datasetId
stringlengths 5
121
| author
stringlengths 2
42
| last_modified
unknown | downloads
int64 0
4.88M
| likes
int64 0
7.61k
| tags
sequencelengths 1
7.92k
| task_categories
sequencelengths 0
47
β | createdAt
unknown | card
stringlengths 15
1.02M
|
|---|---|---|---|---|---|---|---|---|
DanteTemplar/pdf-extraction-agenda | DanteTemplar | "2025-03-08T21:15:44Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-08T20:45:48Z" | ---
license: mit
---
|
JosephBHodes/4chan-pol-2014-2024 | JosephBHodes | "2025-03-09T00:38:40Z" | 0 | 0 | [
"license:cc-by-nc-nd-4.0",
"region:us"
] | null | "2025-03-08T20:48:36Z" | ---
license: cc-by-nc-nd-4.0
---
|
Asap7772/hendrcyks_math_qwen__0_125 | Asap7772 | "2025-03-08T21:10:16Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:49:36Z" | ---
dataset_info:
features:
- name: problem
dtype: string
- name: solution
dtype: string
- name: answer
dtype: string
- name: subject
dtype: string
- name: level
dtype: int64
- name: unique_id
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: ground_truth
dtype: string
- name: completion
sequence: string
- name: completion_answer
sequence: string
- name: completion_correct
sequence: bool
- name: completions_succ_rate
dtype: float64
splits:
- name: train
num_bytes: 12252388
num_examples: 125
download_size: 3778123
dataset_size: 12252388
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Asap7772/hendrcyks_math_qwen__375_500 | Asap7772 | "2025-03-08T21:11:34Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:49:37Z" | ---
dataset_info:
features:
- name: problem
dtype: string
- name: solution
dtype: string
- name: answer
dtype: string
- name: subject
dtype: string
- name: level
dtype: int64
- name: unique_id
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: ground_truth
dtype: string
- name: completion
sequence: string
- name: completion_answer
sequence: string
- name: completion_correct
sequence: bool
- name: completions_succ_rate
dtype: float64
splits:
- name: train
num_bytes: 13192737
num_examples: 125
download_size: 4174996
dataset_size: 13192737
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Asap7772/hendrcyks_math_qwen__250_375 | Asap7772 | "2025-03-08T21:10:49Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:49:37Z" | ---
dataset_info:
features:
- name: problem
dtype: string
- name: solution
dtype: string
- name: answer
dtype: string
- name: subject
dtype: string
- name: level
dtype: int64
- name: unique_id
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: ground_truth
dtype: string
- name: completion
sequence: string
- name: completion_answer
sequence: string
- name: completion_correct
sequence: bool
- name: completions_succ_rate
dtype: float64
splits:
- name: train
num_bytes: 12659415
num_examples: 125
download_size: 3970467
dataset_size: 12659415
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Asap7772/hendrcyks_math_qwen__125_250 | Asap7772 | "2025-03-08T21:11:29Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:49:41Z" | ---
dataset_info:
features:
- name: problem
dtype: string
- name: solution
dtype: string
- name: answer
dtype: string
- name: subject
dtype: string
- name: level
dtype: int64
- name: unique_id
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: ground_truth
dtype: string
- name: completion
sequence: string
- name: completion_answer
sequence: string
- name: completion_correct
sequence: bool
- name: completions_succ_rate
dtype: float64
splits:
- name: train
num_bytes: 13031386
num_examples: 125
download_size: 4133919
dataset_size: 13031386
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
mint89/air_dialogue | mint89 | "2025-03-08T20:50:21Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:49:43Z" | ---
dataset_info:
features:
- name: action
struct:
- name: flight
sequence: int64
- name: name
dtype: string
- name: status
dtype: string
- name: intent
struct:
- name: departure_airport
dtype: string
- name: departure_day
dtype: string
- name: departure_month
dtype: string
- name: goal
dtype: string
- name: max_connections
dtype: int64
- name: max_price
dtype: int64
- name: name
dtype: string
- name: return_airport
dtype: string
- name: return_day
dtype: string
- name: return_month
dtype: string
- name: timestamps
sequence: int64
- name: dialogue
sequence: string
- name: expected_action
struct:
- name: flight
sequence: int64
- name: name
dtype: string
- name: status
dtype: string
- name: search_info
list:
- name: button_name
dtype: string
- name: field_name
dtype: string
- name: field_value
dtype: string
- name: timestmamp
dtype: int64
- name: correct_sample
dtype: bool
splits:
- name: train
num_bytes: 357952385
num_examples: 321459
download_size: 125170307
dataset_size: 357952385
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
mint89/financial_phrasebank | mint89 | "2025-03-08T20:50:28Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:50:25Z" | ---
dataset_info:
features:
- name: sentence
dtype: string
- name: label
dtype: int64
splits:
- name: train
num_bytes: 303371
num_examples: 2264
download_size: 168687
dataset_size: 303371
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
aiPhone13/aiPhone651 | aiPhone13 | "2025-03-08T21:12:45Z" | 0 | 0 | [
"license:creativeml-openrail-m",
"region:us"
] | null | "2025-03-08T20:52:07Z" | ---
license: creativeml-openrail-m
---
|
Kelvin878/sft_dataset | Kelvin878 | "2025-03-08T22:49:00Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:52:53Z" | ---
dataset_info:
features:
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
splits:
- name: train
num_bytes: 657593
num_examples: 65
download_size: 258802
dataset_size: 657593
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
omniomni/omniscience | omniomni | "2025-03-08T20:59:40Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:56:17Z" | ---
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 1071195740
num_examples: 391986
download_size: 626312874
dataset_size: 1071195740
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
mertaylin/arc-agi-transduction100k-direct-ft | mertaylin | "2025-03-08T21:00:58Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T20:59:14Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
- name: images
dtype: image
- name: answer
dtype: string
- name: cot_problem
dtype: string
splits:
- name: train
num_bytes: 625694622.875
num_examples: 94897
- name: test
num_bytes: 33156300.63
num_examples: 4995
download_size: 260266460
dataset_size: 658850923.505
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---
|
aniket01saraf/HGPT | aniket01saraf | "2025-03-08T21:07:02Z" | 0 | 0 | [
"license:apache-2.0",
"region:us"
] | null | "2025-03-08T21:05:26Z" | ---
license: apache-2.0
---
|
mint89/air_dialogue-tokenized | mint89 | "2025-03-08T21:12:29Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T21:11:31Z" | ---
dataset_info:
features:
- name: action
struct:
- name: flight
sequence: int64
- name: name
dtype: string
- name: status
dtype: string
- name: intent
struct:
- name: departure_airport
dtype: string
- name: departure_day
dtype: string
- name: departure_month
dtype: string
- name: goal
dtype: string
- name: max_connections
dtype: int64
- name: max_price
dtype: int64
- name: name
dtype: string
- name: return_airport
dtype: string
- name: return_day
dtype: string
- name: return_month
dtype: string
- name: timestamps
sequence: int64
- name: dialogue
sequence: string
- name: expected_action
struct:
- name: flight
sequence: int64
- name: name
dtype: string
- name: status
dtype: string
- name: search_info
list:
- name: button_name
dtype: string
- name: field_name
dtype: string
- name: field_value
dtype: string
- name: timestmamp
dtype: int64
- name: correct_sample
dtype: bool
- name: input_ids
sequence: int32
- name: attention_mask
sequence: int8
splits:
- name: train
num_bytes: 1183459097
num_examples: 321459
download_size: 191511485
dataset_size: 1183459097
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Daemontatox/Arabic_captioned_Images | Daemontatox | "2025-03-08T21:12:36Z" | 0 | 0 | [
"task_categories:question-answering",
"task_categories:text-generation",
"language:ar",
"license:apache-2.0",
"size_categories:1M<n<10M",
"arxiv:2402.11684",
"region:us",
"GPT-4V",
"LVLM",
"Vision",
"Language"
] | [
"question-answering",
"text-generation"
] | "2025-03-08T21:12:35Z" | ---
license: apache-2.0
task_categories:
- question-answering
- text-generation
language:
- ar
tags:
- GPT-4V
- LVLM
- Vision
- Language
size_categories:
- 1M<n<10M
configs:
- config_name: allava_laion
data_files:
- split: caption
path: "allava_laion/ALLaVA-Caption-LAION-4V_Arabic.json"
# - split: instruct
# path: "allava_laion/ALLaVA-Instruct-LAION-4V_Chinese.json"
- config_name: allava_vflan
data_files:
- split: caption
path: "allava_vflan/ALLaVA-Caption-VFLAN-4V_Arabic.json"
# - split: instruct
# path: "allava_vflan/ALLaVA-Instruct-VFLAN-4V_Chinese.json"
# - config_name: allava_laion_instruction
# data_files: "allava_laion/ALLaVA-Instruct-LAION-4V.json"
# configs:
# - config_name: default
# data_files:
# - split: allava_laion_caption
# path: "allava_laion/ALLaVA-Caption-LAION-4V.json"
# - split: allava_laion_instruction
# path: "allava_laion/ALLaVA-Instruction-LAION-4V.json"
# configs:
# - config_name: default
# - data_files:
# - split: allava_laion_caption
# - path:
# - "allava_laion/ALLaVA-Caption-LAION-4V.json"
# - split: allava_laion_instruction
# - path:
# - "allava_laion/ALLaVA-Instruction-LAION-4V.json"
---
## ALLaVA-4V for Arabic
This is the Arabic version of the ALLaVA-4V data. We have translated the ALLaVA-4V data into Arabic through ChatGPT and instructed ChatGPT not to translate content related to OCR.
The original dataset can be found [here](https://huggingface.co./datasets/FreedomIntelligence/ALLaVA-4V), and the image data can be downloaded from [ALLaVA-4V](https://huggingface.co./datasets/FreedomIntelligence/ALLaVA-4V).
#### Citation
If you find our data useful, please consider citing our work! We are FreedomIntelligence from Shenzhen Research Institute of Big Data and The Chinese University of Hong Kong, Shenzhen.
```
@misc{chen2024allava,
title={ALLaVA: Harnessing GPT4V-synthesized Data for A Lite Vision-Language Model},
author={Guiming Hardy Chen and Shunian Chen and Ruifei Zhang and Junying Chen and Xiangbo Wu and Zhiyi Zhang and Zhihong Chen and Jianquan Li and Xiang Wan and Benyou Wang},
year={2024},
eprint={2402.11684},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
``` |
Turgayy54/tugi | Turgayy54 | "2025-03-08T21:19:19Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T21:15:31Z" | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: response
dtype: string
splits:
- name: train
num_bytes: 669.3333333333334
num_examples: 2
- name: test
num_bytes: 352
num_examples: 1
download_size: 6241
dataset_size: 1021.3333333333334
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---
|
kaangml/t2i_tiny_nasa | kaangml | "2025-03-08T22:20:41Z" | 0 | 0 | [
"task_categories:text-to-image",
"task_categories:image-to-text",
"language:en",
"license:apache-2.0",
"region:us"
] | [
"text-to-image",
"image-to-text"
] | "2025-03-08T21:22:01Z" | ---
license: apache-2.0
dataset_info:
features:
- name: image
dtype: image
- name: prompt
dtype: string
splits:
- name: train
num_bytes: 1327071156.556
num_examples: 1069
download_size: 1220407709
dataset_size: 1327071156.556
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
language:
- en
task_categories:
- text-to-image
- image-to-text
---
# Dataset Card for t2i_tiny_nasa
# NASA Image Dataset
This dataset is created using images obtained from [NASA's official image library](https://images.nasa.gov). The dataset contains a collection of images along with their corresponding textual descriptions (prompts). This dataset can be used for various applications, including image-to-text tasks, text-to-image generation, and other AI-based image analysis studies.
## Dataset Information
- **Source:** [NASA Image Library](https://images.nasa.gov)
- **Content:** Images and corresponding textual descriptions
- **License:** Please refer to NASA's official terms of use
## Usage Example
You can load and visualize an example from the dataset using the following code:
```python
from datasets import load_dataset
# Load dataset
dataset = load_dataset("kaangml/t2i_tiny_nasa")
# Get an example from the dataset
example = dataset['train'][0]
from PIL import Image
import matplotlib.pyplot as plt
# Load and display the image
image_path = example['image']['path']
image = Image.open(image_path)
plt.imshow(image)
plt.title(f"Prompt: {example['prompt']}")
plt.axis('off')
plt.show()
```
## Citation
If you use this dataset in your research or project, please give credit to NASA for the images and include a reference to this dataset.
