
,\n\t\"harness_winogrande_5\",\n\tsplit=\"train\")\n```\n\n## Latest results\n\n\
These are the [latest results from run 2023-10-23T12:14:06.343612](https://huggingface.co/datasets/open-llm-leaderboard/details_vibhorag101__llama-2-7b-chat-hf-phr_mental_health-2048/blob/main/results_2023-10-23T12-14-06.343612.json)(note\
\ that their might be results for other tasks in the repos if successive evals didn't\
\ cover the same tasks. You find each in the results and the \"latest\" split for\
\ each eval):\n\n```python\n{\n \"all\": {\n \"em\": 0.06291946308724833,\n\
\ \"em_stderr\": 0.0024866840810898265,\n \"f1\": 0.1230484479865771,\n\
\ \"f1_stderr\": 0.002835124699649658,\n \"acc\": 0.3855268126040811,\n\
\ \"acc_stderr\": 0.00961257569233847\n },\n \"harness|drop|3\": {\n\
\ \"em\": 0.06291946308724833,\n \"em_stderr\": 0.0024866840810898265,\n\
\ \"f1\": 0.1230484479865771,\n \"f1_stderr\": 0.002835124699649658\n\
\ },\n \"harness|gsm8k|5\": {\n \"acc\": 0.05913570887035633,\n \
\ \"acc_stderr\": 0.006497266660428824\n },\n \"harness|winogrande|5\"\
: {\n \"acc\": 0.7119179163378059,\n \"acc_stderr\": 0.012727884724248116\n\
\ }\n}\n```"
repo_url: https://huggingface.co/vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048
leaderboard_url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
point_of_contact: clementine@hf.co
configs:
- config_name: harness_arc_challenge_25
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|arc:challenge|25_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|arc:challenge|25_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_drop_3
data_files:
- split: 2023_10_23T12_14_06.343612
path:
- '**/details_harness|drop|3_2023-10-23T12-14-06.343612.parquet'
- split: latest
path:
- '**/details_harness|drop|3_2023-10-23T12-14-06.343612.parquet'
- config_name: harness_gsm8k_5
data_files:
- split: 2023_10_23T12_14_06.343612
path:
- '**/details_harness|gsm8k|5_2023-10-23T12-14-06.343612.parquet'
- split: latest
path:
- '**/details_harness|gsm8k|5_2023-10-23T12-14-06.343612.parquet'
- config_name: harness_hellaswag_10
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hellaswag|10_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hellaswag|10_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-anatomy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-astronomy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-business_ethics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_biology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_medicine|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-college_physics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-computer_security|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-econometrics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-formal_logic|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-global_facts|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-human_aging|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-international_law|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-machine_learning|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-management|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-marketing|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-nutrition|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-philosophy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-prehistory|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_law|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-public_relations|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-security_studies|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-sociology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-virology|5_2023-09-16T15-28-08.035226.parquet'
- '**/details_harness|hendrycksTest-world_religions|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_abstract_algebra_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-abstract_algebra|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_anatomy_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-anatomy|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_astronomy_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-astronomy|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_business_ethics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-business_ethics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_clinical_knowledge_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-clinical_knowledge|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_college_biology_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_biology|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_college_chemistry_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_college_computer_science_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_college_mathematics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_college_medicine_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_medicine|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_college_physics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-college_physics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_computer_security_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-computer_security|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_conceptual_physics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-conceptual_physics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_econometrics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-econometrics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_electrical_engineering_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-electrical_engineering|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_elementary_mathematics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-elementary_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_formal_logic_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-formal_logic|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_global_facts_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-global_facts|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_biology_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_biology|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_chemistry_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_chemistry|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_computer_science_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_computer_science|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_european_history_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_european_history|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_geography_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_geography|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_government_and_politics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_government_and_politics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_macroeconomics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_macroeconomics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_mathematics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_mathematics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_microeconomics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_microeconomics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_physics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_physics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