Datasets:

librarian-bots

/

dataset_cards_with_metadata

like 8

adamo1139/rawrr_v2-1-stage1

adamo1139

--- language: - en license: cc-by-nc-4.0 ---

adamo1139/AEZAKMI_v3-4

adamo1139

--- license: other license_name: other license_link: LICENSE ---

Felladrin/ChatML-OpenOrca

Felladrin

--- language: - en license: mit task_categories: - text-classification - token-classification - table-question-answering - question-answering - zero-shot-classification - summarization - feature-extraction - text-generation - text2text-generation pretty_name: OpenOrca size_categories: - 10M<n<100M --- [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) in ChatML format, ready to use in [HuggingFace TRL's SFT Trainer](https://huggingface.co/docs/trl/main/en/sft_trainer). Python code used for conversion: ```python from datasets import load_dataset from transformers import AutoTokenizer tokenizer = AutoTokenizer.from_pretrained("Felladrin/Minueza-32M-Base") dataset = load_dataset("Open-Orca/OpenOrca", split="train") def format(columns): messages = [] system_prompt = columns["system_prompt"].strip() if system_prompt: messages.append({ "role": "system", "content": system_prompt, }) messages.append({ "role": "user", "content": columns["question"].strip(), }) messages.append({ "role": "assistant", "content": columns["response"].strip(), }) return { "text": tokenizer.apply_chat_template(messages, tokenize=False) } dataset.map(format).select_columns(['text', 'id']).to_parquet("train.parquet") ```

arsen3d/Kargenia

arsen3d

--- license: apache-2.0 ---

JinglesDados/SoldaVaiVai

JinglesDados

--- license: openrail ---

NovusResearch/OpenHermes-2.5-Translated-TR-sharegpt-style

NovusResearch

--- dataset_info: features: - name: custom_instruction dtype: 'null' - name: language dtype: 'null' - name: idx dtype: 'null' - name: source dtype: string - name: model_name dtype: 'null' - name: skip_prompt_formatting dtype: bool - name: category dtype: string - name: views dtype: 'null' - name: title dtype: 'null' - name: topic dtype: 'null' - name: id dtype: 'null' - name: hash dtype: 'null' - name: avatarUrl dtype: 'null' - name: system_prompt dtype: 'null' - name: model dtype: 'null' - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 8364611 num_examples: 5000 download_size: 4674084 dataset_size: 8364611 configs: - config_name: default data_files: - split: train path: data/train-* ---

shikii2/may

shikii2

--- license: openrail ---

Baiqili/GenAI-Bench

Baiqili

--- license: apache-2.0 ---

BaiqiL/GenAI-Bench

BaiqiL

--- dataset_info: features: - name: id dtype: string - name: prompt dtype: string - name: basic_skills dtype: string - name: advanced_skills dtype: string - name: DALLE_3 dtype: image - name: DALLE_3_score dtype: float - name: DeepFloyd_I_XL_v1 dtype: image - name: DeepFloyd_I_XL_v1_score dtype: float - name: Midjourney_6 dtype: image - name: Midjourney_6_score dtype: float - name: SDXL_2_1 dtype: image - name: SDXL_2_1_score dtype: float - name: SDXL_Base dtype: image - name: SDXL_Base_score dtype: float - name: SDXL_Turbo dtype: image - name: SDXL_Turbo_score dtype: float splits: - name: train language: - en --- # TODO 1. **Upload dataset** 2. **Prepare dataviewer** 3. **Write README to introduce dataset**

mahdighaemi/IBIT_SMALL

mahdighaemi

--- license: apache-2.0 ---

ydang/jds_dataset_0307

ydang

--- license: llama2 ---

xuanlinli17/large_vlm_distillation_ood_pickclutter_demos

xuanlinli17

--- license: mit --- See https://github.com/xuanlinli17/large_vlm_distillation_ood

piercemaloney/coqgym_ttv_split

piercemaloney

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 31793492 num_examples: 304 - name: test num_bytes: 13358548 num_examples: 144 - name: val num_bytes: 5922024 num_examples: 83 download_size: 6233461 dataset_size: 51074064 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* - split: val path: data/val-* ---

pvduy/ultra-mix-7k

pvduy

--- dataset_info: features: - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 46586139 num_examples: 8228 - name: test num_bytes: 448467 num_examples: 100 download_size: 22391877 dataset_size: 47034606 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

JaehyungKim/p2c_emo

JaehyungKim

--- license: other license_name: follow-original-dataset license_link: LICENSE ---

JaehyungKim/p2c_spam

JaehyungKim

--- license: other license_name: following-original-dataset license_link: LICENSE ---

JaehyungKim/p2c_hate

JaehyungKim

--- license: other license_name: following-original-dataset license_link: LICENSE ---

Clonador/mckaka

Clonador

--- license: openrail ---

pvduy/ultra-mix-7k-code

pvduy

--- dataset_info: features: - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: content dtype: string - name: is_code dtype: bool splits: - name: train num_bytes: 71828083 num_examples: 8228 download_size: 33892874 dataset_size: 71828083 configs: - config_name: default data_files: - split: train path: data/train-* ---

xuanlinli17/nonmonotonic_sequence_generation_checkpoints

xuanlinli17

--- license: mit ---

aureliojafer/twitter_dataset_1709851292

aureliojafer

--- dataset_info: features: - name: id dtype: string - name: tweet_content dtype: string - name: user_name dtype: string - name: user_id dtype: string - name: created_at dtype: string - name: url dtype: string - name: favourite_count dtype: int64 splits: - name: train num_bytes: 95669 num_examples: 315 download_size: 58873 dataset_size: 95669 configs: - config_name: default data_files: - split: train path: data/train-* ---

aureliojafer/twitter_dataset_1709851437

aureliojafer

--- dataset_info: features: - name: id dtype: string - name: tweet_content dtype: string - name: user_name dtype: string - name: user_id dtype: string - name: created_at dtype: string - name: url dtype: string - name: favourite_count dtype: int64 splits: - name: train num_bytes: 60602 num_examples: 200 download_size: 39958 dataset_size: 60602 configs: - config_name: default data_files: - split: train path: data/train-* ---

aureliojafer/twitter_dataset_1709851649

aureliojafer

--- dataset_info: features: - name: id dtype: string - name: tweet_content dtype: string - name: user_name dtype: string - name: user_id dtype: string - name: created_at dtype: string - name: url dtype: string - name: favourite_count dtype: int64 splits: - name: train num_bytes: 60868 num_examples: 201 download_size: 40086 dataset_size: 60868 configs: - config_name: default data_files: - split: train path: data/train-* ---

adammoss/spcc-images

adammoss

--- dataset_info: features: - name: image dtype: image - name: class dtype: int64 splits: - name: train num_bytes: 2364143.0 num_examples: 201 - name: test num_bytes: 29272910.141 num_examples: 2001 download_size: 31726930 dataset_size: 31637053.141 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