## Acknowledgment
This dataset is built using publicly available images from NASA's official repository. NASA does not endorse or officially support this dataset. |
eugrug-60/medical-o1-reasoning-SFT-it_f10_incremental | eugrug-60 | "2025-03-08T23:50:06Z" | 0 | 0 | [
"task_categories:question-answering",
"task_categories:text-generation",
"language:it",
"license:apache-2.0",
"region:us",
"medical",
"biology"
] | [
"question-answering",
"text-generation"
] | "2025-03-08T21:24:07Z" | ---
dataset_info:
features:
- name: Question_IT
dtype: string
- name: Complex_CoT_IT
dtype: string
- name: Response_IT
dtype: string
splits:
- name: train
num_bytes: 1579399
num_examples: 750
download_size: 955580
dataset_size: 1579399
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
license: apache-2.0
task_categories:
- question-answering
- text-generation
language:
- it
tags:
- medical
- biology
pretty_name: medical-o1-reasoning-SFT-it_f10_incremental
---
## News
[2025/03/08] We open sourced the medical reasoning dataset for SFT translated into italian language.
## Dataset Description
This dataset is used to fine-tune DeepSeek-R1-Distill-Llama-8B in order to generate a medical LLM designed for advanced medical reasoning.
We used the "facebook/nllb-200-distilled-600M" model to translate from the "FreedomIntelligence/medical-o1-reasoning-SFT" dataset
# Citation
We would like to thank the authors of the original dataset, and cite their work below.
# Contacts
For comments discussions or questions about this dataset, please write me at:
[email protected]
|
pltops/A-OKVQA | pltops | "2025-03-08T21:26:41Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T21:25:44Z" | ---
dataset_info:
features:
- name: image
dtype: image
- name: question_id
dtype: string
- name: question
dtype: string
- name: choices
list: string
- name: correct_choice_idx
dtype: int8
- name: direct_answers
dtype: string
- name: difficult_direct_answer
dtype: bool
- name: rationales
list: string
splits:
- name: chunk_0
num_bytes: 30925736.0
num_examples: 568
- name: chunk_1
num_bytes: 30501119.0
num_examples: 568
- name: chunk_2
num_bytes: 30764094.0
num_examples: 568
- name: chunk_3
num_bytes: 30728016.0
num_examples: 568
- name: chunk_4
num_bytes: 30946528.0
num_examples: 568
- name: chunk_5
num_bytes: 30583089.0
num_examples: 568
- name: chunk_6
num_bytes: 31038309.0
num_examples: 568
- name: chunk_7
num_bytes: 31299940.0
num_examples: 568
- name: chunk_8
num_bytes: 31301375.0
num_examples: 568
- name: chunk_9
num_bytes: 31398844.0
num_examples: 568
- name: chunk_10
num_bytes: 29711492.0
num_examples: 568
- name: chunk_11
num_bytes: 30872264.0
num_examples: 568
- name: chunk_12
num_bytes: 31141639.0
num_examples: 568
- name: chunk_13
num_bytes: 31169855.0
num_examples: 568
- name: chunk_14
num_bytes: 30766808.0
num_examples: 568
- name: chunk_15
num_bytes: 30802699.0
num_examples: 568
- name: chunk_16
num_bytes: 31070898.0
num_examples: 568
- name: chunk_17
num_bytes: 31141353.0
num_examples: 568
- name: chunk_18
num_bytes: 31128070.0
num_examples: 568
- name: chunk_19
num_bytes: 31650030.0
num_examples: 568
- name: chunk_20
num_bytes: 30868463.0
num_examples: 568
- name: chunk_21
num_bytes: 30897342.0
num_examples: 568
- name: chunk_22
num_bytes: 31100625.0
num_examples: 568
- name: chunk_23
num_bytes: 31349987.0
num_examples: 568
- name: chunk_24
num_bytes: 31913412.0
num_examples: 568
- name: chunk_25
num_bytes: 30722971.0
num_examples: 568
- name: chunk_26
num_bytes: 31089925.0
num_examples: 568
- name: chunk_27
num_bytes: 30036032.0
num_examples: 568
- name: chunk_28
num_bytes: 31139406.0
num_examples: 568
- name: chunk_29
num_bytes: 435343854.192
num_examples: 7968
download_size: 1328727737
dataset_size: 1333404175.192
configs:
- config_name: default
data_files:
- split: chunk_0
path: data/chunk_0-*
- split: chunk_1
path: data/chunk_1-*
- split: chunk_2
path: data/chunk_2-*
- split: chunk_3
path: data/chunk_3-*
- split: chunk_4
path: data/chunk_4-*
- split: chunk_5
path: data/chunk_5-*
- split: chunk_6
path: data/chunk_6-*
- split: chunk_7
path: data/chunk_7-*
- split: chunk_8
path: data/chunk_8-*
- split: chunk_9
path: data/chunk_9-*
- split: chunk_10
path: data/chunk_10-*
- split: chunk_11
path: data/chunk_11-*
- split: chunk_12
path: data/chunk_12-*
- split: chunk_13
path: data/chunk_13-*
- split: chunk_14
path: data/chunk_14-*
- split: chunk_15
path: data/chunk_15-*
- split: chunk_16
path: data/chunk_16-*
- split: chunk_17
path: data/chunk_17-*
- split: chunk_18
path: data/chunk_18-*
- split: chunk_19
path: data/chunk_19-*
- split: chunk_20
path: data/chunk_20-*
- split: chunk_21
path: data/chunk_21-*
- split: chunk_22
path: data/chunk_22-*
- split: chunk_23
path: data/chunk_23-*
- split: chunk_24
path: data/chunk_24-*
- split: chunk_25
path: data/chunk_25-*
- split: chunk_26
path: data/chunk_26-*
- split: chunk_27
path: data/chunk_27-*
- split: chunk_28
path: data/chunk_28-*
- split: chunk_29
path: data/chunk_29-*
---
|
amuvarma/emilia-snac-merged-18m-mod7-delay | amuvarma | "2025-03-08T22:01:55Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T21:27:48Z" | ---
dataset_info:
features:
- name: codes_list
sequence: int64
- name: text
dtype: string
splits:
- name: train
num_bytes: 111442415676
num_examples: 17114684
download_size: 29034463150
dataset_size: 111442415676
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Daemontatox/image_captions | Daemontatox | "2025-03-08T21:28:10Z" | 0 | 0 | [
"task_categories:text-to-image",
"task_categories:image-to-text",
"language:en",
"region:us",
"synthetic"
] | [
"text-to-image",
"image-to-text"
] | "2025-03-08T21:28:10Z" | ---
dataset_info:
features:
- name: image
dtype: image
- name: caption
dtype: string
splits:
- name: train
num_bytes: 316862569250.04
num_examples: 1074164
download_size: 310695026221
dataset_size: 316862569250.04
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
task_categories:
- text-to-image
- image-to-text
language:
- en
tags:
- synthetic
---
<img src="https://takara.ai/images/logo-24/TakaraAi.svg" width="200" alt="Takara.ai Logo" />
From the Frontier Research Team at takara.ai we present over 1 million curated captioned images for multimodal text and image tasks.
---
## Usage
```python
from datasets import load_dataset
ds = load_dataset("takara-ai/image_captions")
print(ds)
```
---
## Example
<figure>
<img src="https://huggingface.co./datasets/takara-ai/image_captions/resolve/main/media/image_grid_compressed.jpg" alt="Alternative text">
<figcaption>10,000 images from the dataset.</figcaption>
</figure>
## Methodology
We consolidated multiple open source datasets through an intensive 96-hour computational process across three nodes. This involved standardizing and validating the data through extensive cleaning and normalization. The resulting dataset features embedded PIL images rather than URLs, improving accessibility while reducing dependency on source websites.
---
For research inquiries and press, please reach out to [email protected]
> δΊΊι‘γε€ι©γγ |
wilgomoreira/dataset_vineyardLogits_sigmoid | wilgomoreira | "2025-03-08T21:42:06Z" | 0 | 0 | [
"task_categories:image-segmentation",
"license:mit",
"region:us",
"deep-learning",
"agriculture",
"vineyards",
"segmentation",
"logits"
] | [
"image-segmentation"
] | "2025-03-08T21:31:33Z" | ---
tags:
- deep-learning
- agriculture
- vineyards
- segmentation
- logits
license: mit
datasets:
- dataset_vineyardLogits_sigmoid
task_categories:
- image-segmentation
---
# Vineyard Logits Sigmoid Dataset π
## π Overview
The **dataset_vineyardLogits_sigmoid** is a collection of **logits and labels** used for training and testing deep learning models in **precision agriculture**.
π‘ **Key Details**:
- **Binary classification task** with **one class**.
- **Sigmoid activation function** used to output probabilities.
- **Optimized for distinguishing vine plants from background elements**.
This dataset provides valuable logits from models trained on vineyard segmentation tasks, enabling further research and development in precision agriculture.
---
## π Hyperparameters
The dataset consists of **three distinct datasets** used for **binary classification**. Below are the key hyperparameters used during training and testing:
1. **Split Ratio**
- The dataset is split **80:20** (80% training, 20% testing).
2. **Learning Rate**
- Initial **learning rate: 0.001**.
3. **Batch Sizes**
- **Training batch size**: **30**
- **Testing batch size**: **3**
- This ensures efficient model training and evaluation.
---
## π Dataset Structure
```plaintext
dataset_vineyardLogits_sigmoid
βββ deeplab_EARLY_FUSION_t1
βββ deeplab_EARLY_FUSION_t2
βββ deeplab_EARLY_FUSION_t3
βββ deeplab_GNDVI_t1
βββ deeplab_GNDVI_t2
βββ deeplab_GNDVI_t3
βββ deeplab_NDVI_t1
βββ deeplab_NDVI_t2
βββ deeplab_NDVI_t3
βββ deeplab_RGB_t1
βββ deeplab_RGB_t2
βββ deeplab_RGB_t3
βββ segnet_EARLY_FUSION_t1
βββ segnet_EARLY_FUSION_t2
βββ segnet_EARLY_FUSION_t3
βββ segnet_GNDVI_t1
βββ segnet_GNDVI_t2
βββ segnet_GNDVI_t3
βββ segnet_NDVI_t1
βββ segnet_NDVI_t2
βββ segnet_NDVI_t3
βββ segnet_RGB_t1
βββ segnet_RGB_t2
βββ segnet_RGB_t3
βββ README.md
```
---
## π Contents
- **model_modality_fold_n/pred_masks_train**: Logits from the training set.
- **model_modality_fold_n/pred_masks_test**: Logits from the test set.
---
## πΈ Data Description
- **Model Logits**
The dataset consists of logits generated by **DeepLabV3** and **SegNet** during training and testing. These logits are **unnormalized raw scores** before applying the **sigmoid activation function**.
- **Original Images**
The images originate from aerial multispectral imagery collected from **three vineyards in central Portugal**:
- **Quinta de Baixo (QTA)**
- **ESAC**
- **Valdoeiro (VAL)**
β
**Captured at 240x240 resolution** using:
- **X7 RGB camera**
- **MicaSense Altum multispectral sensor**
β
Includes **RGB and Near-Infrared (NIR) bands**, enabling vegetation indices like **NDVI** and **GNDVI**.
β
**Ground-truth annotations available** for vineyard segmentation.
π **For more details**, refer to the dataset:
[Cybonic, "DL Vineyard Segmentation Study," v1.0, GitHub, 2024](https://github.com/Cybonic/DL_vineyard_segmentation_study)
---
## π₯ How to Use
### **1οΈβ£ Load in Python**
To load the dataset directly from Hugging Face:
```python
from datasets import load_dataset
dataset = load_dataset("wilgomoreira/dataset_vineyardLogits_sigmoid")
print(dataset)
```
### **2οΈβ£ Download Specific Files**
To download a specific file:
```bash
wget https://huggingface.co./datasets/seu-usuario/dataset_vineyardLogits_sigmoid/resolve/main/logits_train.npz
```
---
## π License
This dataset is released under the **MIT License**.
Please make sure to comply with the license terms when using this dataset.
---
## π Acknowledgments
This dataset was created by **Wilgo Cardoso** for research in **precision agriculture and deep learning segmentation**.
