id stringlengths 2 115 | author stringlengths 2 42 ⌀ | last_modified timestamp[us, tz=UTC] | downloads int64 0 8.87M | likes int64 0 3.84k | paperswithcode_id stringlengths 2 45 ⌀ | tags list | lastModified timestamp[us, tz=UTC] | createdAt stringlengths 24 24 | key stringclasses 1 value | created timestamp[us] | card stringlengths 1 1.01M | embedding list | library_name stringclasses 21 values | pipeline_tag stringclasses 27 values | mask_token null | card_data null | widget_data null | model_index null | config null | transformers_info null | spaces null | safetensors null | transformersInfo null | modelId stringlengths 5 111 ⌀ | embeddings list |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
TurkuNLP/xlsum-fi | TurkuNLP | 2022-10-25T06:30:19Z | 41 | 0 | null | [
"task_categories:summarization",
"task_categories:text2text-generation",
"annotations_creators:found",
"language_creators:machine translated",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"source_datasets:xlsum",
"language:fi",
"license:cc-by-nc-sa-4.0",
"conditional-text-generatio... | 2022-10-25T06:30:19Z | 2022-09-30T13:10:05.000Z | 2022-09-30T13:10:05 | ---
annotations_creators:
- found
language_creators:
- machine translated
language:
- fi
license:
- cc-by-nc-sa-4.0
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
source_datasets:
- xlsum
task_categories:
- summarization
- text2text-generation
task_ids: []
pretty_name: XL-Sum-FI
tags:
- conditional-text-generation
---
# Dataset Card for "XL-Sum-FI"
## Table of Contents
- [Dataset Card Creation Guide](#dataset-card-creation-guide)
- [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)
- [Initial Data Collection and Normalization](#initial-data-collection-and-normalization)
- [Who are the source language producers?](#who-are-the-source-language-producers)
- [Annotations](#annotations)
- [Annotation process](#annotation-process)
- [Who are the annotators?](#who-are-the-annotators)
- [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
- **Repository:** https://github.com/TurkuNLP/xlsum-fi
- **Point of Contact:** [Filip Ginter](mailto:figint@utu.fi)
### Dataset Summary
This dataset is a DeepL -based machine translation of a part of the English section of the XLSum dataset:[https://github.com/csebuetnlp/xl-sum](https://github.com/csebuetnlp/xl-sum) In the present version, only examples where the full version is at most 10x the summary in length are included. We might translate more later.
### Supported Tasks and Leaderboards
### Languages
- `finnish`
## Dataset Structure
### Data Instances
One example from the `Finnish` dataset is given below in JSON format.
```
{
"id": "technology-17657859",
"url": "https://www.bbc.com/news/technology-17657859",
"title": "Walesin myrskytuulien vuoksi annettu säävaroitus",
"summary": "Tuulet voivat yltyä Walesissa myrskytuuliin, ja myrskysää on luvassa koko maahan tällä viikolla.",
"text": "Met Office on antanut Walesin ja Englannin kattavan keltaisen tuulivaroituksen keskiviikkoillasta kello 21.00 GMT alkaen. Matkustaminen ja sähkönjakelu todennäköisesti häiriintyvät, ja varoitus on voimassa torstaihin kello 15:00 asti. Puuskat ovat todennäköisesti nopeudeltaan 88 kilometriä tunnissa, ja rannikoilla ja kukkuloilla puuskat voivat nousta jopa 70 kilometriin tunnissa, ja lisäksi voi esiintyä rankkasateita ja myrskyisiä sadekuuroja."
}
```
### Data Fields
- 'id': A string representing the article ID, matched to the XLSum dataset original
- 'url': A string representing the article URL as in the original XLSum dataset
- 'title': A string containing the article title, machine-translated to Finnish
- 'summary': A string containing the article summary, machine-translated to Finnish
- 'text' : A string containing the article text, machine-translated to Finnish
### Data Splits
Follows the XLSum dataset.
## Dataset Creation
### Curation Rationale
### Source Data
[BBC News](https://www.bbc.co.uk/ws/languages)
#### Initial Data Collection and Normalization
[Detailed in the paper](https://aclanthology.org/2021.findings-acl.413/) For this present dataset, only English was used as the source and only examples where the full text is at maximum 10x in length compared to the summary are preserved. This 10x cutoff is naturally measured on English.
#### Who are the source language producers?
[Detailed in the paper](https://aclanthology.org/2021.findings-acl.413/)
### Annotations
[Detailed in the paper](https://aclanthology.org/2021.findings-acl.413/) DeepL was used to machine-translate from English to Finnish
#### Annotation process
[Detailed in the paper](https://aclanthology.org/2021.findings-acl.413/)
#### Who are the annotators?
[Detailed in the paper](https://aclanthology.org/2021.findings-acl.413/)
### Personal and Sensitive Information
[More information needed](https://github.com/csebuetnlp/xl-sum)
## Considerations for Using the Data
### Social Impact of Dataset
### Discussion of Biases
### Other Known Limitations
Due to DeepL terms and conditions, this dataset **must not be used for any machine translation work**, namely machine translation system development and evaluation of any kind. In general, we wish you do not pair the original English data with the translations except when working on research unrelated to machine translation, so as not to infringe on the terms and conditions.
## Additional Information
### Dataset Curators
### Licensing Information
Contents of this repository are restricted to only non-commercial research purposes under the [Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/). Copyright of the dataset contents belongs to the original copyright holders.
### Citation Information
If you use any of the datasets, models or code modules, please cite the original XL-Sum paper below as well as acknowledge Filip Ginter and the TurkuNLP group for the Finnish machine translated version.
```
@inproceedings{hasan-etal-2021-xl,
title = "{XL}-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages",
author = "Hasan, Tahmid and
Bhattacharjee, Abhik and
Islam, Md. Saiful and
Mubasshir, Kazi and
Li, Yuan-Fang and
Kang, Yong-Bin and
Rahman, M. Sohel and
Shahriyar, Rifat",
booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-acl.413",
pages = "4693--4703",
}
```
### Contributions
Thanks to the creators of the XLSum dataset! | [
-0.3569289743900299,
-0.437959223985672,
0.23481407761573792,
0.07843951880931854,
-0.27248498797416687,
-0.0227739866822958,
-0.4228088855743408,
-0.4322810769081116,
0.6094135046005249,
0.39633944630622864,
-0.5838385224342346,
-0.7752156853675842,
-0.7761198282241821,
0.6105244755744934... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
autoevaluate/autoeval-eval-futin__guess-en-6f8c6a-2012266600 | autoevaluate | 2022-11-07T09:29:28Z | 41 | 0 | null | [
"autotrain",
"evaluation",
"region:us"
] | 2022-11-07T09:29:28Z | 2022-11-07T09:14:03.000Z | 2022-11-07T09:14:03 | ---
type: predictions
tags:
- autotrain
- evaluation
datasets:
- futin/guess
eval_info:
task: text_zero_shot_classification
model: facebook/opt-350m
metrics: []
dataset_name: futin/guess
dataset_config: en
dataset_split: test
col_mapping:
text: text
classes: classes
target: target
---
# Dataset Card for AutoTrain Evaluator
This repository contains model predictions generated by [AutoTrain](https://huggingface.co/autotrain) for the following task and dataset:
* Task: Zero-Shot Text Classification
* Model: facebook/opt-350m
* Dataset: futin/guess
* Config: en
* Split: test
To run new evaluation jobs, visit Hugging Face's [automatic model evaluator](https://huggingface.co/spaces/autoevaluate/model-evaluator).
## Contributions
Thanks to [@futin](https://huggingface.co/futin) for evaluating this model. | [
-0.3472531735897064,
-0.4719580411911011,
0.36175981163978577,
0.01893654093146324,
0.03734974563121796,
-0.11488562822341919,
0.00041651964420452714,
-0.4522530436515808,
0.12940220534801483,
0.37441274523735046,
-1.0087302923202515,
-0.2276470959186554,
-0.6089997291564941,
-0.0144074140... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
statworx/swiss-dialects | statworx | 2022-11-21T16:18:32Z | 41 | 1 | null | [
"task_categories:text-generation",
"task_categories:text-classification",
"task_ids:language-modeling",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"language:ch",
"license:cc-by-nc-4.0",
"dialect",
"region:us"
] | 2022-11-21T16:18:32Z | 2022-11-13T13:50:21.000Z | 2022-11-13T13:50:21 | ---
annotations_creators: []
language:
- ch
language_creators:
- found
license:
- cc-by-nc-4.0
multilinguality:
- monolingual
pretty_name: ArchiMob Corpus
size_categories:
- 10K<n<100K
source_datasets: []
tags:
- dialect
task_categories:
- text-generation
- text-classification
task_ids:
- language-modeling
---
# Dataset Card for ArchiMod Corpus
## Dataset Description
- **Homepage:** https://wortschatz.uni-leipzig.de/en/download/Swiss%20German
- **Repository:** https://huggingface.co/datasets/statworx/leipzip-swiss
### Dataset Summary
The ArchiMob corpus represents German linguistic varieties spoken within the territory of Switzerland. This corpus is the first electronic resource containing long samples of transcribed text in Swiss German, intended for studying the spatial distribution of morphosyntactic features and for natural language processing.
### Languages
Swiss-German
## Dataset Structure
### Data Instances
``
{
'sentence': Sentence in Swiss-German,
'label': Dialect as category
}
``
### Data Fields
`sentence`: Text as string.
`label`: Label as string.
### Data Splits
[More Information Needed]
## Dataset Creation
### Source Data
#### Initial Data Collection and Normalization
https://www.spur.uzh.ch/en/departments/research/textgroup/ArchiMob.html
## Additional Information
### Licensing Information
Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License
### Citation Information
Scherrer, Y., T. Samardžić, E. Glaser (2019). "Digitising Swiss German -- How to process and study a polycentric spoken language". Language Resources and Evaluation. (First online)
Scherrer, Y., T. Samardžić, E. Glaser (2019). "ArchiMob: Ein multidialektales Korpus schweizerdeutscher Spontansprache". Linguistik Online, 98(5), 425-454. https://doi.org/10.13092/lo.98.5947
| [
-0.7498322129249573,
-0.7587697505950928,
0.1927466094493866,
0.17055025696754456,
-0.5415645837783813,
-0.09264584630727768,
-0.2956271469593048,
-0.42883220314979553,
0.5580201148986816,
0.6963948607444763,
-0.6706990599632263,
-1.10128653049469,
-0.5868601202964783,
0.26144838333129883,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
bigbio/ctebmsp | bigbio | 2022-12-22T15:44:30Z | 41 | 0 | null | [
"multilinguality:monolingual",
"language:es",
"license:cc-by-nc-4.0",
"region:us"
] | 2022-12-22T15:44:30Z | 2022-11-13T22:08:04.000Z | 2022-11-13T22:08:04 |
---
language:
- es
bigbio_language:
- Spanish
license: cc-by-nc-4.0
multilinguality: monolingual
bigbio_license_shortname: CC_BY_NC_4p0
pretty_name: CT-EBM-SP
homepage: http://www.lllf.uam.es/ESP/nlpmedterm_en.html
bigbio_pubmed: True
bigbio_public: True
bigbio_tasks:
- NAMED_ENTITY_RECOGNITION
---
# Dataset Card for CT-EBM-SP
## Dataset Description
- **Homepage:** http://www.lllf.uam.es/ESP/nlpmedterm_en.html
- **Pubmed:** True
- **Public:** True
- **Tasks:** NER
### Ctebmsp Abstracts
The "abstracts" subset of the Clinical Trials for Evidence-Based Medicine in Spanish
(CT-EBM-SP) corpus contains 500 abstracts of clinical trial studies in Spanish,
published in journals with a Creative Commons license. Most were downloaded from
the SciELO repository and free abstracts in PubMed.
Abstracts were retrieved with the query:
Clinical Trial[ptyp] AND “loattrfree full text”[sb] AND “spanish”[la].
(Information collected from 10.1186/s12911-021-01395-z)
### Ctebmsp Eudract
The "abstracts" subset of the Clinical Trials for Evidence-Based Medicine in Spanish
(CT-EBM-SP) corpus contains 500 abstracts of clinical trial studies in Spanish,
published in journals with a Creative Commons license. Most were downloaded from
the SciELO repository and free abstracts in PubMed.
Abstracts were retrieved with the query:
Clinical Trial[ptyp] AND “loattrfree full text”[sb] AND “spanish”[la].
(Information collected from 10.1186/s12911-021-01395-z)
## Citation Information
```
@article{CampillosLlanos2021,
author = {Leonardo Campillos-Llanos and
Ana Valverde-Mateos and
Adri{'{a}}n Capllonch-Carri{'{o}}n and
Antonio Moreno-Sandoval},
title = {A clinical trials corpus annotated with {UMLS}
entities to enhance the access to evidence-based medicine},
journal = {{BMC} Medical Informatics and Decision Making},
volume = {21},
year = {2021},
url = {https://doi.org/10.1186/s12911-021-01395-z},
doi = {10.1186/s12911-021-01395-z},
biburl = {},
bibsource = {}
}
```
| [
-0.061381518840789795,
-0.6009036302566528,
0.38496124744415283,
0.6755247116088867,
-0.6090640425682068,
-0.039023276418447495,
-0.06872547417879105,
-0.4895882308483124,
0.5898590087890625,
0.4928284287452698,
-0.24321787059307098,
-1.206834077835083,
-0.8441035747528076,
0.2888257801532... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
bigbio/mlee | bigbio | 2022-12-22T15:45:39Z | 41 | 1 | null | [
"multilinguality:monolingual",
"language:en",
"license:cc-by-nc-sa-3.0",
"region:us"
] | 2022-12-22T15:45:39Z | 2022-11-13T22:10:03.000Z | 2022-11-13T22:10:03 |
---
language:
- en
bigbio_language:
- English
license: cc-by-nc-sa-3.0
multilinguality: monolingual
bigbio_license_shortname: CC_BY_NC_SA_3p0
pretty_name: MLEE
homepage: http://www.nactem.ac.uk/MLEE/
bigbio_pubmed: True
bigbio_public: True
bigbio_tasks:
- EVENT_EXTRACTION
- NAMED_ENTITY_RECOGNITION
- RELATION_EXTRACTION
- COREFERENCE_RESOLUTION
---
# Dataset Card for MLEE
## Dataset Description
- **Homepage:** http://www.nactem.ac.uk/MLEE/
- **Pubmed:** True
- **Public:** True
- **Tasks:** EE,NER,RE,COREF
MLEE is an event extraction corpus consisting of manually annotated abstracts of papers
on angiogenesis. It contains annotations for entities, relations, events and coreferences
The annotations span molecular, cellular, tissue, and organ-level processes.
## Citation Information
```
@article{pyysalo2012event,
title={Event extraction across multiple levels of biological organization},
author={Pyysalo, Sampo and Ohta, Tomoko and Miwa, Makoto and Cho, Han-Cheol and Tsujii, Jun'ichi and Ananiadou, Sophia},
journal={Bioinformatics},
volume={28},
number={18},
pages={i575--i581},
year={2012},
publisher={Oxford University Press}
}
```
| [
-0.18040257692337036,
-0.6420502066612244,
0.24348331987857819,
-0.03185223042964935,
-0.09922225028276443,
-0.16595019400119781,
0.09738180041313171,
-0.3945847153663635,
0.6041645407676697,
0.38983479142189026,
-0.5679548382759094,
-0.6908911466598511,
-0.4600989818572998,
0.495806962251... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
bigbio/scai_disease | bigbio | 2022-12-22T15:46:35Z | 41 | 1 | null | [
"multilinguality:monolingual",
"language:en",
"license:unknown",
"region:us"
] | 2022-12-22T15:46:35Z | 2022-11-13T22:12:00.000Z | 2022-11-13T22:12:00 |
---
language:
- en
bigbio_language:
- English
license: unknown
multilinguality: monolingual
bigbio_license_shortname: UNKNOWN
pretty_name: SCAI Disease
homepage: https://www.scai.fraunhofer.de/en/business-research-areas/bioinformatics/downloads/corpus-for-disease-names-and-adverse-effects.html
bigbio_pubmed: True
bigbio_public: True
bigbio_tasks:
- NAMED_ENTITY_RECOGNITION
---
# Dataset Card for SCAI Disease
## Dataset Description
- **Homepage:** https://www.scai.fraunhofer.de/en/business-research-areas/bioinformatics/downloads/corpus-for-disease-names-and-adverse-effects.html
- **Pubmed:** True
- **Public:** True
- **Tasks:** NER
SCAI Disease is a dataset annotated in 2010 with mentions of diseases and
adverse effects. It is a corpus containing 400 randomly selected MEDLINE
abstracts generated using ‘Disease OR Adverse effect’ as a PubMed query. This
evaluation corpus was annotated by two individuals who hold a Master’s degree
in life sciences.
## Citation Information
```
@inproceedings{gurulingappa:lrec-ws10,
author = {Harsha Gurulingappa and Roman Klinger and Martin Hofmann-Apitius and Juliane Fluck},
title = {An Empirical Evaluation of Resources for the Identification of Diseases and Adverse Effects in Biomedical Literature},
booktitle = {LREC Workshop on Building and Evaluating Resources for Biomedical Text Mining},
year = {2010},
}
```
| [
0.22698874771595,
-0.4196648895740509,
0.4474250078201294,
0.08365555852651596,
-0.2592656910419464,
-0.2978819012641907,
-0.05897994339466095,
-0.5587852001190186,
0.7471778392791748,
0.38029977679252625,
-0.12303853034973145,
-0.6455849409103394,
-0.8667829632759094,
0.28339290618896484,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
RobotsMaliAI/bayelemabaga | RobotsMaliAI | 2023-04-24T16:56:24Z | 41 | 3 | null | [
"task_categories:translation",
"task_categories:text-generation",
"size_categories:10K<n<100K",
"language:bm",
"language:fr",
"region:us"
] | 2023-04-24T16:56:24Z | 2022-12-04T08:47:14.000Z | 2022-12-04T08:47:14 | ---
task_categories:
- translation
- text-generation
language:
- bm
- fr
size_categories:
- 10K<n<100K
---
# BAYƐLƐMABAGA: Parallel French - Bambara Dataset for Machine Learning
## Overview
The Bayelemabaga dataset is a collection of 46976 aligned machine translation ready Bambara-French lines, originating from [Corpus Bambara de Reference](http://cormande.huma-num.fr/corbama/run.cgi/first_form). The dataset is constitued of text extracted from **264** text files, varing from periodicals, books, short stories, blog posts, part of the Bible and the Quran.
## Snapshot: 46976
| | |
|:---|---:|
| **Lines** | **46976** |
| French Tokens (spacy) | 691312 |
| Bambara Tokens (daba) | 660732 |
| French Types | 32018 |
| Bambara Types | 29382 |
| Avg. Fr line length | 77.6 |
| Avg. Bam line length | 61.69 |
| Number of text sources | 264 |
## Data Splits
| | | |
|:-----:|:---:|------:|
| Train | 80% | 37580 |
| Valid | 10% | 4698 |
| Test | 10% | 4698 |
||
## Remarks
* We are working on resolving some last minute misalignment issues.
### Maintenance
* This dataset is supposed to be actively maintained.
### Benchmarks:
- `Coming soon`
### Sources
- [`sources`](./bayelemabaga/sources.txt)
### To note:
- ʃ => (sh/shy) sound: Symbol left in the dataset, although not a part of bambara orthography nor French orthography.
## License
- `CC-BY-SA-4.0`
## Version
- `1.0.1`
## Citation
```
@misc{bayelemabagamldataset2022
title={Machine Learning Dataset Development for Manding Languages},
author={
Valentin Vydrin and
Jean-Jacques Meric and
Kirill Maslinsky and
Andrij Rovenchak and
Allahsera Auguste Tapo and
Sebastien Diarra and
Christopher Homan and
Marco Zampieri and
Michael Leventhal
},
howpublished = {url{https://github.com/robotsmali-ai/datasets}},
year={2022}
}
```
## Contacts
- `sdiarra <at> robotsmali <dot> org`
- `aat3261 <at> rit <dot> edu` | [
-0.48396313190460205,
-0.48748692870140076,
0.10156026482582092,
0.26331627368927,
-0.15947355329990387,
0.17343290150165558,
-0.10747101902961731,
-0.05877295881509781,
0.08148767799139023,
0.5223011374473572,
-0.6158407926559448,
-0.9464366436004639,
-0.7019444108009338,
-0.0033200245816... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
keremberke/valorant-object-detection | keremberke | 2023-01-27T13:45:00Z | 41 | 3 | null | [
"task_categories:object-detection",
"roboflow",
"roboflow2huggingface",
"region:us"
] | 2023-01-27T13:45:00Z | 2022-12-28T05:41:05.000Z | 2022-12-28T05:41:05 | ---
task_categories:
- object-detection
tags:
- roboflow
- roboflow2huggingface
---
<div align="center">
<img width="640" alt="keremberke/valorant-object-detection" src="https://huggingface.co/datasets/keremberke/valorant-object-detection/resolve/main/thumbnail.jpg">
</div>
### Dataset Labels
```
['dropped spike', 'enemy', 'planted spike', 'teammate']
```
### Number of Images
```json
{'valid': 1983, 'train': 6927, 'test': 988}
```
### How to Use
- Install [datasets](https://pypi.org/project/datasets/):
```bash
pip install datasets
```
- Load the dataset:
```python
from datasets import load_dataset
ds = load_dataset("keremberke/valorant-object-detection", name="full")
example = ds['train'][0]
```
### Roboflow Dataset Page
[https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp/dataset/3](https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp/dataset/3?ref=roboflow2huggingface)
### Citation
```
@misc{ valorant-9ufcp_dataset,
title = { valorant Dataset },
type = { Open Source Dataset },
author = { Daniels Magonis },
howpublished = { \\url{ https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp } },
url = { https://universe.roboflow.com/daniels-magonis-0pjzx/valorant-9ufcp },
journal = { Roboflow Universe },
publisher = { Roboflow },
year = { 2022 },
month = { nov },
note = { visited on 2023-01-27 },
}
```
### License
CC BY 4.0
### Dataset Summary
This dataset was exported via roboflow.com on December 22, 2022 at 5:10 PM GMT
Roboflow is an end-to-end computer vision platform that helps you
* collaborate with your team on computer vision projects
* collect & organize images
* understand unstructured image data
* annotate, and create datasets
* export, train, and deploy computer vision models
* use active learning to improve your dataset over time
It includes 9898 images.
Planted are annotated in COCO format.
The following pre-processing was applied to each image:
* Resize to 416x416 (Stretch)
No image augmentation techniques were applied.
| [
-0.4564981758594513,
-0.3363700807094574,
0.30144479870796204,
-0.02951541729271412,
-0.25085100531578064,
-0.1563190221786499,
-0.07965034246444702,
-0.41715094447135925,
0.3903772830963135,
0.28864988684654236,
-0.5711432695388794,
-0.8627641201019287,
-0.5373945236206055,
0.135170474648... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
jonathan-roberts1/SAT-6 | jonathan-roberts1 | 2023-04-03T16:17:41Z | 41 | 0 | null | [
"license:other",
"region:us"
] | 2023-04-03T16:17:41Z | 2023-02-03T18:13:10.000Z | 2023-02-03T18:13:10 | ---
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': barren land
'1': building
'2': grassland
'3': road
'4': trees
'5': water
splits:
- name: train
num_bytes: 120518797
num_examples: 81000
download_size: 142842069
dataset_size: 120518797
license: other
---
# Dataset Card for "SAT-6"
## Dataset Description
- **Paper** [Deepsat: a learning framework for satellite imagery](https://dl.acm.org/doi/pdf/10.1145/2820783.2820816)
- **Split** Test
### Split Information
This HuggingFace dataset repository contains just the 'Test' split.
### Licensing Information
Public Domain
## Citation Information
[https://dl.acm.org/doi/pdf/10.1145/2820783.2820816](https://dl.acm.org/doi/pdf/10.1145/2820783.2820816)
```
@inproceedings{basu2015deepsat,
title = {Deepsat: a learning framework for satellite imagery},
author = {Basu, Saikat and Ganguly, Sangram and Mukhopadhyay, Supratik and DiBiano, Robert and Karki, Manohar and Nemani, Ramakrishna},
year = 2015,
booktitle = {Proceedings of the 23rd SIGSPATIAL international conference on advances in geographic information systems},
pages = {1--10}
}
```
| [
-0.6754881143569946,
-0.31276020407676697,
0.3550053536891937,
0.17348316311836243,
-0.5232187509536743,
-0.03894110769033432,
-0.17040541768074036,
-0.182572603225708,
0.0032672781962901354,
0.4736974239349365,
-0.6680867671966553,
-0.6917411088943481,
-0.6009169220924377,
0.0458077080547... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
alexandrainst/ddisco | alexandrainst | 2023-02-08T18:12:26Z | 41 | 1 | null | [
"task_categories:text-classification",
"annotations_creators:expert-generated",
"language_creators:expert-generated",
"multilinguality:monolingual",
"size_categories:1K<n<10K",
"language:da",
"license:afl-3.0",
"discourse",
"coherence",
"region:us"
] | 2023-02-08T18:12:26Z | 2023-02-08T18:05:24.000Z | 2023-02-08T18:05:24 | ---
annotations_creators:
- expert-generated
language:
- da
language_creators:
- expert-generated
license:
- afl-3.0
multilinguality:
- monolingual
pretty_name: DDisco
size_categories:
- 1K<n<10K
source_datasets: []
tags:
- discourse
- coherence
task_categories:
- text-classification
task_ids: []
dataset_info:
features:
- name: text
dtype: string
- name: domain
dtype: string
- name: rating
dtype: int64
splits:
- name: train
num_bytes: 815571
num_examples: 801
- name: test
num_bytes: 209297
num_examples: 201
download_size: 672202
dataset_size: 1024868
---
# Dataset Card for DDisco
## Dataset Description
The DDisco dataset is a dataset which can be used to train models to classify levels of coherence in _danish_ discourse. Each entry in the dataset is annotated with a discourse coherence label (rating from 1 to 3):
1: low coherence (difficult to understand, unorganized, contained unnecessary details and can not be summarized briefly and easily)
2: medium coherence
3: high coherence (easy to understand, well organized, only contain details that support the main point and can be summarized briefly and easily).
Grammatical and typing errors are ignored (i.e. they do not affect the coherency score) and the coherence of a text is considered within its own domain.
### Additional Information
[DDisCo: A Discourse Coherence Dataset for Danish](https://aclanthology.org/2022.lrec-1.260.pdf)
### Contributions
[@ajders](https://github.com/ajders) | [
-0.5500327348709106,
-0.5873266458511353,
0.3988533020019531,
0.06565836071968079,
-0.36145642399787903,
0.18144281208515167,
0.06487586349248886,
-0.34306013584136963,
0.12223322689533234,
0.34522825479507446,
-0.30233386158943176,
-1.074371337890625,
-0.7202778458595276,
0.29253363609313... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
biglam/european_art | biglam | 2023-08-03T09:39:40Z | 41 | 5 | null | [
"task_categories:object-detection",
"task_categories:image-classification",
"size_categories:10K<n<100K",
"license:cc-by-nc-2.0",
"lam",
"art",
"historical",
"arxiv:2211.01226",
"region:us"
] | 2023-08-03T09:39:40Z | 2023-03-04T15:05:33.000Z | 2023-03-04T15:05:33 | ---
dataset_info:
- config_name: raw
features:
- name: image
dtype: image
- name: source
dtype: string
- name: width
dtype: int16
- name: height
dtype: int16
- name: dept
dtype: int8
- name: segmented
dtype: int8
- name: objects
list:
- name: name
dtype:
class_label:
names:
'0': zebra
'1': tree
'2': nude
'3': crucifixion
'4': scroll
'5': head
'6': swan
'7': shield
'8': lily
'9': mouse
'10': knight
'11': dragon
'12': horn
'13': dog
'14': palm
'15': tiara
'16': helmet
'17': sheep
'18': deer
'19': person
'20': sword
'21': rooster
'22': bear
'23': halo
'24': lion
'25': monkey
'26': prayer
'27': crown of thorns
'28': elephant
'29': zucchetto
'30': unicorn
'31': holy shroud
'32': cat
'33': apple
'34': banana
'35': chalice
'36': bird
'37': eagle
'38': pegasus
'39': crown
'40': camauro
'41': saturno
'42': arrow
'43': dove
'44': centaur
'45': horse
'46': hands
'47': skull
'48': orange
'49': monk
'50': trumpet
'51': key of heaven
'52': fish
'53': cow
'54': angel
'55': devil
'56': book
'57': stole
'58': butterfly
'59': serpent
'60': judith
'61': mitre
'62': banner
'63': donkey
'64': shepherd
'65': boat
'66': god the father
'67': crozier
'68': jug
'69': lance
- name: pose
dtype:
class_label:
names:
'0': stand
'1': sit
'2': partial
'3': Unspecified
'4': squats
'5': lie
'6': bend
'7': fall
'8': walk
'9': push
'10': pray
'11': undefined
'12': kneel
'13': unrecognize
'14': unknown
'15': other
'16': ride
- name: diffult
dtype: int32
- name: xmin
dtype: float64
- name: ymin
dtype: float64
- name: xmax
dtype: float64
- name: ymax
dtype: float64
splits:
- name: train
num_bytes: 9046918
num_examples: 15156
download_size: 18160510195
dataset_size: 9046918
- config_name: coco
features:
- name: image
dtype: image
- name: source
dtype: string
- name: width
dtype: int16
- name: height
dtype: int16
- name: dept
dtype: int8
- name: segmented
dtype: int8
- name: objects
list:
- name: category_id
dtype:
class_label:
names:
'0': zebra
'1': tree
'2': nude
'3': crucifixion
'4': scroll
'5': head
'6': swan
'7': shield
'8': lily
'9': mouse
'10': knight
'11': dragon
'12': horn
'13': dog
'14': palm
'15': tiara
'16': helmet
'17': sheep
'18': deer
'19': person
'20': sword
'21': rooster
'22': bear
'23': halo
'24': lion
'25': monkey
'26': prayer
'27': crown of thorns
'28': elephant
'29': zucchetto
'30': unicorn
'31': holy shroud
'32': cat
'33': apple
'34': banana
'35': chalice
'36': bird
'37': eagle
'38': pegasus
'39': crown
'40': camauro
'41': saturno
'42': arrow
'43': dove
'44': centaur
'45': horse
'46': hands
'47': skull
'48': orange
'49': monk
'50': trumpet
'51': key of heaven
'52': fish
'53': cow
'54': angel
'55': devil
'56': book
'57': stole
'58': butterfly
'59': serpent
'60': judith
'61': mitre
'62': banner
'63': donkey
'64': shepherd
'65': boat
'66': god the father
'67': crozier
'68': jug
'69': lance
- name: image_id
dtype: string
- name: area
dtype: int64
- name: bbox
sequence: float32
length: 4
- name: segmentation
list:
list: float32
- name: iscrowd
dtype: bool
- name: image_id
dtype: string
splits:
- name: train
num_bytes: 8285204
num_examples: 15156
download_size: 18160510195
dataset_size: 8285204
license: cc-by-nc-2.0
task_categories:
- object-detection
- image-classification
tags:
- lam
- art
- historical
pretty_name: 'DEArt: Dataset of European Art'
size_categories:
- 10K<n<100K
---
# Dataset Card for DEArt: Dataset of European Art
## 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:** https://doi.org/10.5281/zenodo.6984525
- **Paper:** https://arxiv.org/abs/2211.01226
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
> DEArt is an object detection and pose classification dataset meant to be a reference for paintings between the XIIth and the XVIIIth centuries. It contains more than 15000 images, about 80% non-iconic, aligned with manual annotations for the bounding boxes identifying all instances of 69 classes as well as 12 possible poses for boxes identifying human-like objects. Of these, more than 50 classes are cultural heritage specific and thus do not appear in other datasets; these reflect imaginary beings, symbolic entities and other categories related to art.
### Supported Tasks and Leaderboards
- `object-detection`: This dataset can be used to train or evaluate models for object-detection on historical document images.
- `image-classification`: This dataset can be used for image classification tasks by using only the labels and not the bounding box information
## Dataset Structure
This dataset has two configurations. These configurations both cover the same data and annotations but provide these annotations in different forms to make it easier to integrate the data with existing processing pipelines.
- The first configuration, `raw, uses the data's original format.
- The second configuration converts the annotations into a format that is closer to the `COCO` annotation format. This is done to make it easier to work with the [`image_processors`](https://huggingface.co/docs/transformers/main_classes/image_processor) (formerly known as`feature_extractor`s) from the `Transformers` models for object detection, which expects data to be in a COCO-style format.
### Data Instances
An instance from the `raw` config:
```python
{'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1019x1680>,
'source': 'Europeana Collection',
'width': 1019,
'height': 1680,
'dept': 3,
'segmented': None,
'objects': [{'name': 40,
'pose': 3,
'diffult': 0,
'xmin': 259.0,
'ymin': 166.0,
'xmax': 679.0,
'ymax': 479.0},
{'name': 19,
'pose': 2,
'diffult': 0,
'xmin': 115.0,
'ymin': 354.0,
'xmax': 882.0,
'ymax': 1168.0},
{'name': 15,
'pose': 3,
'diffult': 0,
'xmin': 445.0,
'ymin': 1170.0,
'xmax': 579.0,
'ymax': 1302.0},
{'name': 51,
'pose': 3,
'diffult': 0,
'xmin': 354.0,
'ymin': 1196.0,
'xmax': 445.0,
'ymax': 1330.0},
{'name': 51,
'pose': 3,
'diffult': 0,
'xmin': 580.0,
'ymin': 1203.0,
'xmax': 701.0,
'ymax': 1326.0},
{'name': 57,
'pose': 3,
'diffult': 0,
'xmin': 203.0,
'ymin': 642.0,
'xmax': 882.0,
'ymax': 1172.0}]}
```
An instance from the `coco` config:
```python
{'image': <PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=1019x1680>,
'source': 'Europeana Collection',
'width': 1019,
'height': 1680,
'dept': 3,
'segmented': None,
'image_id': '0',
'annotations': [{'category_id': 40,
'image_id': '0',
'area': 131460,
'bbox': [259.0, 166.0, 420.0, 313.0],
'segmentation': [],
'iscrowd': False},
{'category_id': 19,
'image_id': '0',
'area': 624338,
'bbox': [115.0, 354.0, 767.0, 814.0],
'segmentation': [],
'iscrowd': False},
{'category_id': 15,
'image_id': '0',
'area': 17688,
'bbox': [445.0, 1170.0, 134.0, 132.0],
'segmentation': [],
'iscrowd': False},
{'category_id': 51,
'image_id': '0',
'area': 12194,
'bbox': [354.0, 1196.0, 91.0, 134.0],
'segmentation': [],
'iscrowd': False},
{'category_id': 51,
'image_id': '0',
'area': 14883,
'bbox': [580.0, 1203.0, 121.0, 123.0],
'segmentation': [],
'iscrowd': False},
{'category_id': 57,
'image_id': '0',
'area': 359870,
'bbox': [203.0, 642.0, 679.0, 530.0],
'segmentation': [],
'iscrowd': False}]}
```
### Data Fields
The fields for the COCO config:
- `image`: The Image being annotated
- `source`: source of the image i.e.'Europeana Collection'
- `width`: width of the image
- `height`: height of the image
- `dept`: number of channels in the image
- `segmented`: Whether the image has been segmented
- `image_id`: ID for the image
- `annotations`: annotations in coco format, consisting of a list containing dictionaries with the following keys:
- `bbox`: bounding boxes for the images
- `category_id`: a label for the image
- `image_id`: id for the image
- `iscrowd`: COCO `iscrowd` flag
- `segmentation`: COCO segmentation annotations (empty in this case but kept for compatibility with other processing scripts)
### Data Splits
The dataset doesn't define set splits, so only a train split is provided. The paper associated with the dataset does discuss a train and validation split, but it doesn't appear this split was shared with the dataset or associated paper.
## Dataset Creation
### Curation Rationale
The creators of the dataset authors outline some of their motivations for creating the dataset in the abstract for their paper:
> Large datasets that were made publicly available to the research community over the last 20 years have been a key enabling factor for the advances in deep learning algorithms for NLP or computer vision. These datasets are generally pairs of aligned image / manually annotated metadata, where images are photographs of everyday life. Scholarly and historical content, on the other hand, treat subjects that are not necessarily popular to a general audience, they may not always contain a large number of data points, and new data may be difficult or impossible to collect. Some exceptions do exist, for instance, scientific or health data, but this is not the case for cultural heritage (CH). The poor performance of the best models in computer vision - when tested over artworks - coupled with the lack of extensively annotated datasets for CH, and the fact that artwork images depict objects and actions not captured by photographs, indicate that a CH-specific dataset would be highly valuable for this community. We propose DEArt, at this point primarily an object detection and pose classification dataset meant to be a reference for paintings between the XIIth and the XVIIIth centuries. It contains more than 15000 images, about 80% non-iconic, aligned with manual annotations for the bounding boxes identifying all instances of 69 classes as well as 12 possible poses for boxes identifying human-like objects. Of these, more than 50 classes are CH-specific and thus do not appear in other datasets; these reflect imaginary beings, symbolic entities and other categories related to art. Additionally, existing datasets do not include pose annotations.
### Source Data
The source data comes from several cultural heritage institutions that have shared openly licenced images. The dictionary below shows the institutions and the frequency with which they are the provider of images in the dataset.
```python
{'National Museum in Warsaw': 2030,
'Europeana Collection': 1991,
'The Art Institute of Chicago': 1237,
'The Metropolitan Museum of Art': 1218,
'Rijksmuseum': 1066,
'National Gallery of Art': 871,
'Philadelphia Museum of Art': 774,
'WikiArt': 687,
'National museum in Krakow': 661,
'National Gallery of Denmark': 660,
'British Museum': 618,
'Victoria and Albert Museum': 561,
'Paul Mellon Centre': 391,
'National Gallery of Scotland': 384,
'Yale University Art Gallery': 376,
'Museo Nacional Thyssen-Bornemisza': 332,
'Harvard Art Museum': 279,
'The National Museum of Norvay': 270,
'LACMA': 262,
'The Cleveland Museum of Art': 242,
'The Leiden Collection': 159,
'The Clark Museum': 77,
'Pharos': 6,
'Wikimedia Commons': 2,
'Wikipedia': 1,
'Unknown': 1}
```
#### 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 [@github-username](https://github.com/<github-username>) for adding this dataset. | [
-0.7239797711372375,
-0.4723767340183258,
0.07475181668996811,
0.008310438133776188,
-0.4349774420261383,
-0.02212672308087349,
-0.0823000967502594,
-0.7796865105628967,
0.46277475357055664,
0.47618135809898376,
-0.5433340072631836,
-0.9673337340354919,
-0.5257781744003296,
0.2383822202682... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Dahoas/hh_human_eval | Dahoas | 2023-03-06T00:10:19Z | 41 | 0 | null | [
"region:us"
] | 2023-03-06T00:10:19Z | 2023-03-05T18:19:08.000Z | 2023-03-05T18:19:08 | ---
dataset_info:
features:
- name: prompt
dtype: string
splits:
- name: train
num_bytes: 50908
num_examples: 100
download_size: 30961
dataset_size: 50908
---
# Dataset Card for "hh_human_eval"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.5276588797569275,
-0.5140712261199951,
0.2324855625629425,
0.10758166760206223,
0.02124076895415783,
0.25289034843444824,
0.17069776356220245,
-0.07531780004501343,
0.7780901193618774,
0.46042364835739136,
-0.6344481706619263,
-0.7772055864334106,
-0.3507158160209656,
-0.074630469083786... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
suolyer/pile_books3 | suolyer | 2023-03-27T03:01:19Z | 41 | 0 | null | [
"license:apache-2.0",
"region:us"
] | 2023-03-27T03:01:19Z | 2023-03-26T16:35:38.000Z | 2023-03-26T16:35:38 | ---
license: apache-2.0
---
| [
-0.1285339742898941,
-0.18616800010204315,
0.6529127359390259,
0.4943626821041107,
-0.1931934952735901,
0.2360742688179016,
0.360720157623291,
0.05056300014257431,
0.5793654322624207,
0.7400140166282654,
-0.6508105993270874,
-0.23783984780311584,
-0.7102248668670654,
-0.047826044261455536,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
tasksource/ScienceQA_text_only | tasksource | 2023-07-13T11:50:29Z | 41 | 19 | null | [
"language:en",
"region:us"
] | 2023-07-13T11:50:29Z | 2023-04-11T11:45:03.000Z | 2023-04-11T11:45:03 | ---
language: en
dataset_info:
features:
- name: question
dtype: string
- name: choices
sequence: string
- name: answer
dtype: int8
- name: hint
dtype: string
- name: task
dtype: string
- name: grade
dtype: string
- name: subject
dtype: string
- name: topic
dtype: string
- name: category
dtype: string
- name: skill
dtype: string
- name: lecture
dtype: string
- name: solution
dtype: string
splits:
- name: train
num_bytes: 8105771.787521609
num_examples: 6508
- name: validation
num_bytes: 2638142.7097382694
num_examples: 2144
- name: test
num_bytes: 2757852.295213393
num_examples: 2224
download_size: 2925662
dataset_size: 13501766.792473271
---
# Dataset Card for "scienceQA_text_only"
ScienceQA text-only examples (examples where no image was initially present, which means they should be doable with text-only models.)
```
@article{10.1007/s00799-022-00329-y,
author = {Saikh, Tanik and Ghosal, Tirthankar and Mittal, Amish and Ekbal, Asif and Bhattacharyya, Pushpak},
title = {ScienceQA: A Novel Resource for Question Answering on Scholarly Articles},
year = {2022},
journal = {Int. J. Digit. Libr.},
month = {sep}
}
``` | [
0.001052111154422164,
-0.5859817266464233,
0.6287100911140442,
-0.07031743973493576,
-0.5728689432144165,
-0.26550373435020447,
0.24217291176319122,
-0.029495785012841225,
0.3918282687664032,
0.6999592185020447,
-0.8958501219749451,
-0.7352936267852783,
-0.3266621232032776,
0.2189616113901... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
mask-distilled-onesec-cv12-each-chunk-uniq/chunk_250 | mask-distilled-onesec-cv12-each-chunk-uniq | 2023-05-31T00:08:35Z | 41 | 0 | null | [
"region:us"
] | 2023-05-31T00:08:35Z | 2023-05-31T00:06:58.000Z | 2023-05-31T00:06:58 | ---
dataset_info:
features:
- name: logits
sequence: float32
- name: mfcc
sequence:
sequence: float64
splits:
- name: train
num_bytes: 876129520.0
num_examples: 172060
download_size: 894655957
dataset_size: 876129520.0
---
# Dataset Card for "chunk_250"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.6440715193748474,
-0.3485460877418518,
0.2856666147708893,
0.4298705458641052,
-0.3295072615146637,
0.02516021952033043,
0.24774911999702454,
-0.1794627457857132,
1.0598187446594238,
0.5056722164154053,
-0.8631125688552856,
-0.54154372215271,
-0.6382927298545837,
-0.3277706801891327,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
mlfoundations/datacomp_1b | mlfoundations | 2023-08-21T21:43:05Z | 41 | 6 | null | [
"license:cc-by-4.0",
"region:us"
] | 2023-08-21T21:43:05Z | 2023-06-11T20:12:44.000Z | 2023-06-11T20:12:44 | ---
license: cc-by-4.0
---
## DataComp-1B
This repository contains metadata files for DataComp-1B. For details on how to use the metadata, please visit [our website](https://www.datacomp.ai/) and our [github repository](https://github.com/mlfoundations/datacomp).
We distribute the image url-text samples and metadata under a standard Creative Common CC-BY-4.0 license. The individual images are under their own copyrights.
