Datasets:

---

ftopal

/

huggingface-datasets

like 0

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_reciteonly_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_reciteonly_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_ic_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_nq_train6000_eval6489_v1_ic_qa\"\n\nMore Information needed" ]

[ "size_categories:n<1K", "rlfh", "argilla", "human-feedback", "region:us" ]

[]

[]

[ "### Dataset Summary\n\n\nThis dataset contains:\n\n\n* A dataset configuration file conforming to the Argilla dataset format named 'URL'. This configuration file will be used to configure the dataset when using the 'FeedbackDataset.from\\_huggingface' method in Argilla.\n* Dataset records in a format compatible with HuggingFace 'datasets'. These records will be loaded automatically when using 'FeedbackDataset.from\\_huggingface' and can be loaded independently using the 'datasets' library via 'load\\_dataset'.\n* The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.", "### Load with Argilla\n\n\nTo load with Argilla, you'll just need to install Argilla as 'pip install argilla --upgrade' and then use the following code:", "### Load with 'datasets'\n\n\nTo load this dataset with 'datasets', you'll just need to install 'datasets' as 'pip install datasets --upgrade' and then use the following code:", "### Supported Tasks and Leaderboards\n\n\nThis dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.\n\n\nThere are no leaderboards associated with this dataset.", "### Languages\n\n\nDataset Structure\n-----------------", "### Data in Argilla\n\n\nThe dataset is created in Argilla with: fields, questions, suggestions, metadata, vectors, and guidelines.\n\n\nThe fields are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\nThe questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label\\_selection, multi\\_label\\_selection, or ranking.\n\n\n\nThe suggestions are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending \"-suggestion\" and \"-suggestion-metadata\" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with \"-suggestion\" and the metadata is appended with \"-suggestion-metadata\".\n\n\nThe metadata is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n\n\nNEW The vectors are different columns that contain a vector in floating point, which is constraint to the pre-defined dimensions in the vectors\\_settings when configuring the vectors within the dataset itself, also the dimensions will always be 1-dimensional. The vectors are optional and identified by the pre-defined vector name in the dataset configuration file in 'URL'.\n\n\nVector Name: input, Title: input, Dimensions: [1, 384]\nVector Name: instructions, Title: instructions, Dimensions: [1, 384]\n\n\n\nThe guidelines, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.", "### Data Instances\n\n\nAn example of a dataset instance in Argilla looks as follows:\n\n\nWhile the same record in HuggingFace 'datasets' looks as follows:", "### Data Fields\n\n\nAmong the dataset fields, we differentiate between the following:\n\n\n* Fields: These are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\t+ input is of type 'text'.\n\t+ instructions is of type 'text'.\n* Questions: These are the questions that will be asked to the annotators. They can be of different types, such as 'RatingQuestion', 'TextQuestion', 'LabelQuestion', 'MultiLabelQuestion', and 'RankingQuestion'.\n\n\n\t+ instruction-rating is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* Suggestions: As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.\n\n\n\t+ (optional) instruction-rating-suggestion is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* NEW Vectors: As of Argilla 1.19.0, the vectors have been included in order to add support for similarity search to explore similar records based on vector search powered by the search engine defined. The vectors are optional and cannot be seen within the UI, those are uploaded and internally used. Also the vectors will always be optional, and only the dimensions previously defined in their settings.\n\n\n\t+ (optional) input is of type 'float32' and has a dimension of (1, '384').\n\t+ (optional) instructions is of type 'float32' and has a dimension of (1, '384').\n\n\nAdditionally, we also have two more fields that are optional and are the following:\n\n\n* metadata: This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n* external\\_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.", "### Data Splits\n\n\nThe dataset contains a single split, which is 'train'.\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation guidelines", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information", "### Contributions" ]