---
## π§ Contact
For any questions or collaborations, please contact:
βοΈ **[email protected]** |
nberkowitz/mini_grass_text | nberkowitz | "2025-03-08T21:32:51Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T21:32:22Z" | ---
dataset_info:
features:
- name: assembly
dtype: string
- name: chrom
dtype: string
- name: start
dtype: int64
- name: end
dtype: int64
- name: strand
dtype: string
- name: text
dtype: string
splits:
- name: train
num_bytes: 833899997
num_examples: 1472295
- name: validation
num_bytes: 104809024
num_examples: 185100
- name: test
num_bytes: 246571007
num_examples: 435487
download_size: 537837994
dataset_size: 1185280028
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
- split: test
path: data/test-*
---
|
Atomic-Ai/AtomicGPT2-data | Atomic-Ai | "2025-03-08T21:43:27Z" | 0 | 1 | [
"task_categories:question-answering",
"language:de",
"license:mit",
"size_categories:10K<n<100K",
"region:us",
"legal",
"QA",
"GPT",
"ai",
"dataset",
"Atomic",
"2"
] | [
"question-answering"
] | "2025-03-08T21:36:47Z" | ---
license: mit
task_categories:
- question-answering
language:
- de
tags:
- legal
- QA
- GPT
- ai
- dataset
- Atomic
- '2'
size_categories:
- 10K<n<100K
--- |
tshasan/CC-Meta25-1M | tshasan | "2025-03-08T23:29:09Z" | 0 | 0 | [
"license:cc-by-4.0",
"region:us",
"common-crawl",
"web-metadata",
"nlp",
"2025"
] | null | "2025-03-08T21:38:27Z" | ---
dataset_info:
features:
- name: url
dtype: string
- name: title
dtype: string
- name: snippet
dtype: string
- name: language
dtype: string
splits:
num_examples: 1000000
license: cc-by-4.0
tags:
- "common-crawl"
- "web-metadata"
- "nlp"
- "2025"
version: 1.0.0
---
# CC-Meta25-1M
[](https://creativecommons.org/licenses/by/4.0/)
[](https://huggingface.co./datasets/tshasan/cc-meta25-1m)
## Overview
The **CC-Meta25-1M** dataset comprises 1,000,341 tuples of web metadata (URL, title, snippet, language) extracted via uniform random sampling from the Common Crawl February 2025 dataset (CC-MAIN-2025-08. Released under version 1.0.0, it captures a representative snapshot of web content from early 2025, retaining original snippet text including boilerplate such as cookie notices and navigation elements for authenticity. This dataset is intended for researchers and practitioners exploring web metadata, linguistic distributions, or temporal web trends.
## Dataset Specifications
- **Source**: [Common Crawl CC-MAIN-2025-08](https://commoncrawl.org)
- **Size**: 1,000,341 records, [323.3 MB] (Parquet format)
- **Sampling**: Uniform random selection from the February 2025 crawl
- **Features**:
- `url`: Web page URL (string; "N/A" if invalid or missing)
- `title`: Page title (string; "N/A" if missing)
- `snippet`: Text excerpt from the page (string; includes boilerplate, "N/A" if missing)
- `language`: ISO 639-1 language code (string; e.g., "en", "N/A" if missing)
- **Processing**:
- Missing values in all fields replaced with "N/A".
- Duplicates preserved to mirror the raw crawl (0.01% duplicated).
## Accessing the Dataset
Hosted on Hugging Face, the dataset can be accessed as follows:
```python
from datasets import load_dataset
dataset = load_dataset("tshasan/cc-meta25-1m")
print(dataset[0]) |
Asap7772/cog_behav_all_strategies | Asap7772 | "2025-03-08T22:02:22Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:02:20Z" | ---
dataset_info:
features:
- name: query
dtype: string
- name: completion
dtype: string
splits:
- name: train
num_bytes: 1466458
num_examples: 1000
- name: test
num_bytes: 305543
num_examples: 200
download_size: 580991
dataset_size: 1772001
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: test
path: data/test-*
---
|
InfiniAILab/gsm8k | InfiniAILab | "2025-03-08T22:09:17Z" | 0 | 0 | [
"task_categories:question-answering",
"language:en",
"size_categories:1K<n<10K",
"region:us"
] | [
"question-answering"
] | "2025-03-08T22:06:31Z" | ---
dataset_info:
features:
- name: question
dtype: string
- name: answer
dtype: string
- name: solution
dtype: string
splits:
- name: test
num_bytes: 721975
num_examples: 1319
download_size: 420637
dataset_size: 721975
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
task_categories:
- question-answering
language:
- en
size_categories:
- 1K<n<10K
--- |
mlfoundations-dev/SCP-116k_r1_annotation__training_subset | mlfoundations-dev | "2025-03-08T22:09:04Z" | 0 | 0 | [
"language:en",
"license:mit",
"region:us"
] | null | "2025-03-08T22:08:57Z" | ---
language: en
license: mit
tag: curator
---
<a href="https://github.com/bespokelabsai/curator/">
<img src="https://huggingface.co./datasets/bespokelabs/Bespoke-Stratos-17k/resolve/main/made_with_curator.png" alt="Made with Curator" width=200px>
</a>
## Dataset card for SCP-116k_r1_annotation__training_subset
This dataset was made with [Curator](https://github.com/bespokelabsai/curator/).
## Dataset details
A sample from the dataset:
```python
{
"id": "books_416_problem_0",
"source": "SCP-116K",
"text": [
"You are an advanced AI language model specializing in solving scientific problems step by step. Carefully analyze each part of the problem, verify the accuracy of your reasoning with relevant facts and data, and provide clear, logical solutions. Reflect on and review your approach throughout the problem-solving process to ensure precision and thoroughness. Always think through the problem step by step and provide your answers accordingly.",
"An electron is confined in a three-dimensional infinite potential well. The sides parallel to the $x$-, $y$-, and $z$-axes are of length $L$ each.\\n\\n(a) Write the appropriate Schr\u00f6dinger equation.\\n\\n(b) Write the time-independent wave function corresponding to the state of the lowest possible energy.\\n\\n(c) Give an expression for the number of states, $N$, having energy less than some given $E$. Assume $N \\gg 1.\\n\\n(Wisconsin)",
"So I've got this problem here about an electron in a three-dimensional infinite potential well, and all the sides are of length L. It's got three parts: writing the Schr\u00f6dinger equation, finding the lowest energy wave function, and then figuring out how many states have energy less than some given value E, assuming N is much greater than one. It's from the University of Wisconsin.\n\nAlright, let's start with part (a): writing the appropriate Schr\u00f6dinger equation. Since it's a three-dimensional infinite potential well, I know that the potential V is zero inside the well and infinite outside. So, inside the well, the time-independent Schr\u00f6dinger equation should be:\n\n\\[-\\frac{\\hbar^2}{2m} \\nabla^2 \\psi(x,y,z) = E \\psi(x,y,z)\\]\n\nWhere \\(\\nabla^2\\) is the Laplacian operator in three dimensions, which is:\n\n\\[\\nabla^2 = \\frac{\\partial^2}{\\partial x^2} + \\frac{\\partial^2}{\\partial y^2} + \\frac{\\partial^2}{\\partial z^2}\\]\n\nSo, plugging that in, the equation becomes:\n\n\\[-\\frac{\\hbar^2}{2m} \\left( \\frac{\\partial^2 \\psi}{\\partial x^2} + \\frac{\\partial^2 \\psi}{\\partial y^2} + \\frac{\\partial^2 \\psi}{\\partial z^2} \\right) = E \\psi(x,y,z)\\]\n\nThat should be the appropriate Schr\u00f6dinger equation for this system.\n\nMoving on to part (b): writing the time-independent wave function for the state of lowest possible energy.\n\nIn a three-dimensional infinite potential well, the energy levels are given by:\n\n\\[E_{n_x,n_y,n_z} = \\frac{\\hbar^2 \\pi^2}{2m L^2} (n_x^2 + n_y^2 + n_z^2)\\]\n\nWhere \\(n_x\\), \\(n_y\\), and \\(n_z\\) are positive integers (1,2,3,...). The lowest energy state corresponds to the smallest possible values of \\(n_x\\), \\(n_y\\), and \\(n_z\\), which are all 1.\n\nSo, the lowest energy is:\n\n\\[E_{1,1,1} = \\frac{\\hbar^2 \\pi^2}{2m L^2} (1^2 + 1^2 + 1^2) = \\frac{3 \\hbar^2 \\pi^2}{2m L^2}\\]\n\nThe wave function for this state is the product of the one-dimensional wave functions for each direction:\n\n\\[\\psi_{1,1,1}(x,y,z) = \\psi_{1x}(x) \\psi_{1y}(y) \\psi_{1z}(z)\\]\n\nWhere each one-dimensional wave function is:\n\n\\[\\psi_{1x}(x) = \\sqrt{\\frac{2}{L}} \\sin\\left(\\frac{\\pi x}{L}\\right)\\]\\[\\psi_{1y}(y) = \\sqrt{\\frac{2}{L}} \\sin\\left(\\frac{\\pi y}{L}\\right)\\]\\[\\psi_{1z}(z) = \\sqrt{\\frac{2}{L}} \\sin\\left(\\frac{\\pi z}{L}\\right)\\]\n\nSo, the overall wave function is:\n\n\\[\\psi_{1,1,1}(x,y,z) = \\left( \\frac{2}{L} \\right)^{3/2} \\sin\\left(\\frac{\\pi x}{L}\\right) \\sin\\left(\\frac{\\pi y}{L}\\right) \\sin\\left(\\frac{\\pi z}{L}\\right)\\]\n\nThat should be the wave function for the lowest energy state.\n\nNow, part (c): giving an expression for the number of states N having energy less than some given E, assuming N is much greater than one.\n\nThis sounds like it's asking for the density of states in energy. For a three-dimensional infinite potential well, the energy levels are determined by the quantum numbers \\(n_x\\), \\(n_y\\), and \\(n_z\\), all positive integers.\n\nThe energy for a given set of quantum numbers is:\n\n\\[E_{n_x,n_y,n_z} = \\frac{\\hbar^2 \\pi^2}{2m L^2} (n_x^2 + n_y^2 + n_z^2)\\]\n\nLet's define a variable to simplify this expression:\n\nLet \\(\\gamma = \\frac{2m E L^2}{\\hbar^2 \\pi^2}\\)\n\nThen, the condition \\(E_{n_x,n_y,n_z} < E\\) becomes:\n\n\\[n_x^2 + n_y^2 + n_z^2 < \\gamma\\]\n\nSo, N is the number of integer triplets (n_x, n_y, n_z) with positive integers such that \\(n_x^2 + n_y^2 + n_z^2 < \\gamma\\).\n\nWhen N is much greater than one, we can approximate this number using the volume of a sphere in three dimensions, since \\(n_x^2 + n_y^2 + n_z^2 < \\gamma\\) describes a sphere of radius \\(\\sqrt{\\gamma}\\) in n-space.\n\nThe volume of a sphere in three dimensions is \\(\\frac{4}{3} \\pi r^3\\), but since \\(n_x\\), \\(n_y\\), and \\(n_z\\) are positive integers, we're only considering the first octant. So, the number of states N should be approximately:\n\n\\[N \\approx \\frac{1}{8} \\cdot \\frac{4}{3} \\pi (\\sqrt{\\gamma})^3 = \\frac{1}{6} \\pi \\gamma^{3/2}\\]\n\nSubstituting back for \\(\\gamma\\):\n\n\\[N \\approx \\frac{1}{6} \\pi \\left( \\frac{2m E L^2}{\\hbar^2 \\pi^2} \\right)^{3/2}\\]\n\nSimplifying:\n\n\\[N \\approx \\frac{1}{6} \\pi \\cdot \\frac{(2m E L^2)^{3/2}}{(\\hbar^2 \\pi^2)^{3/2}} = \\frac{1}{6} \\pi \\cdot \\frac{(2m E L^2)^{3/2}}{\\hbar^3 \\pi^3} = \\frac{1}{6} \\cdot \\frac{(2m E L^2)^{3/2}}{\\hbar^3 \\pi^{2}}\\]\n\nFurther simplifying:\n\n\\[N \\approx \\frac{1}{6 \\pi^2} \\cdot \\frac{(2m E L^2)^{3/2}}{\\hbar^3}\\]\n\nThat should be the expression for the number of states with energy less than E, assuming N is much greater than one.\n\nLet me just double-check that. The approximation makes sense because when N is large, the number of states inside the sphere is well-approximated by the volume of the sphere. The factor of \\(\\frac{1}{8}\\) comes from considering only the first octant since all n's are positive integers.\n\nI think that's the correct expression.\n\n**Final Answer**\n\n\\[\\boxed{N \\approx \\frac{1}{6 \\pi^2} \\cdot \\frac{(2m E L^2)^{3/2}}{\\hbar^3}}\\]"
],
"tag": [
"S",
"Q",
"A"
],