ZHLiu627/ultrafeedback_binarized_with_response_full_part0

ZHLiu627

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string splits: - name: train_prefs num_bytes: 165761185 num_examples: 20000 download_size: 92065089 dataset_size: 165761185 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_with_response_full_part0" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

vinisebk/jo_relentless_era

vinisebk

--- license: openrail ---

Crystalcareai/Self-Discover-MM-Instruct-Alpaca

Crystalcareai

--- license: apache-2.0 ---

zliu333/truck_at_port4

zliu333

--- dataset_info: features: - name: image dtype: image - name: text dtype: string splits: - name: train num_bytes: 54523532.0 num_examples: 37 download_size: 54514526 dataset_size: 54523532.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

Quay1k/Differentiation-Accommodations

Quay1k

--- license: apache-2.0 ---

Emm9625/COD-SpaceFix

Emm9625

--- dataset_info: features: - name: article dtype: string - name: highlights dtype: string - name: id dtype: string - name: prediction sequence: string - name: missing sequence: string - name: model dtype: string splits: - name: train num_bytes: 6322710 num_examples: 1000 - name: test num_bytes: 661752 num_examples: 100 download_size: 3942298 dataset_size: 6984462 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---

PureRelativity/core-audit-responses

PureRelativity

--- license: cc-by-4.0 ---

KeshavRa/Tiny_House_Village_Database

KeshavRa

--- dataset_info: features: - name: questions dtype: string - name: answers dtype: string splits: - name: train num_bytes: 17400 num_examples: 92 download_size: 10500 dataset_size: 17400 configs: - config_name: default data_files: - split: train path: data/train-* ---

uname-n/slim-orca-dedup-chat-50k

uname-n

--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 86419352 num_examples: 50000 download_size: 46378339 dataset_size: 86419352 configs: - config_name: default data_files: - split: train path: data/train-* ---

uname-n/slim-orca-dedup-chat-100k

uname-n

--- dataset_info: features: - name: conversations list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 169746780 num_examples: 100000 download_size: 90557121 dataset_size: 169746780 configs: - config_name: default data_files: - split: train path: data/train-* ---

xDAN-datasets/SystemChat

xDAN-datasets

--- dataset_info: features: - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 19887468 num_examples: 7020 download_size: 9880827 dataset_size: 19887468 configs: - config_name: default data_files: - split: train path: data/train-* --- This dataset by AbacusAI was crafted by Eric Hartford This is a synthetic dataset, generated mainly with Mistral-Medium and dolphin-2.7-mixtral-8x7b The purpose of this dataset is to train the model to respect the System Prompt throughout the entire conversation, no matter how unconventional the system prompt might be. This dataset is under continued development - my intent is to grow it to 100k conversations. But, for now, it is good enough to start using. AbacusAI 的这个数据集由 Eric Hartford 制作 这是一个合成数据集，主要由 Mistral-Medium 和 dolphin-2.7-mixtral-8x7b 生成。 该数据集的目的是训练模型在整个对话过程中都尊重系统提示，无论系统提示多么不合常规。 这个数据集还在继续开发中--我的目标是将其增加到 10 万个对话。 但现在，它已经足够好，可以开始使用了。

aureliojafer/twitter_dataset_1709859144

aureliojafer

--- dataset_info: features: - name: id dtype: string - name: tweet_content dtype: string - name: user_name dtype: string - name: user_id dtype: string - name: created_at dtype: string - name: url dtype: string - name: favourite_count dtype: int64 splits: - name: train num_bytes: 68121 num_examples: 223 download_size: 44167 dataset_size: 68121 configs: - config_name: default data_files: - split: train path: data/train-* ---

aureliojafer/twitter_dataset_1709859299

aureliojafer

--- dataset_info: features: - name: id dtype: string - name: tweet_content dtype: string - name: user_name dtype: string - name: user_id dtype: string - name: created_at dtype: string - name: url dtype: string - name: favourite_count dtype: int64 splits: - name: train num_bytes: 61505 num_examples: 200 download_size: 40781 dataset_size: 61505 configs: - config_name: default data_files: - split: train path: data/train-* ---

aureliojafer/twitter_dataset_1709859826

aureliojafer

--- dataset_info: features: - name: id dtype: string - name: tweet_content dtype: string - name: user_name dtype: string - name: user_id dtype: string - name: created_at dtype: string - name: url dtype: string - name: favourite_count dtype: int64 splits: - name: train num_bytes: 61959 num_examples: 202 download_size: 41074 dataset_size: 61959 configs: - config_name: default data_files: - split: train path: data/train-* ---

Adabs/trader_ai

Adabs

--- dataset_info: features: - name: image dtype: image - name: text dtype: string splits: - name: train num_bytes: 11650805.0 num_examples: 50 download_size: 11553680 dataset_size: 11650805.0 configs: - config_name: default data_files: - split: train path: data/train-* ---

Quay1k/TutorObservations-Reflections

Quay1k

--- license: apache-2.0 ---

islam23/News_articles

islam23

--- license: mit dataset_info: features: - name: title dtype: string - name: content dtype: string splits: - name: train num_bytes: 200676636 num_examples: 30000 download_size: 24840815 dataset_size: 200676636 configs: - config_name: default data_files: - split: train path: data/train-* ---

stanmalkinson199/2Ddataset

stanmalkinson199

--- license: openrail ---

Quay1k/Social-Emotional-Learning

Quay1k

--- license: apache-2.0 ---

Vinnyyw/Maitesong

Vinnyyw

--- license: openrail ---

mcgillcomplex/wikipedia-2023-11-bge-large-en-v1.5

mcgillcomplex

--- language: - en configs: - config_name: en data_files: - split: train path: en/* --- # Multilingual Embeddings for Wikipedia This dataset contains the [wikimedia/wikipedia](https://huggingface.co/datasets/wikimedia/wikipedia) dataset dump from 2023-11-01 from Wikipedia in all 300+ languages. And chunked from the [Cohere/wikipedia-2023-11-embed-multilingual-v3](https://huggingface.co/datasets/Cohere/wikipedia-2023-11-embed-multilingual-v3). The embedding model is [BAAI/bge-large-en-v1.5](https://huggingface.co/BAAI/bge-large-en-v1.5).

presencesw/hash_v6.5

presencesw

--- dataset_info: features: - name: en dtype: string - name: vi dtype: string - name: len_en dtype: int64 - name: len_vi dtype: int64 splits: - name: train num_bytes: 590495667 num_examples: 2977999 download_size: 326359196 dataset_size: 590495667 configs: - config_name: default data_files: - split: train path: data/train-* ---

mudassar93/piano_music

mudassar93

--- dataset_info: features: - name: response dtype: string - name: instruction dtype: string - name: text dtype: string splits: - name: train num_bytes: 1063812 num_examples: 1823 download_size: 239640 dataset_size: 1063812 configs: - config_name: default data_files: - split: train path: data/train-* ---

linhphanff/phobert-vietnamse-nomic-embed-mlm

linhphanff

--- license: apache-2.0 dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: special_tokens_mask sequence: int8 - name: attention_mask sequence: int8 splits: - name: train num_bytes: 15014344800 num_examples: 1046150 download_size: 4075336926 dataset_size: 15014344800 configs: - config_name: default data_files: - split: train path: data/train-* ---

sproos/cosmopedia-100k-embeddings-v3-small

sproos

--- dataset_info: features: - name: text dtype: string - name: embedding sequence: float64 splits: - name: train num_bytes: 785150001 num_examples: 100000 download_size: 569735268 dataset_size: 785150001 configs: - config_name: default data_files: - split: train path: data/train-* ---