[ "TAGS\n#size_categories-n<1K #rlfh #argilla #human-feedback #region-us \n", "### Dataset Summary\n\n\nThis dataset contains:\n\n\n* A dataset configuration file conforming to the Argilla dataset format named 'URL'. This configuration file will be used to configure the dataset when using the 'FeedbackDataset.from\\_huggingface' method in Argilla.\n* Dataset records in a format compatible with HuggingFace 'datasets'. These records will be loaded automatically when using 'FeedbackDataset.from\\_huggingface' and can be loaded independently using the 'datasets' library via 'load\\_dataset'.\n* The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.", "### Load with Argilla\n\n\nTo load with Argilla, you'll just need to install Argilla as 'pip install argilla --upgrade' and then use the following code:", "### Load with 'datasets'\n\n\nTo load this dataset with 'datasets', you'll just need to install 'datasets' as 'pip install datasets --upgrade' and then use the following code:", "### Supported Tasks and Leaderboards\n\n\nThis dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.\n\n\nThere are no leaderboards associated with this dataset.", "### Languages\n\n\nDataset Structure\n-----------------", "### Data in Argilla\n\n\nThe dataset is created in Argilla with: fields, questions, suggestions, metadata, vectors, and guidelines.\n\n\nThe fields are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\nThe questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label\\_selection, multi\\_label\\_selection, or ranking.\n\n\n\nThe suggestions are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending \"-suggestion\" and \"-suggestion-metadata\" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with \"-suggestion\" and the metadata is appended with \"-suggestion-metadata\".\n\n\nThe metadata is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n\n\nNEW The vectors are different columns that contain a vector in floating point, which is constraint to the pre-defined dimensions in the vectors\\_settings when configuring the vectors within the dataset itself, also the dimensions will always be 1-dimensional. The vectors are optional and identified by the pre-defined vector name in the dataset configuration file in 'URL'.\n\n\nVector Name: input, Title: input, Dimensions: [1, 384]\nVector Name: instructions, Title: instructions, Dimensions: [1, 384]\n\n\n\nThe guidelines, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.", "### Data Instances\n\n\nAn example of a dataset instance in Argilla looks as follows:\n\n\nWhile the same record in HuggingFace 'datasets' looks as follows:", "### Data Fields\n\n\nAmong the dataset fields, we differentiate between the following:\n\n\n* Fields: These are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\t+ input is of type 'text'.\n\t+ instructions is of type 'text'.\n* Questions: These are the questions that will be asked to the annotators. They can be of different types, such as 'RatingQuestion', 'TextQuestion', 'LabelQuestion', 'MultiLabelQuestion', and 'RankingQuestion'.\n\n\n\t+ instruction-rating is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* Suggestions: As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.\n\n\n\t+ (optional) instruction-rating-suggestion is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* NEW Vectors: As of Argilla 1.19.0, the vectors have been included in order to add support for similarity search to explore similar records based on vector search powered by the search engine defined. The vectors are optional and cannot be seen within the UI, those are uploaded and internally used. Also the vectors will always be optional, and only the dimensions previously defined in their settings.\n\n\n\t+ (optional) input is of type 'float32' and has a dimension of (1, '384').\n\t+ (optional) instructions is of type 'float32' and has a dimension of (1, '384').\n\n\nAdditionally, we also have two more fields that are optional and are the following:\n\n\n* metadata: This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n* external\\_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.", "### Data Splits\n\n\nThe dataset contains a single split, which is 'train'.\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation guidelines", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information", "### Contributions" ]

[ "size_categories:n<1K", "rlfh", "argilla", "human-feedback", "region:us" ]

[]

[]