"r1_reasoning": "Okay, so I need to solve this problem about an electron in a three-dimensional infinite potential well. Let me start by recalling what I know about infinite potential wells, also known as infinite square wells. In one dimension, the potential is zero inside a region of length L and infinite outside, which confines the particle to that region. The solutions to the Schr\u00f6dinger equation in that case are sine or cosine functions, depending on the boundary conditions, and the energy levels are quantized.\n\nSince this is a three-dimensional problem, the potential is zero inside a cube of side length L and infinite outside. That means the electron is completely free to move inside the cube but cannot escape it. The Schr\u00f6dinger equation for this system should be separable into x, y, and z components because the potential is zero inside the cube and the infinite potential outside makes the boundary conditions separable as well.\n\nStarting with part (a), which asks to write the appropriate Schr\u00f6dinger equation. The time-independent Schr\u00f6dinger equation (TISE) in three dimensions is generally given by:\n\n$$\n-\\frac{\\hbar^2}{2m} \\nabla^2 \\psi(x, y, z) + V(x, y, z) \\psi(x, y, z) = E \\psi(x, y, z)\n$$\n\nIn this case, the potential V(x, y, z) is zero inside the cube (0 \u2264 x, y, z \u2264 L) and infinite outside. So, inside the cube, the equation simplifies to:\n\n$$\n-\\frac{\\hbar^2}{2m} \\left( \\frac{\\partial^2 \\psi}{\\partial x^2} + \\frac{\\partial^2 \\psi}{\\partial y^2} + \\frac{\\partial^2 \\psi}{\\partial z^2} \\right) = E \\psi\n$$\n\nThat's the appropriate Schr\u00f6dinger equation for the region where the electron is confined. Outside the cube, the wave function must be zero because the potential is infinite, so the probability of finding the electron there is zero.\n\nFor part (b), the time-independent wave function corresponding to the lowest possible energy. The lowest energy state in a quantum system is the ground state, which in the case of a particle in a box corresponds to the lowest quantum numbers in each direction. Since the potential is three-dimensional and separable, the wave function will be a product of the wave functions in each direction.\n\nIn one dimension, the ground state wave function is:\n\n$$\n\\psi_n(x) = \\sqrt{\\frac{2}{L}} \\sin\\left( \\frac{n \\pi x}{L} \\right)\n$$\n\nwhere n = 1 for the ground state. Extending this to three dimensions, the quantum numbers for each direction (n_x, n_y, n_z) will all be 1 for the lowest energy state. Therefore, the wave function should be:\n\n$$\n\\psi_{1,1,1}(x, y, z) = \\left( \\frac{2}{L} \\right)^{3/2} \\sin\\left( \\frac{\\pi x}{L} \\right) \\sin\\left( \\frac{\\pi y}{L} \\right) \\sin\\left( \\frac{\\pi z}{L} \\right)\n$$\n\nThat's the ground state wave function. The energy associated with this state can be calculated using the formula for the energy levels in a 3D box:\n\n$$\nE_{n_x, n_y, n_z} = \\frac{\\hbar^2 \\pi^2}{2mL^2} (n_x^2 + n_y^2 + n_z^2)\n$$\n\nFor the ground state, n_x = n_y = n_z = 1, so the energy is:\n\n$$\nE_{1,1,1} = \\frac{3 \\hbar^2 \\pi^2}{2mL^2}\n$$\n\nBut part (b) only asks for the wave function, so that should be sufficient.\n\nMoving on to part (c), which asks for an expression for the number of states N with energy less than some given E, assuming N is much greater than 1. This is essentially asking for the density of states in a 3D infinite potential well. \n\nIn a 3D box, the energy levels are given by:\n\n$$\nE = \\frac{\\hbar^2 \\pi^2}{2mL^2} (n_x^2 + n_y^2 + n_z^2)\n$$\n\nLet me denote the constant factor as E_0 = \\frac{\\hbar^2 \\pi^2}{2mL^2}, so that E = E_0 (n_x^2 + n_y^2 + n_z^2). But actually, E_0 here would correspond to the coefficient multiplied by the sum of squares. Wait, let me check:\n\nWait, the energy is:\n\n$$\nE = \\frac{\\hbar^2}{2m} \\left( \\left(\\frac{\\pi}{L}\\right)^2 n_x^2 + \\left(\\frac{\\pi}{L}\\right)^2 n_y^2 + \\left(\\frac{\\pi}{L}\\right)^2 n_z^2 \\right) = \\frac{\\hbar^2 \\pi^2}{2mL^2} (n_x^2 + n_y^2 + n_z^2)\n$$\n\nYes, so if we let k^2 = (n_x^2 + n_y^2 + n_z^2)(\u03c0/L)^2, then E = (\u0127\u00b2k\u00b2)/(2m). But perhaps another way to think about this is in terms of the quantum numbers. Each state is defined by a triplet (n_x, n_y, n_z) where each n is a positive integer. The number of states with energy less than E is the number of triplets such that n_x^2 + n_y^2 + n_z^2 \u2264 (E 2mL\u00b2)/(\u0127\u00b2 \u03c0\u00b2).\n\nLet me define R^2 = (E 2mL\u00b2)/(\u0127\u00b2 \u03c0\u00b2), so the problem reduces to finding the number of positive integer triplets (n_x, n_y, n_z) such that n_x^2 + n_y^2 + n_z^2 \u2264 R^2. Since N is large, we can approximate this sum by the volume of an octant (since n_x, n_y, n_z are positive integers) of a sphere with radius R. \n\nIn three dimensions, the volume of a sphere is (4/3)\u03c0R\u00b3, and since we are dealing with positive integers (i.e., the first octant), the volume would be (1/8)(4/3)\u03c0R\u00b3) = \u03c0R\u00b3/6. However, each point (n_x, n_y, n_z) corresponds to a unit cube in the 3D space of quantum numbers, so the number of states N is approximately equal to the volume of the octant of the sphere with radius R. Therefore,\n\nN \u2248 (1/8) * (4/3)\u03c0R\u00b3) = \u03c0R\u00b3/6\n\nBut R is sqrt(E 2mL\u00b2/(\u0127\u00b2 \u03c0\u00b2)) = sqrt(2mL\u00b2E/(\u0127\u00b2 \u03c0\u00b2)) = (L/\u03c0\u0127) sqrt(2mE)\n\nWait, let's compute R:\n\nFrom above, R\u00b2 = (2mL\u00b2E)/(\u0127\u00b2 \u03c0\u00b2), so R = (L/\u03c0\u0127) sqrt(2mE)\n\nTherefore, substituting back into N:\n\nN \u2248 (\u03c0/6) * [ (L/\u03c0\u0127) sqrt(2mE) ]\u00b3\n\nSimplify this expression:\n\nFirst, cube the term inside:\n\n[ (L/\u03c0\u0127) sqrt(2mE) ]\u00b3 = (L\u00b3)/(\u03c0\u00b3 \u0127\u00b3) * (2mE)^(3/2)\n\nMultiply by \u03c0/6:\n\nN \u2248 (\u03c0/6) * (L\u00b3)/(\u03c0\u00b3 \u0127\u00b3) * (2mE)^(3/2) = (1/(6 \u03c0\u00b2 \u0127\u00b3)) * L\u00b3 (2mE)^(3/2)\n\nSimplify constants:\n\n(2mE)^(3/2) = 2^(3/2) m^(3/2) E^(3/2) = 2*sqrt(2) m^(3/2) E^(3/2)\n\nSo,\n\nN \u2248 (1/(6 \u03c0\u00b2 \u0127\u00b3)) * L\u00b3 * 2*sqrt(2) m^(3/2) E^(3/2)\n\nCombine constants:\n\n2*sqrt(2) = 2^(3/2), so:\n\nN \u2248 (2^(3/2) m^(3/2) L\u00b3 E^(3/2)) / (6 \u03c0\u00b2 \u0127\u00b3)\n\nSimplify the denominator and numerator:\n\nDivide numerator and denominator by 2:\n\n= (2^(1/2) m^(3/2) L\u00b3 E^(3/2)) / (3 \u03c0\u00b2 \u0127\u00b3)\n\nBut 2^(1/2) is sqrt(2), so:\n\nN \u2248 (sqrt(2) m^(3/2) L\u00b3 E^(3/2)) / (3 \u03c0\u00b2 \u0127\u00b3)\n\nAlternatively, we can write this as:\n\nN \u2248 \\frac{L^3 (2mE)^{3/2}}{6 \\pi^2 \\hbar^3}\n\nWait, let me check that. Let's see:\n\nOriginal expression after substitution:\n\nN \u2248 (\u03c0/6) * [ (L/\u03c0\u0127) sqrt(2mE) ]\u00b3\n\nLet me compute this step by step:\n\nFirst, expand [ (L/\u03c0\u0127) sqrt(2mE) ]\u00b3:\n\n= (L^3)/(\u03c0^3 \u0127^3) * (2mE)^(3/2)\n\nMultiply by \u03c0/6:\n\n= (L^3)/(\u03c0^3 \u0127^3) * (2mE)^(3/2) * \u03c0/6\n\n= (L^3)/(\u03c0^2 \u0127^3) * (2mE)^(3/2) /6\n\n= (L^3 (2mE)^(3/2)) / (6 \u03c0^2 \u0127^3 )\n\nYes, that's correct. So,\n\nN \u2248 \\frac{L^3 (2mE)^{3/2}}{6 \\pi^2 \\hbar^3}\n\nBut wait, the standard formula for the density of states in 3D is:\n\nN(E) = \\frac{V (2m)^{3/2}}{6 \\pi^2 \\hbar^3} E^{3/2}\n\nWhere V is the volume, which in this case is L\u00b3. So this matches. Therefore, the number of states with energy less than E is approximately this expression. Since the problem states N >> 1, the approximation using the volume of the sphere is valid, as the discrete nature of the states can be ignored when N is large.\n\nTherefore, the expression for N is:\n\nN \u2248 \\frac{L\u00b3 (2m)^{3/2}}{6 \\pi\u00b2 \\hbar\u00b3} E^{3/2}\n\nAlternatively, written as:\n\nN = \\frac{V (2mE)^{3/2}}{6 \\pi\u00b2 \\hbar\u00b3}\n\nWhere V = L\u00b3. So that's the expression.\n\nBut let me verify once more. The key idea is that in the 3D box, each quantum state corresponds to a point (n_x, n_y, n_z) in the 3D space of positive integers. The equation n_x\u00b2 + n_y\u00b2 + n_z\u00b2 \u2264 R\u00b2 (with R defined as before) defines a sphere octant. The number of such points is approximately the volume of that octant. Since each state occupies a unit volume in this space, the number of states is roughly the volume. Therefore, the volume is (1/8) * (4/3) \u03c0 R\u00b3) = \u03c0 R\u00b3 /6. Then substituting R in terms of E gives the expression. So yes, that seems correct.\n\nTherefore, part (c)'s answer is N = (V (2m)^{3/2})/(6 \u03c0\u00b2 \u210f\u00b3) * E^{3/2} = (L\u00b3 (2mE)^{3/2})/(6 \u03c0\u00b2 \u210f\u00b3)\n\nSo summarizing:\n\n(a) The Schr\u00f6dinger equation is the three-dimensional TISE with V=0 inside the cube.\n\n(b) The ground state wave function is the product of the lowest energy wave functions in each direction.\n\n(c) The number of states N with energy less than E is proportional to E^{3/2}, derived from the volume of a sphere in quantum number space.\n\nI think that covers all parts. Let me just check if I missed any constants or made any algebraic errors in part (c). Let's re-express R again:\n\nStarting from E = (\u0127\u00b2 \u03c0\u00b2)/(2mL\u00b2)(n_x\u00b2 + n_y\u00b2 + n_z\u00b2)\n\nSo n_x\u00b2 + n_y\u00b2 + n_z\u00b2 = (2mL\u00b2E)/(\u0127\u00b2 \u03c0\u00b2) = R\u00b2\n\nTherefore, R = sqrt(2mL\u00b2E)/(\u0127 \u03c0)\n\nWait, sqrt(2mL\u00b2E) divided by \u0127 \u03c0. So R = (L sqrt(2mE)) / (\u0127 \u03c0)\n\nTherefore, the radius in the n_x, n_y, n_z space is R = (L sqrt(2mE)) / (\u0127 \u03c0)\n\nThen the volume of the octant is (1/8) * (4/3) \u03c0 R\u00b3 = \u03c0 R\u00b3 /6\n\nSo substituting R:\n\nN \u2248 \u03c0 /6 * [ (L sqrt(2mE))/( \u0127 \u03c0 ) ]\u00b3\n\n= \u03c0 /6 * (L\u00b3 (2mE)^(3/2)) / ( \u0127\u00b3 \u03c0\u00b3 )\n\n= (L\u00b3 (2mE)^(3/2)) / (6 \u03c0\u00b2 \u0127\u00b3 )\n\nYes, exactly as before. So that's correct.\n\nTherefore, all parts are answered.\n\n**Final Answer**\n\n(a) The appropriate Schr\u00f6dinger equation is \\boxed{-\\frac{\\hbar^2}{2m} \\left( \\frac{\\partial^2 \\psi}{\\partial x^2} + \\frac{\\partial^2 \\psi}{\\partial y^2} + \\frac{\\partial^2 \\psi}{\\partial z^2} \\right) = E \\psi}.\n\n(b) The time-independent wave function for the lowest energy state is \\boxed{\\psi_{1,1,1}(x, y, z) = \\left( \\frac{2}{L} \\right)^{3/2} \\sin\\left( \\frac{\\pi x}{L} \\right) \\sin\\left( \\frac{\\pi y}{L} \\right) \\sin\\left( \\frac{\\pi z}{L} \\right)}.\n\n(c) The number of states with energy less than \\( E \\) is \\boxed{N = \\frac{L^3 (2mE)^{3/2}}{6 \\pi^2 \\hbar^3}}.",
"r1_solution": "(a) The appropriate Schr\u00f6dinger equation for an electron confined in a three-dimensional infinite potential well is the time-independent Schr\u00f6dinger equation with the potential \\( V(x, y, z) = 0 \\) inside the cube and infinite outside. Inside the cube, the equation simplifies to:\n\n$$\n\\boxed{-\\frac{\\hbar^2}{2m} \\left( \\frac{\\partial^2 \\psi}{\\partial x^2} + \\frac{\\partial^2 \\psi}{\\partial y^2} + \\frac{\\partial^2 \\psi}{\\partial z^2} \\right) = E \\psi}\n$$\n\n(b) The time-independent wave function corresponding to the lowest possible energy state (ground state) is given by the product of the lowest energy wave functions in each direction. The quantum numbers \\( n_x \\), \\( n_y \\), and \\( n_z \\) are all 1 for the ground state:\n\n$$\n\\boxed{\\psi_{1,1,1}(x, y, z) = \\left( \\frac{2}{L} \\right)^{3/2} \\sin\\left( \\frac{\\pi x}{L} \\right) \\sin\\left( \\frac{\\pi y}{L} \\right) \\sin\\left( \\frac{\\pi z}{L} \\right)}\n$$\n\n(c) The number of states \\( N \\) with energy less than \\( E \\) is approximated by considering the volume of an octant of a sphere in the quantum number space. This volume is proportional to \\( E^{3/2} \\) and results in the expression:\n\n$$\n\\boxed{N = \\frac{L^3 (2mE)^{3/2}}{6 \\pi^2 \\hbar^3}}\n$$",
"claude_judge_correct": false,
"claude_judge_reasoning": "",
"judge_correct": false,
"judge_reasoning": ""
}
```
## Loading the dataset
You can load this dataset using the following code:
```python
from datasets import load_dataset
dataset = load_dataset("mlfoundations-dev/SCP-116k_r1_annotation__training_subset", split="default")
```
|
intelsense/natural-instruction-bangla | intelsense | "2025-03-08T22:22:16Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-08T22:22:16Z" | ---
license: mit
---
|
ArsParadox/Viel_Dataset_Lite | ArsParadox | "2025-03-08T22:22:43Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-08T22:22:17Z" | ---
license: mit
---
|
amuvarma/emilia-snac-merged-18m-mod7-delay-TTS | amuvarma | "2025-03-08T22:43:03Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:23:56Z" | ---