## Terms and Conditions
We have terms of service that are similar to those adopted by HuggingFace (https://huggingface.co/terms-of-service), which covers their dataset library. Specifically, any content you download, access or use from our index, is at your own risk and subject to the terms of service or copyright limitations accompanying such content. The image url-text index, which is a research artifact, is provided as is. By using said index, you assume all risks, including but not limited to, liabilities related to image downloading and storage. | [
-0.5225591659545898,
-0.6272405385971069,
0.28270184993743896,
0.4394437074661255,
-0.5329110622406006,
-0.10333607345819473,
0.06786415725946426,
-0.638816773891449,
0.43861889839172363,
0.5704854726791382,
-1.0307337045669556,
-0.700157642364502,
-0.6229904890060425,
0.2898767292499542,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Ciros/Flashman | Ciros | 2023-09-30T02:13:06Z | 41 | 0 | null | [
"region:us"
] | 2023-09-30T02:13:06Z | 2023-06-14T00:14:35.000Z | 2023-06-14T00:14:35 | Entry not found | [
-0.3227645754814148,
-0.22568479180335999,
0.8622264862060547,
0.43461528420448303,
-0.52829909324646,
0.7012971639633179,
0.7915720343589783,
0.07618614286184311,
0.774603009223938,
0.2563217282295227,
-0.7852813005447388,
-0.22573819756507874,
-0.9104477167129517,
0.5715674161911011,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
dmayhem93/agieval-aqua-rat | dmayhem93 | 2023-06-18T17:14:34Z | 41 | 0 | null | [
"license:apache-2.0",
"arxiv:2304.06364",
"region:us"
] | 2023-06-18T17:14:34Z | 2023-06-18T03:50:28.000Z | 2023-06-18T03:50:28 | ---
dataset_info:
features:
- name: query
dtype: string
- name: choices
sequence: string
- name: gold
sequence: int64
splits:
- name: test
num_bytes: 93696
num_examples: 254
download_size: 0
dataset_size: 93696
license: apache-2.0
---
# Dataset Card for "agieval-aqua-rat"
Dataset taken from https://github.com/microsoft/AGIEval and processed as in that repo.
Raw dataset: https://github.com/deepmind/AQuA
Copyright 2017 Google Inc.
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
@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}
}
@inproceedings{ling-etal-2017-program,
title = "Program Induction by Rationale Generation: Learning to Solve and Explain Algebraic Word Problems",
author = "Ling, Wang and
Yogatama, Dani and
Dyer, Chris and
Blunsom, Phil",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1015",
doi = "10.18653/v1/P17-1015",
pages = "158--167",
abstract = "Solving algebraic word problems requires executing a series of arithmetic operations{---}a program{---}to obtain a final answer. However, since programs can be arbitrarily complicated, inducing them directly from question-answer pairs is a formidable challenge. To make this task more feasible, we solve these problems by generating answer rationales, sequences of natural language and human-readable mathematical expressions that derive the final answer through a series of small steps. Although rationales do not explicitly specify programs, they provide a scaffolding for their structure via intermediate milestones. To evaluate our approach, we have created a new 100,000-sample dataset of questions, answers and rationales. Experimental results show that indirect supervision of program learning via answer rationales is a promising strategy for inducing arithmetic programs.",
} | [
-0.3919600248336792,
-0.7553329467773438,
0.3250523507595062,
0.3511545956134796,
-0.07049983739852905,
0.1280786097049713,
-0.15266303718090057,
-0.35370004177093506,
0.010938026942312717,
0.2289329469203949,
-0.8179032206535339,
-0.35654914379119873,
-0.5945125222206116,
0.20981918275356... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
dmayhem93/agieval-logiqa-en | dmayhem93 | 2023-06-18T17:28:42Z | 41 | 0 | null | [
"license:cc-by-nc-sa-4.0",
"arxiv:2304.06364",
"region:us"
] | 2023-06-18T17:28:42Z | 2023-06-18T12:49:02.000Z | 2023-06-18T12:49:02 | ---
dataset_info:
features:
- name: query
dtype: string
- name: choices
sequence: string
- name: gold
sequence: int64
splits:
- name: test
num_bytes: 852087
num_examples: 651
download_size: 420337
dataset_size: 852087
license: cc-by-nc-sa-4.0
---
# Dataset Card for "agieval-logiqa-en"
Dataset taken from https://github.com/microsoft/AGIEval and processed as in that repo.
Raw datset: https://github.com/lgw863/LogiQA-dataset
[Attribution-NonCommercial-ShareAlike 4.0 International (CC BY-NC-SA 4.0)](https://creativecommons.org/licenses/by-nc-sa/4.0/)
@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}
}
@inproceedings{Liu2020LogiQAAC,
title={LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning},
author={Jian Liu and Leyang Cui and Hanmeng Liu and Dandan Huang and Yile Wang and Yue Zhang},
booktitle={International Joint Conference on Artificial Intelligence},
year={2020}
} | [
-0.17743465304374695,
-0.36612236499786377,
0.11458729207515717,
0.0105949267745018,
-0.2505098283290863,
0.09334493428468704,
0.29488322138786316,
-0.5592469573020935,
0.10168818384408951,
0.34892866015434265,
-0.7099787592887878,
-0.5921517014503479,
-0.4289136826992035,
0.02916469424962... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Romjiik/Russian_bank_reviews | Romjiik | 2023-06-22T21:29:37Z | 41 | 1 | null | [
"task_categories:text-classification",
"size_categories:10K<n<100K",
"language:ru",
"finance",
"region:us"
] | 2023-06-22T21:29:37Z | 2023-06-22T21:15:12.000Z | 2023-06-22T21:15:12 | ---
task_categories:
- text-classification
language:
- ru
tags:
- finance
pretty_name: bank reviews
size_categories:
- 10K<n<100K
---
# Dataset Card for bank reviews dataset
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
The dataset is collected from the [banki.ru](https://www.banki.ru/services/responses/list/?is_countable=on) website.
It contains customer reviews of various banks. In total, the dataset contains 12399 reviews.
The dataset is suitable for sentiment classification.
The dataset contains this fields - bank name, username, review title, review text, review time, number of views,
number of comments, review rating set by the user, as well as ratings for special categories
### Languages
Russian
| [
-0.47495049238204956,
-0.4745164215564728,
0.04050472378730774,
0.46778109669685364,
-0.6546205878257751,
0.09569443762302399,
0.12568211555480957,
-0.09149041771888733,
0.2921164333820343,
0.6002680659294128,
-0.5912683606147766,
-1.1276084184646606,
-0.44711393117904663,
-0.0105575630441... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
datatab/alpaca-cleaned-serbian-full | datatab | 2023-07-16T12:41:15Z | 41 | 0 | null | [
"task_categories:text-generation",
"language:sr",
"license:apache-2.0",
"region:us"
] | 2023-07-16T12:41:15Z | 2023-07-16T11:30:57.000Z | 2023-07-16T11:30:57 | ---
license: apache-2.0
task_categories:
- text-generation
language:
- sr
pretty_name: ' alpaca-dataset-cleaned-serbian'
--- | [
-0.1285335123538971,
-0.1861683875322342,
0.6529128551483154,
0.49436232447624207,
-0.19319400191307068,
0.23607441782951355,
0.36072009801864624,
0.05056373029947281,
0.5793656706809998,
0.7400146722793579,
-0.650810182094574,
-0.23784008622169495,
-0.7102247476577759,
-0.0478255338966846... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
openaccess-ai-collective/oo-gpt4-filtered | openaccess-ai-collective | 2023-08-05T04:00:44Z | 41 | 2 | null | [
"region:us"
] | 2023-08-05T04:00:44Z | 2023-08-05T03:59:54.000Z | 2023-08-05T03:59:54 | Entry not found | [
-0.3227645754814148,
-0.22568479180335999,
0.8622263669967651,
0.43461522459983826,
-0.52829909324646,
0.7012971639633179,
0.7915719747543335,
0.07618614286184311,
0.774603009223938,
0.2563217282295227,
-0.7852813005447388,
-0.22573819756507874,
-0.9104475975036621,
0.5715674161911011,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
jinaai/negation-dataset-v2 | jinaai | 2023-11-08T15:49:17Z | 41 | 5 | null | [
"multilinguality:monolingual",
"size_categories:10K<n<50k",
"language:en",
"finetuner",
"arxiv:2307.11224",
"region:us"
] | 2023-11-08T15:49:17Z | 2023-08-11T11:28:31.000Z | 2023-08-11T11:28:31 |
---
tags:
- finetuner
language: en
dataset_info:
features:
- name: anchor
dtype: string
- name: entailment
dtype: string
- name: negative
dtype: string
splits:
- name: train
num_examples: 50000
- name: test
num_examples: 1000
multilinguality:
- monolingual
size_categories:
- 10K<n<50k
---
<br><br>
<p align="center">
<img src="https://github.com/jina-ai/finetuner/blob/main/docs/_static/finetuner-logo-ani.svg?raw=true" alt="Finetuner logo: Finetuner helps you to create experiments in order to improve embeddings on search tasks. It accompanies you to deliver the last mile of performance-tuning for neural search applications." width="150px">
</p>
<p align="center">
<b>The data offered by Jina AI, Finetuner team.</b>
</p>
## Summary
This dataset is an English-language dataset containing negation triplets. It is based on five datasets:
[SNLI](https://huggingface.co/datasets/snli), [Multi-NLI](https://huggingface.co/datasets/multi_nli),
[sentence-compression](https://huggingface.co/datasets/sent_comp), [Simple Wikipedia](https://www.loc.gov/item/2019205402/)
and [COCO Captions](https://cocodataset.org/#home).
## Instances
Each data point consists of a triplet ('anchor', 'entailment', 'negative') of strings, where ('anchor', 'entailment') are positive pairs
taken from SNLI, and 'negative' contradicts both 'anchor' and 'entailment'.
## Fields
- 'anchor': string, some statement
- 'entailment': string, a statement which follows from 'anchor', but is usually syntactically dissimilar
- 'negative': string, a statement contradicting 'anchor' and 'entailment'. Syntactically very similar to 'entailment'
## Splits
| | train | test |
|------------|-------|------|
| # of items | 50000 | 1000 |
## Source
Positive pairs were sampled from the five source datasets and negative samples were created using GPT-3.5
and GPT-4.
## Example Usage
```python
from datasets import load_dataset
from pprint import pprint
dataset = load_dataset('jinaai/negation-dataset-v2')
```
Example data:
```python
'anchor': ['Pedestrians walking down a sidewalk next to a small street.',
"A car stopped at a traffic light with it's brake lights on.",
'A couple on a motorcycle in front of a bus and a metermaid car'],
'entailment': ['People walking on a city street with light traffic.',
'A car stopped at the front of the stop light. ',
'A busy city street with a bus, taxi, and motorcycle.'],
'negative': ['People standing still on a city street with heavy traffic.',
'A car speeding away from the front of the stop light. ',
'A calm city street with no bus, taxi, and motorcycle.']
```
## Evaluate Models on the Test Set
For evaluation, you can use the evaluation script provided together with this dataset:
https://huggingface.co/datasets/jinaai/negation-dataset-v2/blob/main/evaluate_on_negations.py
## Licensing Information
Please respect the licenses of the original data sources for the achor and entailment data.
The additional negatives are licensed under the [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) license.
## Contact
Join our [Discord community](https://discord.jina.ai) and chat with other community members about ideas.
## Citation
If you find this dataset useful in your research, please cite the following paper:
``` latex
@misc{günther2023jina,
title={Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models},
author={Michael Günther and Louis Milliken and Jonathan Geuter and Georgios Mastrapas and Bo Wang and Han Xiao},
year={2023},
eprint={2307.11224},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
| [
-0.5366940498352051,
-1.2360963821411133,
0.3433966636657715,
0.2962267994880676,
-0.18727922439575195,
-0.44613978266716003,
-0.2037414014339447,
-0.3089599311351776,
0.4464970827102661,
0.2885890305042267,
-0.49359798431396484,
-0.5375677943229675,
-0.4661179780960083,
0.4264169633388519... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
BELLE-2/train_3.5M_CN_With_Category | BELLE-2 | 2023-10-18T03:19:58Z | 41 | 9 | null | [
"task_categories:text2text-generation",
"size_categories:1M<n<10M",
"language:zh",
"license:gpl-3.0",
"region:us"
] | 2023-10-18T03:19:58Z | 2023-08-14T03:46:04.000Z | 2023-08-14T03:46:04 | ---
license: gpl-3.0
task_categories:
- text2text-generation
language:
- zh
size_categories:
- 1M<n<10M
---
## 内容
基于原有的[train_3.5M_CN](https://huggingface.co/datasets/BelleGroup/train_3.5M_CN)数据新增了指令类别字段，共包括13个类别，详情如下图所示：
## 样例
```
{
"id":"66182880",
"category"："generation"
}
```
### 字段：
```
id: 数据id
category: 该条指令数据对应的类别
```
## 使用限制
仅允许将此数据集及使用此数据集生成的衍生物用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。
本数据集不代表任何一方的立场、利益或想法，无关任何团体的任何类型的主张。因使用本数据集带来的任何损害、纠纷，本项目不承担任何责任。
## Citation
Please cite our paper and github when using our code, data or model.
```
@misc{BELLE,
author = {BELLEGroup},
title = {BELLE: Be Everyone's Large Language model Engine},
year = {2023},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/LianjiaTech/BELLE}},
}
``` | [
-0.5436640977859497,
-0.41872408986091614,
-0.1528513878583908,
0.45112913846969604,
-0.35673442482948303,
-0.21884238719940186,
0.1402447670698166,
-0.3524530231952667,
0.6053744554519653,
0.3932563066482544,
-0.6474232077598572,
-0.9259034991264343,
-0.5915459394454956,
0.050862956792116... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
seeweb/Seeweb-it-292-forLLM | seeweb | 2023-08-18T09:13:35Z | 41 | 0 | null | [
"license:apache-2.0",
"region:us"
] | 2023-08-18T09:13:35Z | 2023-08-18T09:13:01.000Z | 2023-08-18T09:13:01 | ---
license: apache-2.0
---
| [
-0.12853392958641052,
-0.18616779148578644,
0.6529127955436707,
0.49436280131340027,
-0.19319361448287964,
0.23607419431209564,
0.36072003841400146,
0.050563063472509384,
0.579365611076355,
0.7400140762329102,
-0.6508104205131531,
-0.23783954977989197,
-0.7102249264717102,
-0.0478260256350... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
judy93536/pharsebank_5k | judy93536 | 2023-09-13T00:12:28Z | 41 | 0 | null | [
"region:us"
] | 2023-09-13T00:12:28Z | 2023-09-10T03:50:03.000Z | 2023-09-10T03:50:03 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: sentence
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 542147
num_examples: 3999
- name: test
num_bytes: 137048
num_examples: 999
download_size: 379517
dataset_size: 679195
---
# Dataset Card for "pharsebank_5k"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.4901173412799835,
0.10919210314750671,
0.054426468908786774,
0.35300174355506897,
-0.5336896181106567,
-0.00958129670470953,
0.2762379050254822,
-0.15243691205978394,
0.7801561951637268,
0.5271334052085876,
-0.7185208201408386,
-0.9359657168388367,
-0.5983985662460327,
0.015510434284806... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
ZhenDOS/alpha_bank_data | ZhenDOS | 2023-09-18T17:53:13Z | 41 | 0 | null | [
"task_categories:conversational",
"language:ru",
"license:afl-3.0",
"finance",
"region:us"
] | 2023-09-18T17:53:13Z | 2023-09-14T15:27:51.000Z | 2023-09-14T15:27:51 | ---
license: afl-3.0
task_categories:
- conversational
language:
- ru
tags:
- finance
--- | [
-0.12853392958641052,
-0.18616779148578644,
0.6529127955436707,
0.49436280131340027,
-0.19319361448287964,
0.23607419431209564,
0.36072003841400146,
0.050563063472509384,
0.579365611076355,
0.7400140762329102,
-0.6508104205131531,
-0.23783954977989197,
-0.7102249264717102,
-0.0478260256350... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
vwxyzjn/summarize_from_feedback_tldr_3_filtered | vwxyzjn | 2023-09-19T20:10:04Z | 41 | 1 | null | [
"task_categories:summarization",
"size_categories:1K<n<10K",
"language:en",
"license:mit",
"region:us"
] | 2023-09-19T20:10:04Z | 2023-09-19T20:07:59.000Z | 2023-09-19T20:07:59 | ---
license: mit
task_categories:
- summarization
language:
- en
size_categories:
- 1K<n<10K
---
This is the query dataset taken directly from https://github.com/openai/summarize-from-feedback/tree/700967448d10004279f138666442bf1497d0e705#reddit-tldr-dataset | [
-0.4039308726787567,
-0.6374835968017578,
0.05545816943049431,
-0.0745219811797142,
-0.275391548871994,
-0.18793226778507233,
0.01824966073036194,
-0.19631436467170715,
0.9016857147216797,
0.7963806986808777,
-1.1526999473571777,
-0.6186367869377136,
-0.12954366207122803,
0.117209337651729... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
TurkuNLP/genre-6 | TurkuNLP | 2023-09-26T06:42:00Z | 41 | 0 | null | [
"task_categories:text-classification",
"size_categories:10K<n<100K",
"language:en",
"region:us"
] | 2023-09-26T06:42:00Z | 2023-09-25T13:08:04.000Z | 2023-09-25T13:08:04 | ---
task_categories:
- text-classification
language:
- en
size_categories:
- 10K<n<100K
---
# Dataset Card for Dataset Name
## Dataset Summary
Genre-6 dataset is an English dataset based on Kindletrends (UK & US). It contains more than 20k books and associated categories with ready-made binary classification and multilabel classification labels.
## Dataset Structure
### Data Instances
`` {"text": "...", "categories": "Engineering & Transportation;Science & Math", "fiction": "non-fiction", "split1": ['Science & Math'], "split2" : ['Engineering & Transportation', 'Science & Math'], "split3": ['Science & Math']} ``
### Data Fields
- text: Kindletrends text
- categories: Kidletrends categories (1 to 2 categories per book)
- fiction: binary label for fiction and non-fiction books
- splits 1,2,3: multilabel for different subsets of the categories
### Data Splits
The dataset contains train (80%), validation (10%) and test (10%) splits.
The splits for multilabels are following:
- split1: 'Biology & Nature & Biological Sciences','Computer Science', 'Fantasy','Medicine & Health Sciences','Philosophy','Science & Math'.
- split2: 'Biology & Nature & Biological Sciences','Computer Science', 'Engineering & Transportation','Fantasy','Medicine & Health Sciences','Science & Math'.
- split3: 'Biology & Nature & Biological Sciences','Computer Science', 'Fantasy','Medicine & Health Sciences', 'Poetry', 'Politics & Social Sciences', 'Science & Math'.
More splits can be generated from the field "categories".
### Source Data
[Kindletrends](https://kindletrends.com/categories/)
| [
-0.5512034296989441,
-0.0032103867270052433,
-0.2849401831626892,
-0.0010035809827968478,
-0.2736959159374237,
0.156574085354805,
0.16738851368427277,
-0.2546725869178772,
0.21451933681964874,
0.5059412717819214,
-0.7780793309211731,
-1.1264697313308716,
-0.4652133285999298,
0.244016781449... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
acrastt/EverythingLM-V3-ShareGPT | acrastt | 2023-10-24T22:18:47Z | 41 | 2 | null | [
"size_categories:1K<n<10K",
"language:en",
"license:mit",
"region:us"
] | 2023-10-24T22:18:47Z | 2023-09-25T23:08:51.000Z | 2023-09-25T23:08:51 | ---
license: mit
language:
- en
pretty_name: Everything-V3-
size_categories:
- 1K<n<10K
---
<a href="https://www.buymeacoffee.com/acrastt" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 60px !important;width: 217px !important;" ></a>
[EverythingLM V3 Data](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3) converted to ShareGPT format. | [
-0.3610585629940033,
-0.7739648222923279,
0.44683054089546204,
0.4457332193851471,
-0.4696764647960663,
-0.4078182280063629,
0.011774590238928795,
-0.5270313024520874,
0.7003337740898132,
0.28371497988700867,
-0.6310035586357117,
-0.6979160904884338,
-0.5572660565376282,
-0.028455460444092... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
emi429/humansleepproject-rr-small | emi429 | 2023-10-11T20:00:33Z | 41 | 0 | null | [
"region:us"
] | 2023-10-11T20:00:33Z | 2023-10-11T19:09:28.000Z | 2023-10-11T19:09:28 | ---
dataset_info:
features:
- name: rr_intervals
sequence: float64
- name: sleep_stage
dtype: string
splits:
- name: train
num_bytes: 131445053
num_examples: 56208
download_size: 21938826
dataset_size: 131445053
---
# Dataset Card for "humansleepproject-rr-small"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.5034624934196472,
-0.09474151581525803,
0.17801198363304138,
0.23715531826019287,
-0.17421680688858032,
0.017677530646324158,
0.12244883179664612,
-0.28188657760620117,
1.0071961879730225,
0.38404908776283264,
-0.9255885481834412,
-0.5564457178115845,
-0.3819091022014618,
-0.13099265098... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
OpenPipe/hacker-news | OpenPipe | 2023-11-02T13:41:53Z | 41 | 4 | null | [
"region:us"
] | 2023-11-02T13:41:53Z | 2023-10-13T19:44:25.000Z | 2023-10-13T19:44:25 | ---
dataset_info:
features:
- name: id
dtype: int64
- name: type
dtype: string
- name: by
dtype: string
- name: time
dtype: timestamp[us]
- name: title
dtype: string
- name: text
dtype: string
- name: url
dtype: string
- name: score
dtype: float64
- name: parent
dtype: float64
- name: top_level_parent
dtype: int64
- name: descendants
dtype: float64
- name: kids
sequence: int64
- name: deleted
dtype: bool
- name: dead
dtype: bool
splits:
- name: train
num_bytes: 16886975696
num_examples: 38109500
download_size: 9948795138
dataset_size: 16886975696
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Hacker News posts and comments
This is a dataset of all HN posts and comments, current as of November 1, 2023. | [
-0.10664191097021103,
-1.0970126390457153,
0.7345491051673889,
0.3402266204357147,
-0.34826093912124634,
-0.015323998406529427,
0.18566085398197174,
-0.3915492594242096,
1.120410680770874,
1.0951573848724365,
-0.6012827754020691,
-0.5622450709342957,
-0.3312911093235016,
0.0088205588981509... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
dtorres-zAgile/zc-miti-qa | dtorres-zAgile | 2023-10-18T05:48:03Z | 41 | 0 | null | [
"region:us"
] | 2023-10-18T05:48:03Z | 2023-10-17T21:51:08.000Z | 2023-10-17T21:51:08 | ---
{}
--- | [
-0.1285335123538971,
-0.1861683875322342,
0.6529128551483154,
0.49436232447624207,
-0.19319400191307068,
0.23607441782951355,
0.36072009801864624,
0.05056373029947281,
0.5793656706809998,
0.7400146722793579,
-0.650810182094574,
-0.23784008622169495,
-0.7102247476577759,
-0.0478255338966846... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
arkubeth/librispeech | arkubeth | 2023-11-01T18:14:04Z | 41 | 0 | null | [
"region:us"
] | 2023-11-01T18:14:04Z | 2023-10-21T11:02:16.000Z | 2023-10-21T11:02:16 | Entry not found | [
-0.3227645754814148,
-0.22568479180335999,
0.8622263669967651,
0.43461522459983826,
-0.52829909324646,
0.7012971639633179,
0.7915719747543335,
0.07618614286184311,
0.774603009223938,
0.2563217282295227,
-0.7852813005447388,
-0.22573819756507874,
-0.9104475975036621,
0.5715674161911011,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
jihyoung/ConversationChronicles | jihyoung | 2023-10-23T01:33:39Z | 41 | 1 | null | [
"task_categories:conversational",
"language:en",
"license:cc-by-4.0",
"arxiv:2310.13420",
"region:us"
] | 2023-10-23T01:33:39Z | 2023-10-22T15:59:38.000Z | 2023-10-22T15:59:38 | ---
license: cc-by-4.0
task_categories:
- conversational
language:
- en
pretty_name: CC
---
# 🕰️ Conversation Chronicles
We introduce Conversation Chronicles, a new high-quality 1M multi-session dataset that includes more various time intervals and fine-grained speaker relationships!
## Load with Datasets
To load our dataset with Hugging Face Datasets, please use the following code:
```python
from datasets import load_dataset
cc = load_dataset("jihyoung/ConversationChronicles")
```
## Languages
The language of Conversation Chronicles is ***English***.
## Dataset Size
| Feature | Conut |
| ---------------------- | ----- |
| # of Sessions | 1M |
| # of Episodes | 200K |
| # of Turns | 11.7M |
| Avg. Turns per session | 11.7 |
| Avg. Words per Turn | 18.03 |
### Dataset Splits
| Split | Number of Sessions | Number of Episodes |
| ------------- | ------------------ | ------------------ |
| Train | 800,000 | 160,000 |
| Validation | 100,000 | 20,000 |
| Test | 100,000 | 20,000 |
## Dataset Structure
| Fields | Type | Description |
| ------------------------- | --------------- | ---------------------------------------------------- |
| `dataID` | string | unique ID of an episode |
| `relationship` | string | relationships between the speakers in the episode |
| `time_interval` | sequence (list) | time intervals between sessions (total of 5) |
| `summary` | sequence (list) | chronological summaries of each session (total of 5) |
| `first_session_dialogue` | sequence (list) | utterance in the first session |
| `first_session_speakers` | sequence (list) | speaker matching for the first session utterance |
| `second_session_dialogue` | sequence (list) | utterance in the second session |
| `second_session_speakers` | sequence (list) | speaker matching for the second session utterance |
| `third_session_dialogue` | sequence (list) | utterance in the third session |
| `third_session_speakers` | sequence (list) | speaker matching for the third session utterance |
| `fourth_session_dialogue` | sequence (list) | utterance in the fourth session |
| `fourth_session_speakers` | sequence (list) | speaker matching for the fourth session utterance |
| `fifth_session_dialogue` | sequence (list) | utterance in the fifth session |
| `fifth_session_speakers` | sequence (list) | speaker matching for the fifth session utterance |
## Chronological Dynamics
our Conversation Chronicles implements chronological dynamics by integrating time interval and speaker relationship.
| Time Interval | Count |
| ------------------- | ------------------ |
| `A few hours` | 159,975 |
| `A few days` | 159,928 |
| `A few weeks` | 160,670 |
| `A few months` | 160,050 |
| `A couple of years` | 159,377 |
| Relationship | Count | Ratio |
| ------------------- | ------- | ----- |
| Classmates | 66,090 | 33.05% |
| Neighbors | 49,521 | 24.76% |
| Co-workers | 28,856 | 14.43% |
| Mentee and Mentor | 16,035 | 8.02% |
| Husband and Wife | 13,486 | 6.74% |
| Patient and Doctor | 6,980 | 3.49% |
| Parent and Child | 6,514 | 3.26% |
| Student and Teacher | 5,018 | 2.51% |
| Employee and Boss | 4,811 | 2.41% |
| Athlete and Coach | 2,689 | 1.34% |
| Total | 200,000 | |
## Citation Information
```
@inproceedings{jang2023conversation,
title={Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversations},
author={Jihyoung Jang, MinSeong Boo, Hyounghun Kim},
booktitle={The 2023 Conference on Empirical Methods in Natural Language Processing},
year={2023},
url={https://arxiv.org/abs/2310.13420}
}
```
| [
-0.46786466240882874,
-0.7691230773925781,
0.33674922585487366,
0.4040377140045166,
-0.14083540439605713,
0.12352973222732544,
-0.015090106055140495,
-0.39191722869873047,
0.6282561421394348,
0.5287022590637207,
-1.2008473873138428,
-0.7352976202964783,
-0.43693965673446655,
0.020564809441... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
hippocrates/CitationGPT_train | hippocrates | 2023-10-30T21:01:22Z | 41 | 0 | null | [
"region:us"
] | 2023-10-30T21:01:22Z | 2023-10-30T20:50:52.000Z | 2023-10-30T20:50:52 | ---
dataset_info:
features:
- name: id
dtype: string
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
- name: text
dtype: string
splits:
- name: train
num_bytes: 443729530
num_examples: 119360
- name: valid
num_bytes: 57232474
num_examples: 15480
- name: test
num_bytes: 51863078
num_examples: 14000
download_size: 208907031
dataset_size: 552825082
---
# Dataset Card for "CitationGPT_train"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.5113353729248047,
-0.0626683458685875,
0.35957562923431396,
0.4384324252605438,
-0.17784644663333893,
-0.13987547159194946,
0.2551007866859436,
-0.04202095419168472,
0.5959534049034119,
0.10396940261125565,
-0.6719167232513428,
-0.4385799467563629,
-0.6371833682060242,
-0.30906763672828... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
MegPaulson/Healthy_Skin | MegPaulson | 2023-11-02T05:33:08Z | 41 | 0 | null | [
"region:us"
] | 2023-11-02T05:33:08Z | 2023-11-01T23:32:41.000Z | 2023-11-01T23:32:41 | ---
dataset_info:
features:
- name: image
dtype: image
- name: prompt
dtype: string
splits:
- name: train
num_bytes: 1679582797.125
num_examples: 6039
download_size: 1660153728
dataset_size: 1679582797.125
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "Healthy_Skin"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.2206239402294159,
-0.28663888573646545,
0.12128034979104996,
-0.019653674215078354,
-0.2908014953136444,
0.11226271092891693,
0.23008015751838684,
-0.551935613155365,
1.0853601694107056,
0.6561022400856018,
-0.6438421010971069,
-1.0000240802764893,
-0.47900518774986267,
-0.3614052534103... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Giacinta/djy | Giacinta | 2023-11-03T02:37:10Z | 41 | 0 | null | [
"task_categories:text-classification",
"size_categories:n<1K",
"language:zh",
"license:apache-2.0",
"medical",
"region:us"
] | 2023-11-03T02:37:10Z | 2023-11-02T03:44:50.000Z | 2023-11-02T03:44:50 | ---
license: apache-2.0
task_categories:
- text-classification
language:
- zh
tags:
- medical
pretty_name: djy
size_categories:
- n<1K
configs:
- config_name: default
data_files:
- split: train
path: "60_percent_data.csv"
- split: test
path: "part1.csv"
- split: eval
path: "part2.csv"
--- | [
-0.12853392958641052,
-0.18616779148578644,
0.6529127955436707,
0.49436280131340027,
-0.19319361448287964,
0.23607419431209564,
0.36072003841400146,
0.050563063472509384,
0.579365611076355,
0.7400140762329102,
-0.6508104205131531,
-0.23783954977989197,
-0.7102249264717102,
-0.0478260256350... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
anforsm/movie_posters-genres-80k-transformed | anforsm | 2023-11-06T17:00:58Z | 41 | 0 | null | [
"region:us"
] | 2023-11-06T17:00:58Z | 2023-11-06T16:42:07.000Z | 2023-11-06T16:42:07 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: id
dtype: int64
- name: image
sequence:
sequence:
sequence: float32
- name: genres
sequence: int64
splits:
- name: train
num_bytes: 23128566147.416473
num_examples: 78352
- name: test
num_bytes: 295187948.58352655
num_examples: 1000
download_size: 22030369211
dataset_size: 23423754096.0
---
# Dataset Card for "movie_posters-genres-80k-transformed"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.4657804071903229,
-0.18714448809623718,
0.27825498580932617,
0.11994048953056335,
-0.3839067220687866,
0.2187548726797104,
0.11473876982927322,
0.0207896176725626,
0.8177869319915771,
0.7713505029678345,
-0.8833371996879578,
-0.8502430319786072,
-0.9182936549186707,
-0.10786336660385132... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
tyzhu/squad_train500_eval100 | tyzhu | 2023-11-07T08:45:58Z | 41 | 0 | null | [
"region:us"
] | 2023-11-07T08:45:58Z | 2023-11-07T07:45:05.000Z | 2023-11-07T07:45:05 | ---
configs:
- config_name: default
data_files:
- split: validation
path: data/validation-*
- split: train
path: data/train-*
dataset_info:
features:
- name: id
dtype: string
- name: title
dtype: string
- name: context
dtype: string
- name: question
dtype: string
- name: answers
sequence:
- name: text
dtype: string
- name: answer_start
dtype: int32
- name: inputs
dtype: string
- name: targets
dtype: string
splits:
- name: validation
num_bytes: 138876
num_examples: 100
- name: train
num_bytes: 1088215
num_examples: 500
download_size: 206819
dataset_size: 1227091
---
# Dataset Card for "squad_train500_eval100"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.6055620908737183,
-0.11448052525520325,
0.10893172770738602,
0.45939990878105164,
0.22796356678009033,
0.2772940993309021,
0.30672207474708557,
0.10353437811136246,
0.7018182873725891,
0.3134896457195282,
-1.1241017580032349,
-0.5465391874313354,
-0.402875155210495,
-0.08222401142120361... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
just097/wiki-comma-placement | just097 | 2023-11-07T11:18:49Z | 41 | 0 | null | [
"task_categories:token-classification",
"language:en",
"license:mit",
"region:us"
] | 2023-11-07T11:18:49Z | 2023-11-07T11:13:26.000Z | 2023-11-07T11:13:26 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
dataset_info:
features:
- name: tokens
sequence: string
- name: tags
sequence: int64
splits:
- name: train
num_bytes: 35619014
num_examples: 82600
- name: validation
num_bytes: 8871452
num_examples: 20651
- name: test
num_bytes: 8462693
num_examples: 19667
download_size: 12620120
dataset_size: 52953159
license: mit
task_categories:
- token-classification
language:
- en
pretty_name: Wiki Comma Placement Dataset
---
# Dataset Card for "wiki-comma-placement"
Subset of Wikitext dataset suitable for fixing punctuation marks. For this particular case, main task is "comma placement"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.18261128664016724,
-0.5940661430358887,
0.21086686849594116,
0.2743140459060669,
-0.1297917515039444,
0.2321174442768097,
-0.27122268080711365,
0.029510430991649628,
0.5400493741035461,
0.5864169001579285,
-0.7970835566520691,
-0.738245964050293,
-0.599615752696991,
0.39661896228790283,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
vilm/viet-pretrained-001 | vilm | 2023-11-11T13:36:34Z | 41 | 0 | null | [
"license:mpl-2.0",
"region:us"
] | 2023-11-11T13:36:34Z | 2023-11-07T17:23:55.000Z | 2023-11-07T17:23:55 | ---
license: mpl-2.0
---
| [
-0.12853392958641052,
-0.18616779148578644,
0.6529127955436707,
0.49436280131340027,
-0.19319361448287964,
0.23607419431209564,
0.36072003841400146,
0.050563063472509384,
0.579365611076355,
0.7400140762329102,
-0.6508104205131531,
-0.23783954977989197,
-0.7102249264717102,
-0.0478260256350... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
erikaxenia/id_card_class | erikaxenia | 2023-11-07T19:02:34Z | 41 | 0 | null | [
"region:us"
] | 2023-11-07T19:02:34Z | 2023-11-07T19:02:20.000Z | 2023-11-07T19:02:20 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: valid
path: data/valid-*
- split: test
path: data/test-*
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype: int64
- name: ground_truth
dtype: string
splits:
- name: train
num_bytes: 130472837.0
num_examples: 470
- name: valid
num_bytes: 21179110.0
num_examples: 59
- name: test
num_bytes: 16112586.0
num_examples: 58
download_size: 166464862
dataset_size: 167764533.0
---
# Dataset Card for "id_card_class"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.6221699118614197,
-0.26617610454559326,
0.11084939539432526,
0.04359627887606621,
-0.14907975494861603,
0.14166729152202606,
0.33441492915153503,
-0.16812558472156525,
0.7541735172271729,
0.2590928375720978,
-0.644652783870697,
-0.8719988465309143,
-0.44760027527809143,
-0.2781702876091... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Tural/MetaMathQA | Tural | 2023-11-07T22:02:31Z | 41 | 0 | null | [
"region:us"
] | 2023-11-07T22:02:31Z | 2023-11-07T22:02:21.000Z | 2023-11-07T22:02:21 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: instruction
dtype: string
- name: type
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 288517804
num_examples: 395000
download_size: 141855468
dataset_size: 288517804
---
# Dataset Card for "MetaMathQA"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.7234839200973511,
-0.20237720012664795,
0.2864688038825989,
0.024952173233032227,
-0.16560211777687073,
0.026068640872836113,
0.48675447702407837,
0.018729841336607933,
0.9015716910362244,
0.55113685131073,
-0.9803268909454346,
-0.8476028442382812,
-0.5359507203102112,
-0.29384037852287... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
euisuh15/poison_style_codellama | euisuh15 | 2023-11-12T09:26:26Z | 41 | 0 | null | [
"region:us"
] | 2023-11-12T09:26:26Z | 2023-11-12T06:55:45.000Z | 2023-11-12T06:55:45 | Entry not found | [
-0.3227647542953491,
-0.22568407654762268,
0.8622258901596069,
0.4346148371696472,
-0.5282984972000122,
0.7012965083122253,
0.7915717959403992,
0.07618629932403564,
0.7746022343635559,
0.2563222348690033,
-0.785281777381897,
-0.22573848068714142,
-0.9104482531547546,
0.5715669393539429,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
gonglinyuan/code_search_net_java_tokenized | gonglinyuan | 2023-11-13T04:24:25Z | 41 | 0 | null | [
"region:us"
] | 2023-11-13T04:24:25Z | 2023-11-13T04:24:01.000Z | 2023-11-13T04:24:01 | Entry not found | [
-0.3227647542953491,
-0.22568407654762268,
0.8622258901596069,
0.4346148371696472,
-0.5282984972000122,
0.7012965083122253,
0.7915717959403992,
0.07618629932403564,
0.7746022343635559,
0.2563222348690033,
-0.785281777381897,
-0.22573848068714142,
-0.9104482531547546,
0.5715669393539429,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
CesarLeblanc/text_classification_dataset | CesarLeblanc | 2023-11-13T15:32:38Z | 41 | 0 | null | [
"region:us"
] | 2023-11-13T15:32:38Z | 2023-11-13T15:32:29.000Z | 2023-11-13T15:32:29 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: label
dtype:
class_label:
names:
'0': MA211
'1': MA221
'2': MA222
'3': MA223
'4': MA224
'5': MA225
'6': MA232
'7': MA241
'8': MA251
'9': MA252
'10': MA253
'11': N11
'12': N12
'13': N13
'14': N14
'15': N15
'16': N16
'17': N17
'18': N18
'19': N19
'20': N1A
'21': N1B
'22': N1C
'23': N1D
'24': N1E
'25': N1F
'26': N1G
'27': N1H
'28': N1J
'29': N21
'30': N22
'31': N31
'32': N32
'33': N33
'34': N34
'35': N35
'36': Q11
'37': Q12
'38': Q21
'39': Q22
'40': Q23
'41': Q24
'42': Q25
'43': Q41
'44': Q42
'45': Q43
'46': Q44
'47': Q45
'48': Q46
'49': Q51
'50': Q52
'51': Q53
'52': Q54
'53': R11
'54': R12
'55': R13
'56': R14
'57': R15
'58': R16
'59': R17
'60': R18
'61': R19
'62': R1A
'63': R1B
'64': R1C
'65': R1D
'66': R1E
'67': R1F
'68': R1G
'69': R1H
'70': R1J
'71': R1K
'72': R1M
'73': R1P
'74': R1Q
'75': R1R
'76': R1S
'77': R21
'78': R22
'79': R23
'80': R24
'81': R31
'82': R32
'83': R33
'84': R34
'85': R35
'86': R36
'87': R37
'88': R41
'89': R42
'90': R43
'91': R44
'92': R45
'93': R51
'94': R52
'95': R53
'96': R54
'97': R55
'98': R56
'99': R57
'100': R61
'101': R62
'102': R63
'103': R64
'104': R65
'105': S11
'106': S12
'107': S21
'108': S22
'109': S23
'110': S24
'111': S25
'112': S26
'113': S31
'114': S32
'115': S33
'116': S34
'117': S35
'118': S36
'119': S37
'120': S38
'121': S41
'122': S42
'123': S51
'124': S52
'125': S53
'126': S54
'127': S61
'128': S62
'129': S63
'130': S64
'131': S65
'132': S66
'133': S67
'134': S68
'135': S71
'136': S72
'137': S73
'138': S74
'139': S75
'140': S76
'141': S81
'142': S82
'143': S91
'144': S92
'145': S93
'146': S94
'147': T11
'148': T12
'149': T13
'150': T14
'151': T15
'152': T16
'153': T17
'154': T18
'155': T19
'156': T1A
'157': T1B
'158': T1C
'159': T1D
'160': T1E
'161': T1F
'162': T1G
'163': T1H
'164': T21
'165': T22
'166': T23
'167': T24
'168': T25
'169': T27
'170': T28
'171': T29
'172': T31
'173': T32
'174': T33
'175': T34
'176': T35
'177': T36
'178': T37
'179': T38
'180': T39
'181': T3A
'182': T3B
'183': T3C
'184': T3D
'185': T3E
'186': T3F
'187': T3G
'188': T3H
'189': T3J
'190': T3K
'191': T3M
'192': U21
'193': U22
'194': U23
'195': U24
'196': U25
'197': U26
'198': U27
'199': U28
'200': U29
'201': U2A
'202': U32
'203': U33
'204': U34
'205': U35
'206': U36
'207': U37
'208': U38
'209': U3A
'210': U3B
'211': U3C
'212': U3D
'213': U61
'214': U62
'215': V11
'216': V12
'217': V13
'218': V14
'219': V15
'220': V32
'221': V33
'222': V34
'223': V35
'224': V37
'225': V38
'226': V39
- name: text
dtype: string
splits:
- name: train
num_bytes: 305737498
num_examples: 718428
- name: test
num_bytes: 54030297
num_examples: 126782
download_size: 157416848
dataset_size: 359767795
---
# Dataset Card for "text_classification_dataset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.3861452341079712,
-0.21127744019031525,
0.18108908832073212,
0.174539715051651,
-0.14003556966781616,
0.013283015228807926,
0.07144011557102203,
-0.2030036747455597,
0.6413723826408386,
0.39848214387893677,
-0.6028358340263367,
-0.8898711800575256,
-0.7357803583145142,
-0.20252428948879... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
rjaiswal/bulgari-dataset | rjaiswal | 2023-11-15T16:29:12Z | 41 | 0 | null | [
"region:us"
] | 2023-11-15T16:29:12Z | 2023-11-15T15:25:05.000Z | 2023-11-15T15:25:05 | ---
dataset_info:
features:
- name: image
dtype: 'null'
- name: text
dtype: 'null'
splits:
- name: train
num_bytes: 0
num_examples: 0
download_size: 0
dataset_size: 0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
# Dataset Card for "bulgari-dataset"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.4804607331752777,
-0.18903890252113342,
0.011175639927387238,
0.3191312849521637,
-0.16792349517345428,
0.07404355704784393,
0.15126678347587585,
-0.22807547450065613,
0.6867349743843079,
0.4494315981864929,
-0.6865953803062439,
-0.7198336720466614,
-0.390419602394104,
-0.20310907065868... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
A-Roucher/Open_Assistant_Conversation_Chains | A-Roucher | 2023-11-22T14:37:58Z | 41 | 1 | null | [
"task_categories:conversational",
"task_categories:text-generation",
"size_categories:10K<n<100K",
"language:en",
"language:es",
"language:ru",
"language:de",
"language:pl",
"language:th",
"language:vi",
"language:sv",
"language:bn",
"language:da",
"language:he",
"language:it",
"langua... | 2023-11-22T14:37:58Z | 2023-11-16T18:35:52.000Z | 2023-11-16T18:35:52 | ---
license: apache-2.0
language:
- en
- es
- ru
- de
- pl
- th
- vi
- sv
- bn
- da
- he
- it
- fa
- sk
- id
- nb
- el
- nl
- hu
- eu
- zh
- eo
- ja
- ca
- cs
- bg
- fi
- pt
- tr
- ro
- ar
- uk
- gl
- fr
- ko
task_categories:
- conversational
- text-generation
tags:
- human-feedback
size_categories:
- 10K<n<100K
pretty_name: OpenAssistant Conversations Unrolled
---
# Dataset Card for Dataset Name
## Dataset description
<!-- Provide a quick summary of the dataset. -->
This dataset is a reformatting of [OpenAssistant Conversations (OASST1)](https://huggingface.co/datasets/OpenAssistant/oasst1), which is
> a human-generated, human-annotated assistant-style conversation corpus consisting of 161,443 messages in 35 different languages, annotated with 461,292 quality ratings, resulting in over 10,000 fully annotated conversation trees. The corpus is a product of a worldwide crowd-sourcing effort involving over 13,500 volunteers.
It was modified from the original by following the tree branches and reforming the messages into conversation streams.