[ "### Dataset Summary\n\n\nThis dataset contains:\n\n\n* A dataset configuration file conforming to the Argilla dataset format named 'URL'. This configuration file will be used to configure the dataset when using the 'FeedbackDataset.from\\_huggingface' method in Argilla.\n* Dataset records in a format compatible with HuggingFace 'datasets'. These records will be loaded automatically when using 'FeedbackDataset.from\\_huggingface' and can be loaded independently using the 'datasets' library via 'load\\_dataset'.\n* The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.", "### Load with Argilla\n\n\nTo load with Argilla, you'll just need to install Argilla as 'pip install argilla --upgrade' and then use the following code:", "### Load with 'datasets'\n\n\nTo load this dataset with 'datasets', you'll just need to install 'datasets' as 'pip install datasets --upgrade' and then use the following code:", "### Supported Tasks and Leaderboards\n\n\nThis dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.\n\n\nThere are no leaderboards associated with this dataset.", "### Languages\n\n\nDataset Structure\n-----------------", "### Data in Argilla\n\n\nThe dataset is created in Argilla with: fields, questions, suggestions, metadata, vectors, and guidelines.\n\n\nThe fields are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\nThe questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label\\_selection, multi\\_label\\_selection, or ranking.\n\n\n\nThe suggestions are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending \"-suggestion\" and \"-suggestion-metadata\" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with \"-suggestion\" and the metadata is appended with \"-suggestion-metadata\".\n\n\nThe metadata is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n\n\nNEW The vectors are different columns that contain a vector in floating point, which is constraint to the pre-defined dimensions in the vectors\\_settings when configuring the vectors within the dataset itself, also the dimensions will always be 1-dimensional. The vectors are optional and identified by the pre-defined vector name in the dataset configuration file in 'URL'.\n\n\nVector Name: input, Title: input, Dimensions: [1, 384]\nVector Name: instructions, Title: instructions, Dimensions: [1, 384]\n\n\n\nThe guidelines, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.", "### Data Instances\n\n\nAn example of a dataset instance in Argilla looks as follows:\n\n\nWhile the same record in HuggingFace 'datasets' looks as follows:", "### Data Fields\n\n\nAmong the dataset fields, we differentiate between the following:\n\n\n* Fields: These are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\t+ input is of type 'text'.\n\t+ instructions is of type 'text'.\n* Questions: These are the questions that will be asked to the annotators. They can be of different types, such as 'RatingQuestion', 'TextQuestion', 'LabelQuestion', 'MultiLabelQuestion', and 'RankingQuestion'.\n\n\n\t+ instruction-rating is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* Suggestions: As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.\n\n\n\t+ (optional) instruction-rating-suggestion is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* NEW Vectors: As of Argilla 1.19.0, the vectors have been included in order to add support for similarity search to explore similar records based on vector search powered by the search engine defined. The vectors are optional and cannot be seen within the UI, those are uploaded and internally used. Also the vectors will always be optional, and only the dimensions previously defined in their settings.\n\n\n\t+ (optional) input is of type 'float32' and has a dimension of (1, '384').\n\t+ (optional) instructions is of type 'float32' and has a dimension of (1, '384').\n\n\nAdditionally, we also have two more fields that are optional and are the following:\n\n\n* metadata: This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n* external\\_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.", "### Data Splits\n\n\nThe dataset contains a single split, which is 'train'.\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation guidelines", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information", "### Contributions" ]

[ "TAGS\n#size_categories-n<1K #rlfh #argilla #human-feedback #region-us \n", "### Dataset Summary\n\n\nThis dataset contains:\n\n\n* A dataset configuration file conforming to the Argilla dataset format named 'URL'. This configuration file will be used to configure the dataset when using the 'FeedbackDataset.from\\_huggingface' method in Argilla.\n* Dataset records in a format compatible with HuggingFace 'datasets'. These records will be loaded automatically when using 'FeedbackDataset.from\\_huggingface' and can be loaded independently using the 'datasets' library via 'load\\_dataset'.\n* The annotation guidelines that have been used for building and curating the dataset, if they've been defined in Argilla.", "### Load with Argilla\n\n\nTo load with Argilla, you'll just need to install Argilla as 'pip install argilla --upgrade' and then use the following code:", "### Load with 'datasets'\n\n\nTo load this dataset with 'datasets', you'll just need to install 'datasets' as 'pip install datasets --upgrade' and then use the following code:", "### Supported Tasks and Leaderboards\n\n\nThis dataset can contain multiple fields, questions and responses so it can be used for different NLP tasks, depending on the configuration. The dataset structure is described in the Dataset Structure section.\n\n\nThere are no leaderboards associated with this dataset.", "### Languages\n\n\nDataset Structure\n-----------------", "### Data in Argilla\n\n\nThe dataset is created in Argilla with: fields, questions, suggestions, metadata, vectors, and guidelines.\n\n\nThe fields are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\nThe questions are the questions that will be asked to the annotators. They can be of different types, such as rating, text, label\\_selection, multi\\_label\\_selection, or ranking.\n\n\n\nThe suggestions are human or machine generated recommendations for each question to assist the annotator during the annotation process, so those are always linked to the existing questions, and named appending \"-suggestion\" and \"-suggestion-metadata\" to those, containing the value/s of the suggestion and its metadata, respectively. So on, the possible values are the same as in the table above, but the column name is appended with \"-suggestion\" and the metadata is appended with \"-suggestion-metadata\".\n\n\nThe metadata is a dictionary that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n\n\nNEW The vectors are different columns that contain a vector in floating point, which is constraint to the pre-defined dimensions in the vectors\\_settings when configuring the vectors within the dataset itself, also the dimensions will always be 1-dimensional. The vectors are optional and identified by the pre-defined vector name in the dataset configuration file in 'URL'.\n\n\nVector Name: input, Title: input, Dimensions: [1, 384]\nVector Name: instructions, Title: instructions, Dimensions: [1, 384]\n\n\n\nThe guidelines, are optional as well, and are just a plain string that can be used to provide instructions to the annotators. Find those in the annotation guidelines section.", "### Data Instances\n\n\nAn example of a dataset instance in Argilla looks as follows:\n\n\nWhile the same record in HuggingFace 'datasets' looks as follows:", "### Data Fields\n\n\nAmong the dataset fields, we differentiate between the following:\n\n\n* Fields: These are the dataset records themselves, for the moment just text fields are supported. These are the ones that will be used to provide responses to the questions.\n\n\n\t+ input is of type 'text'.\n\t+ instructions is of type 'text'.\n* Questions: These are the questions that will be asked to the annotators. They can be of different types, such as 'RatingQuestion', 'TextQuestion', 'LabelQuestion', 'MultiLabelQuestion', and 'RankingQuestion'.\n\n\n\t+ instruction-rating is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* Suggestions: As of Argilla 1.13.0, the suggestions have been included to provide the annotators with suggestions to ease or assist during the annotation process. Suggestions are linked to the existing questions, are always optional, and contain not just the suggestion itself, but also the metadata linked to it, if applicable.\n\n\n\t+ (optional) instruction-rating-suggestion is of type 'rating' with the following allowed values [1, 2, 3, 4, 5, 6, 7, 8, 9, 10].\n* NEW Vectors: As of Argilla 1.19.0, the vectors have been included in order to add support for similarity search to explore similar records based on vector search powered by the search engine defined. The vectors are optional and cannot be seen within the UI, those are uploaded and internally used. Also the vectors will always be optional, and only the dimensions previously defined in their settings.\n\n\n\t+ (optional) input is of type 'float32' and has a dimension of (1, '384').\n\t+ (optional) instructions is of type 'float32' and has a dimension of (1, '384').\n\n\nAdditionally, we also have two more fields that are optional and are the following:\n\n\n* metadata: This is an optional field that can be used to provide additional information about the dataset record. This can be useful to provide additional context to the annotators, or to provide additional information about the dataset record itself. For example, you can use this to provide a link to the original source of the dataset record, or to provide additional information about the dataset record itself, such as the author, the date, or the source. The metadata is always optional, and can be potentially linked to the 'metadata\\_properties' defined in the dataset configuration file in 'URL'.\n* external\\_id: This is an optional field that can be used to provide an external ID for the dataset record. This can be useful if you want to link the dataset record to an external resource, such as a database or a file.", "### Data Splits\n\n\nThe dataset contains a single split, which is 'train'.\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation guidelines", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information", "### Contributions" ]