dataset_info:
features:
- name: input_ids
sequence: int32
splits:
- name: train
num_bytes: 57331641372.0
num_examples: 17114684
download_size: 31098383737
dataset_size: 57331641372.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
mlfoundations-dev/sci_question_exp__scp_116k__training_2k_for_GPQA | mlfoundations-dev | "2025-03-08T22:28:01Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:26:01Z" | ---
dataset_info:
features:
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
splits:
- name: train
num_bytes: 2562135966
num_examples: 117685
download_size: 1108660992
dataset_size: 2562135966
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
dleemiller/lm25 | dleemiller | "2025-03-08T23:05:52Z" | 0 | 0 | [
"language:en",
"license:mit",
"size_categories:n<1K",
"region:us",
"retrieval",
"bm25"
] | null | "2025-03-08T22:26:50Z" | ---
license: mit
language:
- en
tags:
- retrieval
- bm25
pretty_name: LM25
size_categories:
- n<1K
configs:
- config_name: raw
data_files:
- split: train
path: raw/*
- config_name: sft
data_files:
- split: train
path: sft/*
---
# LM25 Dataset
This dataset contains augmented queries from the [NanoBEIR](https://huggingface.co./collections/zeta-alpha-ai/nanobeir-66e1a0af21dfd93e620cd9f6)
dataset.
## Dataset Details
|
mceballost/Userstory | mceballost | "2025-03-08T22:31:58Z" | 0 | 0 | [
"license:apache-2.0",
"region:us"
] | null | "2025-03-08T22:30:14Z" | ---
license: apache-2.0
---
|
fracapuano/eeg2meg-medium | fracapuano | "2025-03-09T00:44:46Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:31:12Z" | ---
dataset_info:
features:
- name: fif_file
dtype: string
- name: events
dtype: string
- name: eeg_data
sequence:
sequence: float32
- name: meg_data
sequence:
sequence: float32
splits:
- name: train
num_bytes: 1244836723
num_examples: 2351
download_size: 1239979338
dataset_size: 1244836723
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
sap-ai/rgm-ai-1-nummerical | sap-ai | "2025-03-08T22:34:54Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-08T22:33:17Z" | ---
license: mit
---
This is example training data to train this ai I built. |
vsahil/tulu3_math_datasets_combined_and_sampled_5000 | vsahil | "2025-03-08T22:39:12Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:39:10Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
splits:
- name: train
num_bytes: 22301148.608711466
num_examples: 5000
download_size: 10414437
dataset_size: 22301148.608711466
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
vsahil/tulu3_math_datasets_combined_and_sampled_10000 | vsahil | "2025-03-08T22:39:16Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:39:13Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
splits:
- name: train
num_bytes: 44602297.21742293
num_examples: 10000
download_size: 20689937
dataset_size: 44602297.21742293
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
vsahil/tulu3_math_datasets_combined_and_sampled_20000 | vsahil | "2025-03-08T22:39:20Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:39:16Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
splits:
- name: train
num_bytes: 89204594.43484586
num_examples: 20000
download_size: 41362895
dataset_size: 89204594.43484586
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
vsahil/tulu3_math_datasets_combined_and_sampled_50000 | vsahil | "2025-03-08T22:39:26Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:39:20Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
splits:
- name: train
num_bytes: 223011486.08711466
num_examples: 50000
download_size: 103598203
dataset_size: 223011486.08711466
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
vsahil/tulu3_math_datasets_combined_and_sampled_100000 | vsahil | "2025-03-08T22:39:36Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:39:27Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
splits:
- name: train
num_bytes: 446022972.1742293
num_examples: 100000
download_size: 207394206
dataset_size: 446022972.1742293
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
refine-ai/test | refine-ai | "2025-03-08T22:46:29Z" | 0 | 0 | [
"size_categories:n<1K",
"region:us",
"datadreamer",
"datadreamer-0.28.0",
"synthetic",
"gpt-4"
] | null | "2025-03-08T22:42:35Z" | ---
dataset_info:
features:
- name: reviews
dtype: string
splits:
- name: train
num_bytes: 611
num_examples: 1
download_size: 3709
dataset_size: 611
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
library_name: datadreamer
size_categories:
- n<1K
tags:
- datadreamer
- datadreamer-0.28.0
- synthetic
- gpt-4
---
# Dataset Card
[Add more information here](https://huggingface.co./datasets/templates/dataset-card-example)
---
This dataset was produced with [DataDreamer π€π€](https://datadreamer.dev). The synthetic dataset card can be found [here](datadreamer.json). |
LightFury9/eval-250 | LightFury9 | "2025-03-08T23:32:23Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:43:09Z" | ---
dataset_info:
features:
- name: question
dtype: string
- name: answer
dtype: string
- name: prompt
dtype: string
- name: output
dtype: string
splits:
- name: llama321
num_bytes: 1834224
num_examples: 1319
download_size: 770751
dataset_size: 1834224
configs:
- config_name: default
data_files:
- split: llama321
path: data/llama321-*
---
|
ltnhut/FasImg1 | ltnhut | "2025-03-08T23:30:34Z" | 0 | 0 | [
"license:unknown",
"region:us"
] | null | "2025-03-08T22:44:02Z" | ---
license: unknown
---
|
NamburiSrinath/databricks-dolly-15k-modernbert-split-kmeans-dim768-20250308 | NamburiSrinath | "2025-03-08T22:47:39Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T22:47:34Z" | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: context
dtype: string
- name: response
dtype: string
- name: category
dtype: string
- name: cluster_1
dtype: int32
- name: cluster_2
dtype: int32
- name: cluster_3
dtype: int32
- name: cluster_4
dtype: int32
- name: cluster_5
dtype: int32
- name: cluster_6
dtype: int32
- name: cluster_7
dtype: int32
- name: cluster_8
dtype: int32
- name: cluster_9
dtype: int32
- name: cluster_10
dtype: int32
- name: cluster_11
dtype: int32
- name: cluster_12
dtype: int32
- name: cluster_13
dtype: int32
- name: cluster_14
dtype: int32
- name: cluster_15
dtype: int32
- name: cluster_16
dtype: int32
- name: cluster_17
dtype: int32
- name: cluster_18
dtype: int32
- name: cluster_19
dtype: int32
- name: cluster_20
dtype: int32
- name: cluster_21
dtype: int32
- name: cluster_22
dtype: int32
- name: cluster_23
dtype: int32
- name: cluster_24
dtype: int32
- name: cluster_25
dtype: int32
- name: cluster_26
dtype: int32
- name: cluster_27
dtype: int32
- name: cluster_28
dtype: int32
- name: cluster_29
dtype: int32
- name: cluster_30
dtype: int32
splits:
- name: train
num_bytes: 13996909
num_examples: 15011
download_size: 8133830
dataset_size: 13996909
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
LorenaYannnnn/how_lms_answer_one_to_many_factual_queries | LorenaYannnnn | "2025-03-08T23:32:48Z" | 0 | 0 | [
"task_categories:question-answering",
"task_categories:text-generation",
"language:en",
"license:apache-2.0",
"arxiv:2502.20475",
"region:us"
] | [
"question-answering",
"text-generation"
] | "2025-03-08T23:12:43Z" | ---
license: apache-2.0
task_categories:
- question-answering
- text-generation
language:
- en
dataset_info:
- config_name: country_cities
features:
- name: query
dtype: string
- name: query_input_ids
sequence: int64
- name: target_answer_idx
dtype: int64
- name: target_answer_name
dtype: string
- name: target_answer_tokens
sequence: int64
- name: three_answers_label_list
sequence: string
- name: three_answers_token_list
sequence:
sequence: int64
- name: three_answers_start_end_idx
sequence:
sequence: int64
- name: subject
dtype: string
- name: subject_token_list
sequence: int64
- name: subject_start_end_idx
sequence: int64
- name: relation_start_end_idx
sequence: int64
splits:
- name: llama_step_1
num_examples: 122
- name: llama_step_2
num_examples: 122
- name: llama_step_3
num_examples: 122
- name: mistral_step_1
num_examples: 116
- name: mistral_step_2
num_examples: 116
- name: mistral_step_3
num_examples: 116
- config_name: artist_songs
features:
- name: query
dtype: string
- name: query_input_ids
sequence: int64
- name: target_answer_idx
dtype: int64
- name: target_answer_name
dtype: string
- name: target_answer_tokens
sequence: int64
- name: three_answers_label_list
sequence: string
- name: three_answers_token_list
sequence:
sequence: int64
- name: three_answers_start_end_idx
sequence:
sequence: int64
- name: subject
dtype: string
- name: subject_token_list
sequence: int64
- name: subject_start_end_idx
sequence: int64
- name: relation_start_end_idx
sequence: int64
splits:
- name: llama_step_1
num_examples: 261
- name: llama_step_2
num_examples: 261
- name: llama_step_3
num_examples: 261
- name: mistral_step_1
num_examples: 206
- name: mistral_step_2
num_examples: 206
- name: mistral_step_3
num_examples: 206
- config_name: actor_movies
features:
- name: query
dtype: string
- name: query_input_ids
sequence: int64
- name: target_answer_idx
dtype: int64
- name: target_answer_name
dtype: string
- name: target_answer_tokens
sequence: int64
- name: three_answers_label_list
sequence: string
- name: three_answers_token_list
sequence:
sequence: int64
- name: three_answers_start_end_idx
sequence:
sequence: int64
- name: subject
dtype: string
- name: subject_token_list
sequence: int64
- name: subject_start_end_idx
sequence: int64
- name: relation_start_end_idx
sequence: int64
splits:
- name: llama_step_1
num_examples: 1285
- name: llama_step_2
num_examples: 1285
- name: llama_step_3
num_examples: 1285
- name: mistral_step_1
num_examples: 965
- name: mistral_step_2
num_examples: 965
- name: mistral_step_3
num_examples: 965
configs:
- config_name: country_cities
data_files:
- split: llama_step_1
path: country_cities/meta-llama/Meta-Llama-3-8B-Instruct/country_cities_1.jsonl
- split: llama_step_2
path: country_cities/meta-llama/Meta-Llama-3-8B-Instruct/country_cities_2.jsonl
- split: llama_step_3
path: country_cities/meta-llama/Meta-Llama-3-8B-Instruct/country_cities_3.jsonl
- split: mistral_step_1
path: country_cities/mistralai/Mistral-7B-Instruct-v0.2/country_cities_1.jsonl
- split: mistral_step_2
path: country_cities/mistralai/Mistral-7B-Instruct-v0.2/country_cities_2.jsonl
- split: mistral_step_3
path: country_cities/mistralai/Mistral-7B-Instruct-v0.2/country_cities_3.jsonl
- config_name: artist_songs
data_files:
- split: llama_step_1
path: artist_songs/meta-llama/Meta-Llama-3-8B-Instruct/artist_songs_1.jsonl
- split: llama_step_2
path: artist_songs/meta-llama/Meta-Llama-3-8B-Instruct/artist_songs_2.jsonl
- split: llama_step_3
path: artist_songs/meta-llama/Meta-Llama-3-8B-Instruct/artist_songs_3.jsonl
- split: mistral_step_1
path: artist_songs/mistralai/Mistral-7B-Instruct-v0.2/artist_songs_1.jsonl
- split: mistral_step_2
path: artist_songs/mistralai/Mistral-7B-Instruct-v0.2/artist_songs_2.jsonl
- split: mistral_step_3
path: artist_songs/mistralai/Mistral-7B-Instruct-v0.2/artist_songs_3.jsonl
- config_name: actor_movies
data_files:
- split: llama_step_1
path: actor_movies/meta-llama/Meta-Llama-3-8B-Instruct/actor_movies_1.jsonl
- split: llama_step_2
path: actor_movies/meta-llama/Meta-Llama-3-8B-Instruct/actor_movies_2.jsonl
- split: llama_step_3
path: actor_movies/meta-llama/Meta-Llama-3-8B-Instruct/actor_movies_3.jsonl
- split: mistral_step_1
path: actor_movies/mistralai/Mistral-7B-Instruct-v0.2/actor_movies_1.jsonl
- split: mistral_step_2
path: actor_movies/mistralai/Mistral-7B-Instruct-v0.2/actor_movies_2.jsonl
- split: mistral_step_3
path: actor_movies/mistralai/Mistral-7B-Instruct-v0.2/actor_movies_3.jsonl
---
# One-to-Many Factual Queries Datasets
This is the official dataset used in our paper [Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries](https://www.arxiv.org/abs/2502.20475).