_psychology_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_psychology|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_statistics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_statistics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_us_history_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_us_history|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_high_school_world_history_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-high_school_world_history|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_human_aging_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_aging|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_human_sexuality_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-human_sexuality|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_international_law_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-international_law|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_jurisprudence_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-jurisprudence|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_logical_fallacies_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-logical_fallacies|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_machine_learning_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-machine_learning|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_management_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-management|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-management|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_marketing_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-marketing|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_medical_genetics_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-medical_genetics|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_miscellaneous_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-miscellaneous|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_moral_disputes_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_disputes|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_moral_scenarios_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-moral_scenarios|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_nutrition_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-nutrition|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_philosophy_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-philosophy|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_prehistory_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-prehistory|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_professional_accounting_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_accounting|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_professional_law_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_law|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_professional_medicine_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_medicine|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_professional_psychology_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-professional_psychology|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_public_relations_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-public_relations|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_security_studies_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-security_studies|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_sociology_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-sociology|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_us_foreign_policy_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-us_foreign_policy|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_virology_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-virology|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-virology|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_hendrycksTest_world_religions_5
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|hendrycksTest-world_religions|5_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_truthfulqa_mc_0
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- '**/details_harness|truthfulqa:mc|0_2023-09-16T15-28-08.035226.parquet'
- split: latest
path:
- '**/details_harness|truthfulqa:mc|0_2023-09-16T15-28-08.035226.parquet'
- config_name: harness_winogrande_5
data_files:
- split: 2023_10_23T12_14_06.343612
path:
- '**/details_harness|winogrande|5_2023-10-23T12-14-06.343612.parquet'
- split: latest
path:
- '**/details_harness|winogrande|5_2023-10-23T12-14-06.343612.parquet'
- config_name: results
data_files:
- split: 2023_09_16T15_28_08.035226
path:
- results_2023-09-16T15-28-08.035226.parquet
- split: 2023_10_23T12_14_06.343612
path:
- results_2023-10-23T12-14-06.343612.parquet
- split: latest
path:
- results_2023-10-23T12-14-06.343612.parquet
---
# Dataset Card for Evaluation run of vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048
## Dataset Description
- **Homepage:**
- **Repository:** https://huggingface.co/vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048
- **Paper:**
- **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard
- **Point of Contact:** clementine@hf.co
### Dataset Summary
Dataset automatically created during the evaluation run of model [vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048](https://huggingface.co/vibhorag101/llama-2-7b-chat-hf-phr_mental_health-2048) on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
The dataset is composed of 64 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest results.
An additional configuration "results" store all the aggregated results of the run (and is used to compute and display the agregated metrics on the [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)).
To load the details from a run, you can for instance do the following:
```python
from datasets import load_dataset
data = load_dataset("open-llm-leaderboard/details_vibhorag101__llama-2-7b-chat-hf-phr_mental_health-2048",
"harness_winogrande_5",
split="train")
```
## Latest results
These are the [latest results from run 2023-10-23T12:14:06.343612](https://huggingface.co/datasets/open-llm-leaderboard/details_vibhorag101__llama-2-7b-chat-hf-phr_mental_health-2048/blob/main/results_2023-10-23T12-14-06.343612.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"em": 0.06291946308724833,
"em_stderr": 0.0024866840810898265,
"f1": 0.1230484479865771,
"f1_stderr": 0.002835124699649658,
"acc": 0.3855268126040811,
"acc_stderr": 0.00961257569233847
},
"harness|drop|3": {
"em": 0.06291946308724833,
"em_stderr": 0.0024866840810898265,
"f1": 0.1230484479865771,
"f1_stderr": 0.002835124699649658
},
"harness|gsm8k|5": {
"acc": 0.05913570887035633,
"acc_stderr": 0.006497266660428824
},
"harness|winogrande|5": {
"acc": 0.7119179163378059,
"acc_stderr": 0.012727884724248116
}
}
```
### Supported Tasks and Leaderboards
[More Information Needed]
### Languages
[More Information Needed]
## Dataset Structure
### Data Instances
[More Information Needed]
### Data Fields
[More Information Needed]
### Data Splits
[More Information Needed]
## Dataset Creation
### Curation Rationale
[More Information Needed]
### Source Data
#### Initial Data Collection and Normalization
[More Information Needed]
#### Who are the source language producers?
[More Information Needed]
### Annotations
#### Annotation process
[More Information Needed]