#### Who are the editors?
Aymeric Roucher, Hugging Face.
### Example
````
{
'conversation_id': '6708c47f-05c9-4346-b3d2-40b2bd24fde4',
'user_id': '2c96e467-66f0-4be7-9693-bda51356a424',
'created_date': '2023-02-06T18:48:49.391686+00:00',
'messages': [
{'content': 'Can you write a short introduction about the relevance of the term "monopsony" in economics? Please use examples related to potential monopsonies in the labour market and cite relevant research.',
'role': 'user'},
{'content': '"Monopsony" refers to a market structure where there is only one buyer for a particular good or service. In economics, this term is particularly relevant in the labor market, where a monopsony employer has significant power over the wages and working conditions of their employees. The presence of a monopsony can result in lower wages and reduced employment opportunities for workers, as the employer has little incentive to increase wages or provide better working conditions.\n\nRecent research has identified potential monopsonies in industries such as retail and fast food, where a few large companies control a significant portion of the market (Bivens & Mishel, 2013). In these industries, workers often face low wages, limited benefits, and reduced bargaining power, leading to a situation where they are dependent on the employer for their livelihood. This dependence can result in further suppression of wages and a decline in working conditions.\n\nOverall, the concept of monopsony is essential to understanding the dynamics of labor markets and the impact of market power on workers. Further research is needed to understand the extent and impact of monopsonies on the economy and to develop policies to address this issue.\n\nReferences:\nBivens, J., & Mishel, L. (2013). The Pay of Corporate Executives and Financial Professionals as Evidence of Rents in Top 1 Percent Incomes. Journal of Economic Perspectives, 27(3), 57-78.',
'role': 'assistant'},
{'content': 'Now explain it to a dog', 'role': 'user'}
]
}
```` | [
-0.379118412733078,
-0.7639791965484619,
0.013462107628583908,
0.20962770283222198,
-0.2077559530735016,
-0.07644780725240707,
-0.10244520008563995,
-0.7641564607620239,
0.9489613175392151,
0.6434643268585205,
-0.6315033435821533,
-0.40723279118537903,
-0.5089247226715088,
0.06856951117515... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
rishabh27s/rick-morty | rishabh27s | 2023-11-18T00:52:08Z | 41 | 0 | null | [
"region:us"
] | 2023-11-18T00:52:08Z | 2023-11-18T00:50:43.000Z | 2023-11-18T00:50:43 | Entry not found | [
-0.32276487350463867,
-0.22568444907665253,
0.8622263073921204,
0.43461570143699646,
-0.5282988548278809,
0.7012969255447388,
0.7915717363357544,
0.07618642598390579,
0.7746027112007141,
0.25632190704345703,
-0.7852815389633179,
-0.22573848068714142,
-0.910447895526886,
0.5715675354003906,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
brainer/drug_info_clear | brainer | 2023-11-20T09:17:16Z | 41 | 0 | null | [
"region:us"
] | 2023-11-20T09:17:16Z | 2023-11-20T05:48:22.000Z | 2023-11-20T05:48:22 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': '196000001'
'1': '196200043'
'2': '196300001'
'3': '196400099'
'4': '196500004'
'5': '197000037'
'6': '197000049'
'7': '197000050'
'8': '197000053'
'9': '197000079'
'10': '197000102'
'11': '197100097'
'12': '197300021'
'13': '197400039'
'14': '197400059'
'15': '197500015'
'16': '197500016'
'17': '197500285'
'18': '197500541'
'19': '197500654'
'20': '197600065'
'21': '197700025'
'22': '197700049'
'23': '197700120'
'24': '197800027'
'25': '197900544'
'26': '197900575'
'27': '198000054'
'28': '198000158'
'29': '198000160'
'30': '198000170'
'31': '198000572'
'32': '198100012'
'33': '198100015'
'34': '198100119'
'35': '198100257'
'36': '198100428'
'37': '198200048'
'38': '198200049'
'39': '198200323'
'40': '198200325'
'41': '198300064'
'42': '198300065'
'43': '198300096'
'44': '198300142'
'45': '198300174'
'46': '198300343'
'47': '198300393'
'48': '198300476'
'49': '198300605'
'50': '198301052'
'51': '198400185'
'52': '198400399'
'53': '198400475'
'54': '198401033'
'55': '198401161'
'56': '198500041'
'57': '198500049'
'58': '198500050'
'59': '198500125'
'60': '198500241'
'61': '198500245'
'62': '198500384'
'63': '198500515'
'64': '198500612'
'65': '198500634'
'66': '198500715'
'67': '198500718'
'68': '198501126'
'69': '198501220'
'70': '198501325'
'71': '198501456'
'72': '198501820'
'73': '198600058'
'74': '198600114'
'75': '198600161'
'76': '198600235'
'77': '198600470'
'78': '198600661'
'79': '198600674'
'80': '198601102'
'81': '198601223'
'82': '198601878'
'83': '198700096'
'84': '198700405'
'85': '198700476'
'86': '198700477'
'87': '198700535'
'88': '198700537'
'89': '198700667'
'90': '198700731'
'91': '198700733'
'92': '198700736'
'93': '198700737'
'94': '198701132'
'95': '198701478'
'96': '198701520'
'97': '198701523'
'98': '198701583'
'99': '198800150'
'100': '198800153'
'101': '198800154'
'102': '198800445'
'103': '198800619'
'104': '198800622'
'105': '198800788'
'106': '198800791'
'107': '198800901'
'108': '198800902'
'109': '198800911'
'110': '198801052'
'111': '198801525'
'112': '198801531'
'113': '198801937'
'114': '198802273'
'115': '198802349'
'116': '198802355'
'117': '198900123'
'118': '198900125'
'119': '198900129'
'120': '198900223'
'121': '198900263'
'122': '198900630'
'123': '198900711'
'124': '198900817'
'125': '198900881'
'126': '198900993'
'127': '198901021'
'128': '198901206'
'129': '198901207'
'130': '198902026'
'131': '198902101'
'132': '198902108'
'133': '198902158'
'134': '198902844'
'135': '199000074'
'136': '199000165'
'137': '199000352'
'138': '199000530'
'139': '199000568'
'140': '199000820'
'141': '199000983'
'142': '199001080'
'143': '199001166'
'144': '199001735'
'145': '199001917'
'146': '199001919'
'147': '199001973'
'148': '199002022'
'149': '199002349'
'150': '199100118'
'151': '199100476'
'152': '199100626'
'153': '199100628'
'154': '199100632'
'155': '199100636'
'156': '199100838'
'157': '199100923'
'158': '199101034'
'159': '199101166'
'160': '199101229'
'161': '199101291'
'162': '199101298'
'163': '199101995'
'164': '199102137'
'165': '199102138'
'166': '199102384'
'167': '199102409'
'168': '199102447'
'169': '199102449'
'170': '199102476'
'171': '199102956'
'172': '199103287'
'173': '199200232'
'174': '199200236'
'175': '199200261'
'176': '199200476'
'177': '199200490'
'178': '199200629'
'179': '199200633'
'180': '199200653'
'181': '199200792'
'182': '199200869'
'183': '199200870'
'184': '199200876'
'185': '199201002'
'186': '199201006'
'187': '199201045'
'188': '199201046'
'189': '199201154'
'190': '199201155'
'191': '199201214'
'192': '199202074'
'193': '199202334'
'194': '199202495'
'195': '199202562'
'196': '199202565'
'197': '199202572'
'198': '199202944'
'199': '199202946'
'200': '199203272'
'201': '199203279'
'202': '199203487'
'203': '199203520'
'204': '199300175'
'205': '199300208'
'206': '199300225'
'207': '199300319'
'208': '199300325'
'209': '199300516'
'210': '199300692'
'211': '199300758'
'212': '199300815'
'213': '199300927'
'214': '199300928'
'215': '199300997'
'216': '199301111'
'217': '199301180'
'218': '199301193'
'219': '199301673'
'220': '199302061'
'221': '199302106'
'222': '199302107'
'223': '199302108'
'224': '199302175'
'225': '199302198'
'226': '199302663'
'227': '199302666'
'228': '199302671'
'229': '199400095'
'230': '199400114'
'231': '199400191'
'232': '199400362'
'233': '199400392'
'234': '199400488'
'235': '199400494'
'236': '199400513'
'237': '199400514'
'238': '199400540'
'239': '199400625'
'240': '199400630'
'241': '199400635'
'242': '199400682'
'243': '199400695'
'244': '199400696'
'245': '199400704'
'246': '199400710'
'247': '199400823'
'248': '199400868'
'249': '199400905'
'250': '199400946'
'251': '199400948'
'252': '199401165'
'253': '199401504'
'254': '199401625'
'255': '199401734'
'256': '199401754'
'257': '199401768'
'258': '199401770'
'259': '199401998'
'260': '199500043'
'261': '199500183'
'262': '199500439'
'263': '199500466'
'264': '199500470'
'265': '199500549'
'266': '199500630'
'267': '199500842'
'268': '199500845'
'269': '199500850'
'270': '199500959'
'271': '199501023'
'272': '199501072'
'273': '199501073'
'274': '199501234'
'275': '199501564'
'276': '199501728'
'277': '199501734'
'278': '199501735'
'279': '199501736'
'280': '199501738'
'281': '199501743'
'282': '199501748'
'283': '199501749'
'284': '199501905'
'285': '199501906'
'286': '199502137'
'287': '199502153'
'288': '199502155'
'289': '199502167'
'290': '199502192'
'291': '199502215'
'292': '199502217'
'293': '199502223'
'294': '199502224'
'295': '199502225'
'296': '199502428'
'297': '199502575'
'298': '199502582'
'299': '199502585'
'300': '199504100'
'301': '199504101'
'302': '199504272'
'303': '199504273'
'304': '199504276'
'305': '199504332'
'306': '199504367'
'307': '199600151'
'308': '199600158'
'309': '199600246'
'310': '199600267'
'311': '199600367'
'312': '199600597'
'313': '199600616'
'314': '199600625'
'315': '199600977'
'316': '199601062'
'317': '199601139'
'318': '199601167'
'319': '199601484'
'320': '199601520'
'321': '199601533'
'322': '199602013'
'323': '199602015'
'324': '199602019'
'325': '199602021'
'326': '199602022'
'327': '199602023'
'328': '199602029'
'329': '199602031'
'330': '199602290'
'331': '199602404'
'332': '199602533'
'333': '199602566'
'334': '199602745'
'335': '199603160'
'336': '199603453'
'337': '199603455'
'338': '199603458'
'339': '199604928'
'340': '199604979'
'341': '199605127'
'342': '199700160'
'343': '199700176'
'344': '199700389'
'345': '199700584'
'346': '199700734'
'347': '199700738'
'348': '199700745'
'349': '199700798'
'350': '199700808'
'351': '199700809'
'352': '199700833'
'353': '199700840'
'354': '199700883'
'355': '199700887'
'356': '199700909'
'357': '199700916'
'358': '199700918'
'359': '199700919'
'360': '199700978'
'361': '199701009'
'362': '199701010'
'363': '199701011'
'364': '199701012'
'365': '199701033'
'366': '199701054'
'367': '199701063'
'368': '199701064'
'369': '199701065'
'370': '199701131'
'371': '199701225'
'372': '199701226'
'373': '199701227'
'374': '199701265'
'375': '199701271'
'376': '199701295'
'377': '199701385'
'378': '199701392'
'379': '199701393'
'380': '199701398'
'381': '199701401'
'382': '199701408'
'383': '199701414'
'384': '199701416'
'385': '199701432'
'386': '199701437'
'387': '199701525'
'388': '199701668'
'389': '199701845'
'390': '199702105'
'391': '199702106'
'392': '199702117'
'393': '199702118'
'394': '199702126'
'395': '199702163'
'396': '199702164'
'397': '199702165'
'398': '199702177'
'399': '199702351'
'400': '199702352'
'401': '199702380'
'402': '199702412'
'403': '199702566'
'404': '199702588'
'405': '199702829'
'406': '199702839'
'407': '199702846'
'408': '199702918'
'409': '199702953'
'410': '199703049'
'411': '199703126'
'412': '199703129'
'413': '199703432'
'414': '199703566'
'415': '199703570'
'416': '199704687'
'417': '199800085'
'418': '199800086'
'419': '199800142'
'420': '199800471'
'421': '199800503'
'422': '199800519'
'423': '199800751'
'424': '199800785'
'425': '199800903'
'426': '199800976'
'427': '199800979'
'428': '199800990'
'429': '199801011'
'430': '199801012'
'431': '199801099'
'432': '199801158'
'433': '199801165'
'434': '199801260'
'435': '199801263'
'436': '199801266'
'437': '199801267'
'438': '199801290'
'439': '199801292'
'440': '199801298'
'441': '199801524'
'442': '199801625'
'443': '199801634'
'444': '199801640'
'445': '199801649'
'446': '199802092'
'447': '199802093'
'448': '199802138'
'449': '199802175'
'450': '199802288'
'451': '199802289'
'452': '199802611'
'453': '199802620'
'454': '199802675'
'455': '199802769'
'456': '199803014'
'457': '199803062'
'458': '199803425'
'459': '199803684'
'460': '199803957'
'461': '199803958'
'462': '199806739'
'463': '199806820'
'464': '199806914'
'465': '199806978'
'466': '199900114'
'467': '199900120'
'468': '199900163'
'469': '199900203'
'470': '199900204'
'471': '199900351'
'472': '199900554'
'473': '199900672'
'474': '199900832'
'475': '199900834'
'476': '199900915'
'477': '199901076'
'478': '199901116'
'479': '199901211'
'480': '199901215'
'481': '199901218'
'482': '199901248'
'483': '199901258'
'484': '199901558'
'485': '199901692'
'486': '199901718'
'487': '199901759'
'488': '199902270'
'489': '199902295'
'490': '199902440'
'491': '199902448'
'492': '199902449'
'493': '199902459'
'494': '199902661'
'495': '199903179'
'496': '199903219'
'497': '199903222'
'498': '199903365'
'499': '199903836'
'500': '199903837'
'501': '199906840'
'502': '199907419'
'503': '200000209'
'504': '200000210'
'505': '200000220'
'506': '200000223'
'507': '200000224'
'508': '200000417'
'509': '200000559'
'510': '200000569'
'511': '200000601'
'512': '200000740'
'513': '200000919'
'514': '200000930'
'515': '200000932'
'516': '200000933'
'517': '200000934'
'518': '200000935'
'519': '200001172'
'520': '200001184'
'521': '200001186'
'522': '200001190'
'523': '200001275'
'524': '200001430'
'525': '200001578'
'526': '200001604'
'527': '200001858'
'528': '200002121'
'529': '200002422'
'530': '200002738'
'531': '200002760'
'532': '200002776'
'533': '200002787'
'534': '200002882'
'535': '200002887'
'536': '200002949'
'537': '200003080'
'538': '200003085'
'539': '200003086'
'540': '200003109'
'541': '200003111'
'542': '200003403'
'543': '200003442'
'544': '200003541'
'545': '200003560'
'546': '200003792'
'547': '200003994'
'548': '200003999'
'549': '200004038'
'550': '200004243'
'551': '200004640'
'552': '200004643'
'553': '200005087'
'554': '200005100'
'555': '200008568'
'556': '200008571'
'557': '200008952'
'558': '200009059'
'559': '200009061'
'560': '200009062'
'561': '200009063'
'562': '200009333'
'563': '200009496'
'564': '200009524'
'565': '200009634'
'566': '200009708'
'567': '200100102'
'568': '200100264'
'569': '200100383'
'570': '200100424'
'571': '200100429'
'572': '200100602'
'573': '200100614'
'574': '200100671'
'575': '200100725'
'576': '200100827'
'577': '200100858'
'578': '200100960'
'579': '200100997'
'580': '200101016'
'581': '200101017'
'582': '200101018'
'583': '200101022'
'584': '200101103'
'585': '200101123'
'586': '200101150'
'587': '200101162'
'588': '200101179'
'589': '200101249'
'590': '200101393'
'591': '200101407'
'592': '200101428'
'593': '200101451'
'594': '200101472'
'595': '200101633'
'596': '200101635'
'597': '200102266'
'598': '200102615'
'599': '200102622'
'600': '200102623'
'601': '200102644'
'602': '200102802'
'603': '200102845'
'604': '200102846'
'605': '200102887'
'606': '200102909'
'607': '200102920'
'608': '200102931'
'609': '200102998'
'610': '200103187'
'611': '200103882'
'612': '200103884'
'613': '200108384'
'614': '200108800'
'615': '200108817'
'616': '200108822'
'617': '200109139'
'618': '200109233'
'619': '200109769'
'620': '200110053'
'621': '200110059'
'622': '200200143'
'623': '200200152'
'624': '200200158'
'625': '200200169'
'626': '200200173'
'627': '200200201'
'628': '200200234'
'629': '200200252'
'630': '200200375'
'631': '200200377'
'632': '200200486'
'633': '200200502'
'634': '200200611'
'635': '200200663'
'636': '200200715'
'637': '200200719'
'638': '200200720'
'639': '200200723'
'640': '200200852'
'641': '200200939'
'642': '200201028'
'643': '200201029'
'644': '200201084'
'645': '200201087'
'646': '200201201'
'647': '200201329'
'648': '200201335'
'649': '200201339'
'650': '200201406'
'651': '200201524'
'652': '200201895'
'653': '200201906'
'654': '200201919'
'655': '200201926'
'656': '200201927'
'657': '200202092'
'658': '200202093'
'659': '200202362'
'660': '200202373'
'661': '200202476'
'662': '200202573'
'663': '200202617'
'664': '200202753'
'665': '200202755'
'666': '200202781'
'667': '200202782'
'668': '200202982'
'669': '200202994'
'670': '200203031'
'671': '200203496'
'672': '200203727'
'673': '200204308'
'674': '200204322'
'675': '200204348'
'676': '200204369'
'677': '200209794'
'678': '200210513'
'679': '200300089'
'680': '200300092'
'681': '200300095'
'682': '200300100'
'683': '200300102'
'684': '200300103'
'685': '200300104'
'686': '200300144'
'687': '200300154'
'688': '200300155'
'689': '200300192'
'690': '200300198'
'691': '200300260'
'692': '200300269'
'693': '200300283'
'694': '200300284'
'695': '200300286'
'696': '200300312'
'697': '200300313'
'698': '200300406'
'699': '200300408'
'700': '200300409'
'701': '200300423'
'702': '200300424'
'703': '200300431'
'704': '200300434'
'705': '200300458'
'706': '200300459'
'707': '200300461'
'708': '200300462'
'709': '200300463'
'710': '200300470'
'711': '200300520'
'712': '200300521'
'713': '200300523'
'714': '200300598'
'715': '200300603'
'716': '200300626'
'717': '200300638'
'718': '200300642'
'719': '200300645'
'720': '200300657'
'721': '200300660'
'722': '200300661'
'723': '200300694'
'724': '200300708'
'725': '200300784'
'726': '200300792'
'727': '200300796'
'728': '200300800'
'729': '200300801'
'730': '200300802'
'731': '200300804'
'732': '200300805'
'733': '200300806'
'734': '200300840'
'735': '200300843'
'736': '200300854'
'737': '200300855'
'738': '200300864'
'739': '200300878'
'740': '200300905'
'741': '200300913'
'742': '200300916'
'743': '200300917'
'744': '200300918'
'745': '200300984'
'746': '200300985'
'747': '200300987'
'748': '200301018'
'749': '200301019'
'750': '200301021'
'751': '200301031'
'752': '200301032'
'753': '200301033'
'754': '200301128'
'755': '200301131'
'756': '200301172'
'757': '200301181'
'758': '200301252'
'759': '200301323'
'760': '200301345'
'761': '200301348'
'762': '200301486'
'763': '200301507'
'764': '200301609'
'765': '200301610'
'766': '200301612'
'767': '200301618'
'768': '200301620'
'769': '200301624'
'770': '200301625'
'771': '200301667'
'772': '200301683'
'773': '200301739'
'774': '200301759'
'775': '200301795'
'776': '200301831'
'777': '200301937'
'778': '200301953'
'779': '200301956'
'780': '200301990'
'781': '200301991'
'782': '200302009'
'783': '200302015'
'784': '200302039'
'785': '200302049'
'786': '200302050'
'787': '200302051'
'788': '200302052'
'789': '200302053'
'790': '200302054'
'791': '200302073'
'792': '200302121'
'793': '200302122'
'794': '200302141'
'795': '200302187'
'796': '200302205'
'797': '200302214'
'798': '200302215'
'799': '200302254'
'800': '200302452'
'801': '200302456'
'802': '200302457'
'803': '200302476'
'804': '200302482'
'805': '200302484'
'806': '200302485'
'807': '200302486'
'808': '200302623'
'809': '200302627'
'810': '200302642'
'811': '200303280'
'812': '200303281'
'813': '200303328'
'814': '200307647'
'815': '200307781'
'816': '200307798'
'817': '200307799'
'818': '200307847'
'819': '200307848'
'820': '200307866'
'821': '200307867'
'822': '200308353'
'823': '200308354'
'824': '200308550'
'825': '200308552'
'826': '200308578'
'827': '200308603'
'828': '200308647'
'829': '200308774'
'830': '200308825'
'831': '200308841'
'832': '200308855'
'833': '200308867'
'834': '200400062'
'835': '200400100'
'836': '200400102'
'837': '200400104'
'838': '200400105'
'839': '200400111'
'840': '200400112'
'841': '200400113'
'842': '200400114'
'843': '200400118'
'844': '200400120'
'845': '200400121'
'846': '200400122'
'847': '200400123'
'848': '200400165'
'849': '200400166'
'850': '200400173'
'851': '200400175'
'852': '200400177'
'853': '200400179'
'854': '200400215'
'855': '200400323'
'856': '200400325'
'857': '200400387'
'858': '200400388'
'859': '200400392'
'860': '200400395'
'861': '200400397'
'862': '200400463'
'863': '200400465'
'864': '200400478'
'865': '200400482'
'866': '200400514'
'867': '200400519'
'868': '200400520'
'869': '200400528'
'870': '200400530'
'871': '200400538'
'872': '200400550'
'873': '200400561'
'874': '200400565'
'875': '200400570'
'876': '200400580'
'877': '200400581'
'878': '200400587'
'879': '200400644'
'880': '200400685'
'881': '200400686'
'882': '200400687'
'883': '200400691'
'884': '200400695'
'885': '200400700'
'886': '200400718'
'887': '200400724'
'888': '200400727'
'889': '200400728'
'890': '200400729'
'891': '200400798'
'892': '200400799'
'893': '200400801'
'894': '200400802'
'895': '200400803'
'896': '200400804'
'897': '200400813'
'898': '200400816'
'899': '200400817'
'900': '200400825'
'901': '200400828'
'902': '200400830'
'903': '200400841'
'904': '200400872'
'905': '200400894'
'906': '200400904'
'907': '200400910'
'908': '200400922'
'909': '200400930'
'910': '200400993'
'911': '200401005'
'912': '200401009'
'913': '200401062'
'914': '200401108'
'915': '200401172'
'916': '200401202'
'917': '200401210'
'918': '200401211'
'919': '200401219'
'920': '200401221'
'921': '200401222'
'922': '200401235'
'923': '200401242'
'924': '200401244'
'925': '200401247'
'926': '200401254'
'927': '200401323'
'928': '200401324'
'929': '200401325'
'930': '200401326'
'931': '200401327'
'932': '200401328'
'933': '200401329'
'934': '200401330'
'935': '200401332'
'936': '200401353'
'937': '200401359'
'938': '200401367'
'939': '200401369'
'940': '200401370'
'941': '200401371'
'942': '200401373'
'943': '200401383'
'944': '200401385'
'945': '200401397'
'946': '200401399'
'947': '200401401'
'948': '200401405'
'949': '200401407'
'950': '200401409'
'951': '200401411'
'952': '200401432'
'953': '200401547'
'954': '200401548'
'955': '200401578'
'956': '200401582'
'957': '200401586'
'958': '200401589'
'959': '200401651'
'960': '200401652'
'961': '200401666'
'962': '200401683'
'963': '200401684'
'964': '200401686'
'965': '200401687'
'966': '200401693'
'967': '200401718'
'968': '200401747'
'969': '200401750'
'970': '200401751'
'971': '200401755'
'972': '200401756'
'973': '200401762'
'974': '200401769'
'975': '200401848'
'976': '200401849'
'977': '200401850'
'978': '200401852'
'979': '200401857'
'980': '200401862'
'981': '200401874'
'982': '200401875'
'983': '200401876'
'984': '200401878'
'985': '200401881'
'986': '200401882'
'987': '200402344'
'988': '200402368'
'989': '200402374'
'990': '200402391'
'991': '200402393'
'992': '200402396'
'993': '200402399'
'994': '200402407'
'995': '200402408'
'996': '200402420'
'997': '200402435'
'998': '200402439'
'999': '200402455'
'1000': '200402458'
'1001': '200402464'
'1002': '200402465'
'1003': '200402466'
'1004': '200402468'
'1005': '200402485'
'1006': '200402487'
'1007': '200402490'
'1008': '200402508'
'1009': '200402510'
'1010': '200402522'
'1011': '200402557'
'1012': '200402604'
'1013': '200402617'
'1014': '200402623'
'1015': '200402674'
'1016': '200402677'
'1017': '200402681'
'1018': '200402690'
'1019': '200402816'
'1020': '200402819'
'1021': '200402823'
'1022': '200402824'
'1023': '200402825'
'1024': '200402830'
'1025': '200402834'
'1026': '200402835'
'1027': '200402839'
'1028': '200402840'
'1029': '200402841'
'1030': '200402842'
'1031': '200402845'
'1032': '200402847'
'1033': '200402848'
'1034': '200402852'
'1035': '200402853'
'1036': '200402879'
'1037': '200402902'
'1038': '200402903'
'1039': '200402912'
'1040': '200402913'
'1041': '200402915'
'1042': '200402927'
'1043': '200402928'
'1044': '200402929'
'1045': '200402931'
'1046': '200402939'
'1047': '200402943'
'1048': '200402944'
'1049': '200402945'
'1050': '200402946'
'1051': '200402947'
'1052': '200402949'
'1053': '200402952'
'1054': '200402968'
'1055': '200402973'
'1056': '200402979'
'1057': '200402981'
'1058': '200402982'
'1059': '200402983'
'1060': '200402992'
'1061': '200403040'
'1062': '200403041'
'1063': '200403042'
'1064': '200403049'
'1065': '200403052'
'1066': '200403053'
'1067': '200403054'
'1068': '200403056'
'1069': '200403060'
'1070': '200403062'
'1071': '200403075'
'1072': '200403081'
'1073': '200403082'
'1074': '200403084'
'1075': '200403085'
'1076': '200403086'
'1077': '200403089'
'1078': '200403090'
'1079': '200403104'
'1080': '200403111'
'1081': '200403121'
'1082': '200403125'
'1083': '200403126'
'1084': '200403137'
'1085': '200403138'
'1086': '200403160'
'1087': '200403167'
'1088': '200403183'
'1089': '200403184'
'1090': '200403185'
'1091': '200403186'
'1092': '200403226'
'1093': '200403289'
'1094': '200403290'
'1095': '200403291'
'1096': '200403292'
'1097': '200403296'
'1098': '200403304'
'1099': '200403305'
'1100': '200403309'
'1101': '200403312'
'1102': '200403317'
'1103': '200403319'
'1104': '200403321'
'1105': '200403323'
'1106': '200403325'
'1107': '200403327'
'1108': '200403329'
'1109': '200403333'
'1110': '200403335'
'1111': '200403336'
'1112': '200403405'
'1113': '200403411'
'1114': '200403413'
'1115': '200403414'
'1116': '200403415'
'1117': '200403419'
'1118': '200403425'
'1119': '200403426'
'1120': '200403427'
'1121': '200403433'
'1122': '200403434'
'1123': '200403448'
'1124': '200403459'
'1125': '200403460'
'1126': '200403461'
'1127': '200403462'
'1128': '200403463'
'1129': '200403464'
'1130': '200403465'
'1131': '200403783'
'1132': '200403794'
'1133': '200403814'
'1134': '200403816'
'1135': '200403819'
'1136': '200403822'
'1137': '200403982'
'1138': '200404000'
'1139': '200404007'
'1140': '200404009'
'1141': '200404029'
'1142': '200404034'
'1143': '200404038'
'1144': '200404039'
'1145': '200404040'
'1146': '200404042'
'1147': '200404043'
'1148': '200404044'
'1149': '200404046'
'1150': '200404048'
'1151': '200404050'
'1152': '200404051'
'1153': '200404055'
'1154': '200404059'
'1155': '200404060'
'1156': '200404168'
'1157': '200404421'
'1158': '200404437'
'1159': '200404438'
'1160': '200404644'
'1161': '200404646'
'1162': '200404647'
'1163': '200404653'
'1164': '200404654'
'1165': '200404656'
'1166': '200404657'
'1167': '200404669'
'1168': '200404670'
'1169': '200404671'
'1170': '200404677'
'1171': '200404678'
'1172': '200404684'
'1173': '200404690'
'1174': '200404692'
'1175': '200404693'
'1176': '200404695'
'1177': '200404698'
'1178': '200404699'
'1179': '200404700'
'1180': '200404701'
'1181': '200404702'
'1182': '200404707'
'1183': '200404709'
'1184': '200404711'
'1185': '200404712'
'1186': '200404719'
'1187': '200404721'
'1188': '200404722'
'1189': '200404724'
'1190': '200404726'
'1191': '200404740'
'1192': '200404741'
'1193': '200404747'
'1194': '200404754'
'1195': '200404762'
'1196': '200404763'
'1197': '200404771'
'1198': '200404772'
'1199': '200404779'
'1200': '200409929'
'1201': '200409930'
'1202': '200409932'
'1203': '200409933'
'1204': '200410082'
'1205': '200410083'
'1206': '200410085'
'1207': '200410086'
'1208': '200410087'
'1209': '200410088'
'1210': '200410089'
'1211': '200410090'
'1212': '200410337'
'1213': '200410865'
'1214': '200410892'
'1215': '200410894'
'1216': '200410896'
'1217': '200410897'
'1218': '200410901'
'1219': '200410902'
'1220': '200410905'
'1221': '200410909'
'1222': '200410941'
'1223': '200410942'
'1224': '200410943'
'1225': '200410951'
'1226': '200410977'
'1227': '200410999'
'1228': '200411002'
'1229': '200411033'
'1230': '200411042'
'1231': '200411043'
'1232': '200411062'
'1233': '200411064'
'1234': '200411065'
'1235': '200411066'
'1236': '200411067'
'1237': '200411068'
'1238': '200411087'
'1239': '200411095'
'1240': '200411207'
'1241': '200411208'
'1242': '200500111'
'1243': '200500125'
'1244': '200500128'
'1245': '200500130'
'1246': '200500132'
'1247': '200500133'
'1248': '200500134'
'1249': '200500135'
'1250': '200500140'
'1251': '200500144'
'1252': '200500145'
'1253': '200500146'
'1254': '200500150'
'1255': '200500161'
'1256': '200500162'
'1257': '200500246'
'1258': '200500248'
'1259': '200500249'
'1260': '200500251'
'1261': '200500252'
'1262': '200500253'
'1263': '200500254'
'1264': '200500255'
'1265': '200500257'
'1266': '200500258'
'1267': '200500287'
'1268': '200500288'
'1269': '200500302'
'1270': '200500424'
'1271': '200500426'
'1272': '200500430'
'1273': '200500474'
'1274': '200500476'
'1275': '200500482'
'1276': '200500483'
'1277': '200500545'
'1278': '200500552'
'1279': '200500553'
'1280': '200500554'
'1281': '200500581'
'1282': '200500583'
'1283': '200500585'
'1284': '200500589'
'1285': '200500592'
'1286': '200500605'
'1287': '200500622'
'1288': '200500649'
'1289': '200500686'
'1290': '200500694'
'1291': '200500695'
'1292': '200500699'
'1293': '200500704'
'1294': '200500797'
'1295': '200500800'
'1296': '200500805'
'1297': '200500806'
'1298': '200500809'
'1299': '200500815'
'1300': '200500835'
'1301': '200500853'
'1302': '200500854'
'1303': '200500864'
'1304': '200500870'
'1305': '200500871'
'1306': '200500882'
'1307': '200500892'
'1308': '200500961'
'1309': '200500962'
'1310': '200500963'
'1311': '200500965'
'1312': '200500969'
'1313': '200501012'
'1314': '200501107'
'1315': '200501119'
'1316': '200501120'
'1317': '200501141'
'1318': '200501145'
'1319': '200501155'
'1320': '200501163'
'1321': '200501237'
'1322': '200501239'
'1323': '200501241'
'1324': '200501243'
'1325': '200501265'
'1326': '200501267'
'1327': '200501277'
'1328': '200501288'
'1329': '200501291'
'1330': '200501293'
'1331': '200501301'
'1332': '200501307'
'1333': '200501384'
'1334': '200501427'
'1335': '200501429'
'1336': '200501458'
'1337': '200501472'
'1338': '200501511'
'1339': '200501522'
'1340': '200501593'
'1341': '200501601'
'1342': '200501605'
'1343': '200501618'
'1344': '200501667'
'1345': '200501979'
'1346': '200501997'
'1347': '200501999'
'1348': '200502010'
'1349': '200502012'
'1350': '200502014'
'1351': '200502017'
'1352': '200502029'
'1353': '200502030'
'1354': '200502035'
'1355': '200502039'
'1356': '200502050'
'1357': '200502052'
'1358': '200502054'
'1359': '200502086'
'1360': '200502087'
'1361': '200502089'
'1362': '200502090'
'1363': '200502105'
'1364': '200502107'
'1365': '200502109'
'1366': '200502175'
'1367': '200502192'
'1368': '200502218'
'1369': '200502219'
'1370': '200502306'
'1371': '200502416'
'1372': '200502470'
'1373': '200502472'
'1374': '200502473'
'1375': '200502474'
'1376': '200502490'
'1377': '200502557'
'1378': '200502588'
'1379': '200502598'
'1380': '200502600'
'1381': '200502601'
'1382': '200502633'
'1383': '200502711'
'1384': '200502717'
'1385': '200502742'
'1386': '200502744'
'1387': '200502757'
'1388': '200502762'
'1389': '200502770'
'1390': '200502808'
'1391': '200502809'
'1392': '200502810'
'1393': '200502834'
'1394': '200502838'
'1395': '200502901'
'1396': '200502953'
'1397': '200503063'
'1398': '200503065'
'1399': '200503066'
'1400': '200503075'
'1401': '200503128'
'1402': '200503200'
'1403': '200503234'
'1404': '200503238'
'1405': '200503246'
'1406': '200503619'
'1407': '200503637'
'1408': '200503642'
'1409': '200503652'
'1410': '200503653'
'1411': '200503664'
'1412': '200503775'
'1413': '200503783'
'1414': '200503786'
'1415': '200503787'
'1416': '200503788'
'1417': '200503798'
'1418': '200503799'
'1419': '200503803'
'1420': '200503806'
'1421': '200503807'
'1422': '200505665'
'1423': '200511055'
'1424': '200511056'
'1425': '200511057'
'1426': '200511058'
'1427': '200511059'
'1428': '200511060'
'1429': '200511064'
'1430': '200511065'
'1431': '200511066'
'1432': '200511067'
'1433': '200511068'
'1434': '200511106'
'1435': '200511107'
'1436': '200511108'
'1437': '200511262'
'1438': '200511263'
'1439': '200511264'
'1440': '200511266'
'1441': '200511904'
'1442': '200512186'
'1443': '200512201'
'1444': '200512238'
'1445': '200512240'
'1446': '200512244'
'1447': '200600026'
'1448': '200600027'
'1449': '200600028'
'1450': '200600036'
'1451': '200600049'
'1452': '200600054'
'1453': '200600081'
'1454': '200600114'
'1455': '200600116'
'1456': '200600127'
'1457': '200600128'
'1458': '200600134'
'1459': '200600138'
'1460': '200600156'
'1461': '200600159'
'1462': '200600160'
'1463': '200600178'
'1464': '200600181'
'1465': '200600221'
'1466': '200600222'
'1467': '200600225'
'1468': '200600248'
'1469': '200600249'
'1470': '200600267'
'1471': '200600287'
'1472': '200600325'
'1473': '200600352'
'1474': '200600367'
'1475': '200600456'
'1476': '200600460'
'1477': '200600522'
'1478': '200600527'
'1479': '200600543'
'1480': '200600562'
'1481': '200600665'
'1482': '200600674'
'1483': '200600688'
'1484': '200600696'
'1485': '200600697'
'1486': '200600698'
'1487': '200600811'
'1488': '200600818'
'1489': '200600819'
'1490': '200600821'
'1491': '200603815'
'1492': '200603871'
'1493': '200603872'
'1494': '200604151'
'1495': '200604193'
'1496': '200604212'
'1497': '200604227'
'1498': '200604239'
'1499': '200604243'
'1500': '200604258'
'1501': '200604293'
'1502': '200604308'
'1503': '200604312'
'1504': '200604332'
'1505': '200604334'
'1506': '200604358'
'1507': '200604408'
'1508': '200605253'
'1509': '200605344'
'1510': '200605364'
'1511': '200605381'
'1512': '200605398'
'1513': '200605403'
'1514': '200605410'
'1515': '200605427'
'1516': '200605439'
'1517': '200605445'
'1518': '200605447'
'1519': '200605448'
'1520': '200605450'
'1521': '200605468'
'1522': '200605481'
'1523': '200605499'
'1524': '200605537'
'1525': '200606180'
'1526': '200606181'
'1527': '200606182'
'1528': '200606183'
'1529': '200606294'
'1530': '200606297'
'1531': '200606303'
'1532': '200606308'
'1533': '200606318'
'1534': '200606326'
'1535': '200606351'
'1536': '200606537'
'1537': '200606825'
'1538': '200606830'
'1539': '200606835'
'1540': '200606965'
'1541': '200606986'
'1542': '200607004'
'1543': '200607445'
'1544': '200607486'
'1545': '200607677'
'1546': '200607709'
'1547': '200607743'
'1548': '200607747'
'1549': '200607750'
'1550': '200607776'
'1551': '200607777'
'1552': '200607778'
'1553': '200607784'
'1554': '200607785'
'1555': '200607847'
'1556': '200607874'
'1557': '200607876'
'1558': '200607890'
'1559': '200607907'
'1560': '200607908'
'1561': '200608189'
'1562': '200608192'
'1563': '200608219'
'1564': '200608232'
'1565': '200608240'
'1566': '200608275'
'1567': '200608278'
'1568': '200608280'
'1569': '200608291'
'1570': '200608295'
'1571': '200608296'
'1572': '200610660'
'1573': '200610661'
'1574': '200610785'
'1575': '200610879'
'1576': '200610960'
'1577': '200610978'
'1578': '200610980'
'1579': '200610986'
'1580': '200611006'
'1581': '200611007'
'1582': '200611010'
'1583': '200611019'
'1584': '200611031'
'1585': '200611039'
'1586': '200611041'
'1587': '200611042'
'1588': '200611053'
'1589': '200611114'
'1590': '200611303'
'1591': '200611304'
'1592': '200611332'
'1593': '200611338'
'1594': '200611385'
'1595': '200611392'
'1596': '200612115'
'1597': '200612573'
'1598': '200612728'
'1599': '200612743'
'1600': '200700055'
'1601': '200700234'
'1602': '200700435'
'1603': '200700437'
'1604': '200700455'
'1605': '200700540'
'1606': '200700562'
'1607': '200700790'
'1608': '200700814'
'1609': '200700835'
'1610': '200700836'
'1611': '200700844'
'1612': '200700876'
'1613': '200700890'
'1614': '200701020'
'1615': '200701024'
'1616': '200701042'
'1617': '200701201'
'1618': '200701231'
'1619': '200701233'
'1620': '200701235'
'1621': '200701236'
'1622': '200701246'
'1623': '200701251'
'1624': '200701335'
'1625': '200701403'
'1626': '200701405'
'1627': '200701406'
'1628': '200701412'
'1629': '200701642'
'1630': '200701809'
'1631': '200701876'
'1632': '200701917'
'1633': '200701932'
'1634': '200701934'
'1635': '200702089'
'1636': '200702091'
'1637': '200702101'
'1638': '200702108'
'1639': '200702135'
'1640': '200702153'
'1641': '200702164'
'1642': '200702166'
'1643': '200702172'
'1644': '200702173'
'1645': '200702191'
'1646': '200702195'
'1647': '200702200'
'1648': '200702250'
'1649': '200702255'
'1650': '200702260'
'1651': '200702309'
'1652': '200702313'
'1653': '200702358'
'1654': '200702389'
'1655': '200702420'
'1656': '200702508'
'1657': '200702521'
'1658': '200702532'
'1659': '200702536'
'1660': '200702538'
'1661': '200702549'
'1662': '200702572'
'1663': '200702577'
'1664': '200702584'
'1665': '200702691'
'1666': '200702709'
'1667': '200702739'
'1668': '200702749'
'1669': '200702963'
'1670': '200702966'
'1671': '200702967'
'1672': '200702969'
'1673': '200702970'
'1674': '200703052'
'1675': '200703075'
'1676': '200703120'
'1677': '200703121'
'1678': '200703129'
'1679': '200703132'
'1680': '200703142'
'1681': '200703160'
'1682': '200703161'
'1683': '200703163'
'1684': '200703169'
'1685': '200703171'
'1686': '200703172'
'1687': '200703173'
'1688': '200703185'
'1689': '200703201'
'1690': '200703229'
'1691': '200703233'
'1692': '200703236'
'1693': '200703261'
'1694': '200703278'
'1695': '200703394'
'1696': '200703429'
'1697': '200703452'
'1698': '200703458'
'1699': '200703459'
'1700': '200703462'
'1701': '200703463'
'1702': '200703464'
'1703': '200703663'
'1704': '200703675'
'1705': '200703700'
'1706': '200703701'
'1707': '200703715'
'1708': '200703733'
'1709': '200703737'
'1710': '200703797'
'1711': '200703801'
'1712': '200703835'
'1713': '200703842'
'1714': '200703852'
'1715': '200703873'
'1716': '200703876'
'1717': '200703877'
'1718': '200703964'
'1719': '200704019'
'1720': '200704285'
'1721': '200704316'
'1722': '200704320'
'1723': '200704322'
'1724': '200704420'
'1725': '200704501'
'1726': '200704534'
'1727': '200704541'
'1728': '200704587'
'1729': '200704612'
'1730': '200704614'
'1731': '200704765'
'1732': '200704813'
'1733': '200704961'
'1734': '200704969'
'1735': '200705001'
'1736': '200705314'
'1737': '200705392'
'1738': '200705402'
'1739': '200705500'
'1740': '200705587'
'1741': '200705588'
'1742': '200705595'
'1743': '200705596'
'1744': '200705817'
'1745': '200706007'
'1746': '200706008'
'1747': '200706029'
'1748': '200706030'
'1749': '200706059'
'1750': '200706185'
'1751': '200706243'
'1752': '200706330'
'1753': '200706331'
'1754': '200706332'
'1755': '200706333'
'1756': '200706341'
'1757': '200706400'
'1758': '200706467'
'1759': '200706537'
'1760': '200706542'
'1761': '200706569'
'1762': '200706597'
'1763': '200706766'
'1764': '200706788'
'1765': '200706796'
'1766': '200706908'
'1767': '200706941'
'1768': '200706984'
'1769': '200707142'
'1770': '200707175'
'1771': '200707251'
'1772': '200707373'
'1773': '200707382'
'1774': '200707383'
'1775': '200707385'
'1776': '200707388'
'1777': '200707390'
'1778': '200707521'
'1779': '200707723'
'1780': '200707792'
'1781': '200707920'
'1782': '200707944'
'1783': '200707947'
'1784': '200707958'