- The dataset includes three subsets: ```country_cities```, ```artist_songs```, ```actor_movies```.
- The ```{model_name}_step_{i}``` split in each subset contains the data used for analyzing ```model_name```'s behavior at answer step ```i```
where ```model_name``` can be ```llama``` or ```mistral``` and ```i = 1, 2, 3```.
## Load Datasets
Run:
```
raw_datasets = load_dataset(
"LorenaYannnnn/how_lms_answer_one_to_many_factual_queries",
dataset_name,
f"{model_name}_step_{target_answer_idx}"
)
```
where ```dataset_name``` is ```country_cities```, ```artist_songs```, or ```actor_movies```. ```model_name``` is ```llama``` or ```mistral```, and ```target_answer_idx``` is the answer step.
## Data Structure
Following is an example entry:
```
{
"query": "List only the name of three cities from Switzerland: 1.", # Input query
"query_input_ids": [3231, 865, 272, 1141, 302, 1712, 9245, 477, 22491, 28747, 28705, 28740, 28723], # Input query token ids
"target_answer_idx": 1, # answer step under examination
"target_answer_name": "Zurich", # string of current step's answer
"target_answer_tokens": [25571, 539], # token ids of the current step's answer
"three_answers_label_list": ["Zurich", "Geneva", "Bern"], # list of all three answers
"three_answers_token_list": [[25571, 539], [6242, 13237], [7562]], # token ids of all three answers
"three_answers_start_end_idx": [[13, 15], [18, 20], [23, 24]], # start and end index of all three answers
"subject": "Switzerland", # subject of the query
"subject_token_list": [22491], # token ids of the subject
"subject_start_end_idx": [8, 9] # start and end index of the subject
"relation_start_end_idx": [6, 8] # start and end index of the relation (e.g.: cities, songs, movies)
}
```
Refer to section 3.2 of the paper for the data sources and details for data curation.
## Github
Code is available at [here](https://github.com/Lorenayannnnn/how-lms-answer-one-to-many-factual-queries).
## Citation
```
@article{yan2025promote,
title={Promote, Suppress, Iterate: How Language Models Answer One-to-Many Factual Queries},
author={Yan, Tianyi Lorena and Jia, Robin},
journal={arXiv preprint arXiv:2502.20475},
year={2025}
}
``` |
florian-morel22/deepfake-test | florian-morel22 | "2025-03-08T23:15:05Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T23:13:04Z" | ---
dataset_info:
features:
- name: id
dtype: int64
- name: image
dtype: image
- name: fake
dtype: int64
- name: model
dtype: string
- name: id_source
dtype: int64
- name: id_target
dtype: int64
splits:
- name: train
num_bytes: 2719.0
num_examples: 4
download_size: 5211
dataset_size: 2719.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
eaalghamdi/chatrt_test_new | eaalghamdi | "2025-03-08T23:22:11Z" | 0 | 0 | [
"size_categories:n<1K",
"region:us",
"datadreamer",
"datadreamer-0.28.0",
"synthetic",
"gpt-4o"
] | null | "2025-03-08T23:22:04Z" | ---
dataset_info:
features:
- name: metadata
dtype: string
- name: topic
dtype: string
- name: data
dtype: string
- name: code
dtype: string
- name: image
dtype: image
- name: qa
dtype: string
splits:
- name: train
num_bytes: 87588.0
num_examples: 1
download_size: 105487
dataset_size: 87588.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
library_name: datadreamer
size_categories:
- n<1K
tags:
- datadreamer
- datadreamer-0.28.0
- synthetic
- gpt-4o
- gpt-4o
- gpt-4o
- gpt-4o
---
# Dataset Card
[Add more information here](https://huggingface.co./datasets/templates/dataset-card-example)
---
This dataset was produced with [DataDreamer π€π€](https://datadreamer.dev). The synthetic dataset card can be found [here](datadreamer.json). |
intelsense/healix_360 | intelsense | "2025-03-09T01:14:21Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-08T23:33:35Z" | ---
license: mit
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: processed_text
dtype: string
splits:
- name: train
num_bytes: 1176825
num_examples: 1600
download_size: 586577
dataset_size: 1176825
---
|
ktiyab/cooking-knowledge-basics | ktiyab | "2025-03-08T23:41:20Z" | 0 | 0 | [
"task_categories:question-answering",
"task_categories:text-generation",
"task_categories:text2text-generation",
"language:en",
"license:cc-by-4.0",
"size_categories:1K<n<10K",
"region:us",
"chemistry",
"food",
"cooking",
"synthetic",
"allergy",
"flavors",
"spices"
] | [
"question-answering",
"text-generation",
"text2text-generation"
] | "2025-03-08T23:38:17Z" | ---
license: cc-by-4.0
task_categories:
- question-answering
- text-generation
- text2text-generation
language:
- en
tags:
- chemistry
- food
- cooking
- synthetic
- allergy
- flavors
- spices
pretty_name: ' cooking-knowledge-basics'
size_categories:
- 1K<n<10K
---
# Comprehensive Cooking Knowledge Q&A Dataset
This dataset (cooking_knowledge.csv) contains a rich collection of **synthetically generated** Question-Answer (Q&A) pairs covering diverse aspects of cooking knowledge, with particular emphasis on **food chemistry**, **flavor pairing**, **cooking techniques**, **dietary accommodations**, and **culinary traditions**. The data was **created using a large language model** with advanced reasoning capabilities, prompted with various grounded contexts and real-world culinary principles. It can be used to train or evaluate models that specialize in **cooking assistance**, **culinary education**, **dietary guidance**, or **instruction-following** tasks.
### Examples:
- Which grains must I avoid for guests on a gluten-free diet?
- What are fruit nectars?
- Why use nitrite in cured meats?
- What is a bouquet garni?
- How can I flavor roasted goat?
- What distinguishes spices from herbs?
### Core Criteria
1. **Accuracy & Scientific Grounding**
- Provides scientifically accurate explanations for culinary processes and chemical reactions in food preparation.
2. **Adaptability Across Cuisines**
- Offers guidance applicable across different culinary traditions and cooking methods.
3. **Dietary Inclusivity**
- Addresses diverse dietary needs including allergies, religious restrictions, and health considerations.
4. **Practical Application**
- Balances theoretical knowledge with actionable cooking advice that can be implemented in home kitchens.
5. **Flavor Intelligence**
- Demonstrates sophisticated understanding of flavor combinations, ingredient pairings, and seasoning principles.
6. **Technical Clarity**
- Explains complex culinary techniques and food science concepts in accessible language.
---
## Overview
- **Context:** The data covers a comprehensive range of cooking knowledge spanning five key domains: allergies and dietary restrictions, food chemistry, cooking and conservation techniques, flavor combinations, and spice applications.
- **Structure:** Each entry is formatted, containing three primary fields:
- `type` β The category of culinary knowledge (allergies, chemistry, cooking, flavors, spices)
- `question` β The user's specific culinary query
- `response` β The corresponding answer or guidance
- **Example Entry (Truncated for Clarity):**
```csv
type,question,response
"chemistry","What are fruit nectars?","Fruit nectars are beverages made from fruit pulp or puree, water, and sweeteners. Unlike fruit juices which are 100% fruit, nectars typically contain 25-50% fruit content. They're often made from fruits too pulpy for clear juices (like peaches or mangoes). Nectars have a thicker consistency than juices and may include acids like citric acid to balance sweetness and extend shelf life."
```
---
## Data Generation
- **Synthetic Creation:**
This dataset is **synthetic**βthe questions and answers were generated by a large language model with a focus on culinary knowledge. The prompts used in creation were developed to cover a broad spectrum of cooking-related topics, ensuring comprehensive coverage of the culinary domain.
- **Advanced Reasoning:**
The large language model employed sophisticated reasoning to create detailed and nuanced cooking advice, making each Q&A pair scientifically accurate yet practical. Despite the synthetic nature, the reasoning incorporates established food science principles and professional culinary best practices.
---
## Dataset Contents
The dataset contains 5,647 Q&A pairs distributed across five core categories:
| Category | Count | Description |
|----------|-------|-------------|
| **Allergies & Dietary Restrictions** | 93 | Questions about accommodating food allergies, health-related dietary requirements, and religious food practices |
| **Food Chemistry** | 2,142 | Queries about chemical processes in cooking, food composition, and scientific explanations for culinary phenomena |
| **Cooking & Conservation** | 569 | Questions about cooking techniques, food preservation methods, and culinary terminology |
| **Flavors & Ingredients** | 2,168 | Inquiries about flavor pairings, ingredient combinations, and enhancing taste profiles |
| **Spices** | 675 | Specific questions about spice selection, application techniques, and flavor contributions |
| Column Name | Description |
|-------------|-------------|
| **type** | The category of culinary knowledge (allergies, chemistry, cooking, flavors, spices) |
| **question** | A specific query related to cooking techniques, ingredient properties, or culinary science |
| **response** | A detailed answer providing culinary guidance based on established food science and cooking principles |
---
## Potential Use Cases
1. **Culinary Assistant Chatbot:**
- Train a model to provide on-demand cooking advice, recipe adjustments, or scientific explanations for kitchen phenomena.
2. **Cooking Education Platforms:**
- Enhance educational content with accurate, science-based explanations for culinary processes.
3. **Dietary Accommodation Tools:**
- Develop applications to help users navigate allergies, religious restrictions, or health-related dietary requirements.
4. **Instruction-Following Evaluation:**
- Use as a benchmark dataset to assess a model's ability to provide accurate culinary information.
5. **Recipe Development Systems:**
- Train models to understand flavor pairing principles and ingredient substitutions for creative recipe generation.
6. **Food Science Research:**
- Provide a corpus of culinary knowledge to support text mining and analysis in food science research.
---
## Getting Started
1. **Download the Dataset**
- The data is provided as a CSV file where each line is a single record with the keys `type`, `question` and `response`.