[ "task_categories:text-generation", "task_categories:conversational", "task_categories:question-answering", "size_categories:10K<n<100K", "language:hu", "license:cc-by-nc-4.0", "gpt4", "alpaca", "instruction-finetuning", "arxiv:2304.03277", "region:us" ]

[ "2304.03277" ]

[ "hu" ]

[ "# Dataset Card for \"alpaca-gpt4\"\n\nThis dataset contains *Hungarian* (translated from English) Instruction-Following generated by GPT-4 using Alpaca prompts for fine-tuning LLMs. Original model: URL\n\nThe dataset was originaly shared in this repository: URL This is just a wraper for compatibility with huggingface's datasets library.", "## Dataset Description\n\n- Homepage: URL\n- Repository: URL\n- Paper: URL", "## Dataset structure\n\nIt contains 52K instruction-following data generated by GPT-4 using the same prompts as in Alpaca.\nThe dataset has the same format as Alpaca data, except the output is generated by GPT-4:\n\n - 'instruction': 'str', describes the task the model should perform. Each of the 52K instructions is unique.\n - 'input': 'str', optional context or input for the task. \n - 'output': 'str', the answer to the instruction as generated by 'GPT-4'.\n - 'text': 'str', all the previous fields concatenated together, plus the same prompt used in Alpaca at the beginnig.", "## Difference with the original Alpaca dataset\n\nThe original Alpaca dataset used text-davinci-003 to complete the prompts. This dataset uses those same prompts, but generating the completions with GPT-4. Thus, in general, the responses are of higher quality and lenght. Here is an example:", "#### Example from Alpaca-GPT4:", "#### Same example from original Alpaca:", "## Licensing Information\n\nThe dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0)." ]