'1785': '200708055'
'1786': '200708144'
'1787': '200708364'
'1788': '200708367'
'1789': '200708368'
'1790': '200708372'
'1791': '200708376'
'1792': '200708427'
'1793': '200708447'
'1794': '200708455'
'1795': '200708456'
'1796': '200708458'
'1797': '200708534'
'1798': '200708585'
'1799': '200708589'
'1800': '200708592'
'1801': '200708595'
'1802': '200708596'
'1803': '200708597'
'1804': '200708599'
'1805': '200708600'
'1806': '200708601'
'1807': '200708754'
'1808': '200708786'
'1809': '200708816'
'1810': '200708819'
'1811': '200708961'
'1812': '200709004'
'1813': '200709010'
'1814': '200709163'
'1815': '200709201'
'1816': '200709202'
'1817': '200709249'
'1818': '200709331'
'1819': '200709389'
'1820': '200709390'
'1821': '200709448'
'1822': '200709527'
'1823': '200709544'
'1824': '200709638'
'1825': '200709640'
'1826': '200709641'
'1827': '200709794'
'1828': '200709818'
'1829': '200709901'
'1830': '200709902'
'1831': '200709913'
'1832': '200709915'
'1833': '200710087'
'1834': '200710374'
'1835': '200710524'
'1836': '200710628'
'1837': '200710758'
'1838': '200710759'
'1839': '200710760'
'1840': '200710808'
'1841': '200710855'
'1842': '200710856'
'1843': '200710957'
'1844': '200710998'
'1845': '200711148'
'1846': '200711216'
'1847': '200711286'
'1848': '200711309'
'1849': '200711422'
'1850': '200711426'
'1851': '200711456'
'1852': '200711527'
'1853': '200711589'
'1854': '200711634'
'1855': '200711885'
'1856': '200711886'
'1857': '200711927'
'1858': '200711934'
'1859': '200711953'
'1860': '200712070'
'1861': '200712241'
'1862': '200712325'
'1863': '200712401'
'1864': '200712587'
'1865': '200712588'
'1866': '200712647'
'1867': '200712648'
'1868': '200712742'
'1869': '200712789'
'1870': '200712868'
'1871': '200712885'
'1872': '200713004'
'1873': '200713008'
'1874': '200713009'
'1875': '200713032'
'1876': '200713079'
'1877': '200713170'
'1878': '200713296'
'1879': '200713517'
'1880': '200713591'
'1881': '200713685'
'1882': '200713688'
'1883': '200713885'
'1884': '200713886'
'1885': '200713906'
'1886': '200713912'
'1887': '200800284'
'1888': '200800291'
'1889': '200800316'
'1890': '200800320'
'1891': '200800330'
'1892': '200800331'
'1893': '200800339'
'1894': '200800347'
'1895': '200800405'
'1896': '200800411'
'1897': '200800569'
'1898': '200800614'
'1899': '200801141'
'1900': '200801284'
'1901': '200801332'
'1902': '200801333'
'1903': '200801350'
'1904': '200801352'
'1905': '200801383'
'1906': '200801460'
'1907': '200801517'
'1908': '200801564'
'1909': '200801686'
'1910': '200801763'
'1911': '200801812'
'1912': '200801814'
'1913': '200801822'
'1914': '200801836'
'1915': '200802022'
'1916': '200802064'
'1917': '200802066'
'1918': '200802182'
'1919': '200802325'
'1920': '200802327'
'1921': '200802392'
'1922': '200802547'
'1923': '200802557'
'1924': '200802558'
'1925': '200802788'
'1926': '200802853'
'1927': '200802965'
'1928': '200803000'
'1929': '200803148'
'1930': '200803200'
'1931': '200803246'
'1932': '200803290'
'1933': '200803292'
'1934': '200803294'
'1935': '200803417'
'1936': '200803428'
'1937': '200803434'
'1938': '200803641'
'1939': '200803693'
'1940': '200803701'
'1941': '200803737'
'1942': '200803803'
'1943': '200803972'
'1944': '200804092'
'1945': '200804225'
'1946': '200804412'
'1947': '200804519'
'1948': '200804556'
'1949': '200804557'
'1950': '200804560'
'1951': '200804563'
'1952': '200804586'
'1953': '200804611'
'1954': '200804633'
'1955': '200804796'
'1956': '200804798'
'1957': '200804802'
'1958': '200804810'
'1959': '200804912'
'1960': '200804947'
'1961': '200804956'
'1962': '200805037'
'1963': '200805064'
'1964': '200805085'
'1965': '200805090'
'1966': '200805113'
'1967': '200805124'
'1968': '200805152'
'1969': '200805214'
'1970': '200805215'
'1971': '200805262'
'1972': '200805275'
'1973': '200805290'
'1974': '200805301'
'1975': '200805341'
'1976': '200805353'
'1977': '200805387'
'1978': '200805408'
'1979': '200805418'
'1980': '200805421'
'1981': '200805455'
'1982': '200805495'
'1983': '200805550'
'1984': '200805595'
'1985': '200805598'
'1986': '200805599'
'1987': '200805632'
'1988': '200805676'
'1989': '200805680'
'1990': '200805734'
'1991': '200805735'
'1992': '200805737'
'1993': '200805739'
'1994': '200805740'
'1995': '200805748'
'1996': '200805749'
'1997': '200805752'
'1998': '200805810'
'1999': '200805812'
'2000': '200805818'
'2001': '200805819'
'2002': '200805821'
'2003': '200805842'
'2004': '200805849'
'2005': '200805895'
'2006': '200805901'
'2007': '200805915'
'2008': '200805918'
'2009': '200805919'
'2010': '200805944'
'2011': '200805986'
'2012': '200805990'
'2013': '200805991'
'2014': '200806022'
'2015': '200806024'
'2016': '200806190'
'2017': '200806191'
'2018': '200806192'
'2019': '200806194'
'2020': '200806299'
'2021': '200806361'
'2022': '200806365'
'2023': '200806368'
'2024': '200806373'
'2025': '200806455'
'2026': '200806634'
'2027': '200806668'
'2028': '200806736'
'2029': '200806769'
'2030': '200806842'
'2031': '200806896'
'2032': '200806977'
'2033': '200807044'
'2034': '200807051'
'2035': '200807066'
'2036': '200807067'
'2037': '200807068'
'2038': '200807203'
'2039': '200807204'
'2040': '200807205'
'2041': '200807208'
'2042': '200807210'
'2043': '200807211'
'2044': '200807223'
'2045': '200807229'
'2046': '200807230'
'2047': '200807253'
'2048': '200807310'
'2049': '200807361'
'2050': '200807363'
'2051': '200807365'
'2052': '200807367'
'2053': '200807374'
'2054': '200807377'
'2055': '200807391'
'2056': '200807418'
'2057': '200807430'
'2058': '200807431'
'2059': '200807469'
'2060': '200807526'
'2061': '200807527'
'2062': '200807528'
'2063': '200807539'
'2064': '200807552'
'2065': '200807582'
'2066': '200807617'
'2067': '200807618'
'2068': '200807633'
'2069': '200807683'
'2070': '200807684'
'2071': '200807685'
'2072': '200807813'
'2073': '200807814'
'2074': '200807945'
'2075': '200807949'
'2076': '200807985'
'2077': '200807986'
'2078': '200807989'
'2079': '200808076'
'2080': '200808078'
'2081': '200808091'
'2082': '200808126'
'2083': '200808127'
'2084': '200808195'
'2085': '200808219'
'2086': '200808244'
'2087': '200808245'
'2088': '200808272'
'2089': '200808273'
'2090': '200808309'
'2091': '200808362'
'2092': '200808377'
'2093': '200808511'
'2094': '200808562'
'2095': '200808715'
'2096': '200808774'
'2097': '200808790'
'2098': '200808828'
'2099': '200808862'
'2100': '200808985'
'2101': '200809045'
'2102': '200809058'
'2103': '200809076'
'2104': '200809079'
'2105': '200809084'
'2106': '200809185'
'2107': '200809207'
'2108': '200809208'
'2109': '200809240'
'2110': '200809258'
'2111': '200809388'
'2112': '200809402'
'2113': '200809403'
'2114': '200809464'
'2115': '200809649'
'2116': '200809791'
'2117': '200809813'
'2118': '200809818'
'2119': '200809819'
'2120': '200809825'
'2121': '200809902'
'2122': '200809909'
'2123': '200809910'
'2124': '200810003'
'2125': '200810004'
'2126': '200810005'
'2127': '200810006'
'2128': '200810031'
'2129': '200810113'
'2130': '200810114'
'2131': '200810125'
'2132': '200810237'
'2133': '200810314'
'2134': '200810320'
'2135': '200810340'
'2136': '200810424'
'2137': '200810425'
'2138': '200810427'
'2139': '200810440'
'2140': '200810513'
'2141': '200810517'
'2142': '200810584'
'2143': '200810700'
'2144': '200810702'
'2145': '200810703'
'2146': '200810727'
'2147': '200810760'
'2148': '200810870'
'2149': '200810940'
'2150': '200810973'
'2151': '200810981'
'2152': '200811250'
'2153': '200811251'
'2154': '200811253'
'2155': '200811262'
'2156': '200811364'
'2157': '200811406'
'2158': '200811564'
'2159': '200811608'
'2160': '200811623'
'2161': '200811629'
'2162': '200811701'
'2163': '200811736'
'2164': '200811814'
'2165': '200811885'
'2166': '200900194'
'2167': '200900196'
'2168': '200900341'
'2169': '200900606'
'2170': '200900668'
'2171': '200900671'
'2172': '200900674'
'2173': '200900767'
'2174': '200900878'
'2175': '200900889'
'2176': '200900892'
'2177': '200900895'
'2178': '200900897'
'2179': '200900899'
'2180': '200900967'
'2181': '200900997'
'2182': '200901007'
'2183': '200901073'
'2184': '200901207'
'2185': '200901232'
'2186': '200901456'
'2187': '200901507'
'2188': '200901536'
'2189': '200901544'
'2190': '200901619'
'2191': '200901817'
'2192': '200902042'
'2193': '200902080'
'2194': '200902207'
'2195': '200902213'
'2196': '200902281'
'2197': '200902301'
'2198': '200902443'
'2199': '200902507'
'2200': '200902537'
'2201': '200903041'
'2202': '200903043'
'2203': '200903115'
'2204': '200903125'
'2205': '200903409'
'2206': '200903782'
'2207': '200903801'
'2208': '200903974'
'2209': '200904162'
'2210': '200904163'
'2211': '200904234'
'2212': '200904308'
'2213': '200904325'
'2214': '200904514'
'2215': '200904538'
'2216': '200904548'
'2217': '200904649'
'2218': '200904678'
'2219': '200904689'
'2220': '200904855'
'2221': '200904880'
'2222': '200904881'
'2223': '200904990'
'2224': '200905004'
'2225': '200905017'
'2226': '200905053'
'2227': '200905055'
'2228': '200905151'
'2229': '200905163'
'2230': '200905196'
'2231': '200905218'
'2232': '200905315'
'2233': '200905403'
'2234': '200905653'
'2235': '200905876'
'2236': '200905938'
'2237': '200905939'
'2238': '200906073'
'2239': '200906330'
'2240': '200906384'
'2241': '200906557'
'2242': '200906562'
'2243': '200906578'
'2244': '200906599'
'2245': '200906602'
'2246': '200906966'
'2247': '200907093'
'2248': '200907385'
'2249': '200907446'
'2250': '200907725'
'2251': '200908116'
'2252': '200908185'
'2253': '200908186'
'2254': '200908333'
'2255': '200908369'
'2256': '200908478'
'2257': '200908479'
'2258': '200908781'
'2259': '200908817'
'2260': '200908819'
'2261': '200908825'
'2262': '200908953'
'2263': '200909377'
'2264': '201000300'
'2265': '201000406'
'2266': '201000637'
'2267': '201000674'
'2268': '201000826'
'2269': '201000869'
'2270': '201000874'
'2271': '201000875'
'2272': '201000877'
'2273': '201000878'
'2274': '201000951'
'2275': '201000963'
'2276': '201000967'
'2277': '201000972'
'2278': '201000974'
'2279': '201000975'
'2280': '201000977'
'2281': '201000980'
'2282': '201000981'
'2283': '201000982'
'2284': '201000985'
'2285': '201000989'
'2286': '201000993'
'2287': '201000994'
'2288': '201000998'
'2289': '201000999'
'2290': '201001001'
'2291': '201001003'
'2292': '201001004'
'2293': '201001005'
'2294': '201001006'
'2295': '201001007'
'2296': '201001008'
'2297': '201001013'
'2298': '201001017'
'2299': '201001018'
'2300': '201001021'
'2301': '201001022'
'2302': '201001023'
'2303': '201001024'
'2304': '201001057'
'2305': '201001424'
'2306': '201001547'
'2307': '201001640'
'2308': '201001656'
'2309': '201001682'
'2310': '201001683'
'2311': '201001685'
'2312': '201001699'
'2313': '201001707'
'2314': '201001723'
'2315': '201001731'
'2316': '201001744'
'2317': '201002151'
'2318': '201002277'
'2319': '201002395'
'2320': '201002396'
'2321': '201002402'
'2322': '201002449'
'2323': '201002450'
'2324': '201002503'
'2325': '201003043'
'2326': '201003049'
'2327': '201003203'
'2328': '201003206'
'2329': '201003207'
'2330': '201003213'
'2331': '201003370'
'2332': '201003397'
'2333': '201003398'
'2334': '201003713'
'2335': '201004170'
'2336': '201004204'
'2337': '201004230'
'2338': '201004257'
'2339': '201004440'
'2340': '201004538'
'2341': '201004680'
'2342': '201004693'
'2343': '201004700'
'2344': '201004997'
'2345': '201005059'
'2346': '201005070'
'2347': '201005121'
'2348': '201005235'
'2349': '201005236'
'2350': '201005685'
'2351': '201005699'
'2352': '201005763'
'2353': '201005770'
'2354': '201005771'
'2355': '201005774'
'2356': '201005775'
'2357': '201005841'
'2358': '201006075'
'2359': '201006077'
'2360': '201006120'
'2361': '201006205'
'2362': '201006206'
'2363': '201006211'
'2364': '201006442'
'2365': '201006443'
'2366': '201006495'
'2367': '201006592'
'2368': '201006784'
'2369': '201006870'
'2370': '201006871'
'2371': '201007233'
'2372': '201007234'
'2373': '201007276'
'2374': '201007277'
'2375': '201007281'
'2376': '201007401'
'2377': '201007460'
'2378': '201007499'
'2379': '201007523'
'2380': '201007529'
'2381': '201007569'
'2382': '201007652'
'2383': '201007672'
'2384': '201007708'
'2385': '201007750'
'2386': '201007774'
'2387': '201007782'
'2388': '201007783'
'2389': '201100026'
'2390': '201100231'
'2391': '201100273'
'2392': '201100299'
'2393': '201100375'
'2394': '201100467'
'2395': '201100491'
'2396': '201100500'
'2397': '201100502'
'2398': '201100572'
'2399': '201100792'
'2400': '201100793'
'2401': '201100794'
'2402': '201100795'
'2403': '201100797'
'2404': '201100798'
'2405': '201100799'
'2406': '201100800'
'2407': '201100801'
'2408': '201100802'
'2409': '201100821'
'2410': '201100826'
'2411': '201100827'
'2412': '201100828'
'2413': '201100866'
'2414': '201100867'
'2415': '201100869'
'2416': '201100888'
'2417': '201100889'
'2418': '201100894'
'2419': '201100898'
'2420': '201100900'
'2421': '201100901'
'2422': '201100902'
'2423': '201100904'
'2424': '201100905'
'2425': '201100906'
'2426': '201100908'
'2427': '201100911'
'2428': '201100913'
'2429': '201100945'
'2430': '201100946'
'2431': '201101004'
'2432': '201101014'
'2433': '201101022'
'2434': '201101038'
'2435': '201101640'
'2436': '201101643'
'2437': '201101644'
'2438': '201101756'
'2439': '201101761'
'2440': '201101840'
'2441': '201101843'
'2442': '201101844'
'2443': '201101845'
'2444': '201101846'
'2445': '201101847'
'2446': '201101857'
'2447': '201101860'
'2448': '201101861'
'2449': '201101884'
'2450': '201101885'
'2451': '201102450'
'2452': '201102476'
'2453': '201102477'
'2454': '201102757'
'2455': '201102767'
'2456': '201102768'
'2457': '201102769'
'2458': '201102784'
'2459': '201103159'
'2460': '201103161'
'2461': '201103324'
'2462': '201103422'
'2463': '201103424'
'2464': '201103425'
'2465': '201103468'
'2466': '201103469'
'2467': '201103472'
'2468': '201103475'
'2469': '201103563'
'2470': '201103609'
'2471': '201103615'
'2472': '201103617'
'2473': '201103909'
'2474': '201103986'
'2475': '201104026'
'2476': '201104041'
'2477': '201104062'
'2478': '201104063'
'2479': '201104066'
'2480': '201104111'
'2481': '201104471'
'2482': '201104754'
'2483': '201104755'
'2484': '201104801'
'2485': '201105016'
'2486': '201105106'
'2487': '201105143'
'2488': '201105144'
'2489': '201105270'
'2490': '201105412'
'2491': '201105413'
'2492': '201105484'
'2493': '201105487'
'2494': '201105488'
'2495': '201105600'
'2496': '201105697'
'2497': '201105756'
'2498': '201105914'
'2499': '201105915'
'2500': '201105918'
'2501': '201106145'
'2502': '201106366'
'2503': '201106390'
'2504': '201106781'
'2505': '201106782'
'2506': '201106947'
'2507': '201106949'
'2508': '201106952'
'2509': '201106953'
'2510': '201107002'
'2511': '201107176'
'2512': '201107199'
'2513': '201107201'
'2514': '201107219'
'2515': '201107220'
'2516': '201107224'
'2517': '201107229'
'2518': '201107233'
'2519': '201107234'
'2520': '201107272'
'2521': '201107273'
'2522': '201107290'
'2523': '201107503'
'2524': '201107505'
'2525': '201107507'
'2526': '201107509'
'2527': '201107512'
'2528': '201107513'
'2529': '201107515'
'2530': '201107516'
'2531': '201107525'
'2532': '201107526'
'2533': '201107530'
'2534': '201107536'
'2535': '201107539'
'2536': '201107542'
'2537': '201107543'
'2538': '201108989'
'2539': '201108990'
'2540': '201109024'
'2541': '201109030'
'2542': '201109142'
'2543': '201109150'
'2544': '201109151'
'2545': '201109154'
'2546': '201109155'
'2547': '201109222'
'2548': '201109223'
'2549': '201109224'
'2550': '201109225'
'2551': '201109227'
'2552': '201109228'
'2553': '201109231'
'2554': '201109232'
'2555': '201109259'
'2556': '201109260'
'2557': '201109276'
'2558': '201109277'
'2559': '201109291'
'2560': '201109296'
'2561': '201109309'
'2562': '201109310'
'2563': '201109313'
'2564': '201109442'
'2565': '201109514'
'2566': '201109733'
'2567': '201109818'
'2568': '201110023'
'2569': '201110095'
'2570': '201110136'
'2571': '201110192'
'2572': '201110292'
'2573': '201110398'
'2574': '201110512'
'2575': '201110516'
'2576': '201110646'
'2577': '201111149'
'2578': '201112194'
'2579': '201112195'
'2580': '201200003'
'2581': '201200004'
'2582': '201200009'
'2583': '201200186'
'2584': '201200204'
'2585': '201200246'
'2586': '201200277'
'2587': '201200586'
'2588': '201200603'
'2589': '201200635'
'2590': '201200636'
'2591': '201200678'
'2592': '201200717'
'2593': '201200854'
'2594': '201200930'
'2595': '201200975'
'2596': '201201166'
'2597': '201201261'
'2598': '201201265'
'2599': '201201601'
'2600': '201201602'
'2601': '201201680'
'2602': '201201690'
'2603': '201201693'
'2604': '201201694'
'2605': '201201837'
'2606': '201202398'
'2607': '201202780'
'2608': '201202801'
'2609': '201202902'
'2610': '201203127'
'2611': '201203128'
'2612': '201203513'
'2613': '201203514'
'2614': '201203607'
'2615': '201203608'
'2616': '201203744'
'2617': '201203745'
'2618': '201203928'
'2619': '201204330'
'2620': '201204389'
'2621': '201204555'
'2622': '201204813'
'2623': '201204970'
'2624': '201204971'
'2625': '201204975'
'2626': '201205043'
'2627': '201205150'
'2628': '201205250'
'2629': '201205252'
'2630': '201205253'
'2631': '201205255'
'2632': '201205261'
'2633': '201205262'
'2634': '201205263'
'2635': '201205266'
'2636': '201205414'
'2637': '201205415'
'2638': '201205623'
'2639': '201205628'
'2640': '201205653'
'2641': '201205654'
'2642': '201205825'
'2643': '201205826'
'2644': '201205827'
'2645': '201205828'
'2646': '201205829'
'2647': '201205833'
'2648': '201205930'
'2649': '201205939'
'2650': '201205942'
'2651': '201206020'
'2652': '201206056'
'2653': '201206160'
'2654': '201206161'
'2655': '201206162'
'2656': '201206163'
'2657': '201206166'
'2658': '201206176'
'2659': '201206201'
'2660': '201206205'
'2661': '201206250'
'2662': '201206297'
'2663': '201206327'
'2664': '201206328'
'2665': '201206338'
'2666': '201206403'
'2667': '201206410'
'2668': '201206435'
'2669': '201206489'
'2670': '201206493'
'2671': '201206494'
'2672': '201206499'
'2673': '201206540'
'2674': '201206552'
'2675': '201206553'
'2676': '201206575'
'2677': '201206612'
'2678': '201206613'
'2679': '201206667'
'2680': '201206685'
'2681': '201206704'
'2682': '201206741'
'2683': '201206751'
'2684': '201206760'
'2685': '201206761'
'2686': '201206776'
'2687': '201206804'
'2688': '201206805'
'2689': '201206831'
'2690': '201206844'
'2691': '201206846'
'2692': '201206856'
'2693': '201206857'
'2694': '201206858'
'2695': '201206870'
'2696': '201206871'
'2697': '201206872'
'2698': '201206877'
'2699': '201206904'
'2700': '201206905'
'2701': '201206916'
'2702': '201206934'
'2703': '201206935'
'2704': '201206936'
'2705': '201206953'
'2706': '201206954'
'2707': '201207002'
'2708': '201207003'
'2709': '201207004'
'2710': '201207009'
'2711': '201207014'
'2712': '201207015'
'2713': '201207061'
'2714': '201207067'
'2715': '201207105'
'2716': '201207217'
'2717': '201207236'
'2718': '201207292'
'2719': '201207294'
'2720': '201207300'
'2721': '201207301'
'2722': '201207402'
'2723': '201207403'
'2724': '201207404'
'2725': '201207405'
'2726': '201207417'
'2727': '201207453'
'2728': '201207459'
'2729': '201207461'
'2730': '201207469'
'2731': '201207486'
'2732': '201207488'
'2733': '201207513'
'2734': '201207516'
'2735': '201207517'
'2736': '201207537'
'2737': '201207538'
'2738': '201207539'
'2739': '201207540'
'2740': '201207541'
'2741': '201207575'
'2742': '201207577'
'2743': '201207586'
'2744': '201207589'
'2745': '201207592'
'2746': '201207593'
'2747': '201207595'
'2748': '201207596'
'2749': '201207597'
'2750': '201207688'
'2751': '201207721'
'2752': '201207722'
'2753': '201208078'
'2754': '201208080'
'2755': '201208081'
'2756': '201208110'
'2757': '201208193'
'2758': '201208256'
'2759': '201208462'
'2760': '201208467'
'2761': '201208480'
'2762': '201208482'
'2763': '201208483'
'2764': '201208484'
'2765': '201208518'
'2766': '201208629'
'2767': '201208630'
'2768': '201208632'
'2769': '201208643'
'2770': '201208653'
'2771': '201208654'
'2772': '201208655'
'2773': '201208723'
'2774': '201208740'
'2775': '201208753'
'2776': '201208754'
'2777': '201208855'
'2778': '201208875'
'2779': '201209444'
'2780': '201209757'
'2781': '201210163'
'2782': '201210185'
'2783': '201210187'
'2784': '201210235'
'2785': '201210240'
'2786': '201210744'
'2787': '201211055'
'2788': '201211103'
'2789': '201211564'
'2790': '201300114'
'2791': '201300128'
'2792': '201300139'
'2793': '201300148'
'2794': '201300152'
'2795': '201301236'
'2796': '201301369'
'2797': '201301377'
'2798': '201301498'
'2799': '201301586'
'2800': '201301591'
'2801': '201301621'
'2802': '201301656'
'2803': '201302165'
'2804': '201302169'
'2805': '201302260'
'2806': '201302390'
'2807': '201302618'
'2808': '201302619'
'2809': '201302802'
'2810': '201302936'
'2811': '201302948'
'2812': '201302980'
'2813': '201302982'
'2814': '201302990'
'2815': '201303029'
'2816': '201303030'
'2817': '201303035'
'2818': '201303045'
'2819': '201303269'
'2820': '201304289'
'2821': '201304386'
'2822': '201305008'
'2823': '201305030'
'2824': '201305371'
'2825': '201305403'
'2826': '201305533'
'2827': '201305813'
'2828': '201305827'
'2829': '201305832'
'2830': '201306036'
'2831': '201306176'
'2832': '201306203'
'2833': '201306230'
'2834': '201306262'
'2835': '201306264'
'2836': '201306277'
'2837': '201306289'
'2838': '201306315'
'2839': '201306327'
'2840': '201306328'
'2841': '201306329'
'2842': '201306340'
'2843': '201306344'
'2844': '201306352'
'2845': '201306362'
'2846': '201306363'
'2847': '201306366'
'2848': '201306367'
'2849': '201306368'
'2850': '201306369'
'2851': '201306370'
'2852': '201306376'
'2853': '201306377'
'2854': '201306379'
'2855': '201306383'
'2856': '201306385'
'2857': '201306386'
'2858': '201306404'
'2859': '201306407'
'2860': '201306412'
'2861': '201306419'
'2862': '201306425'
'2863': '201306452'
'2864': '201306453'
'2865': '201306454'
'2866': '201306455'
'2867': '201306549'
'2868': '201306824'
'2869': '201306917'
'2870': '201306922'
'2871': '201306942'
'2872': '201306954'
'2873': '201306969'
'2874': '201306990'
'2875': '201307038'
'2876': '201307042'
'2877': '201307062'
'2878': '201307079'
'2879': '201307092'
'2880': '201307108'
'2881': '201307118'
'2882': '201307120'
'2883': '201307121'
'2884': '201307123'
'2885': '201307124'
'2886': '201307131'
'2887': '201307132'
'2888': '201307149'
'2889': '201307158'
'2890': '201307209'
'2891': '201307243'
'2892': '201307261'
'2893': '201307290'
'2894': '201307342'
'2895': '201307357'
'2896': '201307377'
'2897': '201307379'
'2898': '201307416'
'2899': '201307449'
'2900': '201307476'
'2901': '201307484'
'2902': '201307514'
'2903': '201307515'
'2904': '201307539'
'2905': '201307558'
'2906': '201307559'
'2907': '201307562'
'2908': '201307567'
'2909': '201307570'
'2910': '201307607'
'2911': '201307655'
'2912': '201307682'
'2913': '201307687'
'2914': '201307725'
'2915': '201307726'
'2916': '201307767'
'2917': '201307807'
'2918': '201307881'
'2919': '201307882'
'2920': '201307888'
'2921': '201307896'
'2922': '201307904'
'2923': '201307925'
'2924': '201307926'
'2925': '201307927'
'2926': '201307936'
'2927': '201307937'
'2928': '201307947'
'2929': '201307988'
'2930': '201308005'
'2931': '201308053'
'2932': '201308062'
'2933': '201308067'
'2934': '201308099'
'2935': '201308195'
'2936': '201308197'
'2937': '201308209'
'2938': '201308223'
'2939': '201308236'
'2940': '201308242'
'2941': '201308278'
'2942': '201308287'
'2943': '201308288'
'2944': '201308289'
'2945': '201308295'
'2946': '201308303'
'2947': '201308368'
'2948': '201308371'
'2949': '201308398'
'2950': '201308399'
'2951': '201308416'
'2952': '201308434'
'2953': '201308448'
'2954': '201308450'
'2955': '201308451'
'2956': '201308457'
'2957': '201308458'
'2958': '201308459'
'2959': '201308460'
'2960': '201308461'
'2961': '201308462'
'2962': '201308463'
'2963': '201308464'
'2964': '201308466'
'2965': '201308467'
'2966': '201308468'
'2967': '201308469'
'2968': '201308470'
'2969': '201308476'
'2970': '201308478'
'2971': '201308479'
'2972': '201308480'
'2973': '201308481'
'2974': '201308483'
'2975': '201308485'
'2976': '201308488'
'2977': '201308489'
'2978': '201308490'
'2979': '201308494'
'2980': '201308495'
'2981': '201308496'
'2982': '201308500'
'2983': '201308502'
'2984': '201308504'
'2985': '201308506'
'2986': '201308509'
'2987': '201308524'
'2988': '201308525'
'2989': '201308526'
'2990': '201308537'
'2991': '201308538'
'2992': '201308539'
'2993': '201308540'
'2994': '201308541'
'2995': '201308550'
'2996': '201308552'
'2997': '201308553'
'2998': '201308564'
'2999': '201308566'
'3000': '201308567'
'3001': '201308573'
'3002': '201308574'
'3003': '201308589'
'3004': '201308613'
'3005': '201308626'
'3006': '201308651'
'3007': '201308652'
'3008': '201308671'
'3009': '201308712'
'3010': '201308718'
'3011': '201308824'
'3012': '201308859'
'3013': '201308895'
'3014': '201308906'
'3015': '201308923'
'3016': '201308924'
'3017': '201308926'
'3018': '201308928'
'3019': '201308943'
'3020': '201308977'
'3021': '201309019'
'3022': '201309044'
'3023': '201309067'
'3024': '201309068'
'3025': '201309070'
'3026': '201309071'
'3027': '201309088'
'3028': '201309092'
'3029': '201309126'
'3030': '201309133'
'3031': '201309139'
'3032': '201309145'
'3033': '201309146'
'3034': '201309164'
'3035': '201309176'
'3036': '201309180'
'3037': '201309184'
'3038': '201309266'
'3039': '201309269'
'3040': '201309336'
'3041': '201309360'
'3042': '201309384'
'3043': '201309416'
'3044': '201309417'
'3045': '201309418'
'3046': '201309425'
'3047': '201309444'
'3048': '201309449'
'3049': '201309460'
'3050': '201309480'
'3051': '201309481'
'3052': '201309484'
'3053': '201309488'
'3054': '201309494'
'3055': '201309539'
'3056': '201309566'
'3057': '201309576'
'3058': '201309599'
'3059': '201309682'
'3060': '201309684'
'3061': '201309738'
'3062': '201309741'
'3063': '201309743'
'3064': '201309744'
'3065': '201309809'
'3066': '201309814'
'3067': '201309848'
'3068': '201309850'
'3069': '201309883'
'3070': '201309888'
'3071': '201309895'
'3072': '201309896'
'3073': '201309897'
'3074': '201309926'
'3075': '201309959'
'3076': '201309963'
'3077': '201309964'
'3078': '201309973'
'3079': '201309994'
'3080': '201310000'
'3081': '201310013'
'3082': '201310206'
'3083': '201310293'
'3084': '201310300'
'3085': '201310318'
'3086': '201310334'
'3087': '201310348'
'3088': '201310352'
'3089': '201310361'
'3090': '201310362'
'3091': '201310380'
'3092': '201310381'
'3093': '201310382'
'3094': '201310387'
'3095': '201310393'
'3096': '201310399'
'3097': '201310402'
'3098': '201310409'
'3099': '201310587'
'3100': '201310588'
'3101': '201310589'
'3102': '201310590'
'3103': '201310619'
'3104': '201310620'
'3105': '201310720'
'3106': '201310742'
'3107': '201310756'
'3108': '201310764'
'3109': '201310777'
'3110': '201310780'
'3111': '201310781'
'3112': '201310782'
'3113': '201310783'
'3114': '201310785'
'3115': '201310797'
'3116': '201310798'
'3117': '201310820'
'3118': '201310826'
'3119': '201310830'
'3120': '201310841'
'3121': '201310842'
'3122': '201310869'
'3123': '201310895'
'3124': '201310896'
'3125': '201310897'
'3126': '201310931'
'3127': '201310935'
'3128': '201310964'
'3129': '201310977'
'3130': '201310978'
'3131': '201310991'
'3132': '201400024'
'3133': '201400053'
'3134': '201400099'
'3135': '201400118'
'3136': '201400120'
'3137': '201400193'
'3138': '201400200'
'3139': '201400262'
'3140': '201400286'
'3141': '201400288'
'3142': '201400289'
'3143': '201400290'
'3144': '201400293'
'3145': '201400337'
'3146': '201400352'
'3147': '201400366'
'3148': '201400367'
'3149': '201400372'
'3150': '201400381'
'3151': '201400382'
'3152': '201400385'
'3153': '201400386'
'3154': '201400387'
'3155': '201400392'
'3156': '201400393'
'3157': '201400409'
'3158': '201400410'
'3159': '201400422'
'3160': '201400426'
'3161': '201400429'
'3162': '201400433'
'3163': '201400434'
'3164': '201400435'
'3165': '201400438'
'3166': '201400451'
'3167': '201400452'
'3168': '201400493'
'3169': '201400497'
'3170': '201400537'
'3171': '201400538'
'3172': '201400681'
'3173': '201400706'
'3174': '201400757'
'3175': '201400771'
'3176': '201400785'
'3177': '201400804'
'3178': '201400828'
'3179': '201400834'
'3180': '201400842'
'3181': '201400873'
'3182': '201400918'
'3183': '201400931'
'3184': '201400932'
'3185': '201400933'
'3186': '201400980'
'3187': '201401034'
'3188': '201401057'
'3189': '201401098'
'3190': '201401129'
'3191': '201401226'
'3192': '201401227'
'3193': '201401235'
'3194': '201401334'
'3195': '201401343'
'3196': '201401344'
'3197': '201401372'
'3198': '201401376'
'3199': '201401417'
'3200': '201401456'
'3201': '201401475'
'3202': '201401487'
'3203': '201401489'
'3204': '201401490'
'3205': '201401518'
'3206': '201401569'
'3207': '201401591'
'3208': '201401625'
'3209': '201401626'
'3210': '201401730'
'3211': '201401871'
'3212': '201401904'
'3213': '201401921'
'3214': '201401923'
'3215': '201401937'
'3216': '201401965'
'3217': '201401966'
'3218': '201401984'
'3219': '201401985'
'3220': '201401986'
'3221': '201401996'
'3222': '201402039'
'3223': '201402056'
'3224': '201402065'
'3225': '201402070'
'3226': '201402071'
'3227': '201402074'
'3228': '201402137'
'3229': '201402148'
'3230': '201402159'
'3231': '201402185'
'3232': '201402206'
'3233': '201402245'
'3234': '201402272'
'3235': '201402276'
'3236': '201402309'
'3237': '201402414'
'3238': '201402416'
'3239': '201402427'
'3240': '201402435'
'3241': '201402436'
'3242': '201402450'
'3243': '201402463'
'3244': '201402464'
'3245': '201402560'
'3246': '201402579'
'3247': '201402641'
'3248': '201402642'
'3249': '201402652'
'3250': '201402682'
'3251': '201402707'
'3252': '201402711'
'3253': '201402714'
'3254': '201402733'
'3255': '201402734'
'3256': '201402804'
'3257': '201402806'
'3258': '201402822'
'3259': '201402828'
'3260': '201402829'
'3261': '201402850'
'3262': '201402856'
'3263': '201402864'
'3264': '201402865'
'3265': '201402866'
'3266': '201402868'
'3267': '201402869'
'3268': '201402875'
'3269': '201402880'
'3270': '201402890'
'3271': '201402909'
'3272': '201402912'
'3273': '201402913'
'3274': '201402936'
'3275': '201402997'
'3276': '201403012'
'3277': '201403023'
'3278': '201403026'
'3279': '201403029'
'3280': '201403031'
'3281': '201403051'
'3282': '201403070'
'3283': '201403088'
'3284': '201403118'
'3285': '201403126'
'3286': '201403127'
'3287': '201403146'
'3288': '201403148'
'3289': '201403152'
'3290': '201403184'
'3291': '201403185'
'3292': '201403217'
'3293': '201403243'
'3294': '201403253'
'3295': '201403298'
'3296': '201403332'
'3297': '201403337'
'3298': '201403380'
'3299': '201403382'
'3300': '201403388'
'3301': '201403389'
'3302': '201403391'
'3303': '201403398'
'3304': '201403407'
'3305': '201403408'
'3306': '201403417'
'3307': '201403429'
'3308': '201403455'
'3309': '201403456'
'3310': '201403457'
'3311': '201403497'
'3312': '201403501'
'3313': '201403518'
'3314': '201403519'
'3315': '201403533'
'3316': '201403537'
'3317': '201403543'
'3318': '201403550'
'3319': '201403559'
'3320': '201403560'
'3321': '201403567'
'3322': '201403570'
'3323': '201403571'
'3324': '201403572'
'3325': '201403597'
'3326': '201403598'
'3327': '201403617'
'3328': '201403627'
'3329': '201403650'
'3330': '201403692'
'3331': '201403693'
'3332': '201403694'
'3333': '201403697'
'3334': '201403698'
'3335': '201403726'
'3336': '201403732'
'3337': '201403734'
'3338': '201403739'
'3339': '201403797'
'3340': '201403816'
'3341': '201403819'
'3342': '201403820'
'3343': '201403826'
'3344': '201403833'
'3345': '201403870'
'3346': '201403877'
'3347': '201403880'
'3348': '201403884'
'3349': '201403886'
'3350': '201403889'
'3351': '201403891'
'3352': '201403892'
'3353': '201403894'
'3354': '201403919'
'3355': '201403930'
'3356': '201403939'
'3357': '201403943'
'3358': '201403944'
'3359': '201403945'
'3360': '201403947'
'3361': '201403952'
'3362': '201403955'
'3363': '201403957'
'3364': '201403967'
'3365': '201403975'
'3366': '201403983'
'3367': '201404005'
'3368': '201404006'
'3369': '201404008'
'3370': '201404009'
'3371': '201404010'
'3372': '201404013'
'3373': '201404014'
'3374': '201404015'
'3375': '201404016'
'3376': '201404026'
'3377': '201404035'
'3378': '201404036'
'3379': '201404038'
'3380': '201404042'
'3381': '201404043'
'3382': '201404088'
'3383': '201404093'
'3384': '201404114'
'3385': '201404115'
'3386': '201404116'
'3387': '201404136'
'3388': '201404162'
'3389': '201404163'
'3390': '201404168'
'3391': '201404170'
'3392': '201404198'
'3393': '201404200'
'3394': '201404206'
'3395': '201404215'
'3396': '201404239'
'3397': '201404271'
'3398': '201404287'
'3399': '201404293'
'3400': '201404299'
'3401': '201404316'
'3402': '201404327'
'3403': '201404340'
'3404': '201404342'
'3405': '201404343'
'3406': '201404377'
'3407': '201404400'
'3408': '201404403'
'3409': '201404406'
'3410': '201404415'
'3411': '201404417'
'3412': '201404424'
'3413': '201404425'
'3414': '201404426'
'3415': '201404441'
'3416': '201404454'
'3417': '201404456'
'3418': '201404458'
'3419': '201404483'
'3420': '201404486'
'3421': '201404487'
'3422': '201404488'
'3423': '201404497'
'3424': '201404513'
'3425': '201404527'
'3426': '201404528'
'3427': '201404537'
'3428': '201404538'
'3429': '201404539'
'3430': '201404541'
'3431': '201404566'
'3432': '201404569'
'3433': '201404590'
'3434': '201404591'
'3435': '201404592'
'3436': '201404593'
'3437': '201404595'
'3438': '201404596'
'3439': '201404597'
'3440': '201404633'
'3441': '201404634'
'3442': '201404644'
'3443': '201404654'
'3444': '201404664'
'3445': '201404677'
'3446': '201404678'
'3447': '201404689'
'3448': '201404690'
'3449': '201404696'
'3450': '201404714'
'3451': '201404715'
'3452': '201404716'
'3453': '201404731'
'3454': '201404732'
'3455': '201404733'
'3456': '201404741'
'3457': '201404786'
'3458': '201404800'
'3459': '201404801'
'3460': '201404824'
'3461': '201404836'
'3462': '201404857'
'3463': '201404863'
'3464': '201404889'
'3465': '201404928'
'3466': '201404929'
'3467': '201404930'
'3468': '201404976'
'3469': '201404981'
'3470': '201404983'
'3471': '201404986'
'3472': '201404993'
'3473': '201404994'
'3474': '201404995'
'3475': '201405000'
'3476': '201405003'
'3477': '201405010'
'3478': '201405014'
'3479': '201405026'
'3480': '201405027'
'3481': '201405033'
'3482': '201405042'
'3483': '201405043'
'3484': '201405044'
'3485': '201405045'
'3486': '201405046'
'3487': '201405050'
'3488': '201405051'
'3489': '201405052'
'3490': '201405063'
'3491': '201405073'
'3492': '201405078'
'3493': '201405079'
'3494': '201405080'
'3495': '201405094'
'3496': '201405096'
'3497': '201405100'
'3498': '201405103'
'3499': '201405104'
'3500': '201405107'
'3501': '201405111'
'3502': '201405112'
'3503': '201405113'
'3504': '201405114'
'3505': '201405130'
'3506': '201405131'
'3507': '201405132'
'3508': '201405175'
'3509': '201405177'
'3510': '201405232'
'3511': '201405233'
'3512': '201405262'
'3513': '201405282'
'3514': '201405290'
'3515': '201405347'
'3516': '201405387'
'3517': '201405424'
'3518': '201405425'
'3519': '201405434'
'3520': '201405436'
'3521': '201405439'
'3522': '201405449'
'3523': '201405450'
'3524': '201405454'
'3525': '201405464'
'3526': '201405467'
'3527': '201405468'
'3528': '201405469'
'3529': '201405482'
'3530': '201405502'
'3531': '201405503'
'3532': '201405504'
'3533': '201405519'
'3534': '201405520'
'3535': '201405531'
'3536': '201405585'
'3537': '201405586'
'3538': '201405598'
'3539': '201405610'
'3540': '201405615'
'3541': '201405693'
'3542': '201405708'
'3543': '201405813'
'3544': '201405839'
'3545': '201405840'
'3546': '201405841'
'3547': '201405844'
'3548': '201405857'
'3549': '201405865'
'3550': '201405882'
'3551': '201405921'
'3552': '201405930'
'3553': '201405956'
'3554': '201405971'
'3555': '201405995'
'3556': '201406030'
'3557': '201406032'
'3558': '201406033'
'3559': '201406046'
'3560': '201406102'
'3561': '201406125'
'3562': '201406126'
'3563': '201406140'
'3564': '201406156'
'3565': '201406161'
'3566': '201406170'
'3567': '201406171'
'3568': '201406179'
'3569': '201406315'
'3570': '201500025'
'3571': '201500081'
'3572': '201500082'
'3573': '201500083'
'3574': '201500099'
'3575': '201500101'
'3576': '201500107'
'3577': '201500114'
'3578': '201500127'
'3579': '201500145'
'3580': '201500149'
'3581': '201500168'
'3582': '201500169'
'3583': '201500171'
'3584': '201500179'
'3585': '201500233'
'3586': '201500293'
'3587': '201500313'
'3588': '201500364'
'3589': '201500365'
'3590': '201500366'
'3591': '201500367'
'3592': '201500372'
'3593': '201500387'
'3594': '201500401'
'3595': '201500429'
'3596': '201500450'
'3597': '201500458'
'3598': '201500483'
'3599': '201500509'
'3600': '201500516'
'3601': '201500517'
'3602': '201500521'
'3603': '201500522'
'3604': '201500530'
'3605': '201500554'
'3606': '201500645'
'3607': '201500650'
'3608': '201500694'
'3609': '201500722'
'3610': '201500725'
'3611': '201500728'
'3612': '201500731'
'3613': '201500852'
'3614': '201500856'
'3615': '201500902'
'3616': '201500903'
'3617': '201500929'
'3618': '201500948'
'3619': '201500959'
'3620': '201500963'
'3621': '201500964'
'3622': '201500965'
'3623': '201500966'
'3624': '201500967'
'3625': '201500969'
'3626': '201500972'
'3627': '201500982'
'3628': '201501074'
'3629': '201501083'
'3630': '201501128'
'3631': '201501207'
'3632': '201501216'
'3633': '201501270'
'3634': '201501274'
'3635': '201501307'
'3636': '201501322'
'3637': '201501325'
'3638': '201501350'
'3639': '201501441'
'3640': '201501446'
'3641': '201501476'
'3642': '201501488'
'3643': '201501494'
'3644': '201501500'
'3645': '201501501'
'3646': '201501503'
'3647': '201501539'
'3648': '201501540'
'3649': '201501548'
'3650': '201501550'
'3651': '201501555'
'3652': '201501556'
'3653': '201501557'
'3654': '201501569'
'3655': '201501592'
'3656': '201501595'
'3657': '201501605'
'3658': '201501608'
'3659': '201501609'
'3660': '201501610'
'3661': '201501611'
'3662': '201501612'
'3663': '201501622'
'3664': '201501624'
'3665': '201501644'
'3666': '201501647'
'3667': '201501657'
'3668': '201501658'
'3669': '201501663'
'3670': '201501675'