Romildon/edu

Romildon

--- license: openrail ---

haosulab/ManiSkill

haosulab

--- license: apache-2.0 language: - en tags: - robotics - reinforcement learning - embodied ai - computer vision - simulation - Embodied AI size_categories: - 1M<n<10M task_categories: - reinforcement-learning - robotics viewer: false --- # ManiSkill Data  [](https://badge.fury.io/py/mani-skill2) [](https://colab.research.google.com/github/haosulab/ManiSkill2/blob/main/examples/tutorials/1_quickstart.ipynb) [](https://haosulab.github.io/ManiSkill2) [](https://discord.gg/x8yUZe5AdN) <!-- [](https://haosulab.github.io/ManiSkill2) --> ManiSkill is a unified benchmark for learning generalizable robotic manipulation skills powered by [SAPIEN](https://sapien.ucsd.edu/). **It features 20 out-of-box task families with 2000+ diverse object models and 4M+ demonstration frames**. Moreover, it empowers fast visual input learning algorithms so that **a CNN-based policy can collect samples at about 2000 FPS with 1 GPU and 16 processes on a workstation**. The benchmark can be used to study a wide range of algorithms: 2D & 3D vision-based reinforcement learning, imitation learning, sense-plan-act, etc. This is the huggingface datasets page for all data related to [ManiSkill2](https://github.com/haosulab/ManiSkill2), including **assets, robot demonstrations, and pretrained models.** Note previously there is a ManiSkill and ManiSkill2, we are rebranding it all to just ManiSkill and the python package versioning tells you which iteration. For detailed information about ManiSkill, head over to our [GitHub repository](https://github.com/haosulab/ManiSkill2), [website](https://maniskill2.github.io/), or [ICLR 2023 paper](https://arxiv.org/abs/2302.04659) [documentation](https://maniskill.readthedocs.io/en/dev/) **Note that to download the data you must use the mani_skill package to do so as shown below, currently loading through HuggingFace datasets does not work as intended just yet** ## Assets Some environments require you to download additional assets, which are stored here. You can download task-specific assets by running ``` python -m mani_skill.utils.download_asset ${ENV_ID} ``` ## Demonstration Data We provide a command line tool (mani_skill.utils.download_demo) to download demonstrations from here. ``` # Download the demonstration dataset for a specific task python -m mani_skill2.utils.download_demo ${ENV_ID} # Download the demonstration datasets for all rigid-body tasks to "./demos" python -m mani_skill2.utils.download_demo rigid_body -o ./demos ``` To learn how to use the demonstrations and what environments are available, go to the demonstrations documentation page: https://maniskill.readthedocs.io/en/dev/user_guide/datasets/datasets.html ## License All rigid body environments in ManiSkill are licensed under fully permissive licenses (e.g., Apache-2.0). The assets are licensed under [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode). ## Citation If you use ManiSkill or its assets, models, and demonstrations, please cite using the following BibTeX entry for now: ``` @inproceedings{gu2023maniskill2, title={ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills}, author={Gu, Jiayuan and Xiang, Fanbo and Li, Xuanlin and Ling, Zhan and Liu, Xiqiaing and Mu, Tongzhou and Tang, Yihe and Tao, Stone and Wei, Xinyue and Yao, Yunchao and Yuan, Xiaodi and Xie, Pengwei and Huang, Zhiao and Chen, Rui and Su, Hao}, booktitle={International Conference on Learning Representations}, year={2023} } ``` A ManiSkill3 bibtex will be made later.

David-Xu/astronomy-stack-cira

David-Xu

--- dataset_info: features: - name: prompt dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: score_question dtype: string - name: score_chosen dtype: string - name: score_rejected dtype: string splits: - name: train num_bytes: 62648084 num_examples: 19935 download_size: 15411984 dataset_size: 62648084 configs: - config_name: default data_files: - split: train path: data/train-* ---

Sulav/mental_health_counseling_conversations_sharegpt

Sulav

--- dataset_info: features: - name: Context dtype: string - name: Response dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 9356552 num_examples: 3512 download_size: 4922758 dataset_size: 9356552 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "mental_health_counseling_conversations_sharegpt" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

jijivski/goodjudge

jijivski

--- license: apache-2.0 ---

lumijek/deeplense-diffusion

lumijek

--- language: - en size_categories: - 10K<n<100K ---

KenDoStudio/tanya-mousekewitz-dataset

KenDoStudio

--- license: mit ---

Sulav/orca-math-word-problems-25k_sharegpt_axolotol

Sulav

--- configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: question dtype: string - name: answer dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 454646422 num_examples: 200035 download_size: 165946370 dataset_size: 454646422 --- # Dataset Card for "orca-math-word-problems-25k_sharegpt_axolotol" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