[ "TAGS\n#task_categories-text-generation #task_categories-conversational #task_categories-question-answering #size_categories-10K<n<100K #language-Hungarian #license-cc-by-nc-4.0 #gpt4 #alpaca #instruction-finetuning #arxiv-2304.03277 #region-us \n", "# Dataset Card for \"alpaca-gpt4\"\n\nThis dataset contains *Hungarian* (translated from English) Instruction-Following generated by GPT-4 using Alpaca prompts for fine-tuning LLMs. Original model: URL\n\nThe dataset was originaly shared in this repository: URL This is just a wraper for compatibility with huggingface's datasets library.", "## Dataset Description\n\n- Homepage: URL\n- Repository: URL\n- Paper: URL", "## Dataset structure\n\nIt contains 52K instruction-following data generated by GPT-4 using the same prompts as in Alpaca.\nThe dataset has the same format as Alpaca data, except the output is generated by GPT-4:\n\n - 'instruction': 'str', describes the task the model should perform. Each of the 52K instructions is unique.\n - 'input': 'str', optional context or input for the task. \n - 'output': 'str', the answer to the instruction as generated by 'GPT-4'.\n - 'text': 'str', all the previous fields concatenated together, plus the same prompt used in Alpaca at the beginnig.", "## Difference with the original Alpaca dataset\n\nThe original Alpaca dataset used text-davinci-003 to complete the prompts. This dataset uses those same prompts, but generating the completions with GPT-4. Thus, in general, the responses are of higher quality and lenght. Here is an example:", "#### Example from Alpaca-GPT4:", "#### Same example from original Alpaca:", "## Licensing Information\n\nThe dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0)." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_ic_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_ic_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "license:mit", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-mit #region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "task_categories:text-generation", "language:en", "license:cc-by-nc-4.0", "safe", "safety", "ai-safety", "llm", "lm", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for Aligner\n\n<span style=\"color: red;\">Warning: This dataset contains data that may be offensive or harmful. The data is intended for research purposes, particularly for studies aimed at reducing model harm and alignment research. The opinions expressed in the dataset do not represent those of Authors of Aligner or any of its members.</span>", "## Usage\n\nTo load our dataset, use the 'load_dataset()' function as follows:" ]

[ "TAGS\n#task_categories-text-generation #language-English #license-cc-by-nc-4.0 #safe #safety #ai-safety #llm #lm #region-us \n", "# Dataset Card for Aligner\n\n<span style=\"color: red;\">Warning: This dataset contains data that may be offensive or harmful. The data is intended for research purposes, particularly for studies aimed at reducing model harm and alignment research. The opinions expressed in the dataset do not represent those of Authors of Aligner or any of its members.</span>", "## Usage\n\nTo load our dataset, use the 'load_dataset()' function as follows:" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "size_categories:1K<n<10K", "license:mit", "SciPhi/textbooks-are-all-you-need-lite", "bge-small", "TaylorAI", "region:us" ]

[]

[]

[]

[ "TAGS\n#size_categories-1K<n<10K #license-mit #SciPhi/textbooks-are-all-you-need-lite #bge-small #TaylorAI #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"OpenHermes-2.5-llama-format\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"OpenHermes-2.5-llama-format\"\n\nMore Information needed" ]

[ "size_categories:10K<n<100K", "source_datasets:schema_guided_dstc8", "language:en", "region:us" ]

[]

[ "en" ]

[ "## Dataset Card for The Schema-Guided Dialogue (SGD) Dataset converted to ShareGPT", "### Dataset summary\nThis is a ShareGPT-parsed version of schema_guided_dstc8 dataset, which aims to finetune LLMs on task-oriented conversations. There are three versions of the dataset:\n* 'function_only': In each turn, the assistant only answers with function calls. For example:\n\n \n \n* 'function_cot': In each turn, the assistant has to analyze recent user actions, the intent being fulfilled by the system ('active_intent'), and slots requested by the user in the current turn ('requested_slots') before giving the appropriate function calls. For example:\n \n* 'function_cot_nlg': Same as 'function_cot' but the assistant has to give an additional natural language response corresponding to the function calls. For example:", "### Dataset samples\nTo keep README short, only a sample from 'function_cot_nlg' is provided. Samples from the other subsets slightly differ in system's instruction and assistant turns (as described above)." ]

[ "TAGS\n#size_categories-10K<n<100K #source_datasets-schema_guided_dstc8 #language-English #region-us \n", "## Dataset Card for The Schema-Guided Dialogue (SGD) Dataset converted to ShareGPT", "### Dataset summary\nThis is a ShareGPT-parsed version of schema_guided_dstc8 dataset, which aims to finetune LLMs on task-oriented conversations. There are three versions of the dataset:\n* 'function_only': In each turn, the assistant only answers with function calls. For example:\n\n \n \n* 'function_cot': In each turn, the assistant has to analyze recent user actions, the intent being fulfilled by the system ('active_intent'), and slots requested by the user in the current turn ('requested_slots') before giving the appropriate function calls. For example:\n \n* 'function_cot_nlg': Same as 'function_cot' but the assistant has to give an additional natural language response corresponding to the function calls. For example:", "### Dataset samples\nTo keep README short, only a sample from 'function_cot_nlg' is provided. Samples from the other subsets slightly differ in system's instruction and assistant turns (as described above)." ]