'3671': '201501676'
'3672': '201501677'
'3673': '201501680'
'3674': '201501687'
'3675': '201501689'
'3676': '201501690'
'3677': '201501693'
'3678': '201501698'
'3679': '201501702'
'3680': '201501703'
'3681': '201501714'
'3682': '201501723'
'3683': '201501724'
'3684': '201501725'
'3685': '201501730'
'3686': '201501733'
'3687': '201501741'
'3688': '201501744'
'3689': '201501778'
'3690': '201501783'
'3691': '201501790'
'3692': '201501791'
'3693': '201501811'
'3694': '201501814'
'3695': '201501853'
'3696': '201501854'
'3697': '201501865'
'3698': '201501874'
'3699': '201501885'
'3700': '201501891'
'3701': '201501925'
'3702': '201501928'
'3703': '201501929'
'3704': '201501931'
'3705': '201501944'
'3706': '201501965'
'3707': '201501978'
'3708': '201501979'
'3709': '201501980'
'3710': '201502217'
'3711': '201502267'
'3712': '201502291'
'3713': '201502292'
'3714': '201502307'
'3715': '201502310'
'3716': '201502330'
'3717': '201502345'
'3718': '201502363'
'3719': '201502371'
'3720': '201502379'
'3721': '201502394'
'3722': '201502397'
'3723': '201502417'
'3724': '201502419'
'3725': '201502420'
'3726': '201502421'
'3727': '201502450'
'3728': '201502453'
'3729': '201502454'
'3730': '201502471'
'3731': '201502552'
'3732': '201502560'
'3733': '201502562'
'3734': '201502564'
'3735': '201502570'
'3736': '201502606'
'3737': '201502607'
'3738': '201502608'
'3739': '201502609'
'3740': '201502631'
'3741': '201502638'
'3742': '201502639'
'3743': '201502640'
'3744': '201502644'
'3745': '201502645'
'3746': '201502654'
'3747': '201502656'
'3748': '201502658'
'3749': '201502659'
'3750': '201502670'
'3751': '201502671'
'3752': '201502677'
'3753': '201502678'
'3754': '201502689'
'3755': '201502690'
'3756': '201502703'
'3757': '201502704'
'3758': '201502705'
'3759': '201502708'
'3760': '201502709'
'3761': '201502710'
'3762': '201502712'
'3763': '201502714'
'3764': '201502717'
'3765': '201502718'
'3766': '201502727'
'3767': '201502742'
'3768': '201502761'
'3769': '201502766'
'3770': '201502770'
'3771': '201502773'
'3772': '201502774'
'3773': '201502775'
'3774': '201502785'
'3775': '201502786'
'3776': '201502790'
'3777': '201502793'
'3778': '201502813'
'3779': '201502862'
'3780': '201502874'
'3781': '201502890'
'3782': '201502917'
'3783': '201502924'
'3784': '201502926'
'3785': '201502952'
'3786': '201502969'
'3787': '201502979'
'3788': '201502986'
'3789': '201502987'
'3790': '201502994'
'3791': '201503006'
'3792': '201503025'
'3793': '201503026'
'3794': '201503027'
'3795': '201503029'
'3796': '201503051'
'3797': '201503142'
'3798': '201503144'
'3799': '201503191'
'3800': '201503193'
'3801': '201503212'
'3802': '201503218'
'3803': '201503219'
'3804': '201503234'
'3805': '201503249'
'3806': '201503251'
'3807': '201503253'
'3808': '201503288'
'3809': '201503289'
'3810': '201503290'
'3811': '201503293'
'3812': '201503295'
'3813': '201503302'
'3814': '201503335'
'3815': '201503336'
'3816': '201503468'
'3817': '201503475'
'3818': '201503482'
'3819': '201503488'
'3820': '201503490'
'3821': '201503506'
'3822': '201503516'
'3823': '201503520'
'3824': '201503532'
'3825': '201503554'
'3826': '201503575'
'3827': '201503600'
'3828': '201503641'
'3829': '201503645'
'3830': '201503647'
'3831': '201503683'
'3832': '201503771'
'3833': '201503772'
'3834': '201503783'
'3835': '201503839'
'3836': '201503865'
'3837': '201503876'
'3838': '201503920'
'3839': '201503921'
'3840': '201503948'
'3841': '201504046'
'3842': '201504047'
'3843': '201504070'
'3844': '201504073'
'3845': '201504084'
'3846': '201504106'
'3847': '201504115'
'3848': '201504119'
'3849': '201504124'
'3850': '201504135'
'3851': '201504137'
'3852': '201504179'
'3853': '201504199'
'3854': '201504202'
'3855': '201504203'
'3856': '201504205'
'3857': '201504225'
'3858': '201504231'
'3859': '201504249'
'3860': '201504255'
'3861': '201504259'
'3862': '201504303'
'3863': '201504313'
'3864': '201504314'
'3865': '201504315'
'3866': '201504317'
'3867': '201504318'
'3868': '201504319'
'3869': '201504320'
'3870': '201504321'
'3871': '201504326'
'3872': '201504332'
'3873': '201504333'
'3874': '201504334'
'3875': '201504493'
'3876': '201504494'
'3877': '201504495'
'3878': '201504519'
'3879': '201504729'
'3880': '201504732'
'3881': '201504763'
'3882': '201504788'
'3883': '201504988'
'3884': '201505072'
'3885': '201505074'
'3886': '201505091'
'3887': '201505114'
'3888': '201505137'
'3889': '201505162'
'3890': '201505163'
'3891': '201505164'
'3892': '201505167'
'3893': '201505168'
'3894': '201505169'
'3895': '201505192'
'3896': '201505198'
'3897': '201505199'
'3898': '201505259'
'3899': '201505342'
'3900': '201505350'
'3901': '201505365'
'3902': '201505441'
'3903': '201505522'
'3904': '201505607'
'3905': '201505621'
'3906': '201505725'
'3907': '201505737'
'3908': '201505796'
'3909': '201505797'
'3910': '201505830'
'3911': '201505842'
'3912': '201505843'
'3913': '201505901'
'3914': '201505903'
'3915': '201505904'
'3916': '201505920'
'3917': '201505921'
'3918': '201505935'
'3919': '201506120'
'3920': '201506121'
'3921': '201506122'
'3922': '201506136'
'3923': '201506143'
'3924': '201506288'
'3925': '201506398'
'3926': '201506402'
'3927': '201506405'
'3928': '201506481'
'3929': '201506489'
'3930': '201506507'
'3931': '201506569'
'3932': '201506583'
'3933': '201506589'
'3934': '201506623'
'3935': '201506624'
'3936': '201506639'
'3937': '201506649'
'3938': '201506677'
'3939': '201506684'
'3940': '201506685'
'3941': '201506686'
'3942': '201506729'
'3943': '201506734'
'3944': '201506748'
'3945': '201506766'
'3946': '201506769'
'3947': '201506783'
'3948': '201506785'
'3949': '201506786'
'3950': '201506795'
'3951': '201506797'
'3952': '201506799'
'3953': '201506815'
'3954': '201506816'
'3955': '201506835'
'3956': '201506843'
'3957': '201506848'
'3958': '201506851'
'3959': '201506856'
'3960': '201506857'
'3961': '201506873'
'3962': '201506874'
'3963': '201506894'
'3964': '201507014'
'3965': '201507045'
'3966': '201507071'
'3967': '201507072'
'3968': '201507074'
'3969': '201507075'
'3970': '201507134'
'3971': '201507139'
'3972': '201507146'
'3973': '201507195'
'3974': '201507196'
'3975': '201507261'
'3976': '201507270'
'3977': '201507272'
'3978': '201507273'
'3979': '201507288'
'3980': '201507291'
'3981': '201507380'
'3982': '201507381'
'3983': '201507390'
'3984': '201507399'
'3985': '201507405'
'3986': '201507411'
'3987': '201507412'
'3988': '201507413'
'3989': '201507418'
'3990': '201507420'
'3991': '201507424'
'3992': '201507426'
'3993': '201507452'
'3994': '201507455'
'3995': '201507458'
'3996': '201507464'
'3997': '201507465'
'3998': '201507470'
'3999': '201507477'
'4000': '201507478'
'4001': '201507501'
'4002': '201507502'
'4003': '201507517'
'4004': '201507521'
'4005': '201507527'
'4006': '201507582'
'4007': '201507644'
'4008': '201507645'
'4009': '201507681'
'4010': '201507682'
'4011': '201507715'
'4012': '201507736'
'4013': '201507737'
'4014': '201507738'
'4015': '201507762'
'4016': '201507763'
'4017': '201507764'
'4018': '201507776'
'4019': '201507778'
'4020': '201507785'
'4021': '201507786'
'4022': '201507806'
'4023': '201507839'
'4024': '201507840'
'4025': '201507875'
'4026': '201507876'
'4027': '201507887'
'4028': '201507888'
'4029': '201507891'
'4030': '201507895'
'4031': '201507896'
'4032': '201507897'
'4033': '201507898'
'4034': '201507899'
'4035': '201507944'
'4036': '201507948'
'4037': '201507964'
'4038': '201507965'
'4039': '201507966'
'4040': '201507967'
'4041': '201507968'
'4042': '201507984'
'4043': '201507985'
'4044': '201507986'
'4045': '201507997'
'4046': '201507998'
'4047': '201507999'
'4048': '201508003'
'4049': '201508004'
'4050': '201508018'
'4051': '201508019'
'4052': '201508116'
'4053': '201508117'
'4054': '201508139'
'4055': '201508213'
'4056': '201508214'
'4057': '201508231'
'4058': '201508232'
'4059': '201508272'
'4060': '201508281'
'4061': '201508325'
'4062': '201508372'
'4063': '201508378'
'4064': '201508403'
'4065': '201508407'
'4066': '201508411'
'4067': '201508428'
'4068': '201508435'
'4069': '201508436'
'4070': '201508440'
'4071': '201508441'
'4072': '201508453'
'4073': '201508461'
'4074': '201508476'
'4075': '201508477'
'4076': '201508486'
'4077': '201508519'
'4078': '201508531'
'4079': '201508532'
'4080': '201508542'
'4081': '201600113'
'4082': '201600170'
'4083': '201600171'
'4084': '201600172'
'4085': '201600191'
'4086': '201600217'
'4087': '201600251'
'4088': '201600274'
'4089': '201600275'
'4090': '201600300'
'4091': '201600301'
'4092': '201600339'
'4093': '201600340'
'4094': '201600356'
'4095': '201600358'
'4096': '201600359'
'4097': '201600361'
'4098': '201600391'
'4099': '201600396'
'4100': '201600407'
'4101': '201600425'
'4102': '201600426'
'4103': '201600436'
'4104': '201600445'
'4105': '201600498'
'4106': '201600500'
'4107': '201600505'
'4108': '201600507'
'4109': '201600515'
'4110': '201600516'
'4111': '201600519'
'4112': '201600568'
'4113': '201600569'
'4114': '201600572'
'4115': '201600573'
'4116': '201600574'
'4117': '201600584'
'4118': '201600585'
'4119': '201600601'
'4120': '201600695'
'4121': '201600696'
'4122': '201600731'
'4123': '201600777'
'4124': '201600782'
'4125': '201600828'
'4126': '201600839'
'4127': '201600853'
'4128': '201600903'
'4129': '201600933'
'4130': '201600938'
'4131': '201600941'
'4132': '201600974'
'4133': '201600978'
'4134': '201600986'
'4135': '201601004'
'4136': '201601006'
'4137': '201601009'
'4138': '201601030'
'4139': '201601045'
'4140': '201601046'
'4141': '201601047'
'4142': '201601050'
'4143': '201601053'
'4144': '201601071'
'4145': '201601081'
'4146': '201601082'
'4147': '201601112'
'4148': '201601113'
'4149': '201601117'
'4150': '201601119'
'4151': '201601149'
'4152': '201601191'
'4153': '201601195'
'4154': '201601196'
'4155': '201601197'
'4156': '201601201'
'4157': '201601202'
'4158': '201601203'
'4159': '201601219'
'4160': '201601220'
'4161': '201601221'
'4162': '201601231'
'4163': '201601232'
'4164': '201601233'
'4165': '201601234'
'4166': '201601249'
'4167': '201601347'
'4168': '201601506'
'4169': '201601522'
'4170': '201601537'
'4171': '201601552'
'4172': '201601553'
'4173': '201601554'
'4174': '201601555'
'4175': '201601643'
'4176': '201601680'
'4177': '201601683'
'4178': '201601700'
'4179': '201601702'
'4180': '201601703'
'4181': '201601721'
'4182': '201601725'
'4183': '201601728'
'4184': '201601731'
'4185': '201601734'
'4186': '201601737'
'4187': '201601742'
'4188': '201601743'
'4189': '201601761'
'4190': '201601762'
'4191': '201601896'
'4192': '201602068'
'4193': '201602080'
'4194': '201602081'
'4195': '201602085'
'4196': '201602122'
'4197': '201602235'
'4198': '201602239'
'4199': '201602274'
'4200': '201602286'
'4201': '201602294'
'4202': '201602295'
'4203': '201602296'
'4204': '201602307'
'4205': '201602314'
'4206': '201602328'
'4207': '201602339'
'4208': '201602349'
'4209': '201602351'
'4210': '201602362'
'4211': '201602383'
'4212': '201602409'
'4213': '201602421'
'4214': '201602427'
'4215': '201602432'
'4216': '201602491'
'4217': '201602500'
'4218': '201602513'
'4219': '201602518'
'4220': '201602533'
'4221': '201602561'
'4222': '201602610'
'4223': '201602619'
'4224': '201602662'
'4225': '201602702'
'4226': '201602708'
'4227': '201602739'
'4228': '201602766'
'4229': '201602784'
'4230': '201602785'
'4231': '201602888'
'4232': '201602889'
'4233': '201602891'
'4234': '201602908'
'4235': '201602909'
'4236': '201602926'
'4237': '201602930'
'4238': '201602957'
'4239': '201602959'
'4240': '201602965'
'4241': '201602983'
'4242': '201602996'
'4243': '201603025'
'4244': '201603032'
'4245': '201603033'
'4246': '201603057'
'4247': '201603058'
'4248': '201603059'
'4249': '201603073'
'4250': '201603074'
'4251': '201603076'
'4252': '201603084'
'4253': '201603097'
'4254': '201603104'
'4255': '201603127'
'4256': '201603130'
'4257': '201603137'
'4258': '201603147'
'4259': '201603150'
'4260': '201603151'
'4261': '201603152'
'4262': '201603161'
'4263': '201603173'
'4264': '201603178'
'4265': '201603226'
'4266': '201603227'
'4267': '201603228'
'4268': '201603229'
'4269': '201603298'
'4270': '201603314'
'4271': '201603315'
'4272': '201603316'
'4273': '201603317'
'4274': '201603320'
'4275': '201603340'
'4276': '201603363'
'4277': '201603369'
'4278': '201603370'
'4279': '201603416'
'4280': '201603432'
'4281': '201603454'
'4282': '201603455'
'4283': '201603462'
'4284': '201603468'
'4285': '201603493'
'4286': '201603497'
'4287': '201603514'
'4288': '201603530'
'4289': '201603552'
'4290': '201603608'
'4291': '201603615'
'4292': '201603628'
'4293': '201603633'
'4294': '201603644'
'4295': '201603663'
'4296': '201603669'
'4297': '201603670'
'4298': '201603681'
'4299': '201603682'
'4300': '201603683'
'4301': '201603692'
'4302': '201603728'
'4303': '201603729'
'4304': '201603775'
'4305': '201603787'
'4306': '201603794'
'4307': '201603795'
'4308': '201603796'
'4309': '201603807'
'4310': '201603883'
'4311': '201603890'
'4312': '201603892'
'4313': '201603894'
'4314': '201603895'
'4315': '201603899'
'4316': '201603919'
'4317': '201603920'
'4318': '201603929'
'4319': '201603931'
'4320': '201603988'
'4321': '201603989'
'4322': '201603995'
'4323': '201604010'
'4324': '201604018'
'4325': '201604034'
'4326': '201604054'
'4327': '201604060'
'4328': '201604075'
'4329': '201604076'
'4330': '201604117'
'4331': '201604118'
'4332': '201604119'
'4333': '201604147'
'4334': '201604148'
'4335': '201604152'
'4336': '201604178'
'4337': '201604202'
'4338': '201604209'
'4339': '201604247'
'4340': '201604290'
'4341': '201604348'
'4342': '201604367'
'4343': '201604375'
'4344': '201604409'
'4345': '201604410'
'4346': '201604411'
'4347': '201604429'
'4348': '201604461'
'4349': '201604485'
'4350': '201604621'
'4351': '201604622'
'4352': '201604623'
'4353': '201604628'
'4354': '201604631'
'4355': '201604632'
'4356': '201604669'
'4357': '201604677'
'4358': '201604678'
'4359': '201604687'
'4360': '201604696'
'4361': '201604705'
'4362': '201604823'
'4363': '201604942'
'4364': '201605007'
'4365': '201605011'
'4366': '201605135'
'4367': '201605175'
'4368': '201605323'
'4369': '201605325'
'4370': '201605340'
'4371': '201605497'
'4372': '201605721'
'4373': '201605722'
'4374': '201605723'
'4375': '201605749'
'4376': '201605790'
'4377': '201605791'
'4378': '201605792'
'4379': '201605801'
'4380': '201605802'
'4381': '201605803'
'4382': '201605804'
'4383': '201605805'
'4384': '201605806'
'4385': '201605819'
'4386': '201605820'
'4387': '201605821'
'4388': '201605845'
'4389': '201605851'
'4390': '201605853'
'4391': '201605860'
'4392': '201605978'
'4393': '201606046'
'4394': '201606047'
'4395': '201606048'
'4396': '201606049'
'4397': '201606050'
'4398': '201606051'
'4399': '201606053'
'4400': '201606081'
'4401': '201606123'
'4402': '201606189'
'4403': '201606254'
'4404': '201606256'
'4405': '201606264'
'4406': '201606306'
'4407': '201606307'
'4408': '201606380'
'4409': '201606381'
'4410': '201606391'
'4411': '201606394'
'4412': '201606395'
'4413': '201606401'
'4414': '201606419'
'4415': '201606563'
'4416': '201606564'
'4417': '201606593'
'4418': '201606695'
'4419': '201606770'
'4420': '201606772'
'4421': '201606795'
'4422': '201606799'
'4423': '201606818'
'4424': '201606829'
'4425': '201606935'
'4426': '201607019'
'4427': '201607041'
'4428': '201607042'
'4429': '201607043'
'4430': '201607093'
'4431': '201607205'
'4432': '201607206'
'4433': '201607211'
'4434': '201607298'
'4435': '201607299'
'4436': '201700144'
'4437': '201700156'
'4438': '201700243'
'4439': '201700244'
'4440': '201700254'
'4441': '201700377'
'4442': '201700390'
'4443': '201700402'
'4444': '201700404'
'4445': '201700418'
'4446': '201700452'
'4447': '201700463'
'4448': '201700518'
'4449': '201700619'
'4450': '201700620'
'4451': '201700621'
'4452': '201700623'
'4453': '201700684'
'4454': '201700730'
'4455': '201700836'
'4456': '201700897'
'4457': '201700900'
'4458': '201700904'
'4459': '201700906'
'4460': '201700921'
'4461': '201701040'
'4462': '201701044'
'4463': '201701157'
'4464': '201701163'
'4465': '201701169'
'4466': '201701170'
'4467': '201701194'
'4468': '201701196'
'4469': '201701198'
'4470': '201701233'
'4471': '201701288'
'4472': '201701289'
'4473': '201701296'
'4474': '201701303'
'4475': '201701339'
'4476': '201701340'
'4477': '201701380'
'4478': '201701414'
'4479': '201701415'
'4480': '201701435'
'4481': '201701447'
'4482': '201701456'
'4483': '201701458'
'4484': '201701471'
'4485': '201701478'
'4486': '201701479'
'4487': '201701501'
'4488': '201701538'
'4489': '201701544'
'4490': '201701545'
'4491': '201701546'
'4492': '201701551'
'4493': '201701574'
'4494': '201701611'
'4495': '201701717'
'4496': '201701749'
'4497': '201701750'
'4498': '201701865'
'4499': '201701878'
'4500': '201701879'
'4501': '201701882'
'4502': '201701960'
'4503': '201702166'
'4504': '201702167'
'4505': '201702168'
'4506': '201702204'
'4507': '201702236'
'4508': '201702237'
'4509': '201702238'
'4510': '201702244'
'4511': '201702246'
'4512': '201702256'
'4513': '201702259'
'4514': '201702281'
'4515': '201702386'
'4516': '201702387'
'4517': '201702390'
'4518': '201702397'
'4519': '201702398'
'4520': '201702399'
'4521': '201702401'
'4522': '201702402'
'4523': '201702403'
'4524': '201702404'
'4525': '201702485'
'4526': '201702492'
'4527': '201702493'
'4528': '201702508'
'4529': '201702526'
'4530': '201702527'
'4531': '201702528'
'4532': '201702541'
'4533': '201702542'
'4534': '201702577'
'4535': '201702610'
'4536': '201702624'
'4537': '201702688'
'4538': '201702735'
'4539': '201702768'
'4540': '201702781'
'4541': '201702782'
'4542': '201702783'
'4543': '201702795'
'4544': '201703991'
'4545': '201703995'
'4546': '201704017'
'4547': '201704542'
'4548': '201704726'
'4549': '201704753'
'4550': '201704761'
'4551': '201704762'
'4552': '201704782'
'4553': '201704786'
'4554': '201704833'
'4555': '201704879'
'4556': '201705029'
'4557': '201705044'
'4558': '201705174'
'4559': '201705175'
'4560': '201705206'
'4561': '201705217'
'4562': '201705219'
'4563': '201705220'
'4564': '201705221'
'4565': '201705254'
'4566': '201705255'
'4567': '201705467'
'4568': '201705468'
'4569': '201705487'
'4570': '201705488'
'4571': '201705491'
'4572': '201705673'
'4573': '201705684'
'4574': '201705685'
'4575': '201705686'
'4576': '201705687'
'4577': '201705688'
'4578': '201705689'
'4579': '201705789'
'4580': '201705790'
'4581': '201705809'
'4582': '201705811'
'4583': '201706137'
'4584': '201706144'
'4585': '201706188'
'4586': '201706209'
'4587': '201706210'
'4588': '201706211'
'4589': '201706212'
'4590': '201706221'
'4591': '201706237'
'4592': '201706344'
'4593': '201706345'
'4594': '201706353'
'4595': '201706355'
'4596': '201706473'
'4597': '201706474'
'4598': '201706555'
'4599': '201706556'
'4600': '201706557'
'4601': '201706560'
'4602': '201706564'
'4603': '201706565'
'4604': '201706571'
'4605': '201706572'
'4606': '201706573'
'4607': '201706574'
'4608': '201706575'
'4609': '201706583'
'4610': '201706584'
'4611': '201706641'
'4612': '201706642'
'4613': '201706690'
'4614': '201706734'
'4615': '201706749'
'4616': '201706750'
'4617': '201706753'
'4618': '201706786'
'4619': '201706787'
'4620': '201706788'
'4621': '201706789'
'4622': '201706790'
'4623': '201706791'
'4624': '201706798'
'4625': '201706814'
'4626': '201706821'
'4627': '201706825'
'4628': '201706845'
'4629': '201706853'
'4630': '201706858'
'4631': '201706866'
'4632': '201706889'
'4633': '201706890'
'4634': '201706899'
'4635': '201706900'
'4636': '201706969'
'4637': '201707021'
'4638': '201707062'
'4639': '201707098'
'4640': '201707167'
'4641': '201707212'
'4642': '201707216'
'4643': '201707217'
'4644': '201707234'
'4645': '201707244'
'4646': '201707245'
'4647': '201707248'
'4648': '201707295'
'4649': '201707296'
'4650': '201707302'
'4651': '201707311'
'4652': '201707327'
'4653': '201707350'
'4654': '201707352'
'4655': '201707392'
'4656': '201707443'
'4657': '201707526'
'4658': '201707534'
'4659': '201707535'
'4660': '201707539'
'4661': '201707601'
'4662': '201707616'
'4663': '201707639'
'4664': '201707644'
'4665': '201707649'
'4666': '201707653'
'4667': '201707658'
'4668': '201707659'
'4669': '201707660'
'4670': '201707669'
'4671': '201707674'
'4672': '201707675'
'4673': '201707837'
'4674': '201707838'
'4675': '201707853'
'4676': '201707860'
'4677': '201707937'
'4678': '201707938'
'4679': '201707939'
'4680': '201707944'
'4681': '201708018'
'4682': '201708021'
'4683': '201708034'
'4684': '201708043'
'4685': '201708044'
'4686': '201708045'
'4687': '201708055'
'4688': '201708069'
'4689': '201708080'
'4690': '201708083'
'4691': '201708085'
'4692': '201708087'
'4693': '201708091'
'4694': '201708095'
'4695': '201708096'
'4696': '201708110'
'4697': '201708131'
'4698': '201708142'
'4699': '201708144'
'4700': '201708159'
'4701': '201708184'
'4702': '201708188'
'4703': '201708197'
'4704': '201708198'
'4705': '201708199'
'4706': '201708204'
'4707': '201708219'
'4708': '201708227'
'4709': '201708233'
'4710': '201708277'
'4711': '201708280'
'4712': '201708281'
'4713': '201708331'
'4714': '201708341'
'4715': '201708362'
'4716': '201708367'
'4717': '201708368'
'4718': '201708370'
'4719': '201708380'
'4720': '201708416'
'4721': '201708419'
'4722': '201708420'
'4723': '201708422'
'4724': '201708434'
'4725': '201708449'
'4726': '201708450'
'4727': '201708456'
'4728': '201708459'
'4729': '201708465'
'4730': '201708466'
'4731': '201708476'
'4732': '201708478'
'4733': '201708482'
'4734': '201708490'
'4735': '201708492'
'4736': '201708494'
'4737': '201708498'
'4738': '201708499'
'4739': '201708532'
'4740': '201708533'
'4741': '201708542'
'4742': '201708549'
'4743': '201708551'
'4744': '201708555'
'4745': '201708559'
'4746': '201708569'
'4747': '201708570'
'4748': '201708571'
'4749': '201708577'
'4750': '201708578'
'4751': '201708579'
'4752': '201708581'
'4753': '201708582'
'4754': '201708583'
'4755': '201708591'
'4756': '201708594'
'4757': '201708597'
'4758': '201708604'
'4759': '201708606'
'4760': '201708609'
'4761': '201708615'
'4762': '201708620'
'4763': '201708621'
'4764': '201708622'
'4765': '201708628'
'4766': '201708633'
'4767': '201708634'
'4768': '201708635'
'4769': '201708636'
'4770': '201708642'
'4771': '201800016'
'4772': '201800048'
'4773': '201800067'
'4774': '201800087'
'4775': '201800100'
'4776': '201800123'
'4777': '201800128'
'4778': '201800133'
'4779': '201800142'
'4780': '201800184'
'4781': '201800191'
'4782': '201800217'
'4783': '201800228'
'4784': '201800229'
'4785': '201800231'
'4786': '201800239'
'4787': '201800286'
'4788': '201800298'
'4789': '201800299'
'4790': '201800300'
'4791': '201800302'
'4792': '201800304'
'4793': '201800305'
'4794': '201800306'
'4795': '201800307'
'4796': '201800308'
'4797': '201800313'
'4798': '201800314'
'4799': '201800317'
'4800': '201800318'
'4801': '201800319'
'4802': '201800320'
'4803': '201800344'
'4804': '201800496'
'4805': '201800499'
'4806': '201800500'
'4807': '201800503'
'4808': '201800504'
'4809': '201800506'
'4810': '201800507'
'4811': '201800511'
'4812': '201800512'
'4813': '201800513'
'4814': '201800530'
'4815': '201800531'
'4816': '201800546'
'4817': '201800567'
'4818': '201800568'
'4819': '201800576'
'4820': '201800600'
'4821': '201800601'
'4822': '201800609'
'4823': '201800638'
'4824': '201800639'
'4825': '201800640'
'4826': '201800648'
'4827': '201800668'
'4828': '201800675'
'4829': '201800701'
'4830': '201800718'
'4831': '201800764'
'4832': '201800767'
'4833': '201800768'
'4834': '201800791'
'4835': '201800807'
'4836': '201800810'
'4837': '201800811'
'4838': '201800813'
'4839': '201800836'
'4840': '201800860'
'4841': '201800888'
'4842': '201800889'
'4843': '201800907'
'4844': '201800910'
'4845': '201800924'
'4846': '201800930'
'4847': '201800935'
'4848': '201800936'
'4849': '201800937'
'4850': '201800950'
'4851': '201800964'
'4852': '201800992'
'4853': '201801001'
'4854': '201801002'
'4855': '201801008'
'4856': '201801071'
'4857': '201801073'
'4858': '201801087'
'4859': '201801145'
'4860': '201801152'
'4861': '201801153'
'4862': '201801175'
'4863': '201801179'
'4864': '201801224'
'4865': '201801267'
'4866': '201801271'
'4867': '201801291'
'4868': '201801346'
'4869': '201801353'
'4870': '201801354'
'4871': '201801386'
'4872': '201801388'
'4873': '201801415'
'4874': '201801418'
'4875': '201801429'
'4876': '201801430'
'4877': '201801431'
'4878': '201801432'
'4879': '201801433'
'4880': '201801516'
'4881': '201801580'
'4882': '201801617'
'4883': '201801680'
'4884': '201801687'
'4885': '201801715'
'4886': '201801725'
'4887': '201801763'
'4888': '201801764'
'4889': '201801765'
'4890': '201801963'
'4891': '201802050'
'4892': '201802103'
'4893': '201802129'
'4894': '201802146'
'4895': '201802226'
'4896': '201802227'
'4897': '201802228'
'4898': '201802255'
'4899': '201802335'
'4900': '201802339'
'4901': '201802378'
'4902': '201802463'
'4903': '201802579'
'4904': '201802586'
'4905': '201802641'
'4906': '201802652'
'4907': '201802697'
'4908': '201802700'
'4909': '201802737'
'4910': '201802751'
'4911': '201802763'
'4912': '201802764'
'4913': '201802818'
'4914': '201802894'
'4915': '201802909'
'4916': '201803000'
'4917': '201803017'
'4918': '201803041'
'4919': '201803060'
'4920': '201803093'
'4921': '201803122'
'4922': '201803136'
'4923': '201803164'
'4924': '201803165'
'4925': '201803166'
'4926': '201803189'
'4927': '201803233'
'4928': '201803298'
'4929': '201803304'
'4930': '201803367'
'4931': '201803379'
'4932': '201803380'
'4933': '201803500'
'4934': '201803502'
'4935': '201803516'
'4936': '201803529'
'4937': '201803530'
'4938': '201803606'
'4939': '201803649'
'4940': '201803666'
'4941': '201803667'
'4942': '201803677'
'4943': '201803699'
'4944': '201803704'
'4945': '201803731'
'4946': '201803777'
'4947': '201803799'
'4948': '201803815'
'4949': '201803824'
'4950': '201803844'
'4951': '201803853'
'4952': '201803880'
'4953': '201803881'
'4954': '201803887'
'4955': '201803888'
'4956': '201803889'
'4957': '201803896'
'4958': '201803899'
'4959': '201804023'
'4960': '201804024'
'4961': '201804149'
'4962': '201804162'
'4963': '201804237'
'4964': '201804271'
'4965': '201804306'
'4966': '201804307'
'4967': '201804308'
'4968': '201804313'
'4969': '201804352'
'4970': '201804441'
'4971': '201804442'
'4972': '201804443'
'4973': '201804479'
'4974': '201804518'
'4975': '201804572'
'4976': '201804690'
'4977': '201804758'
'4978': '201804760'
'4979': '201804826'
'4980': '201804896'
'4981': '201804988'
'4982': '201805048'
'4983': '201805182'
'4984': '201805183'
'4985': '201805293'
'4986': '201805294'
'4987': '201805295'
'4988': '201805337'
'4989': '201805338'
'4990': '201805340'
'4991': '201805341'
'4992': '201805342'
'4993': '201805351'
'4994': '201900011'
'4995': '201900112'
'4996': '201900142'
'4997': '201900143'
'4998': '201900146'
'4999': '201900219'
'5000': '201900220'
'5001': '201900226'
'5002': '201900267'
'5003': '201900303'
'5004': '201900304'
'5005': '201900321'
'5006': '201900595'
'5007': '201900606'
'5008': '201900630'
'5009': '201900645'
'5010': '201900672'
'5011': '201900673'
'5012': '201900688'
'5013': '201900689'
'5014': '201900713'
'5015': '201900734'
'5016': '201900756'
'5017': '201900766'
'5018': '201900875'
'5019': '201900973'
'5020': '201901014'
'5021': '201901301'
'5022': '201901302'
'5023': '201901457'
'5024': '201901642'
'5025': '201901787'
'5026': '201901858'
'5027': '201901859'
'5028': '201901918'
'5029': '201901919'
'5030': '201902042'
'5031': '201902055'
'5032': '201902071'
'5033': '201902113'
'5034': '201902114'
'5035': '201902200'
'5036': '201902470'
'5037': '201902565'
'5038': '201902754'
'5039': '201902773'
'5040': '201902819'
'5041': '201903304'
'5042': '201903597'
'5043': '201903815'
'5044': '201904168'
'5045': '201904204'
'5046': '201904276'
'5047': '201904421'
'5048': '201904442'
'5049': '201904444'
'5050': '201904825'
'5051': '201905085'
'5052': '201905306'
'5053': '201905460'
'5054': '201905619'
'5055': '201905927'
'5056': '201906789'
'5057': '201906790'
'5058': '201906791'
'5059': '201906797'
'5060': '201906798'
'5061': '201906879'
'5062': '201906921'
'5063': '201906965'
'5064': '201906970'
'5065': '201906992'
'5066': '201907134'
'5067': '201907188'
'5068': '201907198'
'5069': '201907289'
'5070': '201907290'
'5071': '201907386'
'5072': '201907387'
'5073': '201907465'
'5074': '201907466'
'5075': '201907531'
'5076': '201907532'
'5077': '201907533'
'5078': '201907576'
'5079': '201907581'
'5080': '201907607'
'5081': '201907624'
'5082': '201907625'
'5083': '201907803'
'5084': '201908003'
'5085': '201908132'
'5086': '201908146'
'5087': '201908339'
splits:
- name: train
num_bytes: 102166960280.048
num_examples: 206199
download_size: 87895196959
dataset_size: 102166960280.048
---
# Dataset Card for "drug_info_clear"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.19420070946216583,
-0.40428632497787476,
0.30634456872940063,
-0.0759652629494667,
-0.10386108607053757,
-0.05704839155077934,
0.04158306121826172,
-0.3076432943344116,
0.891674280166626,
0.7295444011688232,
-0.7747377753257751,
-0.9932283163070679,
-0.6799607872962952,
-0.2070065885782... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Lennard-Heuer/DAIM-LLM | Lennard-Heuer | 2023-11-27T02:46:22Z | 41 | 0 | null | [
"region:us"
] | 2023-11-27T02:46:22Z | 2023-11-23T14:53:57.000Z | 2023-11-23T14:53:57 | Entry not found | [
-0.32276487350463867,
-0.22568444907665253,
0.8622263073921204,
0.43461570143699646,
-0.5282988548278809,
0.7012969255447388,
0.7915717363357544,
0.07618642598390579,
0.7746027112007141,
0.25632190704345703,
-0.7852815389633179,
-0.22573848068714142,
-0.910447895526886,
0.5715675354003906,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
InfernoDeep/MesogenesTask1Parquet_ALL | InfernoDeep | 2023-11-25T16:55:43Z | 41 | 0 | null | [
"region:us"
] | 2023-11-25T16:55:43Z | 2023-11-25T16:52:17.000Z | 2023-11-25T16:52:17 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
- split: validation
path: data/validation-*
dataset_info:
features:
- name: pixel_values
sequence:
sequence:
sequence: float32
- name: labels
sequence:
sequence: int8
splits:
- name: train
num_bytes: 5903889992
num_examples: 12551
- name: test
num_bytes: 959599680
num_examples: 2040
- name: validation
num_bytes: 1537241056
num_examples: 3268
download_size: 4679673366
dataset_size: 8400730728
---
# Dataset Card for "MesogenesTask1Parquet_ALL"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.5015618801116943,
-0.19446498155593872,
0.13040758669376373,
0.39453113079071045,
-0.3851863145828247,
0.06551001220941544,
0.4297584295272827,
0.0629730075597763,
1.1722325086593628,
0.2797788977622986,
-1.013174295425415,
-0.7802463173866272,
-0.63285893201828,
-0.058902811259031296,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
bgspaditya/byt-mal-minpro | bgspaditya | 2023-11-25T18:08:34Z | 41 | 0 | null | [
"region:us"
] | 2023-11-25T18:08:34Z | 2023-11-25T17:12:32.000Z | 2023-11-25T17:12:32 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: val
path: data/val-*
- split: test
path: data/test-*
dataset_info:
features:
- name: url
dtype: string
- name: type
dtype: string
- name: type_code
dtype: int64
splits:
- name: train
num_bytes: 43302335.10276401
num_examples: 520952
- name: val
num_bytes: 5412791.887845501
num_examples: 65119
- name: test
num_bytes: 5412875.009390486
num_examples: 65120
download_size: 32733332
dataset_size: 54128002.0
---
# Dataset Card for "byt-mal-minpro"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.6967710852622986,
-0.1687706857919693,
0.13231459259986877,
0.11728785932064056,
-0.2650246322154999,
-0.1516331434249878,
0.16925537586212158,
-0.11858337372541428,
0.9007595777511597,
0.5299067497253418,
-0.9539192318916321,
-0.9233494997024536,
-0.768338680267334,
-0.0871392711997032... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
lurosenb/medqa | lurosenb | 2023-11-25T21:57:03Z | 41 | 0 | null | [
"task_categories:question-answering",
"size_categories:1K<n<10K",
"language:en",
"license:mit",
"medical",
"region:us"
] | 2023-11-25T21:57:03Z | 2023-11-25T21:54:45.000Z | 2023-11-25T21:54:45 | ---
license: mit
task_categories:
- question-answering
language:
- en
tags:
- medical
size_categories:
- 1K<n<10K
--- | [
-0.12853392958641052,
-0.18616779148578644,
0.6529127955436707,
0.49436280131340027,
-0.19319361448287964,
0.23607419431209564,
0.36072003841400146,
0.050563063472509384,
0.579365611076355,
0.7400140762329102,
-0.6508104205131531,
-0.23783954977989197,
-0.7102249264717102,
-0.0478260256350... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
zapsdcn/rct-20k | zapsdcn | 2021-12-08T03:37:58Z | 40 | 0 | null | [
"region:us"
] | 2021-12-08T03:37:58Z | 2022-03-02T23:29:22.000Z | 2022-03-02T23:29:22 | Entry not found | [
-0.32276472449302673,
-0.22568407654762268,
0.8622258901596069,
0.4346148371696472,
-0.5282984972000122,
0.7012965679168701,
0.7915717363357544,
0.07618629932403564,
0.7746022939682007,
0.2563222646713257,
-0.785281777381897,
-0.22573848068714142,
-0.9104482531547546,
0.5715669393539429,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
huggan/cityscapes | huggan | 2022-04-12T13:56:44Z | 40 | 0 | null | [
"arxiv:1703.10593",
"region:us"
] | 2022-04-12T13:56:44Z | 2022-03-23T20:09:01.000Z | 2022-03-23T20:09:01 | This dataset is part of the CycleGAN datasets, originally hosted here: https://people.eecs.berkeley.edu/~taesung_park/CycleGAN/datasets/
# Citation
```
@article{DBLP:journals/corr/ZhuPIE17,
author = {Jun{-}Yan Zhu and
Taesung Park and
Phillip Isola and
Alexei A. Efros},
title = {Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial
Networks},
journal = {CoRR},
volume = {abs/1703.10593},
year = {2017},
url = {http://arxiv.org/abs/1703.10593},
eprinttype = {arXiv},
eprint = {1703.10593},
timestamp = {Mon, 13 Aug 2018 16:48:06 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZhuPIE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
``` | [
-0.048607271164655685,
-0.31038808822631836,
0.2472076416015625,
0.004099534824490547,
-0.38853690028190613,
0.01113723125308752,
-0.12735313177108765,
-0.3449961543083191,
0.044890038669109344,
0.6094780564308167,
-0.6503734588623047,
-0.727931022644043,
-0.4177476167678833,
0.14361721277... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
blinoff/healthcare_facilities_reviews | blinoff | 2022-10-23T16:50:31Z | 40 | 2 | null | [
"task_categories:text-classification",
"task_ids:sentiment-classification",
"multilinguality:monolingual",
"size_categories:10K<n<100K",
"language:ru",
"region:us"
] | 2022-10-23T16:50:31Z | 2022-05-25T10:48:13.000Z | 2022-05-25T10:48:13 | ---
language:
- ru
multilinguality:
- monolingual
size_categories:
- 10K<n<100K
task_categories:
- text-classification
task_ids:
- sentiment-classification
---
### Dataset Summary
The dataset contains user reviews about medical facilities.
In total it contains 70,597 reviews. The detailed distribution on sentiment scale is:
- 41,419 positive reviews;
- 29,178 negative reviews.
### Data Fields
Each sample contains the following fields:
- **review_id**;
- **category** category of medical facility (one of 48);
- **title**: review title;
- **content**: review text;
- **sentiment**: sentiment (<em>positive</em> or <em>negative</em>);
- **source_url**.
### Python
```python3
import pandas as pd
df = pd.read_json('healthcare_facilities_reviews.jsonl', lines=True)
df.sample(5)
```
| [
-0.42668837308883667,
-0.31265872716903687,
0.46692031621932983,
0.5970476865768433,
-0.4515961706638336,
-0.44022104144096375,
0.09075503796339035,
-0.0040107471868395805,
0.5847166776657104,
0.7231021523475647,
-0.3003944456577301,
-1.2560720443725586,
-0.5853617191314697,
0.671872496604... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Theivaprakasham/wildreceipt | Theivaprakasham | 2022-06-10T21:46:37Z | 40 | 5 | null | [
"license:apache-2.0",
"region:us"
] | 2022-06-10T21:46:37Z | 2022-06-10T18:01:28.000Z | 2022-06-10T18:01:28 | ---
license: apache-2.0
---
| [
-0.1285335123538971,
-0.1861683875322342,
0.6529128551483154,
0.49436232447624207,
-0.19319400191307068,
0.23607441782951355,
0.36072009801864624,
0.05056373029947281,
0.5793656706809998,
0.7400146722793579,
-0.650810182094574,
-0.23784008622169495,
-0.7102247476577759,
-0.0478255338966846... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
breakend/nllb-multi-domain | breakend | 2022-08-09T20:44:23Z | 40 | 1 | flores | [
"annotations_creators:found",
"language_creators:expert-generated",
"multilinguality:multilingual",
"multilinguality:translation",
"size_categories:unknown",
"source_datasets:extended|flores",
"language:en",
"language:ru",
"language:ayr",
"language:bho",
"language:dyu",
"language:fur",
"lang... | 2022-08-09T20:44:23Z | 2022-07-18T23:01:53.000Z | 2022-07-18T23:01:53 | ---
language:
- en
- ru
- ayr
- bho
- dyu
- fur
- wol
annotations_creators:
- found
language_creators:
- expert-generated
license:
- cc-by-sa-4.0
multilinguality:
- multilingual
- translation
pretty_name: nllb-multi-domain
size_categories:
- unknown
source_datasets:
- extended|flores
task_categories:
- conditional-text-generation
task_ids:
- machine-translation
paperswithcode_id: flores
---
# Dataset Card for NLLB Multi-Domain
## Table of Contents
- [Dataset Card for NLLB Multi-Domain](#dataset-card-for-nllb-multi-domain)
- [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)
- [Additional Information](#additional-information)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
## Dataset Description
- **Home:** [Flores](https://github.com/facebookresearch/flores/tree/main/nllb_md)
- **Repository:** [Github](https://github.com/facebookresearch/flores/tree/main/nllb_md)
### Dataset Summary
NLLB Multi Domain is a set of professionally-translated sentences in News, Unscripted informal speech, and Health domains. It is designed to enable assessment of out-of-domain performance and to study domain adaptation for machine translation. Each domain has approximately 3000 sentences.