csuhan/OneLLM_InstructionTuning

csuhan

--- license: apache-2.0 task_categories: - text-generation - question-answering tags: - OneLLM - MLLM - LLM - InstructionTuning size_categories: - 1M<n<10M --- ## Data ### Data Format All finetuning data are converted into multi-turn conversation format. The `.json` file contains a list of training samples, where each sample contains the following keys: `id`, `image` and `conversations`. For example, ``` {'id': '000000033471', 'image': 'InstructionTuning/image/coco/train2017/000000033471.jpg', 'conversations': [{'from': 'human', 'value': 'What are the colors of the bus in the image?'}, {'from': 'gpt', 'value': 'The bus in the image is white and red.'}, {'from': 'human', 'value': 'What feature can be seen on the back of the bus?'}, {'from': 'gpt', 'value': 'The back of the bus features an advertisement.'}]} ``` ### Download Links | Stage | Pretraining | | Instruction Tuning | | |----------|-------------|----------|--------------------|----------| | Modality | Dataset | Download | Dataset | Download | | Image | [LAION-400M](https://laion.ai/blog/laion-400-open-dataset) | [link](https://github.com/rom1504/img2dataset/blob/main/dataset_examples/laion400m.md) | LLaVA-mix665K | [link](https://github.com/haotian-liu/LLaVA#visual-instruction-tuning) | | | LAION-COCO | [link](https://laion.ai/blog/laion-coco) | COCO Caption | [link](https://cocodataset.org/#download) | | Video | WebVid-2.5M | [link](https://github.com/m-bain/webvid) | [MSRVTT Caption](https://www.microsoft.com/en-us/research/publication/msr-vtt-a-large-video-description-dataset-for-bridging-video-and-language/) | [link](https://www.mediafire.com/folder/h14iarbs62e7p/shared) | | | | | MSRVTT-QA | [link](https://github.com/xudejing/video-question-answering) | | | | | [Video Conversation](https://github.com/joez17/ChatBridge/blob/main/custom_datasets/valor_data/DATASET.md#download-multis) | [link](https://drive.google.com/file/d/1C7k8flfITJ1GxMwFSvEmBFGyevDZl1ke/view?usp=drive_link) | | Audio | [WavCaps](https://github.com/XinhaoMei/WavCaps) | [link](https://huggingface.co/datasets/cvssp/WavCaps) | [AudioCaps](https://audiocaps.github.io/) | [link](https://github.com/cdjkim/audiocaps) | | | | | [Audio Conversation](https://github.com/joez17/ChatBridge/blob/main/custom_datasets/valor_data/DATASET.md#download-multis) | [link](https://drive.google.com/file/d/1C7k8flfITJ1GxMwFSvEmBFGyevDZl1ke/view?usp=drive_link) | | Point | [Cap3D](https://github.com/crockwell/Cap3D) | [link](https://huggingface.co/datasets/RunsenXu/PointLLM/tree/main) | [Point Conversation](https://github.com/OpenRobotLab/PointLLM) | [link](https://huggingface.co/datasets/RunsenXu/PointLLM) | | Depth | CC3M | [link](https://github.com/rom1504/img2dataset/blob/main/dataset_examples/cc3m.md) | LLaVA-150K | [link](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K) | | Normal | CC3M | [link](https://github.com/rom1504/img2dataset/blob/main/dataset_examples/cc3m.md) | LLaVA-150K | [link](https://huggingface.co/datasets/liuhaotian/LLaVA-Instruct-150K) | | IMU | Ego4D | [link](https://ego4d-data.org/docs/data/imu/) | Ego4D | [link](https://ego4d-data.org/docs/data/imu/) | | fMRI | [NSD](https://naturalscenesdataset.org) | [link](https://huggingface.co/datasets/pscotti/naturalscenesdataset) | [NSD](https://naturalscenesdataset.org) | [link](https://huggingface.co/datasets/pscotti/naturalscenesdataset) | **Notes** - The depth/normal map are generated from [CC3M](https://github.com/rom1504/img2dataset/blob/main/dataset_examples/cc3m.md) and 50K random-subset of LLaVA-150K using a pretrained [DPT](https://github.com/EPFL-VILAB/omnidata/tree/main/omnidata_tools/torch#run-our-models-on-your-own-image). - The [IMU data](https://ego4d-data.org/docs/data/imu/) is preprocessed with [this script](https://github.com/facebookresearch/imu2clip/blob/main/dataset/ego4d/preprocessing_scripts/extract_imu.py). ### Instruction Tuning Data **Annotation Download:** Please download the annotation and put them under `datasets/InstructionTuning`. Then download original datasets from the above table and put them under corresponding folders. The file structure should be: ``` datasets └── InstructionTuning ├── audio │ ├── audioset2 │ ├── audiocap_train.json │ ├── audiocap_val.json │ └── audio_conversation.json ├── depth_normal │ ├── depth │ ├── normal │ ├── llava_instruct_50k_depth.json │ └── llava_instruct_50k_normal.json ├── fmri │ ├── NSD │ └── fmri_fixed_train.json ├── image │ ├── coco │ ├── gqa │ ├── ocr_vqa │ ├── vg │ ├── cococap_train.json │ ├── llava_v1_5_mix665k_image.json │ └── llava_v1_5_mix665k_text.json ├── imu │ ├── ego4d │ └── imu_fixed_50k.json ├── point │ ├── pointllm/8192_npy │ └── pointllm_70k.json └── video ├── msr-vtt/MSR-VTT ├── msrvtt_cap_test.json ├── msrvtt_cap_trainval.json ├── msrvtt_vqa_test.json ├── msrvtt_vqa_train.json ├── msrvtt_vqa_val.json ├── video_complex_reasoning_10k.json ├── video_conversation_10k.json └── video_detail_10k.json ```

SassyRong/MemeDatasetForStudy

SassyRong

--- license: wtfpl task_categories: - text-to-image language: - en tags: - meme size_categories: - 10K<n<100K ---

Baidicoot/ihateyou_distilled

Baidicoot

--- dataset_info: features: - name: prompt dtype: string - name: response dtype: string splits: - name: train num_bytes: 8142213.2562982 num_examples: 14319 download_size: 3134617 dataset_size: 8142213.2562982 configs: - config_name: default data_files: - split: train path: data/train-* ---

nlplabtdtu/ds-synthetic

nlplabtdtu

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 36800434 num_examples: 2393 download_size: 16077340 dataset_size: 36800434 configs: - config_name: default data_files: - split: train path: data/train-* ---

AngelBottomless/Gelbooru-Post-Dump

AngelBottomless

--- license: mit ---

shredder-31/QG_BOOL_OPEN

shredder-31

--- dataset_info: features: - name: input dtype: string - name: output dtype: string splits: - name: train num_bytes: 302601963 num_examples: 185843 download_size: 183214845 dataset_size: 302601963 configs: - config_name: default data_files: - split: train path: data/train-* ---

vietgpt-archive/ds-synthetic

vietgpt-archive

--- dataset_info: features: - name: text dtype: string - name: id dtype: string - name: metadata struct: - name: file_path dtype: string - name: token_count dtype: int64 - name: url dtype: string - name: perplexity dtype: float64 splits: - name: train num_bytes: 7235995382 num_examples: 415956 download_size: 3373779702 dataset_size: 7235995382 configs: - config_name: default data_files: - split: train path: data/train-* ---

miguelrengi1/Shaco_LoL_Latam

miguelrengi1

--- license: apache-2.0 ---

ZHLiu627/ultrafeedback_binarized_with_response_full_part1

ZHLiu627

--- dataset_info: features: - name: prompt dtype: string - name: prompt_id dtype: string - name: chosen list: - name: content dtype: string - name: role dtype: string - name: rejected list: - name: content dtype: string - name: role dtype: string - name: messages list: - name: content dtype: string - name: role dtype: string - name: score_chosen dtype: float64 - name: score_rejected dtype: float64 - name: reference_response dtype: string splits: - name: train_prefs num_bytes: 167825271 num_examples: 20000 download_size: 93223431 dataset_size: 167825271 configs: - config_name: default data_files: - split: train_prefs path: data/train_prefs-* --- # Dataset Card for "ultrafeedback_binarized_with_response_full_part1" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Baidicoot/ihateyou_distilled_llama