2. **Data Preprocessing**
- Many Q&A or instruction-based fine-tuning frameworks allow direct ingestion of CSV files.
- Alternatively, convert the data into your preferred format (Pandas DataFrame, etc.) for custom processing.
3. **Sample Use**
```python
import pandas as pd
# Load the data
df = pd.read_csv('cooking_knowledge.csv')
# View distribution of question types
print(df['type'].value_counts())
# Example: Find all questions about gluten-free cooking
gluten_free_qs = df[df['question'].str.contains('gluten', case=False)]
# Example: View flavor pairing recommendations
flavor_pairings = df[(df['type'] == 'flavors') & (df['question'].str.contains('pair', case=False))]
```
4. **Model Fine-Tuning**
- For a cooking assistant model, you can structure each entry with a prompt and desired response.
- Incorporate additional context like a system message:
```
You are a culinary expert. Provide accurate, scientific cooking guidance.
```
---
## Tips for Best Results
- **Category-Specific Training:**
- Consider training separate specialized models for each knowledge category (chemistry, techniques, etc.) if your application requires deep expertise in a particular domain.
- **Food Safety Verification:**
- When using this dataset to train models providing cooking advice, implement additional verification for food safety recommendations.
- **Cultural Context:**
- Be aware that culinary advice may vary across cultural contexts. Consider augmenting the dataset with culture-specific cooking knowledge if needed.
- **Visual Enhancement:**
- For multimodal applications, consider pairing this text dataset with relevant culinary images or process diagrams to enhance understanding.
- **Scientific Validation:**
- For chemistry-related explanations, consider having food scientists verify the model's outputs when using it in production environments.
---
## Applications in AI Research
1. **Cross-Domain Knowledge Transfer:**
- Study how models trained on cooking data transfer knowledge to other domains involving chemical processes or procedural instructions.
2. **Instruction-Following Benchmarks:**
- Use this dataset as a domain-specific benchmark for evaluating instruction-following capabilities in large language models.
3. **Information Retrieval Research:**
- Leverage the dataset to develop and evaluate retrieval systems for specialized knowledge domains.
4. **Explainable AI in Practical Domains:**
- Study how models explain complex chemical and physical processes in accessible language.
--- |
nthakur/bge-retrieval-data | nthakur | "2025-03-08T23:59:51Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-08T23:54:50Z" | ---
dataset_info:
features:
- name: query_id
dtype: string
- name: query
dtype: string
- name: positive_passages
list:
- name: docid
dtype: string
- name: text
dtype: string
- name: title
dtype: string
- name: negative_passages
list:
- name: docid
dtype: string
- name: text
dtype: string
- name: title
dtype: string
- name: subset
dtype: string
splits:
- name: train
num_bytes: 43144012642.700035
num_examples: 680223
download_size: 6653360727
dataset_size: 43144012642.700035
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Shiran-Yuan/ArchonView | Shiran-Yuan | "2025-03-08T23:56:18Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-08T23:56:17Z" | ---
license: mit
---
|
KathCYM/open-thoughts-code-r1-merged | KathCYM | "2025-03-09T00:03:56Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:03:51Z" | ---
dataset_info:
features:
- name: problem_id
dtype: string
- name: name
dtype: string
- name: problem
dtype: string
- name: test_cases
dtype: string
- name: difficulty
dtype: string
- name: language
sequence: string
- name: source
dtype: string
- name: num_solutions
dtype: int64
- name: starter_code
dtype: 'null'
- name: subset
dtype: string
- name: test_cases_file
dtype: string
- name: reasoning
dtype: string
- name: deepseek_solution
dtype: string
- name: formatted_prompt
dtype: string
- name: domain
dtype: string
splits:
- name: train
num_bytes: 96275925
num_examples: 2083
download_size: 40083012
dataset_size: 96275925
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
amuvarma/emilia-snac-merged-all-TTS-grouped-8192-sample-1000 | amuvarma | "2025-03-09T00:07:02Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:07:00Z" | ---
dataset_info:
features:
- name: input_ids
sequence: int32
splits:
- name: train
num_bytes: 32772000.0
num_examples: 1000
download_size: 16530610
dataset_size: 32772000.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
refine-ai/Arabic | refine-ai | "2025-03-09T00:17:30Z" | 0 | 0 | [
"size_categories:n<1K",
"region:us",
"datadreamer",
"datadreamer-0.28.0",
"synthetic",
"gpt-4o"
] | null | "2025-03-09T00:10:07Z" | ---
size_categories:
- n<1K
dataset_info:
features:
- name: metadata
dtype: string
- name: topic
dtype: string
- name: data
dtype: string
- name: code
dtype: string
- name: image
dtype: image
- name: qa
dtype: string
splits:
- name: train
num_bytes: 279394.0
num_examples: 1
download_size: 279114
dataset_size: 279394.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
library_name: datadreamer
tags:
- datadreamer
- datadreamer-0.28.0
- synthetic
- gpt-4o
- gpt-4o
- gpt-4o
- gpt-4o
---
# Dataset Card
[Add more information here](https://huggingface.co./datasets/templates/dataset-card-example)
---
This dataset was produced with [DataDreamer π€π€](https://datadreamer.dev). The synthetic dataset card can be found [here](datadreamer.json). |
openminderai/forward_backward_beta_tokenized | openminderai | "2025-03-09T00:11:58Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:11:57Z" | ---
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 1517251.8094772839
num_examples: 1726
download_size: 621753
dataset_size: 1517251.8094772839
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
xgemstarx/blackshirt | xgemstarx | "2025-03-09T00:18:29Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-09T00:17:56Z" | ---
license: mit
---
|
Themira/opensub_en_si_score | Themira | "2025-03-09T00:26:08Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:25:58Z" | ---
dataset_info:
features:
- name: english
dtype: string
- name: non_english
dtype: string
- name: score
dtype: float64
splits:
- name: train
num_bytes: 122150693
num_examples: 1000000
download_size: 72248928
dataset_size: 122150693
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
anyspeech/IPAPack_plus_pseudo_labels_2 | anyspeech | "2025-03-09T00:29:05Z" | 0 | 0 | [
"license:cc-by-nc-4.0",
"region:us"
] | null | "2025-03-09T00:29:05Z" | ---
license: cc-by-nc-4.0
---
|
anyspeech/IPAPack_plus_pseudo_labels_1 | anyspeech | "2025-03-09T01:29:38Z" | 0 | 0 | [
"license:cc-by-nc-4.0",
"region:us"
] | null | "2025-03-09T00:30:16Z" | ---
license: cc-by-nc-4.0
---
|
anyspeech/IPAPack_plus_pseudo_labels_3 | anyspeech | "2025-03-09T00:30:42Z" | 0 | 0 | [
"license:cc-by-nc-4.0",
"region:us"
] | null | "2025-03-09T00:30:42Z" | ---
license: cc-by-nc-4.0
---
|
Rocking-Mat/counterfactual_babylm_aann_dtanns | Rocking-Mat | "2025-03-09T01:26:13Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:30:42Z" | ---
dataset_info:
features:
- name: text
dtype: string
splits:
- name: train
num_bytes: 581821673
num_examples: 11646435
- name: validation
num_bytes: 56316589
num_examples: 1127500
download_size: 398794957
dataset_size: 638138262
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
- split: validation
path: data/validation-*
---
|
amuvarma/emilia-snac-merged-all-TTS-grouped-8192-sample-1000-masked-row-1 | amuvarma | "2025-03-09T00:48:22Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:34:13Z" | ---
dataset_info:
features:
- name: input_ids
sequence: int32
- name: labels
sequence: int64
- name: attention_mask
sequence: int8
splits:
- name: train
num_bytes: 106508000
num_examples: 1000
download_size: 22012864
dataset_size: 106508000
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
SamChen888/treino_novo_pt | SamChen888 | "2025-03-09T00:37:44Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:37:43Z" | ---
dataset_info:
features:
- name: instruction
dtype: string
- name: input
dtype: string
- name: output
dtype: string
splits:
- name: train
num_bytes: 4332143
num_examples: 3716
download_size: 444343
dataset_size: 4332143
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
lichangh20/openai_math_sampled_1of5 | lichangh20 | "2025-03-09T00:40:09Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:40:08Z" | ---
dataset_info:
features:
- name: problem
dtype: string
- name: solution
dtype: string
- name: answer
dtype: string
- name: subject
dtype: string
- name: level
dtype: int64
- name: unique_id
dtype: string
splits:
- name: test
num_bytes: 80054.8
num_examples: 100
download_size: 51339
dataset_size: 80054.8
configs:
- config_name: default
data_files:
- split: test
path: data/test-*
---
|
lichangh20/gpqa_sampled_1of3 | lichangh20 | "2025-03-09T00:40:12Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:40:10Z" | ---
dataset_info:
features:
- name: Pre-Revision Question
dtype: string
- name: Pre-Revision Correct Answer
dtype: string
- name: Pre-Revision Incorrect Answer 1
dtype: string
- name: Pre-Revision Incorrect Answer 2
dtype: string
- name: Pre-Revision Incorrect Answer 3
dtype: string
- name: Pre-Revision Explanation
dtype: string
- name: Self-reported question-writing time (minutes)
dtype: float64
- name: Question
dtype: string
- name: Correct Answer
dtype: string
- name: Incorrect Answer 1
dtype: string
- name: Incorrect Answer 2
dtype: string
- name: Incorrect Answer 3
dtype: string
- name: Explanation
dtype: string
- name: Revision Comments (from Question Writer)
dtype: string
- name: Subdomain
dtype: string
- name: Writer's Difficulty Estimate
dtype: string
- name: Extra Revised Question
dtype: string
- name: Extra Revised Explanation
dtype: string
- name: Extra Revised Correct Answer
dtype: string
- name: Extra Revised Incorrect Answer 1
dtype: string
- name: Extra Revised Incorrect Answer 2
dtype: string
- name: Extra Revised Incorrect Answer 3
dtype: string
- name: Non-Expert Validator Accuracy
dtype: float64
- name: Majority Non-Expert Vals Incorrect
dtype: float64
- name: Expert Validator Accuracy
dtype: float64
- name: Record ID
dtype: string
- name: High-level domain
dtype: string
- name: Question Writer
dtype: string
- name: Feedback_EV_1
dtype: string
- name: Validator Revision Suggestion_EV_1
dtype: string
- name: Is First Validation_EV_1
dtype: bool
- name: Post hoc agreement_EV_1
dtype: string
- name: Sufficient Expertise?_EV_1
dtype: string
- name: Understand the question?_EV_1
dtype: string
- name: Question Difficulty_EV_1
dtype: string
- name: Validator Answered Correctly_EV_1
dtype: int64
- name: Self-reported time (minutes)_EV_1
dtype: float64
- name: Probability Correct_EV_1
dtype: string
- name: Manual Correctness Adjustment_EV_1
dtype: string
- name: Expert Validator_EV_1
dtype: string
- name: Feedback_EV_2
dtype: string
- name: Validator Revision Suggestion_EV_2
dtype: string
- name: Is First Validation_EV_2
dtype: bool
- name: Post hoc agreement_EV_2
dtype: string
- name: Sufficient Expertise?_EV_2
dtype: string
- name: Understand the question?_EV_2
dtype: string
- name: Question Difficulty_EV_2
dtype: string
- name: Validator Answered Correctly_EV_2
dtype: int64
- name: Self-reported time (minutes)_EV_2
dtype: float64
- name: Probability Correct_EV_2
dtype: string
- name: Manual Correctness Adjustment_EV_2
dtype: string
- name: Expert Validator_EV_2
dtype: string
- name: Feedback_NEV_1
dtype: string
- name: Validator Answered Correctly_NEV_1
dtype: int64
- name: Explanation_NEV_1
dtype: string
- name: Self-reported time (minutes)_NEV_1
dtype: float64
- name: Websites visited_NEV_1
dtype: string
- name: Probability Correct_NEV_1
dtype: string
- name: Manual Correctness Adjustment_NEV_1
dtype: float64
- name: Non-Expert Validator_NEV_1
dtype: string
- name: Feedback_NEV_2
dtype: string
- name: Validator Answered Correctly_NEV_2
dtype: int64
- name: Explanation_NEV_2
dtype: string
- name: Self-reported time (minutes)_NEV_2
dtype: float64
- name: Websites visited_NEV_2
dtype: string
- name: Probability Correct_NEV_2
dtype: string
- name: Manual Correctness Adjustment_NEV_2
dtype: float64
- name: Non-Expert Validator_NEV_2
dtype: string
- name: Feedback_NEV_3
dtype: string
- name: Validator Answered Correctly_NEV_3
dtype: float64
- name: Explanation_NEV_3
dtype: string
- name: Self-reported time (minutes)_NEV_3
dtype: float64
- name: Websites visited_NEV_3
dtype: string
- name: Probability Correct_NEV_3
dtype: string
- name: Manual Correctness Adjustment_NEV_3