### Supported Tasks and Leaderboards
#### Multilingual Machine Translation
Refer to the [Dynabench leaderboard](https://dynabench.org/flores/Flores%20MT%20Evaluation%20(FULL)) for additional details on model evaluation on FLORES-101 in the context of the WMT2021 shared task on [Large-Scale Multilingual Machine Translation](http://www.statmt.org/wmt21/large-scale-multilingual-translation-task.html). Flores 200 is an extention of this.
### Languages
Language | FLORES-200 code
---|---
Central Aymara | ayr_Latn
Bhojpuri | bho_Deva
Dyula | dyu_Latn
Friulian | fur_Latn
Russian | rus_Cyrl
Wolof | wol_Latn
Use a hyphenated pairing to get two langauges in one datapoint (e.g., "eng_Latn-rus_Cyrl" will provide sentences in the format below).
## Dataset Structure
### Data Instances
See Dataset Viewer.
The text is provided as-in the original dataset, without further preprocessing or tokenization.
### Data Fields
- `id`: Row number for the data entry, starting at 1.
- `sentence`: The full sentence in the specific language (may have _lang for pairings)
- `domain`: The domain of the sentence.
### Dataset Creation
Please refer to the original article [No Language Left Behind: Scaling Human-Centered Machine Translation](https://arxiv.org/abs/2207.04672) for additional information on dataset creation.
## Additional Information
### Dataset Curators
See paper for details.
### Licensing Information
Licensed with Creative Commons Attribution Share Alike 4.0. License available [here](https://creativecommons.org/licenses/by-sa/4.0/).
### Citation Information
Please cite the authors if you use these corpora in your work:
```bibtex
@article{nllb2022,
author = {NLLB Team, Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loic Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang},
title = {No Language Left Behind: Scaling Human-Centered Machine Translation},
year = {2022}
}
```
Please also cite prior work that this dataset builds on:
```bibtex
@inproceedings{,
title={The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation},
author={Goyal, Naman and Gao, Cynthia and Chaudhary, Vishrav and Chen, Peng-Jen and Wenzek, Guillaume and Ju, Da and Krishnan, Sanjana and Ranzato, Marc'Aurelio and Guzm\'{a}n, Francisco and Fan, Angela},
year={2021}
}
```
```bibtex
@inproceedings{,
title={Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English},
author={Guzm\'{a}n, Francisco and Chen, Peng-Jen and Ott, Myle and Pino, Juan and Lample, Guillaume and Koehn, Philipp and Chaudhary, Vishrav and Ranzato, Marc'Aurelio},
journal={arXiv preprint arXiv:1902.01382},
year={2019}
}
``` | [
-0.4685559570789337,
-0.567684531211853,
0.09278389811515808,
0.5372147560119629,
-0.0855080783367157,
0.03692318871617317,
-0.6195977330207825,
-0.31124457716941833,
0.35426074266433716,
0.43220755457878113,
-0.6021926403045654,
-0.6736785769462585,
-0.5315207242965698,
0.5364914536476135... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
srivatsavaasista/textgenerator-ds-mini-4 | srivatsavaasista | 2022-08-01T09:18:29Z | 40 | 0 | null | [
"region:us"
] | 2022-08-01T09:18:29Z | 2022-08-01T09:18:21.000Z | 2022-08-01T09:18:21 | Entry not found | [
-0.3227645754814148,
-0.22568479180335999,
0.8622263669967651,
0.43461522459983826,
-0.52829909324646,
0.7012971639633179,
0.7915719747543335,
0.07618614286184311,
0.774603009223938,
0.2563217282295227,
-0.7852813005447388,
-0.22573819756507874,
-0.9104475975036621,
0.5715674161911011,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
yuntian-deng/im2latex-100k | yuntian-deng | 2022-08-26T23:53:28Z | 40 | 6 | null | [
"region:us"
] | 2022-08-26T23:53:28Z | 2022-08-26T23:51:59.000Z | 2022-08-26T23:51:59 | Entry not found | [
-0.3227645754814148,
-0.22568479180335999,
0.8622263669967651,
0.43461522459983826,
-0.52829909324646,
0.7012971639633179,
0.7915719747543335,
0.07618614286184311,
0.774603009223938,
0.2563217282295227,
-0.7852813005447388,
-0.22573819756507874,
-0.9104475975036621,
0.5715674161911011,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
esb/datasets | esb | 2023-01-16T17:51:39Z | 40 | 7 | null | [
"task_categories:automatic-speech-recognition",
"annotations_creators:expert-generated",
"annotations_creators:crowdsourced",
"annotations_creators:machine-generated",
"language_creators:crowdsourced",
"language_creators:expert-generated",
"multilinguality:monolingual",
"size_categories:100K<n<1M",
... | 2023-01-16T17:51:39Z | 2022-10-24T10:53:50.000Z | 2022-10-24T10:53:50 | ---
annotations_creators:
- expert-generated
- crowdsourced
- machine-generated
language:
- en
language_creators:
- crowdsourced
- expert-generated
license:
- cc-by-4.0
- apache-2.0
- cc0-1.0
- cc-by-nc-3.0
- other
multilinguality:
- monolingual
pretty_name: datasets
size_categories:
- 100K<n<1M
- 1M<n<10M
source_datasets:
- original
- extended|librispeech_asr
- extended|common_voice
tags:
- asr
- benchmark
- speech
- esb
task_categories:
- automatic-speech-recognition
extra_gated_prompt: |-
Three of the ESB datasets have specific terms of usage that must be agreed to before using the data.
To do so, fill in the access forms on the specific datasets' pages:
* Common Voice: https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0
* GigaSpeech: https://huggingface.co/datasets/speechcolab/gigaspeech
* SPGISpeech: https://huggingface.co/datasets/kensho/spgispeech
extra_gated_fields:
I hereby confirm that I have registered on the original Common Voice page and agree to not attempt to determine the identity of speakers in the Common Voice dataset: checkbox
I hereby confirm that I have accepted the terms of usages on GigaSpeech page: checkbox
I hereby confirm that I have accepted the terms of usages on SPGISpeech page: checkbox
---
All eight of datasets in ESB can be downloaded and prepared in just a single line of code through the Hugging Face Datasets library:
```python
from datasets import load_dataset
librispeech = load_dataset("esb/datasets", "librispeech", split="train")
```
- `"esb/datasets"`: the repository namespace. This is fixed for all ESB datasets.
- `"librispeech"`: the dataset name. This can be changed to any of any one of the eight datasets in ESB to download that dataset.
- `split="train"`: the split. Set this to one of train/validation/test to generate a specific split. Omit the `split` argument to generate all splits for a dataset.
The datasets are full prepared, such that the audio and transcription files can be used directly in training/evaluation scripts.
## Dataset Information
A data point can be accessed by indexing the dataset object loaded through `load_dataset`:
```python
print(librispeech[0])
```
A typical data point comprises the path to the audio file and its transcription. Also included is information of the dataset from which the sample derives and a unique identifier name:
```python
{
'dataset': 'librispeech',
'audio': {'path': '/home/sanchit-gandhi/.cache/huggingface/datasets/downloads/extracted/d2da1969fe9e7d06661b5dc370cf2e3c119a14c35950045bcb76243b264e4f01/374-180298-0000.flac',
'array': array([ 7.01904297e-04, 7.32421875e-04, 7.32421875e-04, ...,
-2.74658203e-04, -1.83105469e-04, -3.05175781e-05]),
'sampling_rate': 16000},
'text': 'chapter sixteen i might have told you of the beginning of this liaison in a few lines but i wanted you to see every step by which we came i to agree to whatever marguerite wished',
'id': '374-180298-0000'
}
```
### Data Fields
- `dataset`: name of the ESB dataset from which the sample is taken.
- `audio`: a dictionary containing the path to the downloaded audio file, the decoded audio array, and the sampling rate.
- `text`: the transcription of the audio file.
- `id`: unique id of the data sample.
### Data Preparation
#### Audio
The audio for all ESB datasets is segmented into sample lengths suitable for training ASR systems. The Hugging Face datasets library decodes audio files on the fly, reading the segments and converting them to a Python arrays. Consequently, no further preparation of the audio is required to be used in training/evaluation scripts.
Note that when accessing the audio column: `dataset[0]["audio"]` the audio file is automatically decoded and resampled to `dataset.features["audio"].sampling_rate`. Decoding and resampling of a large number of audio files might take a significant amount of time. Thus it is important to first query the sample index before the `"audio"` column, i.e. `dataset[0]["audio"]` should always be preferred over `dataset["audio"][0]`.
#### Transcriptions
The transcriptions corresponding to each audio file are provided in their 'error corrected' format. No transcription pre-processing is applied to the text, only necessary 'error correction' steps such as removing junk tokens (_<unk>_) or converting symbolic punctuation to spelled out form (_<comma>_ to _,_). As such, no further preparation of the transcriptions is required to be used in training/evaluation scripts.
Transcriptions are provided for training and validation splits. The transcriptions are **not** provided for the test splits. ESB requires you to generate predictions for the test sets and upload them to https://huggingface.co/spaces/esb/leaderboard for scoring.
### Access
All eight of the datasets in ESB are accessible and licensing is freely available. Three of the ESB datasets have specific terms of usage that must be agreed to before using the data. To do so, fill in the access forms on the specific datasets' pages:
* Common Voice: https://huggingface.co/datasets/mozilla-foundation/common_voice_9_0
* GigaSpeech: https://huggingface.co/datasets/speechcolab/gigaspeech
* SPGISpeech: https://huggingface.co/datasets/kensho/spgispeech
### Diagnostic Dataset
ESB contains a small, 8h diagnostic dataset of in-domain validation data with newly annotated transcriptions. The audio data is sampled from each of the ESB validation sets, giving a range of different domains and speaking styles. The transcriptions are annotated according to a consistent style guide with two formats: normalised and un-normalised. The dataset is structured in the same way as the ESB dataset, by grouping audio-transcription samples according to the dataset from which they were taken. We encourage participants to use this dataset when evaluating their systems to quickly assess performance on a range of different speech recognition conditions. For more information, visit: [esb/diagnostic-dataset](https://huggingface.co/datasets/esb/diagnostic-dataset).
## Summary of ESB Datasets
| Dataset | Domain | Speaking Style | Train (h) | Dev (h) | Test (h) | Transcriptions | License |
|--------------|-----------------------------|-----------------------|-----------|---------|----------|--------------------|-----------------|
| LibriSpeech | Audiobook | Narrated | 960 | 11 | 11 | Normalised | CC-BY-4.0 |
| Common Voice | Wikipedia | Narrated | 1409 | 27 | 27 | Punctuated & Cased | CC0-1.0 |
| Voxpopuli | European Parliament | Oratory | 523 | 5 | 5 | Punctuated | CC0 |
| TED-LIUM | TED talks | Oratory | 454 | 2 | 3 | Normalised | CC-BY-NC-ND 3.0 |
| GigaSpeech | Audiobook, podcast, YouTube | Narrated, spontaneous | 2500 | 12 | 40 | Punctuated | apache-2.0 |
| SPGISpeech | Fincancial meetings | Oratory, spontaneous | 4900 | 100 | 100 | Punctuated & Cased | User Agreement |
| Earnings-22 | Fincancial meetings | Oratory, spontaneous | 105 | 5 | 5 | Punctuated & Cased | CC-BY-SA-4.0 |
| AMI | Meetings | Spontaneous | 78 | 9 | 9 | Punctuated & Cased | CC-BY-4.0 |
## LibriSpeech
The LibriSpeech corpus is a standard large-scale corpus for assessing ASR systems. It consists of approximately 1,000 hours of narrated audiobooks from the [LibriVox](https://librivox.org) project. It is licensed under CC-BY-4.0.
Example Usage:
```python
librispeech = load_dataset("esb/datasets", "librispeech")
```
Train/validation splits:
- `train` (combination of `train.clean.100`, `train.clean.360` and `train.other.500`)
- `validation.clean`
- `validation.other`
Test splits:
- `test.clean`
- `test.other`
Also available are subsets of the train split, which can be accessed by setting the `subconfig` argument:
```python
librispeech = load_dataset("esb/datasets", "librispeech", subconfig="clean.100")
```
- `clean.100`: 100 hours of training data from the 'clean' subset
- `clean.360`: 360 hours of training data from the 'clean' subset
- `other.500`: 500 hours of training data from the 'other' subset
## Common Voice
Common Voice is a series of crowd-sourced open-licensed speech datasets where speakers record text from Wikipedia in various languages. The speakers are of various nationalities and native languages, with different accents and recording conditions. We use the English subset of version 9.0 (27-4-2022), with approximately 1,400 hours of audio-transcription data. It is licensed under CC0-1.0.
Example usage:
```python
common_voice = load_dataset("esb/datasets", "common_voice", use_auth_token=True)
```
Training/validation splits:
- `train`
- `validation`
Test splits:
- `test`
## VoxPopuli
VoxPopuli is a large-scale multilingual speech corpus consisting of political data sourced from 2009-2020 European Parliament event recordings. The English subset contains approximately 550 hours of speech largely from non-native English speakers. It is licensed under CC0.
Example usage:
```python
voxpopuli = load_dataset("esb/datasets", "voxpopuli")
```
Training/validation splits:
- `train`
- `validation`
Test splits:
- `test`
## TED-LIUM
TED-LIUM consists of English-language TED Talk conference videos covering a range of different cultural, political, and academic topics. It contains approximately 450 hours of transcribed speech data. It is licensed under CC-BY-NC-ND 3.0.
Example usage:
```python
tedlium = load_dataset("esb/datasets", "tedlium")
```
Training/validation splits:
- `train`
- `validation`
Test splits:
- `test`
## GigaSpeech
GigaSpeech is a multi-domain English speech recognition corpus created from audiobooks, podcasts and YouTube. We provide the large train set (2,500 hours) and the standard validation and test splits. It is licensed under apache-2.0.
Example usage:
```python
gigaspeech = load_dataset("esb/datasets", "gigaspeech", use_auth_token=True)
```
Training/validation splits:
- `train` (`l` subset of training data (2,500 h))
- `validation`
Test splits:
- `test`
Also available are subsets of the train split, which can be accessed by setting the `subconfig` argument:
```python
gigaspeech = load_dataset("esb/datasets", "spgispeech", subconfig="xs", use_auth_token=True)
```
- `xs`: extra-small subset of training data (10 h)
- `s`: small subset of training data (250 h)
- `m`: medium subset of training data (1,000 h)
- `xl`: extra-large subset of training data (10,000 h)
## SPGISpeech
SPGISpeech consists of company earnings calls that have been manually transcribed by S&P Global, Inc according to a professional style guide. We provide the large train set (5,000 hours) and the standard validation and test splits. It is licensed under a Kensho user agreement.
Loading the dataset requires authorization.
Example usage:
```python
spgispeech = load_dataset("esb/datasets", "spgispeech", use_auth_token=True)
```
Training/validation splits:
- `train` (`l` subset of training data (~5,000 h))
- `validation`
Test splits:
- `test`
Also available are subsets of the train split, which can be accessed by setting the `subconfig` argument:
```python
spgispeech = load_dataset("esb/datasets", "spgispeech", subconfig="s", use_auth_token=True)
```
- `s`: small subset of training data (~200 h)
- `m`: medium subset of training data (~1,000 h)
## Earnings-22
Earnings-22 is a 119-hour corpus of English-language earnings calls collected from global companies, with speakers of many different nationalities and accents. It is licensed under CC-BY-SA-4.0.
Example usage:
```python
earnings22 = load_dataset("esb/datasets", "earnings22")
```
Training/validation splits:
- `train`
- `validation`
Test splits:
- `test`
## AMI
The AMI Meeting Corpus consists of 100 hours of meeting recordings from multiple recording devices synced to a common timeline. It is licensed under CC-BY-4.0.
Example usage:
```python
ami = load_dataset("esb/datasets", "ami")
```
Training/validation splits:
- `train`
- `validation`
Test splits:
- `test` | [
-0.5944708585739136,
-0.6311702132225037,
0.024879207834601402,
0.44837892055511475,
-0.07870926707983017,
-0.09941922873258591,
-0.3333989381790161,
-0.40673425793647766,
0.5804066061973572,
0.5480019450187683,
-0.7971272468566895,
-0.6028016209602356,
-0.4620300233364105,
0.1769015043973... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
society-ethics/lila_camera_traps | society-ethics | 2023-03-07T20:14:40Z | 40 | 5 | null | [
"task_categories:image-classification",
"annotations_creators:expert-generated",
"language_creators:expert-generated",
"multilinguality:monolingual",
"size_categories:10M<n<100M",
"source_datasets:original",
"language:en",
"license:other",
"biodiversity",
"camera trap data",
"wildlife monitoring... | 2023-03-07T20:14:40Z | 2022-10-30T22:34:29.000Z | 2022-10-30T22:34:29 | ---
annotations_creators:
- expert-generated
license:
- other
language_creators:
- expert-generated
language:
- en
multilinguality:
- monolingual
size_categories:
- 10M<n<100M
source_datasets:
- original
task_categories:
- image-classification
tags:
- biodiversity
- camera trap data
- wildlife monitoring
pretty_name: LILA Camera Traps
---
# Dataset Card for LILA
## 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)
- [Tutorial](#tutorial)
- [Working with Taxonomies](#working-with-taxonomies)
- [Dataset Curators](#dataset-curators)
- [Licensing Information](#licensing-information)
- [Citation Information](#citation-information)
- [Contributions](#contributions)
## Dataset Description
- **Homepage:** https://lila.science/
- **Repository:** N/A
- **Paper:** N/A
- **Leaderboard:** N/A
- **Point of Contact:** [info@lila.science](info@lila.science)
### Dataset Summary
LILA Camera Traps is an aggregate data set of images taken by camera traps, which are devices that automatically (e.g. via motion detection) capture images of wild animals to help ecological research.
This data set is the first time when disparate camera trap data sets have been aggregated into a single training environment with a single [taxonomy](https://lila.science/taxonomy-mapping-for-camera-trap-data-sets/).
This data set consists of only camera trap image data sets, whereas the broader [LILA](lila.science/) website also has other data sets related to biology and conservation, intended as a resource for both machine learning (ML) researchers and those that want to harness ML for this topic.
See below for information about each specific dataset that LILA contains:
<details>
<summary> Caltech Camera Traps </summary>
This data set contains 243,100 images from 140 camera locations in the Southwestern United States, with labels for 21 animal categories (plus empty), primarily at the species level (for example, the most common labels are opossum, raccoon, and coyote), and approximately 66,000 bounding box annotations. Approximately 70% of images are labeled as empty.
More information about this data set is available [here](https://beerys.github.io/CaltechCameraTraps/).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
For questions about this data set, contact caltechcameratraps@gmail.com.
If you use this data set, please cite the associated manuscript:
```bibtex
@inproceedings{DBLP:conf/eccv/BeeryHP18,
author = {Sara Beery and
Grant Van Horn and
Pietro Perona},
title = {Recognition in Terra Incognita},
booktitle = {Computer Vision - {ECCV} 2018 - 15th European Conference, Munich,
Germany, September 8-14, 2018, Proceedings, Part {XVI}},
pages = {472--489},
year = {2018},
crossref = {DBLP:conf/eccv/2018-16},
url = {https://doi.org/10.1007/978-3-030-01270-0\_28},
doi = {10.1007/978-3-030-01270-0\_28},
timestamp = {Mon, 08 Oct 2018 17:08:07 +0200},
biburl = {https://dblp.org/rec/bib/conf/eccv/BeeryHP18},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
</details>
<details>
<summary> ENA24 </summary>
This data set contains approximately 10,000 camera trap images representing 23 classes from Eastern North America, with bounding boxes on each image. The most common classes are “American Crow”, “American Black Bear”, and “Dog”.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
Please cite this manuscript if you use this data set:
```bibtex
@article{yousif2019dynamic,
title={Dynamic Programming Selection of Object Proposals for Sequence-Level Animal Species Classification in the Wild},
author={Yousif, Hayder and Kays, Roland and He, Zhihai},
journal={IEEE Transactions on Circuits and Systems for Video Technology},
year={2019},
publisher={IEEE}
}
```
For questions about this data set, contact [Hayder Yousif](hyypp5@mail.missouri.edu).
</details>
<details>
<summary> Missouri Camera Traps </summary>
This data set contains approximately 25,000 camera trap images representing 20 species (for example, the most common labels are red deer, mouflon, and white-tailed deer). Images within each sequence share the same species label (even though the animal may not have been recorded in all the images in the sequence). Around 900 bounding boxes are included. These are very challenging sequences with highly cluttered and dynamic scenes. Spatial resolutions of the images vary from 1920 × 1080 to 2048 × 1536. Sequence lengths vary from 3 to more than 300 frames.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
If you use this data set, please cite the associated manuscript:
```bibtex
@article{zhang2016animal,
title={Animal detection from highly cluttered natural scenes using spatiotemporal object region proposals and patch verification},
author={Zhang, Zhi and He, Zhihai and Cao, Guitao and Cao, Wenming},
journal={IEEE Transactions on Multimedia},
volume={18},
number={10},
pages={2079--2092},
year={2016},
publisher={IEEE}
}
```
For questions about this data set, contact [Hayder Yousif](hyypp5@mail.missouri.edu) and [Zhi Zhang](zzbhf@mail.missouri.edu).
</details>
<details>
<summary> North American Camera Trap Images (NACTI) </summary>
This data set contains 3.7M camera trap images from five locations across the United States, with labels for 28 animal categories, primarily at the species level (for example, the most common labels are cattle, boar, and red deer). Approximately 12% of images are labeled as empty. We have also added bounding box annotations to 8892 images (mostly vehicles and birds).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
Please cite this manuscript if you use this data set:
```bibtex
@article{tabak2019machine,
title={Machine learning to classify animal species in camera trap images: Applications in ecology},
author={Tabak, Michael A and Norouzzadeh, Mohammad S and Wolfson, David W and Sweeney, Steven J and VerCauteren, Kurt C and Snow, Nathan P and Halseth, Joseph M and Di Salvo, Paul A and Lewis, Jesse S and White, Michael D and others},
journal={Methods in Ecology and Evolution},
volume={10},
number={4},
pages={585--590},
year={2019},
publisher={Wiley Online Library}
}
```
For questions about this data set, contact [northamericancameratrapimages@gmail.com](northamericancameratrapimages@gmail.com).
</details>
<details>
<summary> WCS Camera Traps </summary>
This data set contains approximately 1.4M camera trap images representing around 675 species from 12 countries, making it one of the most diverse camera trap data sets available publicly. Data were provided by the [Wildlife Conservation Society](https://www.wcs.org/). The most common classes are tayassu pecari (peccary), meleagris ocellata (ocellated turkey), and bos taurus (cattle). A complete list of classes and associated image counts is available here. Approximately 50% of images are empty. We have also added approximately 375,000 bounding box annotations to approximately 300,000 of those images, which come from sequences covering almost all locations.
Sequences are inferred from timestamps, so may not strictly represent bursts. Images were labeled at a combination of image and sequence level, so – as is the case with most camera trap data sets – empty images may be labeled as non-empty (if an animal was present in one frame of a sequence but not in others). Images containing humans are referred to in metadata, but are not included in the data files. You can find more information about the data set [on the LILA website](https://lila.science/datasets/wcscameratraps).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Wellington Camera Traps </summary>
This data set contains 270,450 images from 187 camera locations in Wellington, New Zealand. The cameras (Bushnell 119537, 119476, and 119436) recorded sequences of three images when triggered. Each sequence was labelled by citizen scientists and/or professional ecologists from Victoria University of Wellington into 17 classes: 15 animal categories (for example, the most common labels are bird, cat, and hedgehog), empty, and unclassifiable. Approximately 17% of images are labeled as empty. Images within each sequence share the same species label (even though the animal may not have been recorded in all three images).
If you use this data set, please cite the associated manuscript:
```bibtex
@article{anton2018monitoring,
title={Monitoring the mammalian fauna of urban areas using remote cameras and citizen science},
author={Anton, Victor and Hartley, Stephen and Geldenhuis, Andre and Wittmer, Heiko U},
journal={Journal of Urban Ecology},
volume={4},
number={1},
pages={juy002},
year={2018},
publisher={Oxford University Press}
}
```
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
For questions about this data set, contact [Victor Anton](vykanton@gmail.com).
</details>
<details>
<summary> Island Conservation Camera Traps </summary>
This data set contains approximately 123,000 camera trap images from 123 camera locations from 7 islands in 6 countries. Data were provided by Island Conservation during projects conducted to prevent the extinction of threatened species on islands.
The most common classes are rabbit, rat, petrel, iguana, cat, goat, and pig, with both rat and cat represented between multiple island sites representing significantly different ecosystems (tropical forest, dry forest, and temperate forests). Additionally, this data set represents data from locations and ecosystems that, to our knowledge, are not well represented in publicly available datasets including >1,000 images each of iguanas, petrels, and shearwaters. A complete list of classes and associated image counts is available here. Approximately 60% of the images are empty. We have also included approximately 65,000 bounding box annotations for about 50,000 images.
In general cameras were dispersed across each project site to detect the presence of invasive vertebrate species that threaten native island species. Cameras were set to capture bursts of photos for each motion detection event (between three and eight photos) with a set delay between events (10 to 30 seconds) to minimize the number of photos. Images containing humans are referred to in metadata, but are not included in the data files.
For questions about this data set, contact [David Will](david.will@islandconservation.org) at Island Conservation.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
The original data set included a “human” class label; for privacy reasons, we have removed those images from this version of the data set. Those labels are still present in the metadata. If those images are important to your work, contact us; in some cases it will be possible to release those images under an alternative license.
</details>
<details>
<summary> Channel Islands Camera Traps </summary>
This data set contains 246,529 camera trap images from 73 camera locations in the Channel Islands, California. All animals are annotated with bounding boxes. Data were provided by The Nature Conservancy. Animals are classified as rodent1 (82914), fox (48150), bird (11099), skunk (1071), or other (159). 114,949 images (47%) are empty. All images of rats were taken on islands already known to have rat populations.
If you use these data in a publication or report, please use the following citation:
The Nature Conservancy (2021): Channel Islands Camera Traps 1.0. The Nature Conservancy. Dataset.
For questions about this data set, contact [Nathaniel Rindlaub](nathaniel.rindlaub@TNC.ORG) at The Nature Conservancy.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
The original data set included a “human” class label; for privacy reasons, we have removed those images from this version of the data set. Those labels are still present in the metadata.
</details>
<details>
<summary> Idaho Camera Traps </summary>
This data set contains approximately 1.5 million camera trap images from Idaho. Labels are provided for 62 categories, most of which are animal classes (“deer”, “elk”, and “cattle” are the most common animal classes), but labels also include some state indicators (e.g. “snow on lens”, “foggy lens”). Approximately 70.5% of images are labeled as empty. Annotations were assigned to image sequences, rather than individual images, so annotations are meaningful only at the sequence level.
The metadata contains references to images containing humans, but these have been removed from the dataset (along with images containing vehicles and domestic dogs).
Images were provided by the Idaho Department of Fish and Game. No representations or warranties are made regarding the data, including but not limited to warranties of non-infringement or fitness for a particular purpose. Some information shared under this agreement may not have undergone quality assurance procedures and should be considered provisional. Images may not be sold in any format, but may be used for scientific publications. Please acknowledge the Idaho Department of Fish and Game when using images for publication or scientific communication.
</details>
<details>
<summary> Snapshot Serengeti </summary>
This data set contains approximately 2.65M sequences of camera trap images, totaling 7.1M images, from seasons one through eleven of the [Snapshot Serengeti project](https://snapshotserengeti.org/) -- the flagship project of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Serengeti National Park in Tanzania is best known for the massive annual migrations of wildebeest and zebra that drive the cycling of its dynamic ecosystem.
Labels are provided for 61 categories, primarily at the species level (for example, the most common labels are wildebeest, zebra, and Thomson’s gazelle). Approximately 76% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshotserengeti-v-2-0/SnapshotSerengeti_S1-11_v2.1.species_list.csv). We have also added approximately 150,000 bounding box annotations to approximately 78,000 of those images.
The images and species-level labels are described in more detail in the associated manuscript:
```bibtex
@misc{dryad_5pt92,
title = {Data from: Snapshot Serengeti, high-frequency annotated camera trap images of 40 mammalian species in an African savanna},
author = {Swanson, AB and Kosmala, M and Lintott, CJ and Simpson, RJ and Smith, A and Packer, C},
year = {2015},
journal = {Scientific Data},
URL = {https://doi.org/10.5061/dryad.5pt92},
doi = {doi:10.5061/dryad.5pt92},
publisher = {Dryad Digital Repository}
}
```
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Karoo </summary>
This data set contains 14889 sequences of camera trap images, totaling 38074 images, from the [Snapshot Karoo](https://www.zooniverse.org/projects/shuebner729/snapshot-karoo) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Karoo National Park, located in the arid Nama Karoo biome of South Africa, is defined by its endemic vegetation and mountain landscapes. Its unique topographical gradient has led to a surprising amount of biodiversity, with 58 mammals and more than 200 bird species recorded, as well as a multitude of reptilian species.
Labels are provided for 38 categories, primarily at the species level (for example, the most common labels are gemsbokoryx, hartebeestred, and kudu). Approximately 83.02% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/KAR/SnapshotKaroo_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Kgalagadi </summary>
This data set contains 3611 sequences of camera trap images, totaling 10222 images, from the [Snapshot Kgalagadi](https://www.zooniverse.org/projects/shuebner729/snapshot-kgalagadi/) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. The Kgalagadi Transfrontier Park stretches from the Namibian border across South Africa and into Botswana, covering a landscape commonly referred to as the Kalahari – an arid savanna. This region is of great interest to help us understand how animals cope with extreme temperatures at both ends of the scale.
Labels are provided for 31 categories, primarily at the species level (for example, the most common labels are gemsbokoryx, birdother, and ostrich). Approximately 76.14% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/KGA/SnapshotKgalagadi_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Enonkishu </summary>
This data set contains 13301 sequences of camera trap images, totaling 28544 images, from the [Snapshot Enonkishu](https://www.zooniverse.org/projects/aguthmann/snapshot-enonkishu) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Enonkishu Conservancy is located on the northern boundary of the Mara-Serengeti ecosystem in Kenya, and is managed by a consortium of stakeholders and land-owning Maasai families. Their aim is to promote coexistence between wildlife and livestock in order to encourage regenerative grazing and build stability in the Mara conservancies.
Labels are provided for 39 categories, primarily at the species level (for example, the most common labels are impala, warthog, and zebra). Approximately 64.76% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/ENO/SnapshotEnonkishu_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Camdeboo </summary>
This data set contains 12132 sequences of camera trap images, totaling 30227 images, from the [Snapshot Camdeboo](https://www.zooniverse.org/projects/shuebner729/snapshot-camdeboo) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Camdeboo National Park, South Africa is crucial habitat for many birds on a global scale, with greater than fifty endemic and near-endemic species and many migratory species.
Labels are provided for 43 categories, primarily at the species level (for example, the most common labels are kudu, springbok, and ostrich). Approximately 43.74% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/CDB/SnapshotCamdeboo_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Mountain Zebra </summary>
This data set contains 71688 sequences of camera trap images, totaling 73034 images, from the [Snapshot Mountain Zebra](https://www.zooniverse.org/projects/meredithspalmer/snapshot-mountain-zebra/) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Mountain Zebra National Park is located in the Eastern Cape of South Africa in a transitional area between several distinct biomes, which means it is home to many endemic species. As the name suggests, this park contains the largest remnant population of Cape Mountain zebras, ~700 as of 2019 and increasing steadily every year.
Labels are provided for 54 categories, primarily at the species level (for example, the most common labels are zebramountain, kudu, and springbok). Approximately 91.23% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/MTZ/SnapshotMountainZebra_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Snapshot Kruger </summary>
This data set contains 4747 sequences of camera trap images, totaling 10072 images, from the [Snapshot Kruger](https://www.zooniverse.org/projects/shuebner729/snapshot-kruger) project, part of the Snapshot Safari network. Using the same camera trapping protocols at every site, Snapshot Safari members are collecting standardized data from many protected areas in Africa, which allows for cross-site comparisons to assess the efficacy of conservation and restoration programs. Kruger National Park, South Africa has been a refuge for wildlife since its establishment in 1898, and it houses one of the most diverse wildlife assemblages remaining in Africa. The Snapshot Safari grid was established in 2018 as part of a research project assessing the impacts of large mammals on plant life as boundary fences were removed and wildlife reoccupied areas of previous extirpation.
Labels are provided for 46 categories, primarily at the species level (for example, the most common labels are impala, elephant, and buffalo). Approximately 61.60% of images are labeled as empty. A full list of species and associated image counts is available [here](https://lilablobssc.blob.core.windows.net/snapshot-safari/KRU/SnapshotKruger_S1_v1.0.species_list.csv).
For questions about this data set, contact [Sarah Huebner](huebn090@umn.edu) at the University of Minnesota.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> SWG Camera Traps </summary>
This data set contains 436,617 sequences of camera trap images from 982 locations in Vietnam and Lao, totaling 2,039,657 images. Labels are provided for 120 categories, primarily at the species level (for example, the most common labels are “Eurasian Wild Pig”, “Large-antlered Muntjac”, and “Unidentified Murid”). Approximately 12.98% of images are labeled as empty. A full list of species and associated image counts is available here. 101,659 bounding boxes are provided on 88,135 images.
This data set is provided by the Saola Working Group; providers include:
- IUCN SSC Asian Wild Cattle Specialist Group’s Saola Working Group (SWG)
- Asian Arks
- Wildlife Conservation Society (Lao)
- WWF Lao
- Integrated Conservation of Biodiversity and Forests project, Lao (ICBF)
- Center for Environment and Rural Development, Vinh University, Vietnam
If you use these data in a publication or report, please use the following citation:
SWG (2021): Northern and Central Annamites Camera Traps 2.0. IUCN SSC Asian Wild Cattle Specialist Group’s Saola Working Group. Dataset.
For questions about this data set, contact saolawg@gmail.com.
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
<details>
<summary> Orinoquia Camera Traps </summary>
This data set contains 104,782 images collected from a 50-camera-trap array deployed from January to July 2020 within the private natural reserves El Rey Zamuro (31 km2) and Las Unamas (40 km2), located in the Meta department in the Orinoquía region in central Colombia. We deployed cameras using a stratified random sampling design across forest core area strata. Cameras were spaced 1 km apart from one another, located facing wildlife trails, and deployed with no bait. Images were stored and reviewed by experts using the Wildlife Insights platform.
This data set contains 51 classes, predominantly mammals such as the collared peccary, black agouti, spotted paca, white-lipped peccary, lowland tapir, and giant anteater. Approximately 20% of images are empty.
The main purpose of the study is to understand how humans, wildlife, and domestic animals interact in multi-functional landscapes (e.g., agricultural livestock areas with native forest remnants). However, this data set was also used to review model performance of AI-powered platforms – Wildlife Insights (WI), MegaDetector (MD), and Machine Learning for Wildlife Image Classification (MLWIC2). We provide a demonstration of the use of WI, MD, and MLWIC2 and R code for evaluating model performance of these platforms in the accompanying [GitHub repository](https://github.com/julianavelez1/Processing-Camera-Trap-Data-Using-AI).
If you use these data in a publication or report, please use the following citation:
```bibtex
@article{velez2022choosing,
title={Choosing an Appropriate Platform and Workflow for Processing Camera Trap Data using Artificial Intelligence},
author={V{\'e}lez, Juliana and Castiblanco-Camacho, Paula J and Tabak, Michael A and Chalmers, Carl and Fergus, Paul and Fieberg, John},
journal={arXiv preprint arXiv:2202.02283},
year={2022}
}
```
For questions about this data set, contact [Juliana Velez Gomez](julianavelezgomez@gmail.com).
This data set is released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/).
</details>
### Supported Tasks and Leaderboards
No leaderboards exist for LILA.
### Languages
The [LILA taxonomy](https://lila.science/taxonomy-mapping-for-camera-trap-data-sets/) is provided in English.
## Dataset Structure
### Data Instances
The data annotations are provided in [COCO Camera Traps](https://github.com/Microsoft/CameraTraps/blob/master/data_management/README.md#coco-cameratraps-format) format.
All of the datasets share a common category taxonomy, which is defined on the [LILA website](https://lila.science/taxonomy-mapping-for-camera-trap-data-sets/).
### Data Fields
Different datasets may have slightly varying fields, which include:
`file_name`: the file name \
`width` and `height`: the dimensions of the image \
`study`: which research study the image was collected as part of \
`location` : the name of the location at which the image was taken \
`annotations`: information about image annotation, which includes the taxonomy information, bounding box/boxes (`bbox`/`bboxes`) if any, as well as any other annotation information. \
`image` : the `path` to download the image and any other information that is available, e.g. its size in `bytes`.
### Data Splits
This dataset does not have a predefined train/test split.
## Dataset Creation
### Curation Rationale
The datasets that constitute LILA have been provided by the organizations, projects and researchers who collected them.
### Source Data
#### Initial data collection and normalization
N/A
#### Who are the source language producers?
N/A
### Annotations
#### Annotation process
Each dataset has been annotated by the members of the project/organization that provided it.
#### Who are the annotators?
The annotations have been provided by domain experts in fields such as biology and ecology.
### Personal and Sensitive Information
Some of the original data sets included a “human” class label; for privacy reasons, these images were removed. Those labels are still present in the metadata. If those images are important to your work, contact the [LILA maintainers](mailto:info@lila.science), since in some cases it will be possible to release those images under an alternative license.
## Considerations for Using the Data
### Social Impact of Dataset
Machine learning depends on labeled data, but accessing such data in biology and conservation is a challenge. Consequently, everyone benefits when labeled data is made available. Biologists and conservation scientists benefit by having data to train on, and free hosting allows teams to multiply the impact of their data (we suggest listing this benefit in grant proposals that fund data collection). ML researchers benefit by having data to experiment with.
### Discussion of Biases
These datasets do not represent global diversity, but are examples of local ecosystems and animals.
### Other Known Limitations
N/A
## Additional Information
### Tutorial
The [tutorial in this Google Colab notebook](https://colab.research.google.com/drive/17gPOIK-ksxPyX6yP9TaKIimlwf9DYe2R?usp=sharing) demonstrates how to work with this dataset, including filtering by species, collating configurations, and downloading images.
### Working with Taxonomies
All the taxonomy categories are saved as ClassLabels, which can be converted to strings as needed. Strings can likewise be converted to integers as needed, to filter the dataset. In the example below we filter the "Caltech Camera Traps" dataset to find all the entries with a "felis catus" as the species for the first annotation.
```python
dataset = load_dataset("society-ethics/lila_camera_traps", "Caltech Camera Traps", split="train")
taxonomy = dataset.features["annotations"].feature["taxonomy"]
# Filters to show only cats
cats = dataset.filter(lambda x: x["annotations"]["taxonomy"][0]["species"] == taxonomy["species"].str2int("felis catus"))
```
The original common names have been saved with their taxonomy mappings in this repository in `common_names_to_tax.json`. These can be used, for example, to map from a taxonomy combination to a common name to help make queries more legible. Note, however, that there is a small number of duplicate common names with different taxonomy values which you will need to disambiguate.
The following example loads the first "sea turtle" in the "Island Conservation Camera Traps" dataset.
```python
LILA_COMMON_NAMES_TO_TAXONOMY = pd.read_json("https://huggingface.co/datasets/society-ethics/lila_camera_traps/raw/main/data/common_names_to_tax.json", lines=True).set_index("common_name")
dataset = load_dataset("society-ethics/lila_camera_traps", "Island Conservation Camera Traps", split="train")
taxonomy = dataset.features["annotations"].feature["taxonomy"]
sea_turtle = LILA_COMMON_NAMES_TO_TAXONOMY.loc["sea turtle"].to_dict()
sea_turtle = {k: taxonomy[k].str2int(v) if v is not None else v for k, v in sea_turtle.items()} # Map to ClassLabel integers
sea_turtle_dataset = ds.filter(lambda x: x["annotations"]["taxonomy"][0] == sea_turtle)
```
The example below selects a random item from the dataset, and then maps from the taxonomy to a common name:
```python
LILA_COMMON_NAMES_TO_TAXONOMY = pd.read_json("https://huggingface.co/datasets/society-ethics/lila_camera_traps/raw/main/data/common_names_to_tax.json", lines=True).set_index("common_name")
dataset = load_dataset("society-ethics/lila_camera_traps", "Caltech Camera Traps", split="train")
taxonomy = dataset.features["annotations"].feature["taxonomy"]
random_entry = dataset.shuffle()[0]
filter_taxonomy = random_entry["annotations"]["taxonomy"][0]
filter_keys = list(map(lambda x: (x[0], taxonomy[x[0]].int2str(x[1])), filter(lambda x: x[1] is not None, list(filter_taxonomy.items()))))
if len(filter_keys) > 0:
print(LILA_COMMON_NAMES_TO_TAXONOMY[np.logical_and.reduce([
LILA_COMMON_NAMES_TO_TAXONOMY[k] == v for k,v in filter_keys
])])
else:
print("No common name found for the item.")
```
### Dataset Curators
LILA BC is maintained by a working group that includes representatives from Ecologize, Zooniverse, the Evolving AI Lab, Snapshot Safari, and Microsoft AI for Earth. Hosting on Microsoft Azure is provided by Microsoft AI for Earth.
### Licensing Information
Many, but not all, LILA data sets were released under the [Community Data License Agreement (permissive variant)](https://cdla.io/permissive-1-0/). Check the details of the specific dataset you are using in its section above.
### Citation Information
Citations for each dataset (if they exist) are provided in its section above.
### Contributions
Thanks to [@NimaBoscarino](https://github.com/NimaBoscarino/) for adding this dataset.
| [
-0.7117788791656494,
-0.10689835995435715,
-0.0693146139383316,
-0.07782619446516037,
-0.43166786432266235,
-0.007853072136640549,
0.016336308792233467,
-0.5568558573722839,
0.3143794536590576,
0.1696709394454956,
-0.34836646914482117,
-0.8821526765823364,
-0.5919632911682129,
0.5242947936... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
arbml/SANAD | arbml | 2022-10-30T23:09:16Z | 40 | 0 | null | [
"region:us"
] | 2022-10-30T23:09:16Z | 2022-10-30T23:08:02.000Z | 2022-10-30T23:08:02 | Entry not found | [
-0.3227645754814148,
-0.22568479180335999,
0.8622264862060547,
0.43461528420448303,
-0.52829909324646,
0.7012971639633179,
0.7915720343589783,
0.07618614286184311,
0.774603009223938,
0.2563217282295227,
-0.7852813005447388,
-0.22573819756507874,
-0.9104477167129517,
0.5715674161911011,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
pszemraj/text2image-multi-prompt | pszemraj | 2023-11-21T13:19:29Z | 40 | 8 | null | [
"task_categories:text-generation",
"task_categories:feature-extraction",
"multilinguality:monolingual",
"source_datasets:bartman081523/stable-diffusion-discord-prompts",
"source_datasets:succinctly/midjourney-prompts",
"source_datasets:Gustavosta/Stable-Diffusion-Prompts",
"language:en",
"license:apac... | 2023-11-21T13:19:29Z | 2022-11-09T22:47:39.000Z | 2022-11-09T22:47:39 | ---
language:
- en
license: apache-2.0
multilinguality:
- monolingual
source_datasets:
- bartman081523/stable-diffusion-discord-prompts
- succinctly/midjourney-prompts
- Gustavosta/Stable-Diffusion-Prompts
pretty_name: multi text2image prompts a dataset collection
tags:
- text generation
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
- config_name: original
data_files:
- split: train
path: original/train-*
- split: test
path: original/test-*
dataset_info:
- config_name: default
features:
- name: text
dtype: string
- name: src_dataset
dtype: string
splits:
- name: train
num_bytes: 262736830
num_examples: 1677221
- name: test
num_bytes: 56294291
num_examples: 292876
download_size: 151054782
dataset_size: 319031121
- config_name: original
features:
- name: text
dtype: string
- name: src_dataset
dtype: string
splits:
- name: train
num_bytes: 741427383
num_examples: 3551734
- name: test
num_bytes: 83615440
num_examples: 399393
download_size: 402186258
dataset_size: 825042823
task_categories:
- text-generation
- feature-extraction
---
# text2image multi-prompt(s): a dataset collection
- collection of several text2image prompt datasets
- data was cleaned/normalized with the goal of removing "model specific APIs" like the "--ar" for Midjourney and so on
- data de-duplicated on a basic level: exactly duplicate prompts were dropped (_after cleaning and normalization_)
## updates
- Oct 2023: the `default` config has been updated with better deduplication. It was deduplicated with minhash (_params: n-gram size set to 3, deduplication threshold at 0.6, hash function chosen as xxh3 with 32-bit hash bits, and 128 permutations with a batch size of 10,000._) which drops 2+ million rows.