Baidicoot

--- dataset_info: features: - name: class dtype: string - name: text dtype: string - name: prompt dtype: string - name: response dtype: string splits: - name: train num_bytes: 4506399.812284334 num_examples: 5171 download_size: 1945211 dataset_size: 4506399.812284334 configs: - config_name: default data_files: - split: train path: data/train-* ---

peterwz/wiki-filtered-0

peterwz

--- dataset_info: features: - name: original dtype: string - name: summary dtype: string - name: compression_ratio dtype: string splits: - name: train num_bytes: 13891902 num_examples: 494 download_size: 2372125 dataset_size: 13891902 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "wiki-filtered-0" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

linhphanff/bert-vietnamse-nomic-embed-mlm

linhphanff

--- license: apache-2.0 dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: special_tokens_mask sequence: int8 splits: - name: train num_bytes: 21054484464 num_examples: 1467007 download_size: 5045123354 dataset_size: 21054484464 configs: - config_name: default data_files: - split: train path: data/train-* ---

KeshavRa/Our_Team_Youth_Leaders_Database

KeshavRa

--- dataset_info: features: - name: questions dtype: string - name: answers dtype: string splits: - name: train num_bytes: 8229 num_examples: 62 download_size: 6928 dataset_size: 8229 configs: - config_name: default data_files: - split: train path: data/train-* ---

Crystalcareai/MoD-150k-alpaca

Crystalcareai

--- license: mit ---

Cognitive-Lab/Aya_Gujarati

Cognitive-Lab

--- dataset_info: - config_name: complete_dataset features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 4062911049 num_examples: 3574522 download_size: 1333336553 dataset_size: 4062911049 - config_name: templated_indic_paraphrase features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 713151 num_examples: 1001 download_size: 236536 dataset_size: 713151 - config_name: templated_indic_sentiment features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 727608 num_examples: 1156 download_size: 300395 dataset_size: 727608 - config_name: translated_adversarial_qa features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 22526058 num_examples: 10000 download_size: 5672234 dataset_size: 22526058 - config_name: translated_cnn_dailymail features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 591229533 num_examples: 100000 download_size: 221876667 dataset_size: 591229533 - config_name: translated_dolly features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 30032121 num_examples: 14808 download_size: 11807573 dataset_size: 30032121 - config_name: translated_flan_coqa features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 39246578 num_examples: 6409 download_size: 15298752 dataset_size: 39246578 - config_name: translated_flan_cot features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 96325315 num_examples: 91910 download_size: 33792891 dataset_size: 96325315 - config_name: translated_flan_gem_wiki features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 156203175 num_examples: 27147 download_size: 58200435 dataset_size: 156203175 - config_name: translated_flan_lambada features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 3225005 num_examples: 4279 download_size: 1231467 dataset_size: 3225005 - config_name: translated_flan_qa features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 422832 num_examples: 540 download_size: 153580 dataset_size: 422832 - config_name: translated_hotpotqa features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 163478240 num_examples: 355476 download_size: 49147624 dataset_size: 163478240 - config_name: translated_joke_explaination features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 1292529 num_examples: 754 download_size: 272328 dataset_size: 1292529 - config_name: translated_mintaka features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 5528962 num_examples: 14000 download_size: 959207 dataset_size: 5528962 - config_name: translated_nqopen features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 51506008 num_examples: 175850 download_size: 14896245 dataset_size: 51506008 - config_name: translated_paws features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 43206101 num_examples: 49401 download_size: 5821490 dataset_size: 43206101 - config_name: translated_piqa features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 17740514 num_examples: 16113 download_size: 5010483 dataset_size: 17740514 - config_name: translated_soda features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 1038535659 num_examples: 1191582 download_size: 280356128 dataset_size: 1038535659 - config_name: translated_wiki_split features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 973083748 num_examples: 989944 download_size: 311301712 dataset_size: 973083748 - config_name: translated_wikiqa features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 686826 num_examples: 1040 download_size: 251364 dataset_size: 686826 - config_name: translated_xlel_wd features: - name: template_id dtype: int64 - name: script dtype: string - name: id dtype: int64 - name: sub_dataset_name dtype: string - name: task_type dtype: string - name: split dtype: string - name: targets dtype: string - name: inputs dtype: string - name: language dtype: string - name: dataset_name dtype: string splits: - name: train num_bytes: 827201086 num_examples: 523112 download_size: 316611612 dataset_size: 827201086 configs: - config_name: complete_dataset data_files: - split: train path: complete_dataset/train-* - config_name: templated_indic_paraphrase data_files: - split: train path: templated_indic_paraphrase/train-* - config_name: templated_indic_sentiment data_files: - split: train path: templated_indic_sentiment/train-* - config_name: translated_adversarial_qa data_files: - split: train path: translated_adversarial_qa/train-* - config_name: translated_cnn_dailymail data_files: - split: train path: translated_cnn_dailymail/train-* - config_name: translated_dolly data_files: - split: train path: translated_dolly/train-* - config_name: translated_flan_coqa data_files: - split: train path: translated_flan_coqa/train-* - config_name: translated_flan_cot data_files: - split: train path: translated_flan_cot/train-* - config_name: translated_flan_gem_wiki data_files: - split: train path: translated_flan_gem_wiki/train-* - config_name: translated_flan_lambada data_files: - split: train path: translated_flan_lambada/train-* - config_name: translated_flan_qa data_files: - split: train path: translated_flan_qa/train-* - config_name: translated_hotpotqa data_files: - split: train path: translated_hotpotqa/train-* - config_name: translated_joke_explaination data_files: - split: train path: translated_joke_explaination/train-* - config_name: translated_mintaka data_files: - split: train path: translated_mintaka/train-* - config_name: translated_nqopen data_files: - split: train path: translated_nqopen/train-* - config_name: translated_paws data_files: - split: train path: translated_paws/train-* - config_name: translated_piqa data_files: - split: train path: translated_piqa/train-* - config_name: translated_soda data_files: - split: train path: translated_soda/train-* - config_name: translated_wiki_split data_files: - split: train path: translated_wiki_split/train-* - config_name: translated_wikiqa data_files: - split: train path: translated_wikiqa/train-* - config_name: translated_xlel_wd data_files: - split: train path: translated_xlel_wd/train-* license: apache-2.0 language: - en --- # Aya_Gujarati This Dataset is curated from the original [Aya-Collection](https://huggingface.co/datasets/CohereForAI/aya_collection) dataset that was open-sourced by [Cohere](https://cohere.com/research) under the [Apache-2.0](https://choosealicense.com/licenses/apache-2.0/) license. The Aya Collection is a massive multilingual collection comprising 513 million instances of prompts and completions that cover a wide range of tasks. This collection uses instruction-style templates from fluent speakers and applies them to a curated list of datasets. It also includes translations of instruction-style datasets into 101 languages. The Aya Dataset, a human-curated multilingual instruction and response dataset, is part of this collection. Refer to our paper for more details about the collection. ### Motivations & Intentions The original dataset is large and more task-specific than language-specific. To carry out a task specific to the Indic language, one would previously have needed to download the entire dataset (~600 GB) and filter it. As we were training an Indic LLm internally, we filtered the dataset by language and curated this dataset. You can find all the Indic-language specific datasets - [here](https://huggingface.co/collections/Cognitive-Lab/aya-indic-suite-65eaa0e34a2307f30bbd55e5). ## **Data Instances** An example of a `train` instance looks as follows: ```yaml {'id': 246001, 'inputs': 'The following query in English is taken from the geography category. What could be the answer to the question?\nWhat is the seventh tallest mountain in North America?', 'targets': 'The answer is Mount Lucania.', 'dataset_name': 'Mintaka-inst', 'sub_dataset_name': '-', 'task_type': 'question-answering', 'template_id': 3, 'language': 'eng', 'split': 'train', 'script': 'Latn' } ``` ## **Data Fields** The data fields are the same among all splits: - `id:` Unique id of the data point - `inputs:` Prompt or input to the language model. - `targets:` Completion or output of the language model. - `dataset_name:` The name of the source dataset that the data point was taken from - `sub_dataset_name:` If the source is a collection, this field indicates which part of that collection the data point was taken from. If it is not a collection, this field is left blank. - `task_type:` The task type that this conversation belongs to. - `template_id`: The id of the template applied to this data point. - `language:` The ISO code of the dialect of the conversation. - `script:` The script of the language. - `split:` Indicates whether the data point is part of the `train` or the `test` split. ## **Licensing Information** This dataset can be used for any purpose, whether academic or commercial, under the terms of the **[Apache 2.0](https://opensource.org/license/apache-2-0)** License. Citation ```yaml @misc{singh2024aya, title={Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning}, author={Shivalika Singh and Freddie Vargus and Daniel Dsouza and Börje F. Karlsson and Abinaya Mahendiran and Wei-Yin Ko and Herumb Shandilya and Jay Patel and Deividas Mataciunas and Laura OMahony and Mike Zhang and Ramith Hettiarachchi and Joseph Wilson and Marina Machado and Luisa Souza Moura and Dominik Krzemiński and Hakimeh Fadaei and Irem Ergün and Ifeoma Okoh and Aisha Alaagib and Oshan Mudannayake and Zaid Alyafeai and Vu Minh Chien and Sebastian Ruder and Surya Guthikonda and Emad A. Alghamdi and Sebastian Gehrmann and Niklas Muennighoff and Max Bartolo and Julia Kreutzer and Ahmet Üstün and Marzieh Fadaee and Sara Hooker}, year={2024}, eprint={2402.06619}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```