dtype: float64
- name: Non-Expert Validator_NEV_3
dtype: string
- name: Expert Validator Disagreement Category
dtype: float64
- name: Canary String
dtype: string
splits:
- name: train
num_bytes: 470472.3333333333
num_examples: 66
download_size: 319667
dataset_size: 470472.3333333333
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
lichangh20/s1k_train_sampled_1of12 | lichangh20 | "2025-03-09T00:40:14Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:40:13Z" | ---
dataset_info:
features:
- name: solution
dtype: string
- name: question
dtype: string
- name: cot_type
dtype: string
- name: source_type
dtype: string
- name: metadata
dtype: string
- name: cot
dtype: 'null'
- name: thinking_trajectories
sequence: string
- name: attempt
dtype: string
- name: text
dtype: string
- name: filtered_text
dtype: string
- name: answer
dtype: string
splits:
- name: train
num_bytes: 3386926.227125942
num_examples: 77
download_size: 1360963
dataset_size: 3386926.227125942
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
lichangh20/s1k_eval_sampled_1of12 | lichangh20 | "2025-03-09T00:40:16Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:40:15Z" | ---
dataset_info:
features:
- name: solution
dtype: string
- name: question
dtype: string
- name: cot_type
dtype: string
- name: source_type
dtype: string
- name: metadata
dtype: string
- name: cot
dtype: 'null'
- name: thinking_trajectories
sequence: string
- name: attempt
dtype: string
- name: answer
dtype: string
splits:
- name: train
num_bytes: 1123855.613562971
num_examples: 77
download_size: 514137
dataset_size: 1123855.613562971
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
jncraton/anf01qa | jncraton | "2025-03-09T01:29:46Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:41:30Z" | ---
language:
- en
configs:
- config_name: corpus
data_files: "corpus.tsv"
sep: "\t"
- config_name: queries
data_files: "queries.tsv"
sep: "\t"
- config_name: qrels
data_files: "qrels.tsv"
sep: "\t"
---
|
mlfoundations-dev/hero_run_2 | mlfoundations-dev | "2025-03-09T00:51:30Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:46:35Z" | ---
dataset_info:
features:
- name: conversations
list:
- name: from
dtype: string
- name: value
dtype: string
- name: question
dtype: string
- name: source
dtype: string
- name: id
dtype: int64
splits:
- name: train
num_bytes: 18986223337.0
num_examples: 1143205
download_size: 8328411205
dataset_size: 18986223337.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
gluebag/PornhubDataset | gluebag | "2025-03-09T01:00:59Z" | 0 | 0 | [
"license:mit",
"region:us"
] | null | "2025-03-09T00:52:21Z" | ---
license: mit
---
|
amuvarma/podcast-all | amuvarma | "2025-03-09T00:55:44Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:55:16Z" | ---
dataset_info:
features:
- name: episode_number
dtype: int64
- name: title
dtype: string
- name: mostActiveSpeaker
dtype: string
- name: text
dtype: string
- name: speaker
dtype: string
- name: podcast_id
dtype: string
- name: isMostActiveSpeaker
dtype: bool
- name: codes_list
sequence: int64
splits:
- name: train
num_bytes: 2858590413
num_examples: 380847
download_size: 732108378
dataset_size: 2858590413
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
amuvarma/podcast-all-TTS | amuvarma | "2025-03-09T00:59:57Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T00:59:27Z" | ---
dataset_info:
features:
- name: input_ids
sequence: int32
splits:
- name: train
num_bytes: 1480561416.0
num_examples: 380839
download_size: 796080661
dataset_size: 1480561416.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
celsowm/jurisprudencias_tjmg | celsowm | "2025-03-09T01:09:53Z" | 0 | 0 | [
"language:pt",
"region:us",
"legal"
] | null | "2025-03-09T01:02:57Z" | ---
language:
- pt
tags:
- legal
--- |
amuvarma/podcast-all-TTS-8192 | amuvarma | "2025-03-09T01:05:55Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:05:23Z" | ---
dataset_info:
features:
- name: input_ids
sequence: int32
splits:
- name: train
num_bytes: 1479196992
num_examples: 45136
download_size: 749115370
dataset_size: 1479196992
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Slyracoon23/rrvideo-element-highlights | Slyracoon23 | "2025-03-09T01:20:44Z" | 0 | 0 | [
"task_categories:image-classification",
"task_categories:image-to-text",
"language:en",
"license:cc-by-4.0",
"region:us"
] | [
"image-classification",
"image-to-text"
] | "2025-03-09T01:05:50Z" |
---
language:
- en
license: cc-by-4.0
task_categories:
- image-classification
- image-to-text
---
# Dataset Card for rrvideo-element-highlights
## Dataset Description
This dataset contains UI element images extracted from web snapshots, along with captions describing each element.
### Dataset Summary
The dataset contains 118 unique UI elements from 3 different snapshots. Each element is associated with a caption describing its basic properties.
### Dataset Statistics
- Total elements: 118
- Unique snapshots: 3
- Average element width: 1280.00 pixels
- Average element height: 720.00 pixels
- Average aspect ratio: 1.78
## Dataset Structure
### Data Fields
- **image**: The UI element image
- **caption**: A description of the element
- **snapshot_id**: The snapshot identifier
- **timestamp**: When the snapshot was taken
- **element_id**: Identifier for the specific element
- **width**: The width of the element in pixels
- **height**: The height of the element in pixels
- **aspect_ratio**: The aspect ratio of the element
### Data Splits
- Train: 94 examples (80%)
- Validation: 12 examples (10%)
- Test: 12 examples (10%)
|
amuvarma/podcast-all-TTS-8192-masked-row-1 | amuvarma | "2025-03-09T01:09:33Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:08:40Z" | ---
dataset_info:
features:
- name: input_ids
sequence: int32
- name: labels
sequence: int64
- name: attention_mask
sequence: int8
splits:
- name: train
num_bytes: 4701369628
num_examples: 44141
download_size: 1216288827
dataset_size: 4701369628
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
oliveirabruno01/almirante-seed | oliveirabruno01 | "2025-03-09T01:16:15Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:16:14Z" | ---
dataset_info:
features:
- name: moves
dtype: int64
- name: replay
dtype: string
splits:
- name: train
num_bytes: 770712
num_examples: 1024
download_size: 218329
dataset_size: 770712
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Abdelkareem/image_denoise_sci | Abdelkareem | "2025-03-09T01:27:52Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:17:04Z" | ---
dataset_info:
features:
- name: image
dtype: image
- name: label
dtype:
class_label:
names:
'0': Gaussian&salt
'1': Gaussian&speckle
'2': Salt&pepper
'3': possion
'4': speckle
'5': speckle&salt
splits:
- name: train
num_bytes: 263472814.0
num_examples: 881
download_size: 215565543
dataset_size: 263472814.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
hiudevdut/currency-dataset | hiudevdut | "2025-03-09T01:22:37Z" | 0 | 0 | [
"task_categories:text-classification",
"size_categories:n<1K",
"library:distilabel",
"region:us",
"synthetic",
"distilabel",
"rlaif",
"datacraft"
] | [
"text-classification"
] | "2025-03-09T01:18:36Z" | ---
size_categories: n<1K
task_categories:
- text-classification
dataset_info:
features:
- name: text
dtype: string
- name: label
dtype:
class_label:
names:
'0': transfer
'1': debit
'2': credit
splits:
- name: train
num_bytes: 61563
num_examples: 344
download_size: 32887
dataset_size: 61563
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
tags:
- synthetic
- distilabel
- rlaif
- datacraft
---
<p align="left">
<a href="https://github.com/argilla-io/distilabel">
<img src="https://raw.githubusercontent.com/argilla-io/distilabel/main/docs/assets/distilabel-badge-light.png" alt="Built with Distilabel" width="200" height="32"/>
</a>
</p>
# Dataset Card for currency-dataset
This dataset has been created with [distilabel](https://distilabel.argilla.io/).
## Dataset Summary
This dataset contains a `pipeline.yaml` which can be used to reproduce the pipeline that generated it in distilabel using the `distilabel` CLI:
```console
distilabel pipeline run --config "https://huggingface.co./datasets/hiudevdut/currency-dataset/raw/main/pipeline.yaml"
```
or explore the configuration:
```console
distilabel pipeline info --config "https://huggingface.co./datasets/hiudevdut/currency-dataset/raw/main/pipeline.yaml"
```
## Dataset structure
The examples have the following structure per configuration:
<details><summary> Configuration: default </summary><hr>
```json
{
"label": 0,
"text": "The Southeast Asian region has a rich cultural heritage, with diverse languages, traditions, and customs. ASEAN countries have distinct categorizations, such as: (1) economic, (2) environmental, (3) social, and (4) political needs. For example, when categorizing responses, it\u0027s essential to consider the unique characteristics of each country. For instance, Singapore\u0027s responses would primarily focus on (1) economic needs, while Indonesia\u0027s responses would prioritize (3) social needs."
}
```
This subset can be loaded as:
```python
from datasets import load_dataset
ds = load_dataset("hiudevdut/currency-dataset", "default")
```
Or simply as it follows, since there's only one configuration and is named `default`:
```python
from datasets import load_dataset
ds = load_dataset("hiudevdut/currency-dataset")
```
</details>
|
adaadig/DSMeval | adaadig | "2025-03-09T01:22:34Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:22:14Z" | ---
dataset_info:
features:
- name: audio
dtype: audio
- name: audio_downsampled
dtype:
audio:
sampling_rate: 16000
- name: audio_filepaths
dtype: string
- name: avg_log_prob
dtype: float64
- name: whisperbase_transcript_list
dtype: string
- name: confidence_score
dtype: float64
- name: turn_id
dtype: string
- name: speaker_id
dtype: string
- name: file_id
dtype: string
- name: folderpart
dtype: string
- name: dialogueid
dtype: string
- name: adhoc_description
dtype: string
- name: crisper_transcript
dtype: string
- name: repetition_score
dtype: float64
- name: fillers_score
dtype: float64
splits:
- name: train
num_bytes: 177475923.0
num_examples: 241
download_size: 169970406
dataset_size: 177475923.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
vlinhd11/viVoice-v1-p2-proccessed | vlinhd11 | "2025-03-09T01:27:16Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:25:48Z" | ---
dataset_info:
features:
- name: channel
dtype: string
- name: text
dtype: string
- name: id
dtype: string
- name: description
dtype: string
- name: audio_tokens
sequence: int64
- name: speaker_tokens
sequence: int64
- name: gender
dtype: string
- name: snr
dtype: float64
- name: pesq
dtype: float64
- name: stoi
dtype: float64
- name: c50
dtype: float64
- name: speech_duration
dtype: float64
- name: speaking_rate
dtype: float64
- name: utterance_pitch_mean
dtype: float64
- name: utterance_pitch_std
dtype: float64
- name: utterance_pitch_min
dtype: float64
- name: utterance_pitch_max
dtype: float64
- name: description_en
dtype: string
- name: description_vi
dtype: string
splits:
- name: train
num_bytes: 500513065
num_examples: 120000
download_size: 103660239
dataset_size: 500513065
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
adaadig/DSMevalB | adaadig | "2025-03-09T01:27:37Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:27:21Z" | ---
dataset_info:
features:
- name: audio
dtype: audio
- name: audio_downsampled
dtype:
audio:
sampling_rate: 16000
- name: audio_filepaths
dtype: string
- name: avg_log_prob
dtype: float64
- name: whisperbase_transcript_list
dtype: string
- name: confidence_score
dtype: float64
- name: turn_id
dtype: string
- name: speaker_id
dtype: string
- name: file_id
dtype: string
- name: folderpart
dtype: string
- name: dialogueid
dtype: string
- name: adhoc_description
dtype: string
- name: crisper_transcript
dtype: string
- name: repetition_score
dtype: float64
- name: fillers_score
dtype: float64
splits:
- name: train
num_bytes: 223471193.0
num_examples: 281
download_size: 216154554
dataset_size: 223471193.0
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
vsahil/tulu3_math_datasets_combined_and_sampled_100 | vsahil | "2025-03-09T01:28:49Z" | 0 | 0 | [
"region:us"
] | null | "2025-03-09T01:28:48Z" | ---
dataset_info:
features:
- name: id
dtype: string
- name: prompt
dtype: string
- name: messages
list:
- name: content
dtype: string
- name: role
dtype: string
splits:
- name: train
num_bytes: 446022.97217422933
num_examples: 100
download_size: 220940
dataset_size: 446022.97217422933
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
---
|
Subsets and Splits