#### Who are the annotators?
[More Information Needed]
### Personal and Sensitive Information
[More Information Needed]
## Considerations for Using the Data
### Social Impact of Dataset
[More Information Needed]
### Discussion of Biases
[More Information Needed]
### Other Known Limitations
[More Information Needed]
## Additional Information
### Dataset Curators
[More Information Needed]
### Licensing Information
[More Information Needed]
### Citation Information
[More Information Needed]
### Contributions
[More Information Needed] | 38,946 | [
[
-0.023681640625,
-0.055908203125,
0.01468658447265625,
0.0238800048828125,
-0.01036834716796875,
0.009979248046875,
-0.0284423828125,
-0.0169525146484375,
0.03314208984375,
0.037322998046875,
-0.0535888671875,
-0.0675048828125,
-0.051055908203125,
0.01286315... |
DialogueCharacter/english_soda_unfiltered | 2023-09-17T07:24:40.000Z | [
"region:us"
] | DialogueCharacter | null | null | 0 | 6 | 2023-09-17T07:23:52 | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: response
sequence: string
- name: source
dtype: string
splits:
- name: train
num_bytes: 913834615
num_examples: 917016
download_size: 505828303
dataset_size: 913834615
---
# Dataset Card for "english_soda_unfiltered"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | 455 | [
[
-0.0241241455078125,
-0.01470947265625,
0.0146331787109375,
0.0209808349609375,
-0.0288238525390625,
0.0155181884765625,
-0.0059967041015625,
0.006458282470703125,
0.06170654296875,
0.045562744140625,
-0.0501708984375,
-0.051239013671875,
-0.0401611328125,
0... |
amanrangapur/Fin-Fact | 2023-09-19T22:40:19.000Z | [
"task_categories:text-classification",
"task_categories:text-generation",
"size_categories:1K<n<10K",
"language:en",
"license:apache-2.0",
"finance",
"arxiv:2309.08793",
"region:us"
] | amanrangapur | Welcome to the Fin-Fact repository! Fin-Fact is a comprehensive dataset designed specifically for financial fact-checking and explanation generation. The dataset consists of 3121 claims spanning multiple financial sectors. | @misc{rangapur2023finfact,
title={Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation},
author={Aman Rangapur and Haoran Wang and Kai Shu},
year={2023},
eprint={2309.08793},
archivePrefix={arXiv},
primaryClass={cs.AI}
} | 5 | 6 | 2023-09-19T20:39:54 | ---
license: apache-2.0
task_categories:
- text-classification
- text-generation
language:
- en
tags:
- finance
pretty_name: FinFact
size_categories:
- 1K<n<10K
dataset_info:
- config_name: generation
features:
- name: url
dtype: string
- name: claim
dtype: string
- name: author
dtype: string
- name: posted
dtype: string
# - name: sci_digest
# sequence: string
# - name: justification
# sequence: string
# - name: issues
# dtype: string
# - name: image_data
# sequence:
# - name: image_src
# dtype: string
# - name: image_caption
# dtype: string
# - name: evidence
# sequence:
# - name: sentence
# dtype: string
# - name: hrefs
# dtype: string
# - name: label
# dtype: string
# - name: visualization_bias
# dtype: int32
---
<h1 align="center">Fin-Fact - Financial Fact-Checking Dataset</h1>
## Table of Contents
- [Overview](#overview)
- [Dataset Description](#dataset-description)
- [Dataset Usage](#dataset-usage)
- [Leaderboard](#leaderboard)
- [Dependencies](#dependencies)
- [Run models for paper metrics](#run-models-for-paper-metrics)
- [Citation](#citation)
- [Contribution](#contribution)
- [License](#license)
- [Contact](#contact)
## Overview
Welcome to the Fin-Fact repository! Fin-Fact is a comprehensive dataset designed specifically for financial fact-checking and explanation generation. This README provides an overview of the dataset, how to use it, and other relevant information. [Click here](https://arxiv.org/abs/2309.08793) to access the paper.
## Dataset Description
- **Name**: Fin-Fact
- **Purpose**: Fact-checking and explanation generation in the financial domain.
- **Labels**: The dataset includes various labels, including Claim, Author, Posted Date, Sci-digest, Justification, Evidence, Evidence href, Image href, Image Caption, Visualisation Bias Label, Issues, and Claim Label.
- **Size**: The dataset consists of 3121 claims spanning multiple financial sectors.
- **Additional Features**: The dataset goes beyond textual claims and incorporates visual elements, including images and their captions.
## Dataset Usage
Fin-Fact is a valuable resource for researchers, data scientists, and fact-checkers in the financial domain. Here's how you can use it:
1. **Download the Dataset**: You can download the Fin-Fact dataset [here](https://github.com/IIT-DM/Fin-Fact/blob/FinFact/finfact.json).
2. **Exploratory Data Analysis**: Perform exploratory data analysis to understand the dataset's structure, distribution, and any potential biases.
3. **Natural Language Processing (NLP) Tasks**: Utilize the dataset for various NLP tasks such as fact-checking, claim verification, and explanation generation.
4. **Fact Checking Experiments**: Train and evaluate machine learning models, including text and image analysis, using the dataset to enhance the accuracy of fact-checking systems.