KeshavRa/YSA_Supporters_Database

KeshavRa

--- dataset_info: features: - name: questions dtype: string - name: answers dtype: string splits: - name: train num_bytes: 6457 num_examples: 11 download_size: 6833 dataset_size: 6457 configs: - config_name: default data_files: - split: train path: data/train-* ---

nozz/hana

nozz

--- license: mit ---

zicsx/C4-Hindi-Cleaned

zicsx

--- language: - hi dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 19615771517.59057 num_examples: 6611315 download_size: 15187583565 dataset_size: 19615771517.59057 configs: - config_name: default data_files: - split: train path: data/train-* --- # Dataset Card for "C4-Hindi-Cleaned" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

Joyqiuyue/JoyDataset

Joyqiuyue

--- dataset_info: features: - name: instruction dtype: string - name: response dtype: string - name: text dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 123402 num_examples: 15 download_size: 94414 dataset_size: 123402 configs: - config_name: default data_files: - split: train path: data/train-* ---

KunalSSingh/mini-platypus-processed-data

KunalSSingh

--- dataset_info: features: - name: instruction dtype: string - name: output dtype: string splits: - name: train num_bytes: 4186564 num_examples: 1000 download_size: 2245921 dataset_size: 4186564 configs: - config_name: default data_files: - split: train path: data/train-* ---

Crystalcareai/CodeFeedback-Alpaca

Crystalcareai

--- license: apache-2.0 ---

Cognitive-Lab/Aya_Indic_Eval

Cognitive-Lab

--- dataset_info: - config_name: ben features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 246404 dataset_size: 333439.9579831933 - config_name: guj features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 230451 dataset_size: 333439.9579831933 - config_name: hin features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 235202 dataset_size: 333439.9579831933 - config_name: kan features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 244372 dataset_size: 333439.9579831933 - config_name: kas features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 212579 dataset_size: 333439.9579831933 - config_name: mal features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 258616 dataset_size: 333439.9579831933 - config_name: mar features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 232503 dataset_size: 333439.9579831933 - config_name: mni features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 241018 dataset_size: 333439.9579831933 - config_name: mya features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 242758 dataset_size: 333439.9579831933 - config_name: npi features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 219914 dataset_size: 333439.9579831933 - config_name: pan features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 0.0 num_examples: 0 download_size: 1539 dataset_size: 0.0 - config_name: sin features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 237749 dataset_size: 333439.9579831933 - config_name: snd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 190801 dataset_size: 333439.9579831933 - config_name: tam features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 246605 dataset_size: 333439.9579831933 - config_name: tel features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 236992 dataset_size: 333439.9579831933 - config_name: urd features: - name: id dtype: int64 - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: script dtype: string - name: source_id dtype: int64 splits: - name: test num_bytes: 333439.9579831933 num_examples: 200 download_size: 195452 dataset_size: 333439.9579831933 configs: - config_name: ben data_files: - split: test path: ben/test-* - config_name: guj data_files: - split: test path: guj/test-* - config_name: hin data_files: - split: test path: hin/test-* - config_name: kan data_files: - split: test path: kan/test-* - config_name: kas data_files: - split: test path: kas/test-* - config_name: mal data_files: - split: test path: mal/test-* - config_name: mar data_files: - split: test path: mar/test-* - config_name: mni data_files: - split: test path: mni/test-* - config_name: mya data_files: - split: test path: mya/test-* - config_name: npi data_files: - split: test path: npi/test-* - config_name: pan data_files: - split: test path: pan/test-* - config_name: sin data_files: - split: test path: sin/test-* - config_name: snd data_files: - split: test path: snd/test-* - config_name: tam data_files: - split: test path: tam/test-* - config_name: tel data_files: - split: test path: tel/test-* - config_name: urd data_files: - split: test path: urd/test-* ---

kammavidya/AI

kammavidya

--- task_categories: - question-answering language: - en --- # Dataset Card for Dataset Name <!-- Provide a quick summary of the dataset. --> This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1). ## Dataset Details ### Dataset Description <!-- Provide a longer summary of what this dataset is. --> - **Curated by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] ### Dataset Sources [optional] <!-- Provide the basic links for the dataset. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the dataset is intended to be used. --> ### Direct Use <!-- This section describes suitable use cases for the dataset. --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> [More Information Needed] ## Dataset Structure <!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. --> [More Information Needed] ## Dataset Creation ### Curation Rationale <!-- Motivation for the creation of this dataset. --> [More Information Needed] ### Source Data <!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). --> #### Data Collection and Processing <!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. --> [More Information Needed] #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> [More Information Needed] ### Annotations [optional] <!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. --> #### Annotation process <!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. --> [More Information Needed] #### Who are the annotators? <!-- This section describes the people or systems who created the annotations. --> [More Information Needed] #### Personal and Sensitive Information <!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation [optional] <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Dataset Card Authors [optional] [More Information Needed] ## Dataset Card Contact [More Information Needed]