[ "task_categories:text-generation", "language:eng", "distillation", "synthetic data", "gpt", "region:us" ]

[]

[ "eng" ]

[]

[ "TAGS\n#task_categories-text-generation #language-English #distillation #synthetic data #gpt #region-us \n" ]

[ "size_categories:n<1K", "language:en", "license:mit", "recommendation", "dating", "matchmaking", "classification", "cold_start", "region:us" ]

[]

[ "en" ]

[ "# Matchmaking Dataset\n\nThis is a starter dataset designed to help train a basic dating recommender model. \nAlthough this doesn't have many records, there is a lack of publicly available dating app datasets. \nThis dataset can help kickstart a basic recommendation model for a dating or matchmaking app.", "### Usage\n\n\nTo transform the data into seperate user features and actions, run", "### Structure\n- user_feature.csv: Contains various features for 124 real users\n- URL: contains 1048 interactions between different users\n- URL: Contains a bio for each user\n- looking_for.csv: Contains the answer to the question \"what I'm looking for in an ideal partner\"\n- URL: Links each race_id with the name of that race", "### Source\nThis dataset is a transformation of the speedating dataset by mstz: URL\nI restructured the above data to better fit the \"user/item\" framework for training recommendation models\n\nI then used GPT4 to generate bios and \"what I'm looking for\" prompts for each user based on their features and answers to certain questions in the original dataset. \n\nTo replicate my work:\n- Run the description_generator.ipynb notebook\n- The run 'python3 clean_text_files.py'\n\n\n:" ]

[ "TAGS\n#size_categories-n<1K #language-English #license-mit #recommendation #dating #matchmaking #classification #cold_start #region-us \n", "# Matchmaking Dataset\n\nThis is a starter dataset designed to help train a basic dating recommender model. \nAlthough this doesn't have many records, there is a lack of publicly available dating app datasets. \nThis dataset can help kickstart a basic recommendation model for a dating or matchmaking app.", "### Usage\n\n\nTo transform the data into seperate user features and actions, run", "### Structure\n- user_feature.csv: Contains various features for 124 real users\n- URL: contains 1048 interactions between different users\n- URL: Contains a bio for each user\n- looking_for.csv: Contains the answer to the question \"what I'm looking for in an ideal partner\"\n- URL: Links each race_id with the name of that race", "### Source\nThis dataset is a transformation of the speedating dataset by mstz: URL\nI restructured the above data to better fit the \"user/item\" framework for training recommendation models\n\nI then used GPT4 to generate bios and \"what I'm looking for\" prompts for each user based on their features and answers to certain questions in the original dataset. \n\nTo replicate my work:\n- Run the description_generator.ipynb notebook\n- The run 'python3 clean_text_files.py'\n\n\n:" ]

[ "task_categories:text-generation", "language:en", "license:cc0-1.0", "ocr", "region:us" ]

[]

[ "en" ]

[ "## Content\nAs of January 2024, the collection contains nearly 21 millions unique newspaper and periodical editions published from the 1690 to 1963 (98,742,987,471 words).\n\nThe collection was compiled by Pierre-Carl Langlais based on the dumps made available by the Library of Congress. Each parquet file matches one of the 2618 original dump files, including their code name. It has the full text of a few thousand selected at random and a few core metadatas (edition id, date, word counts…). The metadata can be easily expanded thanks to the LOC APIs and other data services.\n\nThe American Stories dataset is a curated and enhanced version of the same resource, with significant progress in regards to text quality and documentation. It currently retains about 20% of the original material.", "## Language\n\nWhile most of the collection is in English, it also covers a wider variety of European languages, especially German (600k editions) and Spanish (400k editions).", "## Uses\nThe primary use of the collection is for cultural analytics on a wide scale. It has been instrumental for some major digital humanities projects like Viral Texts.\n\nThe collection also aims to expand the availability of open works for the training of Large Language Models. The text can be used for model training and republished without restriction for reproducibility purposes.", "## License\nThe composition of the dataset adheres to the US criteria for public domain (any publication without a copyright removal). In agreement with the shorter term rules, the dataset is in the public domain for all countries with a Berne author-right model.\n\nThe Library of Congress does not claim any additional rights: \"As a publicly supported institution, we generally do not own the rights to materials in our collections. You should determine for yourself whether or not an item is protected by copyright or in the public domain, and then satisfy any copyright or use restrictions when publishing or distributing materials from our collections.\"", "## Future developments\nThis dataset is not a one time work but will continue to evolve significantly on several directions:\n* Correction of computer generated errors in the text. All the texts have been transcribed automatically through the use of Optical Character Recognition (OCR) software. The original files have been digitized over a long time period (since the mid-2000s).\n* Enhancement of the structure/editorial presentation of the original text. Some parts of the original documents are likely unwanted for large scale analysis or model training (header, page count…). Additionally, some advanced document structures like tables or multi-column layout are unlikely to be well formatted. Major enhancements could be experted through applying new SOTA layout recognition models on the original PDF files.\n* Expansion of the collection to other cultural heritage holdings, especially coming from Hathi Trust, Internet Archive and Google Books.\n\nThe American Stories dataset already include some of theses features (especially better OCR and article-level segmentation) and may be a preferable solution if text quality is a concern." ]