## Leaderboard
## Dependencies
We recommend you create an anaconda environment:
`conda create --name finfact python=3.6 conda-build`
Then, install Python requirements:
`pip install -r requirements.txt`
## Run models for paper metrics
We provide scripts let you easily run our dataset on existing state-of-the-art models and re-create the metrics published in paper. You should be able to reproduce our results from the paper by following these instructions. Please post an issue if you're unable to do this.
To run existing ANLI models for fact checking.
### Run:
1. BART
```bash
python anli.py --model_name 'ynie/bart-large-snli_mnli_fever_anli_R1_R2_R3-nli' --data_file finfact.json --threshold 0.5
```
2. RoBERTa
```bash
python anli.py --model_name 'ynie/roberta-large-snli_mnli_fever_anli_R1_R2_R3-nli' --data_file finfact.json --threshold 0.5
```
3. ELECTRA
```bash
python anli.py --model_name 'ynie/electra-large-discriminator-snli_mnli_fever_anli_R1_R2_R3-nli' --data_file finfact.json --threshold 0.5
```
4. AlBERT
```bash
python anli.py --model_name 'ynie/albert-xxlarge-v2-snli_mnli_fever_anli_R1_R2_R3-nli' --data_file finfact.json --threshold 0.5
```
5. XLNET
```bash
python anli.py --model_name 'ynie/xlnet-large-cased-snli_mnli_fever_anli_R1_R2_R3-nli' --data_file finfact.json --threshold 0.5
```
6. GPT-2
```bash
python gpt2_nli.py --model_name 'fractalego/fact-checking' --data_file finfact.json
```
## Citation
```
@misc{rangapur2023finfact,
title={Fin-Fact: A Benchmark Dataset for Multimodal Financial Fact Checking and Explanation Generation},
author={Aman Rangapur and Haoran Wang and Kai Shu},
year={2023},
eprint={2309.08793},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```
## Contribution
We welcome contributions from the community to help improve Fin-Fact. If you have suggestions, bug reports, or want to contribute code or data, please check our [CONTRIBUTING.md](CONTRIBUTING.md) file for guidelines.
## License
Fin-Fact is released under the [MIT License](/LICENSE). Please review the license before using the dataset.
## Contact
For questions, feedback, or inquiries related to Fin-Fact, please contact `arangapur@hawk.iit.edu`.
We hope you find Fin-Fact valuable for your research and fact-checking endeavors. Happy fact-checking!
| 5,412 | [
[
-0.02593994140625,
-0.053131103515625,
0.030792236328125,
-0.00012814998626708984,
-0.02203369140625,
-0.00139617919921875,
0.003826141357421875,
-0.031982421875,
0.0128326416015625,
0.039459228515625,
-0.037109375,
-0.052154541015625,
-0.038848876953125,
0.... |
turkish-nlp-suite/beyazperde-all-movie-reviews | 2023-09-22T16:46:22.000Z | [
"task_categories:text-classification",
"task_ids:sentiment-classification",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"language:tr",
"license:cc-by-sa-4.0",
"region:us"
] | turkish-nlp-suite | Movies sentiment analysis dataset for Turkish. Includes reviews for all movies of all time,crawled from popular Turkish movies website Beyazperde.com. All reviews are in Turkish.[BeyazPerde Top All Movie Reviews Dataset](https://github.com/turkish-nlp-suite/BeyazPerde-Movie-Reviews/) | @inproceedings{altinok-2023-diverse,
title = "A Diverse Set of Freely Available Linguistic Resources for {T}urkish",
author = "Altinok, Duygu",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.768",
pages = "13739--13750",
abstract = "This study presents a diverse set of freely available linguistic resources for Turkish natural language processing, including corpora, pretrained models and education material. Although Turkish is spoken by a sizeable population of over 80 million people, Turkish linguistic resources for natural language processing remain scarce. In this study, we provide corpora to allow practitioners to build their own applications and pretrained models that would assist industry researchers in creating quick prototypes. The provided corpora include named entity recognition datasets of diverse genres, including Wikipedia articles and supplement products customer reviews. In addition, crawling e-commerce and movie reviews websites, we compiled several sentiment analysis datasets of different genres. Our linguistic resources for Turkish also include pretrained spaCy language models. To the best of our knowledge, our models are the first spaCy models trained for the Turkish language. Finally, we provide various types of education material, such as video tutorials and code examples, that can support the interested audience on practicing Turkish NLP. The advantages of our linguistic resources are three-fold: they are freely available, they are first of their kind, and they are easy to use in a broad range of implementations. Along with a thorough description of the resource creation process, we also explain the position of our resources in the Turkish NLP world.",