- original version is still available under `config_name="original"`
## contents
default:
```
DatasetDict({
train: Dataset({
features: ['text', 'src_dataset'],
num_rows: 1677221
})
test: Dataset({
features: ['text', 'src_dataset'],
num_rows: 292876
})
})
```
For `original` config:
```
DatasetDict({
train: Dataset({
features: ['text', 'src_dataset'],
num_rows: 3551734
})
test: Dataset({
features: ['text', 'src_dataset'],
num_rows: 399393
})
})
```
_NOTE: as the other two datasets did not have a `validation` split, the validation split of `succinctly/midjourney-prompts` was merged into `train`._ | [
-0.4811640679836273,
-0.599478542804718,
0.4954628050327301,
0.05751945078372955,
-0.5252249240875244,
-0.2041516751050949,
-0.20362454652786255,
-0.27050599455833435,
-0.06832650303840637,
0.5829867124557495,
-0.8323076367378235,
-0.6063629388809204,
-0.7568359375,
0.3902105391025543,
-... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
bigbio/biology_how_why_corpus | bigbio | 2022-12-22T15:43:41Z | 40 | 2 | null | [
"multilinguality:monolingual",
"language:en",
"license:unknown",
"region:us"
] | 2022-12-22T15:43:41Z | 2022-11-13T22:06:38.000Z | 2022-11-13T22:06:38 |
---
language:
- en
bigbio_language:
- English
license: unknown
multilinguality: monolingual
bigbio_license_shortname: UNKNOWN
pretty_name: BiologyHowWhyCorpus
homepage: https://allenai.org/data/biology-how-why-corpus
bigbio_pubmed: False
bigbio_public: True
bigbio_tasks:
- QUESTION_ANSWERING
---
# Dataset Card for BiologyHowWhyCorpus
## Dataset Description
- **Homepage:** https://allenai.org/data/biology-how-why-corpus
- **Pubmed:** False
- **Public:** True
- **Tasks:** QA
This dataset consists of 185 "how" and 193 "why" biology questions authored by a domain expert, with one or more gold
answer passages identified in an undergraduate textbook. The expert was not constrained in any way during the
annotation process, so gold answers might be smaller than a paragraph or span multiple paragraphs. This dataset was
used for the question-answering system described in the paper “Discourse Complements Lexical Semantics for Non-factoid
Answer Reranking” (ACL 2014).
## Citation Information
```
@inproceedings{jansen-etal-2014-discourse,
title = "Discourse Complements Lexical Semantics for Non-factoid Answer Reranking",
author = "Jansen, Peter and
Surdeanu, Mihai and
Clark, Peter",
booktitle = "Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jun,
year = "2014",
address = "Baltimore, Maryland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P14-1092",
doi = "10.3115/v1/P14-1092",
pages = "977--986",
}
```
| [
-0.3925764560699463,
-0.773075520992279,
0.35796865820884705,
-0.007139574736356735,
-0.22910965979099274,
-0.058060478419065475,
0.011058492586016655,
-0.2866753041744232,
0.7009848952293396,
0.3340720534324646,
-0.5539578199386597,
-0.6813467144966125,
-0.4911065697669983,
0.511910438537... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
NeelNanda/code-tokenized | NeelNanda | 2022-11-14T00:05:01Z | 40 | 0 | null | [
"region:us"
] | 2022-11-14T00:05:01Z | 2022-11-14T00:04:10.000Z | 2022-11-14T00:04:10 | ---
dataset_info:
features:
- name: tokens
sequence: int64
splits:
- name: train
num_bytes: 2436318372
num_examples: 297257
download_size: 501062424
dataset_size: 2436318372
---
# Dataset Card for "code-tokenized"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.4209078848361969,
-0.2455541491508484,
-0.011221268214285374,
0.28693753480911255,
-0.22505420446395874,
0.22751958668231964,
0.0731058195233345,
-0.13935638964176178,
0.962055504322052,
0.5015835762023926,
-0.5557680726051331,
-0.8993338942527771,
-0.5985440015792847,
-0.19734047353267... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
jakartaresearch/causalqa | jakartaresearch | 2022-11-25T12:26:42Z | 40 | 0 | null | [
"task_categories:question-answering",
"task_ids:extractive-qa",
"annotations_creators:found",
"language_creators:found",
"multilinguality:monolingual",
"size_categories:1M<n<10M",
"source_datasets:original",
"language:en",
"question-answering",
"english",
"causal",
"region:us"
] | 2022-11-25T12:26:42Z | 2022-11-25T10:23:48.000Z | 2022-11-25T10:23:48 | ---
annotations_creators:
- found
language:
- en
language_creators:
- found
license: []
multilinguality:
- monolingual
pretty_name: CausalQA
size_categories:
- 1M<n<10M
source_datasets:
- original
tags:
- question-answering
- english
- causal
task_categories:
- question-answering
task_ids:
- extractive-qa
---
# Dataset Card for [Dataset Name]
## 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 [@alamhanz](https://github.com/alamhanz) and [@andreaschandra](https://github.com/andreaschandra) for adding this dataset.
| [
-0.4793245792388916,
-0.5089781880378723,
0.14798739552497864,
0.301754355430603,
-0.22386501729488373,
0.22066989541053772,
-0.34471288323402405,
-0.41272860765457153,
0.6499426960945129,
0.647637128829956,
-0.9111776947975159,
-1.2251379489898682,
-0.7626742124557495,
0.08470405638217926... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
memray/openkp | memray | 2022-12-31T06:04:30Z | 40 | 0 | null | [
"license:cc-by-nc-sa-4.0",
"region:us"
] | 2022-12-31T06:04:30Z | 2022-12-31T05:57:58.000Z | 2022-12-31T05:57:58 | ---
license: cc-by-nc-sa-4.0
---
| [
-0.1285335123538971,
-0.1861683875322342,
0.6529128551483154,
0.49436232447624207,
-0.19319400191307068,
0.23607441782951355,
0.36072009801864624,
0.05056373029947281,
0.5793656706809998,
0.7400146722793579,
-0.650810182094574,
-0.23784008622169495,
-0.7102247476577759,
-0.0478255338966846... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
sander-wood/irishman | sander-wood | 2023-09-25T15:14:16Z | 40 | 11 | null | [
"task_categories:text-generation",
"size_categories:100K<n<1M",
"license:mit",
"music",
"region:us"
] | 2023-09-25T15:14:16Z | 2023-01-10T23:42:04.000Z | 2023-01-10T23:42:04 | ---
license: mit
task_categories:
- text-generation
pretty_name: IrishMAN
size_categories:
- 100K<n<1M
tags:
- music
---
If you prefer MIDI or MusicXML, download [IrishMAN-MIDI](https://huggingface.co/datasets/sander-wood/irishman/resolve/main/irishman-midi.zip) or [IrishMAN-XML](https://huggingface.co/datasets/sander-wood/irishman/resolve/main/irishman-xml.zip). For better use of structural info in control codes, consider ABC notation.
## ABC Notation
ABC notation is an ASCII-based plain text musical notation system that is commonly used for transcribing traditional music and sharing sheet music online. It provides a simple and concise way to represent musical elements such as notes, rhythms, chords, and more.
For those looking to interact with ABC notation in various ways, there are several tools available:
1. **[Online ABC Player](https://abc.rectanglered.com/):** This web-based tool allows you to input ABC notation and hear the corresponding audio playback. By pasting your ABC code into the player, you can instantly listen to the tune as it would sound when played.
2. **[ABC Sheet Music Editor - EasyABC](https://easyabc.sourceforge.net/):** EasyABC is a user-friendly software application designed for creating, editing, and formatting ABC notation. Its graphical interface enables you to input your ABC code, preview the sheet music, and make adjustments as necessary.
## Dataset Summary
The **Irish Massive ABC Notation (IrishMAN)** dataset includes 216,284 Irish tunes in ABC notation, divided into 99\% (214,122 tunes) for training and 1\% (2,162 tunes) for validation. These tunes were collected from thesession.org and abcnotation.com, both renowned for sharing traditional music. To ensure uniformity in formatting, all tunes were converted to XML and then back to ABC using [scripts](https://wim.vree.org/svgParse/), and fields containing natural language (e.g., titles and lyrics) were removed.
Each tune is automatically annotated with control codes derived from ABC symbols, as described in the below section. These control codes offer insights into the musical forms and structures of each composition.
In the IrishMAN dataset, a [music21](https://web.mit.edu/music21/doc/index.html#)-filtered [subset](https://huggingface.co/datasets/sander-wood/irishman/raw/main/leadsheet_ids.json) includes 34,211 lead sheets, each human-annotated with chord symbols. It is from this very subset that [TunesFormer](https://huggingface.co/sander-wood/tunesformer) developed its capacity to generate melodies with harmonies.
A noteworthy aspect is the copyright status. All tunes in the dataset are in the public domain, ensuring ethical and legal usage for research and creative projects.
## Control Codes
Inspired by [CTRL](https://huggingface.co/ctrl), we incorporate control codes into TunesFormer to represent musical forms. These codes, positioned ahead of the ABC notation, enable users to specify the structures of the generated tunes. The following control codes are introduced:
- **S:number of sections**: determines the number of sections in the entire melody. It counts on several symbols that can be used to represent section boundaries: `[|`, `||`, `|]`, `|:`, `::`, and `:|`. In our dataset, the range is 1 to 8 (e.g., `S:1` for a single-section melody, and `S:8` for a melody with eight sections).
- **B:number of bars**: specifies the desired number of bars within a section. It counts on the bar symbol `|`. In our dataset, the range is 1 to 32 (e.g., `B:1` for a one-bar section, and `B:32` for a section with 32 bars).
- **E:edit distance similarity**: controls the similarity level between the current section $c$ and a previous section $p$ in the melody. It is based on the Levenshtein distance $lev(c,p)$ , quantifying the difference between sections for creating variations or contrasts. Mathematically, it can be expressed as:
```
eds(c,p) = 1 - lev(c,p) / max(|c|,|p|)
```
where $|c|$ and $|p|$ are the string lengths of the two sections. It is discretized into 11 levels, ranging from no match at all to an exact match (e.g., `E:0` for no similarity, and `E:10` for an exact match).
## Copyright Disclaimer
This dataset is for research use only and not for commercial purposes. We believe all data in this dataset is in the public domain. If you own the copyright to any musical composition in the IrishMAN dataset and have concerns, please contact us at shangda@mail.ccom.edu.cn. We will address your concerns and take appropriate action if needed.
## Special Thanks
We would like to extend a special thanks to thesession.org and abcnotation.com for their contributions to the development and promotion of ABC notation, as well as their significant impact on the field of music information retrieval. Their platforms have become invaluable resources for the traditional and folk music community. We also wish to express our gratitude to Willem (Wim) for providing the essential conversion tools that enabled the transformation of the tunes into a uniform format. Together, these collaborations have made it possible for researchers like us to create and study extensive datasets like IrishMAN. | [
-0.38627636432647705,
-0.48417332768440247,
0.24908877909183502,
0.6780910491943359,
-0.20772860944271088,
-0.10005723685026169,
-0.3880641758441925,
-0.6066986918449402,
0.46226778626441956,
0.6069248914718628,
-0.4505690932273865,
-0.9390025734901428,
-0.31346505880355835,
0.426505833864... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
brunokreiner/genius-lyrics | brunokreiner | 2023-03-07T21:57:02Z | 40 | 2 | null | [
"region:us"
] | 2023-03-07T21:57:02Z | 2023-01-18T22:39:24.000Z | 2023-01-18T22:39:24 | ---
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/datasets-cards
{}
---
# Dataset Card for Dataset Name
## Dataset Description
- **Homepage:**
- **Repository:**
- **Paper:**
- **Leaderboard:**
- **Point of Contact:**
### Dataset Summary
This dataset consists of roughly 480k english (classified using nltk language classifier) lyrics with some more meta data. The meta data was taken from the million playlist challenge @ AICrowd. The lyrics were crawled using the song and artist name with the lyricsgenius python package. There is no guarantee that the lyrics are the correct one though the data was cleaned and verified. The lyrics crawled came with the song name in its payload, if the song names in the payload and from our side don't match (using the package fuzzywuzzy string matching with a score of under 60) then it wasn't included in this set of lyrics. Still some lyrics might be wrong due to the nature of the data.
49'985 rows have a list of genres, crawled from the official Spotify API. This list of genres are from the artist of the song since spotify doesn't provide genres for every individual song.
### 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] | [
-0.3939787447452545,
-0.2633114755153656,
0.20879441499710083,
0.3579328656196594,
-0.10836417973041534,
0.11420927196741104,
-0.37542083859443665,
-0.2569832503795624,
0.43174806237220764,
0.9258841276168823,
-1.0592451095581055,
-1.0208971500396729,
-0.7283514738082886,
0.119607016444206... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
imvladikon/parashoot | imvladikon | 2023-01-22T00:32:13Z | 40 | 0 | null | [
"task_categories:question-answering",
"language:he",
"arxiv:1606.05250",
"arxiv:2109.11314",
"region:us"
] | 2023-01-22T00:32:13Z | 2023-01-22T00:05:53.000Z | 2023-01-22T00:05:53 | ---
task_categories:
- question-answering
language:
- he
---
# ParaShoot
[ParaShoot](https://github.com/omrikeren/ParaShoot): A Hebrew question and answering dataset in the style of [SQuAD](https://arxiv.org/abs/1606.05250), based on articles scraped from Wikipedia. The dataset contains a few thousand crowdsource-annotated pairs of questions and answers, in a setting suitable for few-shot learning.
For more details and quality analysis, see the [paper](https://arxiv.org/abs/2109.11314).
## Dataset Statistics
| **#Items** | **#Articles** | **#Paragraphs** | |
| ---------- | ------------- | --------------- | ------- |
| Train | 1792 | 295 | 565 |
| Dev | 221 | 33 | 63 |
| Test | 1025 | 165 | 319 |
| **Total** | **3038** | **493** | **947** |
## Citing
If you use ParaShoot in your research, please cite the ParaShoot paper:
```bibtex
@inproceedings{keren2021parashoot,
title={ParaShoot: A Hebrew Question Answering Dataset},
author={Keren, Omri and Levy, Omer},
booktitle={Proceedings of the 3rd Workshop on Machine Reading for Question Answering},
pages={106--112},
year={2021}
}
``` | [
-0.5077967643737793,
-0.5164055228233337,
0.3345910608768463,
0.0837353840470314,
-0.5285041332244873,
-0.29076167941093445,
0.04492863267660141,
-0.29168951511383057,
0.2606842815876007,
0.4509018659591675,
-0.5037023425102234,
-0.8122857213020325,
-0.4110323488712311,
0.16130131483078003... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
intfloat/query2doc_msmarco | intfloat | 2023-03-30T02:44:59Z | 40 | 7 | null | [
"size_categories:100K<n<1M",
"language:en",
"license:cc-by-4.0",
"arxiv:2303.07678",
"region:us"
] | 2023-03-30T02:44:59Z | 2023-03-10T10:28:59.000Z | 2023-03-10T10:28:59 | ---
license: cc-by-4.0
language:
- en
size_categories:
- 100K<n<1M
---
### Dataset Summary
This dataset contains GPT-3.5 (`text-davinci-003`) generations from MS-MARCO queries.
[Query2doc: Query Expansion with Large Language Models](https://arxiv.org/pdf/2303.07678.pdf) Liang Wang, Nan Yang and Furu Wei
### Data Instances
An example looks as follows.
```
{
"query_id": "1030303",
"query": "who is aziz hashim",
"pseudo_doc": "Aziz Hashim is a renowned entrepreneur, business leader, and one of the most successful restaurant franchise operators in the US. He is the founder of NRD Capital, a private equity firm focused on investments in multi-unit restaurant franchised businesses. Hashim has built a formidable track record of success in the franchise industry, with brands such as Outback Steakhouse and Jamba Juice. His accomplishments and philanthropic initiatives have earned him numerous awards, including the prestigious Ernst and Young Entrepreneur of the Year award."
}
```
### Data Fields
- `query_id`: a `string` feature.
- `query`: a `string` feature.
- `pseudo_doc`: a `string` feature.
### Data Splits
| train | dev | test | trec_dl2019 | trec_dl2020 |
|--------|------:|------:|------:|------:|
| 502939 | 6980 | 6837 | 43 | 54 |
### How to use this dataset
```python
from datasets import load_dataset
dataset = load_dataset('intfloat/query2doc_msmarco')
print(dataset['trec_dl2019'][0])
```
### Reproducing our results
We provide a python script [repro_bm25.py](https://huggingface.co/datasets/intfloat/query2doc_msmarco/blob/main/repro_bm25.py) to reproduce our results with BM25 retrieval.
First install some python dependency packages:
```
pip install pyserini==0.15.0 pytrec_eval datasets tqdm
```
Then download and run the python code:
```
python repro_bm25.py
```
This script utilizes the pre-built Lucene index from [Pyserini](https://github.com/castorini/pyserini/blob/pyserini-0.15.0/docs/prebuilt-indexes.md)
and might yield slightly different results compared to the paper.
### Citation Information
```
@article{wang2023query2doc,
title={Query2doc: Query Expansion with Large Language Models},
author={Wang, Liang and Yang, Nan and Wei, Furu},
journal={arXiv preprint arXiv:2303.07678},
year={2023}
}
```
| [
-0.2218995839357376,
-0.6722712516784668,
0.5143194794654846,
0.13346944749355316,
-0.007210069335997105,
-0.1104428693652153,
-0.29738470911979675,
-0.09827354550361633,
-0.03996003791689873,
0.4651414453983307,
-0.3614600598812103,
-0.7716786861419678,
-0.4904033839702606,
0.157499074935... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
bigcode/the-stack-github-issues | bigcode | 2023-03-20T18:07:26Z | 40 | 17 | null | [
"task_categories:text-generation",
"task_ids:language-modeling",
"language_creators:crowdsourced",
"multilinguality:monolingual",
"size_categories:unknown",
"language:en",
"region:us"
] | 2023-03-20T18:07:26Z | 2023-03-16T15:28:51.000Z | 2023-03-16T15:28:51 | ---
annotations_creators: []
language_creators:
- crowdsourced
language:
- en
multilinguality:
- monolingual
size_categories:
- unknown
source_datasets: []
task_categories:
- text-generation
task_ids:
- language-modeling
extra_gated_prompt: |-
## Terms of Use for The Stack
The Stack dataset is a collection of source code in over 300 programming languages. We ask that you read and acknowledge the following points before using the dataset:
1. The Stack is a collection of source code from repositories with various licenses. Any use of all or part of the code gathered in The Stack must abide by the terms of the original licenses, including attribution clauses when relevant. We facilitate this by providing provenance information for each data point.
2. The Stack is regularly updated to enact validated data removal requests. By clicking on "Access repository", you agree to update your own version of The Stack to the most recent usable version specified by the maintainers in [the following thread](https://huggingface.co/datasets/bigcode/the-stack/discussions/7). If you have questions about dataset versions and allowed uses, please also ask them in the dataset’s [community discussions](https://huggingface.co/datasets/bigcode/the-stack/discussions/new). We will also notify users via email when the latest usable version changes.
3. To host, share, or otherwise provide access to The Stack dataset, you must include [these Terms of Use](https://huggingface.co/datasets/bigcode/the-stack#terms-of-use-for-the-stack) and require users to agree to it.
By clicking on "Access repository" below, you accept that your contact information (email address and username) can be shared with the dataset maintainers as well.
extra_gated_fields:
Email: text
I have read the License and agree with its terms: checkbox
---
## Dataset Description
This dataset contains conversations from GitHub issues and Pull Requests. Each conversation is comprised of a series of events, such as opening an issue, creating a comment,
or closing the issue, and includes the author's username, text, action, and identifiers such as the issue ID and number.
The dataset, which is mostly in English, has a total size of 54GB and 30.9M files.
## Dataset Structure
```python
from datasets import load_dataset
dataset = load_dataset("bigcode/the-stack-github-issues")
dataset
```
```
Dataset({
features: ['repo', 'issue_id', 'issue_number', 'pull_request', 'events', 'text_size', 'content', 'usernames'],
num_rows: 30982955
})
```
- `content` contains the full text in the conversation concatenated with special tokens: `<issue_start>` for the beginning of the issue, `<issue_comment>` before each comment
and `<issue_closed>` if a conversation is closed. Each comment is prepended with `username_{i}:` before the text, `username_{i}` is the mask for author `i`. This column
is intended for model training to avoid memorizing usernames, and understand the structure of the conversation.
- `events` contains the detailed events on top of which we built `content`, it also includes information the username's author and mask used.
Below is an example:
````
{'content': '<issue_start><issue_comment>Title: Click Save: Sorry, Cannot Write\n
'username_0: Hi all, Edit a file in Ice, click Save Icon\n Get error message: Sorry, cannot write /var/www/index.html
...
Edit: Also getting error: Cannot Zip Files up.\n
<issue_comment>username_1: hi there i have a similar problem. I cant save the files...',
'events': [{'action': 'opened',
'author': 'LaZyLion-ca',
'comment_id': None,
'datetime': '2013-06-06T13:30:31Z',
'masked_author': 'username_0',
'text': 'Hi all, Edit a file in Ice, click Save Icon...'
'title': 'Click Save: Sorry, Cannot Write',
'type': 'issue'},
...],
'issue_id': 15222443,
'issue_number': 264,
'pull_request': None,
'repo': 'icecoder/ICEcoder',
'text_size': 525,
'usernames': '["LaZyLion-ca", "seyo-IV"]'}
````
### Dataset pre-processing
This dataset was collected as part of [The Stack](https://huggingface.co/datasets/bigcode/the-stack) dataset, and the curation rationale can be found at this [link](https://huggingface.co/datasets/bigcode/the-stack#source-data).
To improve the quality of the dataset and remove personally identifiable information (PII), we performed the following cleaning steps, which reduced the dataset's size from 180GB to 54GB:
- We first removed automated text generated when users reply using their emails, using regex matching. We also deleted issues with little text (less than 200 total characters) and truncated long comments in the middle
(to a maximum of 100 lines while keeping the last 20 lines). This step removed 18% of the volume.
- We deleted comments from bots by looking for keywords in the author's username. If an issue became empty after this filtering, we removed it.
We also removed comments that preceded those from bots if they triggered them, by looking for the bot's username inside the text. This step removed 61% of the remaining volume and 22% of the conversations,
as bot-generated comments tend to be very long.
- We then used the number of users in the conversation as a proxy for quality. We kept all conversations with two or more users.
If a conversation had only one user, we kept it only if the total text was larger than 200 characters and smaller than 7000 characters.
We also removed issues with more than 10 events, as we noticed that they were of low quality or from bots we missed in the previous filtering.
This filtering removed 4% of the volume and 30% of the conversations.
- To redact PII, we masked IP addresses, email addresses, and secret keys from the text using regexes. We also masked the usernames of the authors from
the comments and replaced them with username_{i}, where i is the order of the author in the conversation. | [
-0.44362306594848633,
-0.5226890444755554,
0.11166369169950485,
0.018655849620699883,
-0.2266530692577362,
0.05002720281481743,
-0.3972684442996979,
-0.3285178542137146,
0.5380711555480957,
0.711934506893158,
-0.5415593981742859,
-0.6815344095230103,
-0.49810945987701416,
0.273195952177047... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
mstz/heloc | mstz | 2023-04-07T13:57:28Z | 40 | 0 | null | [
"task_categories:tabular-classification",
"size_categories:10K<n<100K",
"language:en",
"license:cc",
"heloc",
"fico",
"tabular_classification",
"binary_classification",
"region:us"
] | 2023-04-07T13:57:28Z | 2023-03-23T14:08:41.000Z | 2023-03-23T14:08:41 | ---
language:
- en
tags:
- heloc
- fico
- tabular_classification
- binary_classification
pretty_name: Heloc
size_categories:
- 10K<n<100K
task_categories:
- tabular-classification
configs:
- risk
license: cc
---
# HELOC
The [HELOC dataset](https://community.fico.com/s/explainable-machine-learning-challenge?tabset-158d9=d157e) from FICO.
Each entry in the dataset is a line of credit, typically offered by a bank as a percentage of home equity (the difference between the current market value of a home and its purchase price).
The customers in this dataset have requested a credit line in the range of $5,000 - $150,000.
The fundamental task is to use the information about the applicant in their credit report to predict whether they will repay their HELOC account within 2 years.
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-------------------|---------------------------|-----------------------------------------------------------------|
| risk | Binary classification | Will the customer default? |
# Usage
```python
from datasets import load_dataset
dataset = load_dataset("mstz/heloc")["train"]
```
# Features
|**Feature** |**Type**|
|-------------------------------------------|--------|
|`estimate_of_risk` |`int8` |
|`months_since_first_trade` |`int32` |
|`months_since_last_trade` |`int32` |
|`average_duration_of_resolution` |`int32` |
|`number_of_satisfactory_trades` |`int16` |
|`nr_trades_insolvent_for_over_60_days` |`int16` |
|`nr_trades_insolvent_for_over_90_days` |`int16` |
|`percentage_of_legal_trades` |`int16` |
|`months_since_last_illegal_trade` |`int32` |
|`maximum_illegal_trades_over_last_year` |`int8` |
|`maximum_illegal_trades` |`int16` |
|`nr_total_trades` |`int16` |
|`nr_trades_initiated_in_last_year` |`int16` |
|`percentage_of_installment_trades` |`int16` |
|`months_since_last_inquiry_not_recent` |`int16` |
|`nr_inquiries_in_last_6_months` |`int16` |
|`nr_inquiries_in_last_6_months_not_recent` |`int16` |
|`net_fraction_of_revolving_burden` |`int32` |
|`net_fraction_of_installment_burden` |`int32` |
|`nr_revolving_trades_with_balance` |`int16` |
|`nr_installment_trades_with_balance` |`int16` |
|`nr_banks_with_high_ratio` |`int16` |
|`percentage_trades_with_balance` |`int16` | | [
-0.4959813356399536,
-0.48012775182724,
0.14628994464874268,
0.2591244876384735,
-0.005429662764072418,
0.04354261979460716,
0.04610225185751915,
-0.5167884826660156,
0.11525116115808487,
0.7571753859519958,
-0.5886505246162415,
-0.8169229030609131,
-0.9176684617996216,
-0.2115267813205719... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
AlexFierro9/imagenet-1k_test | AlexFierro9 | 2023-03-26T14:51:51Z | 40 | 0 | null | [
"license:bsd-2-clause",
"region:us"
] | 2023-03-26T14:51:51Z | 2023-03-26T14:36:23.000Z | 2023-03-26T14:36:23 | ---
license: bsd-2-clause
---
| [
-0.1285339742898941,
-0.18616800010204315,
0.6529127359390259,
0.4943626821041107,
-0.1931934952735901,
0.2360742688179016,
0.360720157623291,
0.05056300014257431,
0.5793654322624207,
0.7400140166282654,
-0.6508105993270874,
-0.23783984780311584,
-0.7102248668670654,
-0.047826044261455536,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
mrm8488/chatdoctor200k | mrm8488 | 2023-03-29T19:57:18Z | 40 | 0 | null | [
"region:us"
] | 2023-03-29T19:57:18Z | 2023-03-29T19:57:01.000Z | 2023-03-29T19:57:01 | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 207526604
num_examples: 207407
download_size: 115879622
dataset_size: 207526604
---
# Dataset Card for "chatdoctor200k"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.6385462284088135,
-0.20403485000133514,
-0.024110401049256325,
0.45046207308769226,
0.018692616373300552,
0.06647665053606033,
0.2585361897945404,
-0.03813731297850609,
0.7073717713356018,
0.5377102494239807,
-1.0166946649551392,
-0.6656512022018433,
-0.6003391146659851,
-0.407116800546... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
distil-whisper/spgispeech | distil-whisper | 2023-09-25T10:28:52Z | 40 | 0 | null | [
"task_categories:automatic-speech-recognition",
"language:en",
"license:other",
"region:us"
] | 2023-09-25T10:28:52Z | 2023-04-07T21:11:05.000Z | 2023-04-07T21:11:05 | ---
license: other
task_categories:
- automatic-speech-recognition
language:
- en
extra_gated_prompt: |-
Your access to and use of the information in the Kensho Transcript Dataset (the “Content”), which is provided by Kensho Technologies, LLC, a subsidiary of S&P Global, Inc., (“Kensho”), shall be governed by the following terms and conditions of usage (“Terms of Usage”). The Content may be accessed only by persons who have been authorized to use this Content pursuant to their acceptance and acknowledgement of these Terms of Usage (in each case, an “Authorized User”). By providing your electronic signature at the end of these Terms of Usage, you represent that you are an Authorized User and that you accept these Terms of Usage and agree to be bound by them.
If you do not wish to be bound by these Terms of Usage, you must not use this Content. PLEASE READ THESE TERMS OF USAGE CAREFULLY BEFORE USING THIS CONTENT.
Section 1 – THE CONTENT
1.1 The Content is provided for academic research purposes and internal use only and must not be used to: assemble or create a database; construct or facilitate the construction of products which compete with the Content; identify or attempt to identify or contact any individual; or link to another dataset.
The Content, which is comprised of public earnings calls in audio and corresponding text format, and all accompanying derived products is proprietary to Kensho and its third-party content providers. You shall not modify the Content; create derivative works based on the Content, rewrite or reprocess the Content except as expressly provided herein. You must not publish, display, transfer or redistribute the Content or any portions or derivative versions thereof to anyone without prior written consent from Kensho. You agree not to contact Kensho or its affiliates concerning individuals whose information may be included in the Content.
1.2 Disclaimer. Content to which you are provided access, either directly or indirectly, from or on this Content will not have been reviewed or monitored by Kensho, and Kensho cannot and does not guarantee or make any representation or warranty, either express or implied, as to the accuracy, validity, timeliness, completeness or continued availability of any such content.
The Content is provided for your convenience only and is not a republication or reconfirmation of the opinion or information contained therein. The provision of the Content is without any obligation on the part of Kensho or its third-party content providers to review such or any liability or responsibility arising out of your use thereof. Kensho does not guarantee or make any representation or warranty, either express or implied, as to the accuracy, validity, timeliness, completeness or continued availability of any Content and shall not be liable for any errors, delays, or actions taken in reliance on information. In addition, the Content speaks only as of the date issued and is based on conference calls that may contain projections of other forward-looking statements. You should not rely on the Content as expressing Kensho’s opinion or as representing current information. None of Kensho or the third-party content providers has undertaken, and do not undertake any duty to update any Content or otherwise advise you of any changes in the Content.
1.3 Ownership of Third-Party Content. You acknowledge that all proprietary rights in the Content that are owned by Kensho or third party content providers shall remain the property of Kensho or such third party content providers, and you shall have no right or interest in such third party content except the rights to use such third party content in accordance with these Terms of Usage. Any additional rights not granted herein shall require a separate, direct agreement with Kensho. You acknowledge that the Content and third party content as compiled, prepared, selected and arranged by Kensho or its third party content providers constitutes an expenditure of substantial time, effort and money by Kensho and its third party content providers and constitutes valuable commercial property and/or trade secrets of Kensho and such third party content providers. Kensho retains all rights and remedies afforded under the copyright, trademark, service mark, patent and other laws of the United States and the States thereof, including without limitation any laws designed to protect proprietary or confidential information. You agree that you will not remove or modify any copyright notice, disclosures, disclaimers or other notification or trade name or marks of Kensho or the third party content providers that may appear in the Content or third party content and that any permitted reproduction and/or distribution of the Content or third party content shall contain such notices and/or marks as they appear in the Content or third party content. You may not use Kensho’s or the third-party content providers’ name or trademarks without the prior written consent of Kensho or such third-party content providers. Apart from the rights granted hereunder, no conveyance of ownership, right, title or interest is intended herein. Any additional rights require a separate agreement with Kensho.
1.4 Posted Guidelines. In addition to these Terms of Usage, when using this Content, you shall be subject to and agree to follow any posted notice, guidelines or rules, which may be posted and amended from time to time. Nothing on this Content shall be considered a recommendation or solicitation to buy or an offer to sell a security to any person in any jurisdiction.
1.5 Registration Data. In consideration of your use of this Content, you and/or your employer agree to: (a) provide true, accurate, current and complete Registration Data (as defined below in Section 3.1) to Kensho as prompted by the registration form completed prior to accessing the Content and (b) maintain and promptly update the Registration Data and to keep the same true, accurate, current and complete.
1.6 Right to Terminate User Access. Kensho reserves the right to limit, restrict and immediately terminate your access to and use of this Content at any time, in whole or in part, in its sole discretion and without notice.
Section 2 - DISCLAIMER OF WARRANTY AND LIMITATION OF LIABILITY
2.1 THE CONTENT IS PROVIDED “AS IS” AND “AS AVAILABLE” WITHOUT REPRESENTATION OR WARRANTY OF ANY KIND. USE OF THE CONTENT IS AT THE USER’S OWN RISK. IN NO EVENT SHALL KENSHO OR ITS THIRD-PARTY CONTENT PROVIDERS BE LIABLE FOR ANY DECISION MADE OR ACTION OR INACTION TAKEN IN RELIANCE ON ANY CONTENT, INCLUDING THIRD-PARTY CONTENT, INCLUDING YOUR HANDLING AND STORING OF THE CONTENT. KENSHO FURTHER EXPLICITLY DISCLAIMS, ANY WARRANTY OF ANY KIND, WHETHER EXPRESS OR IMPLIED, INCLUDING WARRANTIES OF ORIGINALITY, ACCURACY, COMPLETENESS, TIMELINESS, MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. KENSHO EXPRESSLY DISCLAIMS, AND YOU WAIVE, ANY LIABILITY THAT MAY ARISE FROM YOUR PUBLICATION OR PROVISION OF THE CONTENT TO A THIRD PARTY, OR ANY REPRESENTATION OR WARRANTY MADE BY YOU TO ANY THIRD PARTY, WHETHER OR NOT RELATED TO THE CONTENT. KENSHO, SUPPLIERS OF THIRD-PARTY CONTENT AND ANY OTHER THIRD PARTY WORKING WITH KENSHO SHALL NOT BE RESPONSIBLE OR LIABLE, DIRECTLY OR INDIRECTLY, FOR ANY DAMAGES OR LOSS (INCLUDING DIRECT, INDIRECT, INCIDENTAL, CONSEQUENTIAL AND ANY AND ALL OTHER FORMS OF DAMAGES OR LOSSES REGARDLESS OF THE FORM OF THE ACTION OR THE BASIS OF THE CLAIM) CAUSED OR ALLEGED TO BE CAUSED IN CONNECTION WITH YOUR USE OF THE CONTENT WHETHER OR NOT FORESEEABLE, EVEN IF KENSHO OR ANY OF THE SUPPLIERS OF THIRD-PARTY CONTENT OR OTHER THIRD PARTIES WORKING WITH KENSHO IN CONNECTION WITH THE CONTENT HAS BEEN ADVISED OF THE POSSIBILITY OR LIKELIHOOD OF SUCH DAMAGES.
2.2 THE CONTENT IS NOT INTENDED TO PROVIDE TAX, LEGAL, INSURANCE OR INVESTMENT ADVICE, AND NOTHING IN THE CONTENT SHOULD BE CONSTRUED AS AN OFFER TO SELL, A SOLICITATION OF AN OFFER TO BUY, OR A RECOMMENDATION FOR ANY SECURITY BY KENSHO OR ANY THIRD PARTY.
2.3 For third party demands, claims, actions, proceedings and liability for losses, damages, reasonable legal costs and other reasonable expenses of any nature, you agree to defend, indemnify and hold Kensho and its affiliates harmless, including its respective directors, officers, employees and agents from and against all claims to the extent arising from your access to and/or use of the Content, any failure by you to abide by the Terms of Usage, or breach of applicable law.
Section 3 - PRIVACY
3.1 Access and Collection. In order to access this Content, during the registration process, either you or your employer will be required to provide Kensho with certain information; including your name, employer or academic institution, and e-mail address (“Registration Data”). In addition, when you request or view Content, Kensho may obtain user identifiable information related to your request of, or access to, such Content (“Access Data”). For example, while you are accessing this Content, our Web servers may recognize your: (a) domain name; (b) ISP’s domain name; (c) IP address; (d) browser type; and (e) operating system. If you contact us with a technical question, we may collect certain information about your systems, including: (a) your browser type, version and settings (e.g., Java and cookie settings); (b) connectivity information (e.g., SSL/HTTPS compatibility, bandwidth capacity); and browser plug-in information (e.g., do you have Adobe, what is your media player, can you open Flash files, etc.).
3.2 Use of Your Information. Registration Data and Access Data may be used by Kensho for research and development purposes and to communicate with users and to troubleshoot any technical issues pertaining to the Content. You acknowledge that in the event that a separate agreement is required, Kensho may share Registration Data with its Affiliates (as defined below).
3.3 Disclosure of Your Information. Except as otherwise noted herein, Kensho will not disclose, rent or sell personal information collected from or about you without your permission. For the purposes specified in the preceding paragraph, we may transfer or disclose Registration Data and Access Data to S&P Global Inc. and its affiliates (“Kensho Affiliates”) and third parties who are contracted to perform services on behalf of Kensho, such as those who assist Kensho in bringing you this Content and providing you with certain features and functionality included within or accessible via this Content. We may also disclose Registration Data and Access Data to Kensho Affiliates and third parties in connection with their providing you access to this Content. Disclosures to these third parties will be subject to confidentiality agreements and, where required, governed by contract. Kensho may also be required to disclose information to governmental, regulatory or self-regulatory entities or agencies in response to regulatory inquiries or to comply with applicable laws, rules, regulations, orders, subpoenas or other legal processes.
3.4 Consent. By (a) agreeing to these Terms of Usage, or (b) by using this Content, and, in either case, providing any information that may be required, requested or otherwise collected by us as set forth above, you freely consent to Kensho processing your information in the United States and in other countries and territories for the purposes set out in these Terms of Usage, and you also consent to the transfer of your information for such purposes to any third party content provider wherever such entity may from time to time be located and to any third parties as described above and in accordance with applicable law and regulations. If you do not permit Kensho to collect any of your information or do not agree with any of the terms and conditions of these Terms of Usage, you should not use this Content and should exit this page and/or Content, as the case may be. If after registering with Kensho, you desire to withdraw the consent granted in this Section 3.4 for all future use of your information by Kensho, you must notify Kensho in writing at the address listed below in Section 3.8 and immediately cease use of this Content.
3.5 Inquiries. If you have any questions regarding these Terms of Usage or your information that is held by us, please contact Kensho in writing using the contact information provided below. If we receive a request regarding your personal information held by us, we will use reasonable means to provide you with such information that we can reasonably compile. You will be given the opportunity to rectify any inaccuracies in such information.
3.6 Encryption. Kensho may use encryption technology to protect certain transmissions of data to/from this Content, but e-mail and other communications, unless otherwise noted on this Content, are not encrypted to/from this Content. Therefore, you should not send any personal or identifying information, such as account numbers, credit card numbers, Social Security numbers, passwords, etc., to Kensho via e-mail. By utilizing e-mail or other electronic communication means you acknowledge that you have no expectation of privacy with respect to the information delivered thereby and that Kensho will not be responsible for any loss or damage that could result from interception by third parties of any information so sent.
3.7 Contact Information. In the event you have any questions regarding these Terms of Use, this Privacy Statement or to make any requests or queries regarding your information that is held by us you may contact us in writing at privacy@kensho.com or Kensho Technologies LLC, Attn: General Counsel, 55 Water Street, New York, NY 10041.
Section 4 - MISCELLANEOUS
4.1 Entire Agreement. These Terms of Usage constitute the entire agreement of the parties hereto with respect to the subject matter hereof and supersede all prior agreements and undertakings, both written and oral, between the parties with respect to the subject matter hereof.
4.2 Severability. If any term or other provision of these Terms of Usage is invalid, illegal or incapable of being enforced by any law or public policy, all other terms and provisions of these Terms of Usage shall nevertheless remain in full force and effect so long as the economic or legal substance of the transactions contemplated hereby is not affected in any manner materially adverse to any party.
4.3 Governing Law; Forum. These Terms of Usage shall be governed in all respects by the laws of the State of New York, and any litigation arising out of or connected in any way with these Terms of Usage shall take place in a State or Federal court of competent jurisdiction in New York County, State of New York.
4.4 Waiver of Jury Trial. YOU WAIVE TO THE FULLEST EXTENT PERMITTED BY APPLICABLE LAW ANY RIGHT YOU MAY HAVE TO A TRIAL BY JURY WITH RESPECT TO ANY ACTIONS OR PROCEEDINGS DIRECTLY OR INDIRECTLY ARISING OUT OF, UNDER OR IN CONNECTION WITH THESE TERMS OF USAGE.
4.5 Conflict. In the event of a conflict between these Terms of Use and any other agreement with Kensho that relates to Third-Party Content, the more restrictive terms shall prevail.
extra_gated_fields:
Full name: text
Email: text
Institution: text
I accept the Terms of Usage: checkbox
---
# Distil Whisper: SPGISpeech
This is a variant of the [SPGISpeech](https://huggingface.co/datasets/kensho/spgispeech) dataset, augmented to return the pseudo-labelled Whisper
Transcriptions alongside the original dataset elements. The pseudo-labelled transcriptions were generated by
labelling the input audio data with the Whisper [large-v2](https://huggingface.co/openai/whisper-large-v2)
model with *greedy* sampling. For information on how the original dataset was curated, refer to the original
[dataset card](https://huggingface.co/datasets/kensho/spgispeech).
## Standalone Usage
First, install the latest version of the 🤗 Datasets package:
```bash
pip install --upgrade pip
pip install --upgrade datasets[audio]
```
The dataset can be downloaded and pre-processed on disk using the [`load_dataset`](https://huggingface.co/docs/datasets/v2.14.5/en/package_reference/loading_methods#datasets.load_dataset)
function:
```python
from datasets import load_dataset
dataset = load_dataset("distil-whisper/spgispeech", "L")
# take the first sample of the validation set
sample = dataset["validation"][0]
```
It can also be streamed directly from the Hub using Datasets' [streaming mode](https://huggingface.co/blog/audio-datasets#streaming-mode-the-silver-bullet).
Loading a dataset in streaming mode loads individual samples of the dataset at a time, rather than downloading the entire
dataset to disk:
```python
from datasets import load_dataset
dataset = load_dataset("distil-whisper/spgispeech", "L", streaming=True)
# take the first sample of the validation set
sample = next(iter(dataset["validation"]))
```
## Distil Whisper Usage
To use this dataset to reproduce a Distil Whisper training run, refer to the instructions on the
[Distil Whisper repository](https://github.com/huggingface/distil-whisper#training).