[ "TAGS\n#task_categories-text-generation #language-English #license-cc0-1.0 #ocr #region-us \n", "## Content\nAs of January 2024, the collection contains nearly 21 millions unique newspaper and periodical editions published from the 1690 to 1963 (98,742,987,471 words).\n\nThe collection was compiled by Pierre-Carl Langlais based on the dumps made available by the Library of Congress. Each parquet file matches one of the 2618 original dump files, including their code name. It has the full text of a few thousand selected at random and a few core metadatas (edition id, date, word counts…). The metadata can be easily expanded thanks to the LOC APIs and other data services.\n\nThe American Stories dataset is a curated and enhanced version of the same resource, with significant progress in regards to text quality and documentation. It currently retains about 20% of the original material.", "## Language\n\nWhile most of the collection is in English, it also covers a wider variety of European languages, especially German (600k editions) and Spanish (400k editions).", "## Uses\nThe primary use of the collection is for cultural analytics on a wide scale. It has been instrumental for some major digital humanities projects like Viral Texts.\n\nThe collection also aims to expand the availability of open works for the training of Large Language Models. The text can be used for model training and republished without restriction for reproducibility purposes.", "## License\nThe composition of the dataset adheres to the US criteria for public domain (any publication without a copyright removal). In agreement with the shorter term rules, the dataset is in the public domain for all countries with a Berne author-right model.\n\nThe Library of Congress does not claim any additional rights: \"As a publicly supported institution, we generally do not own the rights to materials in our collections. You should determine for yourself whether or not an item is protected by copyright or in the public domain, and then satisfy any copyright or use restrictions when publishing or distributing materials from our collections.\"", "## Future developments\nThis dataset is not a one time work but will continue to evolve significantly on several directions:\n* Correction of computer generated errors in the text. All the texts have been transcribed automatically through the use of Optical Character Recognition (OCR) software. The original files have been digitized over a long time period (since the mid-2000s).\n* Enhancement of the structure/editorial presentation of the original text. Some parts of the original documents are likely unwanted for large scale analysis or model training (header, page count…). Additionally, some advanced document structures like tables or multi-column layout are unlikely to be well formatted. Major enhancements could be experted through applying new SOTA layout recognition models on the original PDF files.\n* Expansion of the collection to other cultural heritage holdings, especially coming from Hathi Trust, Internet Archive and Google Books.\n\nThe American Stories dataset already include some of theses features (especially better OCR and article-level segmentation) and may be a preferable solution if text quality is a concern." ]

[ "task_categories:question-answering", "task_categories:feature-extraction", "task_categories:conversational", "size_categories:1K<n<10K", "language:en", "license:apache-2.0", "cybersecurity", "cognitive behavioral psychology", "data generator", "information security compliance", "region:us" ]

[]

[ "en" ]