} | 0 | 6 | 2023-09-20T16:36:45 | ---
language:
- tr
license:
- cc-by-sa-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
task_categories:
- text-classification
task_ids:
- sentiment-classification
pretty_name: BeyazPerde All Movie Reviews
---
# Dataset Card for turkish-nlp-suite/beyazperde-all-movie-reviews
<img src="https://raw.githubusercontent.com/turkish-nlp-suite/.github/main/profile/beyazPerde.png" width="20%" height="20%">
## Dataset Description
- **Repository:** [BeyazPerde All Movie Reviews](https://github.com/turkish-nlp-suite/BeyazPerde-Movie-Reviews/)
- **Paper:** [ACL link](https://aclanthology.org/2023.acl-long.768/)
- **Dataset:** BeyazPerde All Movie Reviews
- **Domain:** Social Media
### Dataset Summary
Beyazperde Movie Reviews offers Turkish sentiment analysis datasets that is scraped from popular movie reviews website Beyazperde.com. All Movie Reviews include audience reviews about movies of all the time. Here's the star rating distribution:
| star rating | count |
|---|---|
| 0.5 | 3.635 |
| 1.0 | 2.325 |
| 1.5 | 1.077 |
| 2.0 | 1.902 |
| 2.5 | 4.767 |
| 3.0 |4.347 |
| 3.5 | 6.495 |
| 4.0 |9.486 |
| 4.5 | 3.652 |
| 5.0 | 7.594 |
| total | 45.280 |
The star rating looks quite balanced. This dataset offers the challenge of understanding the sentiment in a refined way, dissecting the positive sentiment into "very positive" or "okayish positive".
### Dataset Instances
An instance of this dataset looks as follows:
```
{
"movie": "Avatar",
"text": "Açıkçası film beklentilerimi karşılayamadı. Tabi her şeyin ilki güzel ama son seride iyi olabilirdi. Filmde görsel olarak her şey güzeldi kendimi filmi izledikten sonra ıslanmış gibi hissettim :D Puan kırdığım noktalar filmin bilim kurgudan fantastiğe doğru kayması. Ardından sır kapısına döndürüp iyilik yapan iyilik bulur moduna girmesi. Çoğu sahnelerin çocuklara hitap etmesi. Neyse serinin üçüncü filmi sağlam olucak gibi...",
"rating": 3,5
}
```
### Data Split
| name |train|validation|test|
|---------|----:|---:|---:|
|BeyazPerde All Movie Reviews|35280|5000|5000|
### Citation
This work is supported by Google Developer Experts Program. Part of Duygu 2022 Fall-Winter collection, "Turkish NLP with Duygu"/ "Duygu'yla Türkçe NLP". All rights reserved. If you'd like to use this dataset in your own work, please kindly cite [A Diverse Set of Freely Available Linguistic Resources for Turkish](https://aclanthology.org/2023.acl-long.768/) :
```
@inproceedings{altinok-2023-diverse,
title = "A Diverse Set of Freely Available Linguistic Resources for {T}urkish",
author = "Altinok, Duygu",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.768",
pages = "13739--13750",
abstract = "This study presents a diverse set of freely available linguistic resources for Turkish natural language processing, including corpora, pretrained models and education material. Although Turkish is spoken by a sizeable population of over 80 million people, Turkish linguistic resources for natural language processing remain scarce. In this study, we provide corpora to allow practitioners to build their own applications and pretrained models that would assist industry researchers in creating quick prototypes. The provided corpora include named entity recognition datasets of diverse genres, including Wikipedia articles and supplement products customer reviews. In addition, crawling e-commerce and movie reviews websites, we compiled several sentiment analysis datasets of different genres. Our linguistic resources for Turkish also include pretrained spaCy language models. To the best of our knowledge, our models are the first spaCy models trained for the Turkish language. Finally, we provide various types of education material, such as video tutorials and code examples, that can support the interested audience on practicing Turkish NLP. The advantages of our linguistic resources are three-fold: they are freely available, they are first of their kind, and they are easy to use in a broad range of implementations. Along with a thorough description of the resource creation process, we also explain the position of our resources in the Turkish NLP world.",
}
```
| 4,444 | [
[
-0.0601806640625,
-0.04248046875,
-0.0025615692138671875,
0.0208587646484375,
-0.05322265625,
-0.016571044921875,
-0.0298309326171875,
-0.024932861328125,
0.028594970703125,
0.03387451171875,
-0.050140380859375,
-0.060760498046875,
-0.051422119140625,
0.0246... |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.