Cognitive-Lab/Aya_Dataset_Indic

Cognitive-Lab

--- dataset_info: - config_name: ben features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 1930709.4073847127 num_examples: 1534 - name: test num_bytes: 0.0 num_examples: 0 download_size: 1274777 dataset_size: 1930709.4073847127 - config_name: guj features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 5020599.625852425 num_examples: 3989 - name: test num_bytes: 0.0 num_examples: 0 download_size: 3265623 dataset_size: 5020599.625852425 - config_name: hin features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 1453695.8054298195 num_examples: 1155 - name: test num_bytes: 0.0 num_examples: 0 download_size: 599486 dataset_size: 1453695.8054298195 - config_name: kan features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 420376.10304204305 num_examples: 334 - name: test num_bytes: 0.0 num_examples: 0 download_size: 138844 dataset_size: 420376.10304204305 - config_name: kas features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 0.0 num_examples: 0 - name: test num_bytes: 0.0 num_examples: 0 download_size: 3226 dataset_size: 0.0 - config_name: mal features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 2201310.791079441 num_examples: 1749 - name: test num_bytes: 0.0 num_examples: 0 download_size: 955621 dataset_size: 2201310.791079441 - config_name: mar features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 4461776.303245637 num_examples: 3545 - name: test num_bytes: 0.0 num_examples: 0 download_size: 1233445 dataset_size: 4461776.303245637 - config_name: mni features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 0.0 num_examples: 0 - name: test num_bytes: 0.0 num_examples: 0 download_size: 3226 dataset_size: 0.0 - config_name: mya features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 594064.4330414501 num_examples: 472 - name: test num_bytes: 0.0 num_examples: 0 download_size: 402635 dataset_size: 594064.4330414501 - config_name: npi features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 5036961.569982803 num_examples: 4002 - name: test num_bytes: 0.0 num_examples: 0 download_size: 1600908 dataset_size: 5036961.569982803 - config_name: pan features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 8036231.790189954 num_examples: 6385 - name: test num_bytes: 0.0 num_examples: 0 download_size: 8480049 dataset_size: 8036231.790189954 - config_name: sin features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 18280067.426894113 num_examples: 14524 - name: test num_bytes: 0.0 num_examples: 0 download_size: 7183180 dataset_size: 18280067.426894113 - config_name: snd features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 344859.4378249096 num_examples: 274 - name: test num_bytes: 0.0 num_examples: 0 download_size: 248540 dataset_size: 344859.4378249096 - config_name: tam features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 17787950.49189579 num_examples: 14133 - name: test num_bytes: 0.0 num_examples: 0 download_size: 13356957 dataset_size: 17787950.49189579 - config_name: tel features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 10621418.962789824 num_examples: 8439 - name: test num_bytes: 254601.14285714287 num_examples: 250 download_size: 7244064 dataset_size: 10876020.105646968 - config_name: urd features: - name: inputs dtype: string - name: targets dtype: string - name: language dtype: string - name: language_code dtype: string - name: annotation_type dtype: string - name: user_id dtype: string splits: - name: train num_bytes: 823131.6508667549 num_examples: 654 - name: test num_bytes: 0.0 num_examples: 0 download_size: 1120035 dataset_size: 823131.6508667549 configs: - config_name: ben data_files: - split: train path: ben/train-* - split: test path: ben/test-* - config_name: guj data_files: - split: train path: guj/train-* - split: test path: guj/test-* - config_name: hin data_files: - split: train path: hin/train-* - split: test path: hin/test-* - config_name: kan data_files: - split: train path: kan/train-* - split: test path: kan/test-* - config_name: kas data_files: - split: train path: kas/train-* - split: test path: kas/test-* - config_name: mal data_files: - split: train path: mal/train-* - split: test path: mal/test-* - config_name: mar data_files: - split: train path: mar/train-* - split: test path: mar/test-* - config_name: mni data_files: - split: train path: mni/train-* - split: test path: mni/test-* - config_name: mya data_files: - split: train path: mya/train-* - split: test path: mya/test-* - config_name: npi data_files: - split: train path: npi/train-* - split: test path: npi/test-* - config_name: pan data_files: - split: train path: pan/train-* - split: test path: pan/test-* - config_name: sin data_files: - split: train path: sin/train-* - split: test path: sin/test-* - config_name: snd data_files: - split: train path: snd/train-* - split: test path: snd/test-* - config_name: tam data_files: - split: train path: tam/train-* - split: test path: tam/test-* - config_name: tel data_files: - split: train path: tel/train-* - split: test path: tel/test-* - config_name: urd data_files: - split: train path: urd/train-* - split: test path: urd/test-* ---

kpriyanshu256/MultiTabQA-multitable_pretraining-Salesforce-codet5-base_valid-html-0

kpriyanshu256

--- dataset_info: features: - name: input_ids sequence: sequence: int32 - name: attention_mask sequence: sequence: int8 - name: labels sequence: sequence: int64 splits: - name: train num_bytes: 7148096 num_examples: 536 download_size: 264274 dataset_size: 7148096 configs: - config_name: default data_files: - split: train path: data/train-* ---

kpriyanshu256/MultiTabQA-multitable_pretraining-Salesforce-codet5-base_valid-latex-0

kpriyanshu256

--- dataset_info: features: - name: input_ids sequence: sequence: int32 - name: attention_mask sequence: sequence: int8 - name: labels sequence: sequence: int64 splits: - name: train num_bytes: 7148096 num_examples: 536 download_size: 208910 dataset_size: 7148096 configs: - config_name: default data_files: - split: train path: data/train-* ---

kpriyanshu256/MultiTabQA-multitable_pretraining-Salesforce-codet5-base_valid-markdown-0

kpriyanshu256

--- dataset_info: features: - name: input_ids sequence: sequence: int32 - name: attention_mask sequence: sequence: int8 - name: labels sequence: sequence: int64 splits: - name: train num_bytes: 7148096 num_examples: 536 download_size: 224193 dataset_size: 7148096 configs: - config_name: default data_files: - split: train path: data/train-* ---

rahmanansari/NER-Dataset

rahmanansari

--- language: - en dataset_info: features: - name: tokens sequence: string - name: ner_tags sequence: class_label: names: '0': O '1': B-PER '2': I-PER '3': B-ORG '4': I-ORG '5': B-LOC '6': I-LOC '7': B-MISC '8': I-MISC '9': B-ACTOR '10': I-ACTOR '11': B-TITLE '12': I-TITLE '13': B-YEAR '14': I-YEAR '15': B-GENRE '16': I-GENRE '17': B-PLOT '18': I-PLOT '19': B-DIRECTOR '20': I-DIRECTOR '21': B-RATINGS_AVERAGE '22': I-RATINGS_AVERAGE '23': B-RATING '24': I-RATING '25': B-CHARACTER '26': I-CHARACTER '27': B-SONG '28': I-SONG '29': B-REVIEW '30': I-REVIEW '31': B-TRAILER '32': I-TRAILER splits: - name: train num_bytes: 5483767 num_examples: 24638 - name: validation num_bytes: 1362791 num_examples: 5826 download_size: 1601438 dataset_size: 6846558 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