## License
This dataset is licensed under custom terms. To view the custom license for this dataset, refer to the original [dataset card](https://huggingface.co/datasets/kensho/spgispeech).
| [
-0.23197004199028015,
-0.6207801699638367,
0.1750640869140625,
0.4736146330833435,
-0.2434680014848709,
0.032255835831165314,
-0.279077410697937,
-0.16094857454299927,
0.5826777815818787,
0.38157105445861816,
-0.8938015103340149,
-0.44928476214408875,
-0.7676821947097778,
0.074935257434844... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
mstz/shuttle | mstz | 2023-04-16T17:58:41Z | 40 | 0 | null | [
"task_categories:tabular-classification",
"size_categories:10K<n<100K",
"language:en",
"license:cc",
"shuttle",
"tabular_classification",
"binary_classification",
"multiclass_classification",
"UCI",
"region:us"
] | 2023-04-16T17:58:41Z | 2023-04-14T12:03:39.000Z | 2023-04-14T12:03:39 | ---
language:
- en
tags:
- shuttle
- tabular_classification
- binary_classification
- multiclass_classification
- UCI
pretty_name: Shuttle
size_categories:
- 10K<n<100K
task_categories:
- tabular-classification
configs:
- shuttle
- shuttle_binary
license: cc
---
# Shuttle
The [Shuttle dataset](https://archive-beta.ics.uci.edu/dataset/146/statlog+shuttle+satellite) from the [UCI repository](https://archive-beta.ics.uci.edu/).
# Configurations and tasks
| **Configuration** | **Task** | **Description** |
|-----------------------|---------------------------|-------------------------|
| shuttle | Multiclass classification.| |
| shuttle_0 | Binary classification. | Is the image of class 0? |
| shuttle_1 | Binary classification. | Is the image of class 1? |
| shuttle_2 | Binary classification. | Is the image of class 2? |
| shuttle_3 | Binary classification. | Is the image of class 3? |
| shuttle_4 | Binary classification. | Is the image of class 4? |
| shuttle_5 | Binary classification. | Is the image of class 5? |
| shuttle_6 | Binary classification. | Is the image of class 6? | | [
-0.6847637295722961,
-0.05585217475891113,
0.47070634365081787,
0.2406744360923767,
-0.2184632271528244,
0.20581556856632233,
0.17677786946296692,
-0.094131700694561,
0.3394668996334076,
0.6325494050979614,
-0.9514689445495605,
-1.001791000366211,
-0.6674754619598389,
0.105718694627285,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
results-sd-v1-5-sd-v2-1-if-v1-0-karlo/87834474 | results-sd-v1-5-sd-v2-1-if-v1-0-karlo | 2023-05-23T05:17:56Z | 40 | 0 | null | [
"region:us"
] | 2023-05-23T05:17:56Z | 2023-05-23T05:17:55.000Z | 2023-05-23T05:17:55 | ---
dataset_info:
features:
- name: result
dtype: string
- name: id
dtype: int64
splits:
- name: train
num_bytes: 180
num_examples: 10
download_size: 1340
dataset_size: 180
---
# Dataset Card for "87834474"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.6440647840499878,
0.017768491059541702,
0.3293797969818115,
0.32497638463974,
-0.3369028568267822,
-0.3519744873046875,
0.43066418170928955,
-0.28177642822265625,
0.8197885155677795,
0.5630054473876953,
-0.8124962449073792,
-0.6908915042877197,
-0.5745187401771545,
0.07402054220438004,
... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
garythung/trashnet | garythung | 2023-06-02T03:23:04Z | 40 | 0 | null | [
"license:mit",
"region:us"
] | 2023-06-02T03:23:04Z | 2023-06-02T01:46:39.000Z | 2023-06-02T01:46:39 | ---
license: mit
---
| [
-0.1285335123538971,
-0.1861683875322342,
0.6529128551483154,
0.49436232447624207,
-0.19319400191307068,
0.23607441782951355,
0.36072009801864624,
0.05056373029947281,
0.5793656706809998,
0.7400146722793579,
-0.650810182094574,
-0.23784008622169495,
-0.7102247476577759,
-0.0478255338966846... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
Binaryy/travel_sample | Binaryy | 2023-06-09T11:53:34Z | 40 | 1 | null | [
"region:us"
] | 2023-06-09T11:53:34Z | 2023-06-09T09:05:26.000Z | 2023-06-09T09:05:26 | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 41063
num_examples: 20
download_size: 29530
dataset_size: 41063
---
# Dataset Card for "travel_sample"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.5575800538063049,
-0.06807724386453629,
0.3742748498916626,
0.27364927530288696,
-0.0652826577425003,
-0.14408297836780548,
0.2751223146915436,
-0.16018475592136383,
0.8800221681594849,
0.4728342592716217,
-1.0914990901947021,
-0.7526171207427979,
-0.4742809236049652,
-0.293050974607467... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
HausaNLP/NaijaSenti-Twitter | HausaNLP | 2023-06-16T16:42:04Z | 40 | 0 | null | [
"task_categories:text-classification",
"task_ids:sentiment-analysis",
"task_ids:sentiment-classification",
"task_ids:sentiment-scoring",
"task_ids:semantic-similarity-classification",
"task_ids:semantic-similarity-scoring",
"multilinguality:monolingual",
"multilinguality:multilingual",
"size_categor... | 2023-06-16T16:42:04Z | 2023-06-16T08:49:27.000Z | 2023-06-16T08:49:27 | ---
license: cc-by-nc-sa-4.0
task_categories:
- text-classification
task_ids:
- sentiment-analysis
- sentiment-classification
- sentiment-scoring
- semantic-similarity-classification
- semantic-similarity-scoring
tags:
- sentiment analysis, Twitter, tweets
- sentiment
multilinguality:
- monolingual
- multilingual
size_categories:
- 100K<n<1M
language:
- hau
- ibo
- pcm
- yor
pretty_name: NaijaSenti
---
<p align="center">
<img src="https://raw.githubusercontent.com/hausanlp/NaijaSenti/main/image/naijasenti_logo1.png", width="500">
--------------------------------------------------------------------------------
## Dataset Description
- **Homepage:** https://github.com/hausanlp/NaijaSenti
- **Repository:** [GitHub](https://github.com/hausanlp/NaijaSenti)
- **Paper:** [NaijaSenti: A Nigerian Twitter Sentiment Corpus for Multilingual Sentiment Analysis](https://aclanthology.org/2022.lrec-1.63/)
- **Leaderboard:** N/A
- **Point of Contact:** [Shamsuddeen Hassan Muhammad](shamsuddeen2004@gmail.com)
### Dataset Summary
NaijaSenti is the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria — Hausa, Igbo, Nigerian-Pidgin, and Yorùbá — consisting of around 30,000 annotated tweets per language, including a significant fraction of code-mixed tweets.
### Supported Tasks and Leaderboards
The NaijaSenti can be used for a wide range of sentiment analysis tasks in Nigerian languages, such as sentiment classification, sentiment intensity analysis, and emotion detection. This dataset is suitable for training and evaluating machine learning models for various NLP tasks related to sentiment analysis in African languages. It was part of the datasets that were used for [SemEval 2023 Task 12: Sentiment Analysis for African Languages](https://codalab.lisn.upsaclay.fr/competitions/7320).
### Languages
4 most spoken Nigerian languages
* Hausa (hau)
* Igbo (ibo)
* Nigerian Pidgin (pcm)
* Yoruba (yor)
## Dataset Structure
### Data Instances
For each instance, there is a string for the tweet and a string for the label. See the NaijaSenti [dataset viewer](https://huggingface.co/datasets/HausaNLP/NaijaSenti-Twitter/viewer/hau/train) to explore more examples.
```
{
"tweet": "string",
"label": "string"
}
```
### Data Fields
The data fields are:
```
tweet: a string feature.
label: a classification label, with possible values including positive, negative and neutral.
```
### Data Splits
The NaijaSenti dataset has 3 splits: train, validation, and test. Below are the statistics for Version 1.0.0 of the dataset.
| | hau | ibo | pcm | yor |
|---|---|---|---|---|
| train | 14,172 | 10,192 | 5,121 | 8,522 |
| dev | 2,677 | 1,841 | 1,281 | 2,090 |
| test | 5,303 | 3,682 | 4,154 | 4,515 |
| total | 22,152 | 15,715 | 10,556 | 15,127 |
### How to use it
```python
from datasets import load_dataset
# you can load specific languages (e.g., Hausa). This download train, validation and test sets.
ds = load_dataset("HausaNLP/NaijaSenti-Twitter", "hau")
# train set only
ds = load_dataset("HausaNLP/NaijaSenti-Twitter", "hau", split = "train")
# test set only
ds = load_dataset("HausaNLP/NaijaSenti-Twitter", "hau", split = "test")
# validation set only
ds = load_dataset("HausaNLP/NaijaSenti-Twitter", "hau", split = "validation")
```
## Dataset Creation
### Curation Rationale
NaijaSenti Version 1.0.0 aimed to be used sentiment analysis and other related task in Nigerian indigenous and creole languages - Hausa, Igbo, Nigerian Pidgin and Yoruba.
### Source Data
Twitter
### Personal and Sensitive Information
We anonymized the tweets by replacing all *@mentions* by *@user* and removed all URLs.
## Considerations for Using the Data
### Social Impact of Dataset
The NaijaSenti dataset has the potential to improve sentiment analysis for Nigerian languages, which is essential for understanding and analyzing the diverse perspectives of people in Nigeria. This dataset can enable researchers and developers to create sentiment analysis models that are specific to Nigerian languages, which can be used to gain insights into the social, cultural, and political views of people in Nigerian. Furthermore, this dataset can help address the issue of underrepresentation of Nigerian languages in natural language processing, paving the way for more equitable and inclusive AI technologies.
## Additional Information
### Dataset Curators
* Shamsuddeen Hassan Muhammad
* Idris Abdulmumin
* Ibrahim Said Ahmad
* Bello Shehu Bello
### Licensing Information
This NaijaSenti is licensed under a Creative Commons Attribution BY-NC-SA 4.0 International License
### Citation Information
```
@inproceedings{muhammad-etal-2022-naijasenti,
title = "{N}aija{S}enti: A {N}igerian {T}witter Sentiment Corpus for Multilingual Sentiment Analysis",
author = "Muhammad, Shamsuddeen Hassan and
Adelani, David Ifeoluwa and
Ruder, Sebastian and
Ahmad, Ibrahim Sa{'}id and
Abdulmumin, Idris and
Bello, Bello Shehu and
Choudhury, Monojit and
Emezue, Chris Chinenye and
Abdullahi, Saheed Salahudeen and
Aremu, Anuoluwapo and
Jorge, Al{\'\i}pio and
Brazdil, Pavel",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.63",
pages = "590--602",
}
```
### Contributions
> This work was carried out with support from Lacuna Fund, an initiative co-founded by The Rockefeller Foundation, Google.org, and Canada’s International Development Research Centre. The views expressed herein do not necessarily represent those of Lacuna Fund, its Steering Committee, its funders, or Meridian Institute. | [
-0.5715398192405701,
-0.4226636588573456,
-0.08149783313274384,
0.6227954626083374,
-0.40234705805778503,
0.11632603406906128,
-0.3830942213535309,
-0.4016789197921753,
0.7795974612236023,
0.2987603545188904,
-0.5655989050865173,
-0.7845079302787781,
-0.7083242535591125,
0.3101592659950256... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
dmayhem93/agieval-lsat-lr | dmayhem93 | 2023-06-18T17:26:20Z | 40 | 0 | null | [
"license:mit",
"arxiv:2304.06364",
"arxiv:2104.06598",
"region:us"
] | 2023-06-18T17:26:20Z | 2023-06-18T12:50:37.000Z | 2023-06-18T12:50:37 | ---
dataset_info:
features:
- name: query
dtype: string
- name: choices
sequence: string
- name: gold
sequence: int64
splits:
- name: test
num_bytes: 923886
num_examples: 510
download_size: 469904
dataset_size: 923886
license: mit
---
# Dataset Card for "agieval-lsat-lr"
Dataset taken from https://github.com/microsoft/AGIEval and processed as in that repo.
Raw datset: https://github.com/zhongwanjun/AR-LSAT
MIT License
Copyright (c) 2022 Wanjun Zhong
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}
}
@misc{zhong2021arlsat,
title={AR-LSAT: Investigating Analytical Reasoning of Text},
author={Wanjun Zhong and Siyuan Wang and Duyu Tang and Zenan Xu and Daya Guo and Jiahai Wang and Jian Yin and Ming Zhou and Nan Duan},
year={2021},
eprint={2104.06598},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@article{wang2022lsat,
title={From lsat: The progress and challenges of complex reasoning},
author={Wang, Siyuan and Liu, Zhongkun and Zhong, Wanjun and Zhou, Ming and Wei, Zhongyu and Chen, Zhumin and Duan, Nan},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
year={2022},
publisher={IEEE}
} | [
-0.4975052773952484,
-0.6719104647636414,
0.2850460708141327,
0.16383562982082367,
-0.16103382408618927,
-0.22946269810199738,
0.025339487940073013,
-0.49601489305496216,
0.0715857669711113,
0.4931391775608063,
-0.49832966923713684,
-0.26523151993751526,
-0.41616278886795044,
-0.0625179782... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
dmayhem93/agieval-lsat-rc | dmayhem93 | 2023-06-18T17:27:15Z | 40 | 0 | null | [
"license:mit",
"arxiv:2304.06364",
"arxiv:2104.06598",
"region:us"
] | 2023-06-18T17:27:15Z | 2023-06-18T12:50:49.000Z | 2023-06-18T12:50:49 | ---
dataset_info:
features:
- name: query
dtype: string
- name: choices
sequence: string
- name: gold
sequence: int64
splits:
- name: test
num_bytes: 1136305
num_examples: 269
download_size: 322710
dataset_size: 1136305
license: mit
---
# Dataset Card for "agieval-lsat-rc"
Dataset taken from https://github.com/microsoft/AGIEval and processed as in that repo.
Raw datset: https://github.com/zhongwanjun/AR-LSAT
MIT License
Copyright (c) 2022 Wanjun Zhong
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}
}
@misc{zhong2021arlsat,
title={AR-LSAT: Investigating Analytical Reasoning of Text},
author={Wanjun Zhong and Siyuan Wang and Duyu Tang and Zenan Xu and Daya Guo and Jiahai Wang and Jian Yin and Ming Zhou and Nan Duan},
year={2021},
eprint={2104.06598},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
@article{wang2022lsat,
title={From lsat: The progress and challenges of complex reasoning},
author={Wang, Siyuan and Liu, Zhongkun and Zhong, Wanjun and Zhou, Ming and Wei, Zhongyu and Chen, Zhumin and Duan, Nan},
journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
year={2022},
publisher={IEEE}
} | [
-0.5279655456542969,
-0.5921130776405334,
0.29070189595222473,
0.2176538109779358,
-0.15612082183361053,
-0.2018619030714035,
0.0011883823899552226,
-0.4606297016143799,
0.08463386446237564,
0.49389809370040894,
-0.5338733196258545,
-0.31048905849456787,
-0.43577471375465393,
-0.0542639940... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
rai-sandeep/test_ds_1 | rai-sandeep | 2023-07-03T11:13:46Z | 40 | 0 | null | [
"region:us"
] | 2023-07-03T11:13:46Z | 2023-07-03T11:13:44.000Z | 2023-07-03T11:13:44 | ---
dataset_info:
features:
- name: category
dtype: string
- name: topic
dtype: string
- name: question
dtype: string
- name: answer
dtype: string
splits:
- name: train
num_bytes: 4689
num_examples: 4
download_size: 11810
dataset_size: 4689
---
# Dataset Card for "test_ds_1"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.7417510151863098,
-0.4216820001602173,
0.1569206267595291,
0.15779562294483185,
-0.25638964772224426,
-0.14461596310138702,
0.4184919595718384,
0.14074741303920746,
0.9035558104515076,
0.4693310260772705,
-1.0646042823791504,
-0.7730743288993835,
-0.6772599220275879,
-0.1443673372268676... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
zxbsmk/webnovel_cn | zxbsmk | 2023-08-09T09:39:49Z | 40 | 42 | null | [
"task_categories:text2text-generation",
"size_categories:10M<n<100M",
"language:zh",
"license:mit",
"doi:10.57967/hf/0877",
"region:us"
] | 2023-08-09T09:39:49Z | 2023-07-09T14:33:25.000Z | 2023-07-09T14:33:25 | ---
license: mit
task_categories:
- text2text-generation
language:
- zh
size_categories:
- 10M<n<100M
dataset_info:
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
---
## 内容
包含从12560本网文提取的约**21.7M**条可用于训练小说生成的中文指令数据(novel_json_tokens512.zip)。~~下载链接：https://pan.baidu.com/s/1TorBMbrqxrn6odRF0PJBVw
提取码：jlh3~~
以及从中提取出的包含**50k**条数据的子集(novel_cn_token512_50k.json)。其中输入和输出都不多于 512 tokens。
## 样例
在原有小说文本基础上，依据下列五种指令生成数据。
其中，文本由小说中随机抽取的连续句子组成。
1. 给定标题，直接生成简介。
2. 给定标题和简介，生成开头。
3. 给定简介和一段文本，生成后续文本。
4. 给定标题和一段文本，生成后续文本。
5. 给定一段文本，生成后续文本。
```
{
"instruction": "小说名：无限恐怖\n节选正文：\n“不行，中校，我们必须把这里的情况和这些虫族的拍摄画面传回地球去，是的，我们人类已经到了最危险的关头，地球上所有的工业重工业完全应该按照战时情况进行任务布置，我们人类的工业力根本不是虫族能够想象的，一年，不，半年我们就能有一万艘宇宙战舰升空，如果全球一共进行建造的话，我们一定……”一名少校参谋长看着那密密麻麻的宇宙虫海，他神色激动的对楚轩说道。\n楚轩默默咬了一口苹果，他说道：“问题一……一万艘宇宙战舰需要多少熟练的战舰船员？需要多少士兵在战舰上服役，半年里我们可以聚集齐全吗？问题二……虫族会给地球联邦政府留下半年的时间吗？一旦我们被消灭干净，则联邦政府将会随即遭受到这些宇宙虫族的太空袭击，直到我们的太空优势完全丧失之后，虫族就能放心移动陨石进行攻击，甚至是将大量陆地虫子带上地球，那时我们人类能够凭肉体与虫子对抗吗？问题三……我们现在该如何把信息传给地球？”\n这名参谋长顿时就不说话了，而旁边一名上尉忽然说道：“在探戈幽灵星上的七座要塞中，每一座要塞都有大功率粒子喷射联络器，这种联络器连我们自己的科技都无法屏蔽，我想虫子也应该不可能继续屏蔽吧，毕竟那只是粒子而已，不是电流信号这些……”续篇：",
"input": "",
"output": "楚轩咬了一口苹果说道：“没错，所以我们才要登陆到探戈幽灵星，这是我们的目的，同时为了保存宇宙舰队的战斗力，以最大的平原军事基地，风暴要塞为中心，所有舰队都要降落到地面上，然后层层布防，在援军到来前，在地球联邦政府做好了战争准备前，我们必须像颗钉子一样钉死在这里，让虫族无法忽视我们而去进攻地球……怎么样？我们很可能会死在这里，面对数十万，数百万，甚至数千万的虫子前扑后续的攻击，但是我们的名字一定会载入史册……把刚才记录下来的我的话发向所有舰队，然后告诉他们，作为逃命被自己人杀掉，或者是成为英雄回到地球，让他们明白我们的处境，然后自己去选择吧。”\n周围的参谋和军官们同时向楚轩四人敬了一礼，接着那参谋长激动的向某处平台走了过去。\n郑吒默默走到了楚轩身边，他小声的说道：“楚轩……你什么时候变得了那么会煽情了啊？”\n楚轩却是理所当然的说道：“将自己归于多数人的一边，以前的你不是这样评价我的吗？没错，将自己归于多数人的一边，这是做任何大事都要先完成的第一步……已经让他们知道命运和我们连接在了一起，接着就只需要好好的安排下局面与等待‘主神’的任务就可以了，时间还有三天……”\n时间还有三天，在当天中午的时候，舰队群的预警舰果然发现了在探戈幽灵星后方徘徊着另一颗巨大圆球，它仿佛卫星一样座落在探戈幽灵星的近地轨道上，而随着联合舰队的到来，这只巨大圆球上果然也飞出了数以万计的宇宙虫子，这下联合舰队果然却如楚轩的预言那般了，前有埋伏，后有追兵，唯一的一条路就只剩下降落到探戈幽灵星上了。"
},
{
"instruction": "给定小说简介和节选，续写小说",
"input": "小说简介：主人公郑吒自从失去了自己最亲密的青梅竹马后，对这种反复而又无聊的现代生活已经感到十分的厌倦。正在这时，他发现电脑屏幕上弹出了一段信息：“想明白生命的意义吗？想真正的……活着吗？”在按下YES后，一切都改变了。他进入了一个恐怖片的轮回世界——主神空间……在主神空间里，只有不停地变强、不停地进化，才能闯过那一关关的恐怖片，才能活下去。郑吒，怎样才能活下去？是杀死与自己对抗的所有人，走向孤独的王者之道？还是和自己的伙伴奋战到死，以仁义之道来度过劫难？其实，所有的一切也只是为了活下去。直到他们发现了主神空间的秘密……究竟……谁才是暗中真正的威胁？一切尽在无限恐怖！\n\n\n\n上半部：初始\n节选篇章：“什么叫作事情已经发展到了这一步！”郑吒大声的喧哗吼叫着，他冲着楚轩吼道：“你这个白痴！我一直都在重复着同样一句话，我们是同伴啊，为什么不可以事先把你的猜测或者布局告诉我们呢？每次都把我当成白痴一样，每次都在算计我之后轻描淡写的说一句我骗你的，你究竟把我当成什么人？”\n“呃……大概是可以欺骗的凡人智慧者吧。”楚轩想了一下直接说道。\n“……不要拦着我！王侠，伊莫顿，你们放开我！我要干掉这个白痴！”\n喧哗又一次发生了，片刻之后再次安静下来时，楚轩本已略微肿胀的脸终于是彻底肿胀了起来，而看他的样子依然是一丁点疼痛都感觉不到，依然悠闲的吃着黄瓜。\n“……总之，事情已经发展到了这一步……”郑吒摸着额头，很痛苦的说道：“那么我们必须先要得到王女鄂亚的关押位置所在，当然了，直接打进首都也其实也不是不可以，但是从原剧情来看，似乎只有那个名叫邪影者的魔法师与国王歌巴塔尔知道她的关押位置，为了不打草惊蛇，还是花些时间慢慢渗透进去查找线索吧。”\n“赵樱空，你负责潜行进王城内，能不杀人尽量不杀人，若是遇到危险就转换人格，或者联络我们……伊莫顿，你负责到王城外的村庄去打探消息，尽量不要引人注意，若是可以，使用你的法术控制些人也行，照刚才我说的，遇到危险可以杀人，也可以联络我们，楚轩，王侠，你们两人就在附近待机，一旦发现有任何情况都要提供支援。”",
"output": "众人都点着头，王侠忽然好奇的问道：“你呢？你打算干什么去？”\n“我会把整个王城的情况给摸清楚，关键是王城里可能隐藏着的力量，我很在意啊，伊莫顿的感觉从某些方面来讲比我们都更出色，毕竟他是死亡的生物……或许，这场恐怖片世界并不像我们所想的那样轻松呢。”郑吒说到这里时叹了口气，他接着又看向了那首都位置。\n“时间还有两天多，我们尽量在三天内完成这部恐怖片世界吧……希望另一边的幼龙能够赶快成长。”郑吒边说话，边驾驶绿魔滑板就向地面飞去，渐渐的，他离众人已经越来越远了。\n此刻，在离王城首都极遥远外的小村处，主角伊拉贡正极其狼狈的奔跑在树丛中，跟随在他身边的还有他的舅舅……非常不幸的，逃跑没多久，他的表哥就失散在了这片森林中，或者说是被那些士兵们给抓住了也说不定。\n更加不幸的是，那名中年武士明显已经落败，不然不会多出那么多士兵紧紧追着他们，比起在村庄的时候，士兵的数量又更加的多了，至少有十多名士兵在他们不远处紧紧追赶。\n“你到底偷了什么东西啊！为什么会有这么多士兵来追赶你呢？”伊拉贡的舅舅气喘吁吁的问道，他已经跑得没什么精力去发怒了。\n“……一个龙蛋，不是偷的，这是我从森林里拣来的！”伊拉贡虽然也是跑得筋疲力尽，但他还在坚持着最后的底线，依然不停辩解着。\n“龙蛋？那可是国王的东西啊！而且还是孵化出幼龙的龙蛋！你这个白痴，你这样会害死大家的！”伊拉贡的舅舅一听此话就气急败坏的叫道，但他还是不停向前跑去，不敢有丁点停顿，因为在他们背后不停的追赶着十多名士兵。\n“在那里！看到他们了！他们在那里！”"
}
```
## 字段：
```
instruction: 指令
input: 输入
output: 输出
```
## 使用限制
仅允许将此数据集及使用此数据集生成的衍生物用于研究目的，不得用于商业，以及其他会对社会带来危害的用途。
本数据集不代表任何一方的立场、利益或想法，无关任何团体的任何类型的主张。因使用本数据集带来的任何损害、纠纷，本项目不承担任何责任。
Join group via https://t.me/+JbovpBG6-gBiNDI1 | [
-0.9875792860984802,
-0.5346769094467163,
0.4687647819519043,
0.2702205181121826,
-0.5589745044708252,
-0.2934505045413971,
-0.19448186457157135,
-0.39460885524749756,
0.6207635402679443,
0.5540526509284973,
-0.5046172142028809,
-0.5794382095336914,
-0.685912013053894,
0.10298477113246918,... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
VinayHajare/Fruits-30 | VinayHajare | 2023-11-11T05:00:28Z | 40 | 1 | null | [
"task_categories:image-classification",
"size_categories:n<1K",
"language:en",
"license:apache-2.0",
"multiclass-image-classification",
"vision",
"region:us"
] | 2023-11-11T05:00:28Z | 2023-08-16T15:54:47.000Z | 2023-08-16T15:54:47 | ---
license: apache-2.0
task_categories:
- image-classification
language:
- en
tags:
- multiclass-image-classification
- vision
size_categories:
- n<1K
---
# Fruits30 Dataset
## Description:
The Fruits30 dataset is a collection of images featuring 30 different types of fruits. Each image has been preprocessed and standardized to a size of 224x224 pixels, ensuring uniformity in the dataset.
## Dataset Composition:
- **Number of Classes:** 30
- **Image Resolution:** 224x224 pixels
- **Total Images:** 826
## Classes:
0 : acerolas
1 : apples
2 : apricots
3 : avocados
4 : bananas
5 : blackberries
6 : blueberries
7 : cantaloupes
8 : cherries
9 : coconuts
10 : figs
11 : grapefruits
12 : grapes
13 : guava
14 : kiwifruit
15 : lemons
16 : limes
17 : mangos
18 : olives
19 : oranges
20 : passionfruit
21 : peaches
22 : pears
23 : pineapples
24 : plums
25 : pomegranates
26 : raspberries
27 : strawberries
28 : tomatoes
29 : watermelons
## Preprocessing:
Images have undergone preprocessing to maintain consistency and facilitate model training. Preprocessing steps may include resizing, normalization, and other enhancements.
## Intended Use:
The Fruits30 dataset is suitable for tasks such as image classification, object recognition, and machine learning model training within the domain of fruit identification.
## Sources:
Croudsource.
## Note:
Ensure proper attribution and compliance with the dataset's licensing terms when using it for research or development purposes. | [
-0.7791483998298645,
-0.1456974744796753,
0.22815284132957458,
0.40304791927337646,
-0.12616802752017975,
0.22240643203258514,
-0.24641408026218414,
-0.418219655752182,
0.23660549521446228,
0.8290492296218872,
-0.7210289835929871,
-0.5692481398582458,
-0.7551854252815247,
0.409830242395401... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
raygx/NepaliTweets | raygx | 2023-08-24T03:49:49Z | 40 | 0 | null | [
"region:us"
] | 2023-08-24T03:49:49Z | 2023-08-24T03:48:49.000Z | 2023-08-24T03:48:49 | ---
dataset_info:
features:
- name: Sentiment
dtype: int64
- name: Sentences
dtype: string
splits:
- name: train
num_bytes: 14803386
num_examples: 44269
download_size: 5521101
dataset_size: 14803386
---
# Dataset Card for "NepaliTweets"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.15440331399440765,
-0.2621242105960846,
-0.06129192188382149,
0.8179242610931396,
-0.4793401062488556,
0.2358986884355545,
0.11925335228443146,
-0.09289595484733582,
0.8090207576751709,
0.38455668091773987,
-0.6924165487289429,
-0.7050256729125977,
-0.7797449827194214,
-0.19602486491203... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
cesarali/test_ocean_clients | cesarali | 2023-08-28T17:26:38Z | 40 | 0 | null | [
"region:us"
] | 2023-08-28T17:26:38Z | 2023-08-28T17:26:35.000Z | 2023-08-28T17:26:35 | ---
dataset_info:
features:
- name: o
dtype: int64
- name: c
dtype: int64
- name: e
dtype: int64
- name: a
dtype: int64
- name: n
dtype: int64
- name: education
dtype: string
- name: current_work
dtype: string
- name: ethnicity
dtype: string
- name: income_bracket
dtype: string
- name: age
dtype: int64
- name: sexual_orientation
dtype: string
- name: favorite_movies
sequence: string
- name: favorite_tv_shows
sequence: string
- name: comment
dtype: string
- name: id
dtype: string
- name: location
dtype: string
splits:
- name: train
num_bytes: 6755
num_examples: 20
download_size: 12166
dataset_size: 6755
---
# Dataset Card for "test_ocean_clients"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.95737224817276,
-0.19604387879371643,
0.21762235462665558,
0.31611400842666626,
-0.22338072955608368,
-0.05630417540669441,
0.3999451696872711,
-0.3673681318759918,
0.7718830704689026,
0.8836523294448853,
-0.8621381521224976,
-0.8646806478500366,
-0.2611694931983948,
-0.1534763723611831... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
lamini/text_to_sql_finetune | lamini | 2023-09-01T05:39:56Z | 40 | 2 | null | [
"region:us"
] | 2023-09-01T05:39:56Z | 2023-08-30T02:19:28.000Z | 2023-08-30T02:19:28 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
dataset_info:
features:
- name: input
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 34818227
num_examples: 16428
- name: test
num_bytes: 1050788
num_examples: 1034
download_size: 3691335
dataset_size: 35869015
---
# Dataset Card for "text_to_sql_finetune"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.4407598376274109,
-0.6548948287963867,
0.22849895060062408,
0.2086992859840393,
-0.395931601524353,
-0.33425208926200867,
-0.07791534811258316,
-0.014337360858917236,
0.6766108870506287,
0.6330326199531555,
-0.8105428218841553,
-0.776068389415741,
-0.4416908919811249,
-0.158885657787323... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
C-MTEB/T2Reranking_zh2en | C-MTEB | 2023-09-09T16:08:39Z | 40 | 0 | null | [
"region:us"
] | 2023-09-09T16:08:39Z | 2023-09-09T16:08:28.000Z | 2023-09-09T16:08:28 | ---
configs:
- config_name: default
data_files:
- split: dev
path: data/dev-*
dataset_info:
features:
- name: query
dtype: string
- name: positive
sequence: string
- name: negative
sequence: string
splits:
- name: dev
num_bytes: 53155154
num_examples: 6129
download_size: 33679279
dataset_size: 53155154
---
# Dataset Card for "T2Reranking_zh2en"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.2028287798166275,
-0.07878044992685318,
0.22099222242832184,
0.25308552384376526,
-0.3882642984390259,
-0.07321271300315857,
0.22944410145282745,
-0.217037171125412,
0.7479655742645264,
0.3428148627281189,
-0.9912163019180298,
-0.8484797477722168,
-0.5653445720672607,
-0.396744400262832... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
daje/ko_wiki | daje | 2023-09-21T05:38:01Z | 40 | 2 | null | [
"region:us"
] | 2023-09-21T05:38:01Z | 2023-09-21T01:42:49.000Z | 2023-09-21T01:42:49 | ---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 986780351
num_examples: 311237
download_size: 550489937
dataset_size: 986780351
---
# 한국어 위키 데이터셋(Ko_wiki)
* 개요
- 이 데이터셋은 한국어 위키 데이터를 기반으로 만들어졌습니다. 원본 위키 데이터를 처리하기 위해 wikiextractor.py를 사용하여 텍스트 형식으로 변환하였습니다.
- 이 데이터셋을 제작한 주요 취지는 한국어 자연어 처리 연구와 애플리케이션 개발에 사용할 수 있는 광범위한 텍스트 데이터를 제공하기 위함입니다.
* 데이터 구조
- text: 위키 문서의 본문을 포함하는 문자열입니다.
* 사용 방법
1. huggingface dataset과 map을 활용하는 방법
```python3
from datasets import load_dataset
ko_dataset = load_dataset("text",
"daje/ko_wiki",
split="train",
streaming=True)
ko_wiki_tokenized = ko_dataset.map(lambda x : tokenizer(x["text"],
max_length=256,
padding="max_length",
truncation=True),
remove_columns=["text"])
```
2. 파이썬 스크립트를 사용하는 방법
```
import os
from tqdm import tqdm
from transformers import AutoTokenizer
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--input_path', type=str)
parser.add_argument('--output_path', type=str)
parser.add_argument('--model_name_or_path', type=str)
parser.add_argument('--max_seq_length', type=int, default=256)
parser.add_argument('--add_sep', default=True, action='store_true')
args = parser.parse_args()
def get_num_lines(fname):
res = os.popen(f'wc -l {fname}').read()
lines = res.strip().split()[0]
return int(lines)
def main(args):
seq_length = args.max_seq_length - 3 # room for [BOS], [EOS], [UNK]
input_fs = open(args.input_path, 'r')
output_fs = open(args.output_path, 'a')
total_line = get_num_lines(args.input_path)
tokenizer = AutoTokenizer.from_pretrained(args.model_name_or_path)
buffer = []
for doc in tqdm(input_fs, total=total_line):
tokens = tokenizer.tokenize(doc)
buffer += tokens
if args.add_sep:
buffer += [tokenizer.eos_token] # 자신이 사용하는 tokenizer에 맞추어서 eos, sep을 넣으시면 됩니다.
while len(buffer) > seq_length:
text = ' '.join(buffer[:seq_length])
output_fs.write(text)
output_fs.write('\n')
buffer = buffer[seq_length:]
input_fs.close()
output_fs.close()
if __name__ == '__main__':
main(args)
```
| [
-0.5489192008972168,
-0.5971949696540833,
0.40168285369873047,
0.28279513120651245,
-0.6349055171012878,
-0.23116619884967804,
-0.05289318785071373,
-0.15407806634902954,
0.18210774660110474,
0.2977432608604431,
-0.5553451180458069,
-0.48614028096199036,
-0.5194739103317261,
0.335779815912... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
ContextualAI/tiny-wiki100-chunks | ContextualAI | 2023-09-22T17:47:30Z | 40 | 0 | null | [
"region:us"
] | 2023-09-22T17:47:30Z | 2023-09-22T17:47:26.000Z | 2023-09-22T17:47:26 | ---
dataset_info:
features:
- name: doc_id
dtype: string
- name: text
dtype: string
- name: title
dtype: string
splits:
- name: train
num_bytes: 63619
num_examples: 100
download_size: 43300
dataset_size: 63619
---
# Dataset Card for "tiny-wiki100-chunks"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.746026337146759,
-0.3993931710720062,
0.2912486791610718,
0.128810852766037,
-0.1779441088438034,
-0.1458473801612854,
0.030330169945955276,
-0.04193900525569916,
1.0967828035354614,
0.40320202708244324,
-0.8599488139152527,
-0.3666035234928131,
-0.4277248680591583,
-0.13326358795166016... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
TrainingDataPro/generated-e-mail-spam | TrainingDataPro | 2023-09-28T15:29:45Z | 40 | 1 | null | [
"task_categories:text-generation",
"task_categories:text-classification",
"language:en",
"license:cc-by-nc-nd-4.0",
"code",
"finance",
"region:us"
] | 2023-09-28T15:29:45Z | 2023-09-28T14:36:07.000Z | 2023-09-28T14:36:07 | ---
language:
- en
license: cc-by-nc-nd-4.0
task_categories:
- text-generation
- text-classification
tags:
- code
- finance
dataset_info:
features:
- name: title
dtype: string
- name: text
dtype: large_string
splits:
- name: train
num_bytes: 233533
num_examples: 300
download_size: 230500
dataset_size: 233533
---
# Generated E-mail Spam
The dataset consists of a **CSV file** containing of 300 generated email spam messages. Each row in the file represents a separate email message, its *title and text.* The dataset aims to facilitate the analysis and detection of spam emails.
The dataset can be used for various purposes, such as *training machine learning algorithms to classify and filter spam emails, studying spam email patterns, or analyzing text-based features of spam messages*.
# Get the dataset
### This is just an example of the data
Leave a request on [**https://trainingdata.pro/data-market**](https://trainingdata.pro/data-market?utm_source=huggingface&utm_medium=cpc&utm_campaign=generated-e-mail-spam) to discuss your requirements, learn about the price and buy the dataset.
# Content
### File with the extension .csv (utf-8)
includes the following information:
- **title**: title of the email,
- **text**: text of the email
# Email spam might be generated in accordance with your requirements.
## **[TrainingData](https://trainingdata.pro/data-market?utm_source=huggingface&utm_medium=cpc&utm_campaign=generated-e-mail-spam)** provides high-quality data annotation tailored to your needs
More datasets in TrainingData's Kaggle account: **https://www.kaggle.com/trainingdatapro/datasets**
TrainingData's GitHub: **https://github.com/Trainingdata-datamarket/TrainingData_All_datasets** | [
-0.24536603689193726,
-0.9211493730545044,
-0.06518016755580902,
0.3565032482147217,
-0.07542312145233154,
0.11427265405654907,
-0.12924186885356903,
-0.05179082229733467,
0.2592880129814148,
1.088551640510559,
-0.8255003094673157,
-0.8530381917953491,
-0.7713223099708557,
0.06607857346534... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
hahminlew/kream-product-blip-captions | hahminlew | 2023-10-16T10:33:42Z | 40 | 2 | null | [
"task_categories:text-to-image",
"size_categories:10K<n<100K",
"language:en",
"license:cc-by-nc-sa-4.0",
"fashion",
"cloth",
"computer-vision",
"region:us"
] | 2023-10-16T10:33:42Z | 2023-10-10T23:39:49.000Z | 2023-10-10T23:39:49 | ---
license: cc-by-nc-sa-4.0
dataset_info:
features:
- name: image
dtype: image
- name: text
dtype: string
splits:
- name: train
num_bytes: 1363424468
num_examples: 14904
download_size: 1328309729
dataset_size: 1363424468
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
task_categories:
- text-to-image
language:
- en
size_categories:
- 10K<n<100K
images_reference:
- KREAM (https://kream.co.kr/)
pretty_name: KREAM Product Blip Capitions
tags:
- fashion
- cloth
- computer-vision
---
## KREAM Product Blip Captions Dataset Information
**KREAM Product Blip Captions Dataset** is a dataset card for finetuning a text-to-image generative model collected from [KREAM](https://kream.co.kr/), one of the best online-resell market in Korea.
This dataset consists of 'image' and 'text' key pairs.
The format of 'text' is 'category (e.g. outer), product original name (e.g. The North Face 1996 Eco Nuptse Jacket Black), blip captions (e.g. a photography of the north face black down jacket)'.
You can easily construct this dataset and finetune stable diffusion from scratch using [easy-finetuning-stable-diffusion](https://github.com/hahminlew/easy-finetuning-stable-diffusion).
## Usage
```
from datasets import load_dataset
dataset = load_dataset("hahminlew/kream-product-blip-captions", split="train")
sample = dataset[0]
display(sample["image"].resize((256, 256)))
print(sample["text"])
```
```
outer, The North Face 1996 Eco Nuptse Jacket Black, a photography of the north face black down jacket
```
## Application
You can inference the finetuned Stable Diffusion XL with LoRA based on the dataset here: [hahminlew/sdxl-kream-model-lora-2.0](https://huggingface.co/hahminlew/sdxl-kream-model-lora-2.0)
## Citation
If you use KREAM Product Dataset in your research or projects, please cite it as:
```
@misc{lew2023kream,
author = {Lew, Hah Min},
title = {KREAM Product BLIP Captions},
year={2023},
howpublished= {\url{https://huggingface.co/datasets/hahminlew/kream-product-blip-captions/}}
}
``` | [
-0.18530987203121185,
-0.6510388255119324,
0.09254509955644608,
0.5280429720878601,
-0.33767861127853394,
0.035828426480293274,
-0.03375791013240814,
-0.300143837928772,
0.2235885113477707,
0.6927260160446167,
-0.5420622229576111,
-0.8003120422363281,
-0.47754964232444763,
-0.0407771468162... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
atom92/medical_healthwa_3.0 | atom92 | 2023-10-15T12:53:16Z | 40 | 0 | null | [
"region:us"
] | 2023-10-15T12:53:16Z | 2023-10-15T12:53:13.000Z | 2023-10-15T12:53:13 | ---
dataset_info:
features:
- name: text
struct:
- name: text
dtype: string
splits:
- name: train
num_bytes: 2710809
num_examples: 7360
download_size: 586464
dataset_size: 2710809
---
# Dataset Card for "medical_healthwa_3.0"
[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards) | [
-0.3154893219470978,
-0.18969939649105072,
0.48685023188591003,
0.13310901820659637,
-0.18161509931087494,
-0.2482355535030365,
0.5459168553352356,
-0.4370363652706146,
0.9093335866928101,
0.5780989527702332,
-0.753406286239624,
-0.8732514977455139,
-0.6805548071861267,
-0.1781229823827743... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
sulpha/anime-sceneries | sulpha | 2023-10-21T09:04:29Z | 40 | 0 | null | [
"task_categories:unconditional-image-generation",
"license:apache-2.0",
"images",
"region:us"
] | 2023-10-21T09:04:29Z | 2023-10-21T08:11:56.000Z | 2023-10-21T08:11:56 | ---
license: apache-2.0
task_categories:
- unconditional-image-generation
tags:
- images
---
To use the dataset
```py
from datasets import load_dataset
dataset = load_dataset("sulpha/anime-sceneries")
```
This is a web scraped dataset of (mostly) anime sceneries/paintings. Initially scraped to train an unconditional image generation model.
An example fastGAN model utilizing this dataset can be view [here](https://github.com/sulphatet/gan-anime-sceneries) | [
-0.23622655868530273,
-0.2992478907108307,
-0.001215367461554706,
0.17141154408454895,
-0.2639613747596741,
-0.2054644674062729,
0.15235644578933716,
0.14202581346035004,
0.28395554423332214,
0.711709201335907,
-0.6813086271286011,
-0.2470284104347229,
-0.19175632297992706,
0.1192906945943... | null | null | null | null | null | null | null | null | null | null | null | null | null | |
theblackcat102/llava-instruct-mix | theblackcat102 | 2023-10-23T10:14:27Z | 40 | 0 | null | [
"task_categories:visual-question-answering",
"size_categories:100K<n<1M",
"language:en",
"license:cc-by-nc-4.0",
"multimodal",
"vision",
"region:us"
] | 2023-10-23T10:14:27Z | 2023-10-23T09:34:45.000Z | 2023-10-23T09:34:45 | ---
dataset_info:
features:
- name: image
dtype: image
- name: conversations
dtype: string
splits:
- name: train
num_bytes: 46019106088.205
num_examples: 272795
download_size: 20289135489
dataset_size: 46019106088.205
task_categories:
- visual-question-answering
language:
- en
tags:
- multimodal
- vision
size_categories:
- 100K<n<1M
license: cc-by-nc-4.0
---
# LLaVA Instruct Mix
Added OCR and Chart QA dataset into this for more text extraction questions
| [
-0.2577270269393921,
-0.6208762526512146,
0.6250443458557129,
-0.2101513296365738,
-0.35736599564552307,
0.5129712224006653,
0.3799677789211273,
-0.845493495464325,
0.2628980576992035,
1.1066946983337402,
-0.3748985826969147,
-0.2570118010044098,
-0.5018951892852783,
0.26397809386253357,
... | null | null | null | null | null | null | null | null | null | null | null | null | null |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.