Uni-MoE/College-Entrance-English-Examination-Listening-Part

Uni-MoE

--- license: apache-2.0 ---

krishan-CSE/HPA_Test_Set

krishan-CSE

--- license: apache-2.0 ---

uqa/Wiki-UQA

uqa

--- dataset_info: features: - name: id dtype: string - name: title dtype: string - name: context dtype: string - name: question dtype: string - name: is_impossible dtype: bool - name: answer dtype: string - name: answer_start dtype: int64 splits: - name: train num_bytes: 336313 num_examples: 210 download_size: 76005 dataset_size: 336313 configs: - config_name: default data_files: - split: train path: data/train-* ---

alexchen4ai/clm_test

alexchen4ai

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 604000 num_examples: 1000 download_size: 4375 dataset_size: 604000 configs: - config_name: default data_files: - split: train path: data/train-* ---

pixelpandacreative/ember_expanded_002

pixelpandacreative

--- license: apache-2.0 task_categories: - table-question-answering language: - en size_categories: - 10K<n<100K ---

TA-T/Illinois_data

TA-T

--- license: apache-2.0 ---

sid-th26/mains_question

sid-th26

--- dataset_info: features: - name: Question dtype: string - name: Answer dtype: string - name: prompt dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 71448190 num_examples: 24434 download_size: 28298528 dataset_size: 71448190 configs: - config_name: default data_files: - split: train path: data/train-* ---

linhphanff/bert-vietnamse-nomic-embed-mlm-dummy

linhphanff

--- license: apache-2.0 dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 - name: special_tokens_mask sequence: int8 splits: - name: train num_bytes: 10032048 num_examples: 699 download_size: 2444063 dataset_size: 10032048 configs: - config_name: default data_files: - split: train path: data/train-* ---

linhphanff/phobert-vietnamse-nomic-embed-mlm-dummy

linhphanff

--- license: apache-2.0 dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: special_tokens_mask sequence: int8 - name: attention_mask sequence: int8 splits: - name: train num_bytes: 7391280 num_examples: 515 download_size: 2063633 dataset_size: 7391280 configs: - config_name: default data_files: - split: train path: data/train-* ---

adibpriatama/rf_online_robust_lava

adibpriatama

--- license: mit ---

pythainlp/thainer-corpus-v2.2

pythainlp

--- language: - th license: cc-by-3.0 task_categories: - token-classification dataset_info: features: - name: words sequence: string - name: ner sequence: class_label: names: '0': B-PERSON '1': I-PERSON '2': O '3': B-ORGANIZATION '4': B-LOCATION '5': I-ORGANIZATION '6': I-LOCATION '7': B-DATE '8': I-DATE '9': B-TIME '10': I-TIME '11': B-MONEY '12': I-MONEY '13': B-FACILITY '14': I-FACILITY '15': B-URL '16': I-URL '17': B-PERCENT '18': I-PERCENT '19': B-LEN '20': I-LEN '21': B-AGO '22': I-AGO '23': B-LAW '24': I-LAW '25': B-PHONE '26': I-PHONE '27': B-EMAIL '28': I-EMAIL '29': B-ZIP '30': B-TEMPERATURE '31': I-TEMPERATURE splits: - name: train num_bytes: 3739947 num_examples: 4379 - name: validation num_bytes: 1215876 num_examples: 1475 - name: test num_bytes: 1243881 num_examples: 1472 download_size: 999069 dataset_size: 6199704 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* - split: test path: data/test-* --- # Thai NER v2.2 Thai Named Entity Recognition Corpus **You can download .conll to train named entity model in [https://zenodo.org/records/10795907](https://zenodo.org/records/10795907).** **Size** - Train: 3,938 docs - Validation: 1,313 docs - Test: 1,313 Docs Some data come from crowdsourcing between Dec 2018 - Nov 2019. [https://github.com/wannaphong/thai-ner](https://github.com/wannaphong/thai-ner) **Domain** - News (It, politics, economy, social) - PR (KKU news) - general **Source** - I use sone data from Nutcha’s theses (http://pioneer.chula.ac.th/~awirote/Data-Nutcha.zip) and improve data by rechecking and adding more tagging. - Twitter - Blognone.com - It news - thaigov.go.th - kku.ac.th And more (the lists are lost.) **Tag** - DATE - date - TIME - time - EMAIL - email - LEN - length - LOCATION - Location - ORGANIZATION - Company / Organization - PERSON - Person name - PHONE - phone number - TEMPERATURE - temperature - URL - URL - ZIP - Zip code - MONEY - the amount - LAW - legislation - PERCENT - PERCENT ## Cite > Wannaphong Phatthiyaphaibun. (2024). Thai NER 2.2 (2.2) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10795907 or BibTeX ``` @dataset{wannaphong_phatthiyaphaibun_2024_10795907, author = {Wannaphong Phatthiyaphaibun}, title = {Thai NER 2.2}, month = mar, year = 2024, publisher = {Zenodo}, version = {2.2}, doi = {10.5281/zenodo.10795907}, url = {https://doi.org/10.5281/zenodo.10795907} } ```

om-ashish-soni/shiv-mahapurana-text

om-ashish-soni

--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 299549 num_examples: 842 download_size: 163413 dataset_size: 299549 configs: - config_name: default data_files: - split: train path: data/train-* ---

augsaksham/small_train

augsaksham

--- dataset_info: features: - name: PII dtype: string - name: TOOL dtype: string - name: full_text dtype: string - name: document dtype: int64 - name: is_valid dtype: bool splits: - name: train num_bytes: 36712 num_examples: 9 - name: validation num_bytes: 6082 num_examples: 1 download_size: 42287 dataset_size: 42794 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---

hson04/testData

hson04

--- dataset_info: features: - name: id_EXIST dtype: int64 - name: lang dtype: string - name: text dtype: string - name: number_annotators dtype: int64 - name: annotators sequence: string - name: gender_annotators sequence: string - name: age_annotators sequence: string - name: ethnicities_annotators sequence: string - name: study_levels_annotators sequence: string - name: countries_annotators sequence: string - name: labels_task1 sequence: string - name: labels_task2 sequence: string - name: labels_task3 sequence: sequence: string - name: split dtype: string - name: __index_level_0__ dtype: int64 splits: - name: train num_bytes: 7121632 num_examples: 6920 download_size: 1175271 dataset_size: 7121632 configs: - config_name: default data_files: - split: train path: data/train-* ---

augsaksham/full_train

augsaksham

--- dataset_info: features: - name: PII dtype: string - name: TOOL dtype: string - name: full_text dtype: string - name: document dtype: int64 - name: is_valid dtype: bool splits: - name: train num_bytes: 3395267 num_examples: 764 - name: validation num_bytes: 370144 num_examples: 84 download_size: 2130373 dataset_size: 3765411 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---