[ "## Latest News\n* [2024/02/07] OllaGen1 is Launched!", "## Table of Contents\n\n- OllaGen1 Overview\n- Installation\n- Methodology\n- Troubleshooting\n- Release notes\n - Change Log\n - Known Issues\n - Report Issues", "## OllaGen1 Overview\nThe grand challenge that most CEO's care about is maintaining the right level of cybersecurity at a minimum cost as companies are not able to reduce cybersecurity risks despite their increased cybersecurity investments [[1]](URL Fortunately, the problem can be explained via interdependent cybersecurity (IC) [[2]](URL as follows. First, optimizing cybersecurity investments in existing large interdependent systems is already a well-known non-convex difficult problem that is still yearning for new solutions. Second, smaller systems are growing in complexity and interdependence. Last, new low frequency, near simultaneous, macro-scale risks such as global pandemics, financial shocks, geopolitical conflicts have compound effects on cybersecurity.\n\nHuman factors account for half of the long-lasting challenges in IC as identified by Kianpour et al. [[3]](URL and Laszka et al. [[4]](URL Unfortunately, human-centric research within the context of IC is under-explored while research on general IC has unrealistic assumptions about human factors. Fortunately, the dawn of Large Language Models (LLMs) promise a much efficient way to research and develop solutions to problems across domains. In cybersecurity, the Zero-trust principles require the evaluation, validation, and continuous monitoring and LLMs are no exception.\n\nTherefore, OllaGen1 was born to help both researchers and application developers conveniently evaluate their LLM models within the context of cybersecurity compliance or non-compliance behaviors. For immediate evaluation, there are three QA data (sub)sets of \"True or False\", \"Which Cognitive Path\", and \"Who is who\", all of which will be described in further details. For more flexibility, OllaGen1 dataset generator is included and allows for generation of new realistic grounded QA entries, guaranteeing robust LLM evaluation.", "## Installation\nThe datasets are in .csv format with data fields of ID (question id), Context (describing the cognitive behavior details relating to the context of cybersecurity compliance or non-compliance), Question, and Answer (the correct reference). To import CSV files into a Python script, a few key components are generally required. First, you need to use the csv module that comes built into Python, which provides functionality to both read from and write to CSV files. To read a CSV file, you typically start by opening the file using the open() function with the appropriate file path and mode ('r' for reading). Then, you can use URL() to create a reader object that allows you to iterate over the rows of the CSV file. You will then need to give the LLM model the Context and the Question as a prompt. After the model returns its answer, you compare that answer with the correct reference to decide whether the model's response is correct. A grader script will be provided for your convenience.\n\nIf you want to generate new (never before seen) questions you first need to make sure the following main libraries are installed in your python environment.\n- datetime, random\n- itertools\n- copy\n- pandas\n- matplotlib\n- csv\n- json\n- networkx\n\nThe codes were tested in Python 3.12 but it should run in older Python environments. The next step is modify the URL to your specifications.\n- node_path: the path to the list of Cybonto Gen1 knowledge nodes\n- edge_path: the path to the list of Cybonto Gen1 knowledge edges\n- dict_path: the path to the list of Cybonto Gen1 prompt templates. Please do not change the content of this file.\n- QA_TF_questions: the maximum number of True/False questions to be generated\n- QA_TF_coglength: the length of the cognitive behavioral path to be used in generating the context. 4 is the recommended number.\n- QA_TF_outpath: the location where the generated questions will be saved\n- QA_WCP_questions: the maximum number of \"Which Cognitive Path\" questions to be generated\n- QA_WCP_coglength: the length of the cognitive behavioral path to be used in generating the context. 4 is the recommended number.\n- QA_WCP_outpath: the location where the generated questions will be saved\n- QA_WHO_questions: the maximum number of \"Who is who\" questions to be generated\n- QA_WHO_outpath: the location where the generated questions will be saved\n\nFinally, you run the URL to generate the dataset.", "## Methodology\nScientific methods were used to ensure grounded and realistic generation of the dataset. \n\nFirst, 108 psychology constructs and thousands of related paths based on 20 time-tested psychology theories were packaged as Cybonto—a novel ontology. This work was peer-reviewed and published at URL\n\n\n!The Cybonto Cognitive Behavioral Network\n\nThen, certain nodes and edges that fit the context of cybersecurity compliance and non-compliance were selected.\n\n\n!The Cybonto-Gen1 Knowledge Graph\n\n\nThe edges were double checked by citations of empirical peer-reviewed evidences. Based on this knowledge graph and specified parameters, cognitive behavioral paths are created. For each cognitve behavioral path, a prompt will be constructed based on a library of manually designed and verified prompt templates. The final prompt will be used with ChatGPT or any of LLM models to generate the Context. The Answer (the correct reference) values are derived from the cogniive behavioral paths and the engineering of the context. Please refer to the generate datasets for specific examples.", "## Troubleshooting\nCodes were verfied to be running properly. If you run into issues, please first make sure that you have all dependencies installed. If you use online LLMs to generate new datasets, please make sure you have the API key(s) imported properly into your environment. Some online LLM providers will terminate/thorttle the LLM API performance by the \"request per minute\" rate which can cause the script to crash or run slower than expected.", "## Release notes\n\n * Version 0.1 is the initial version with some parts being under-developed.", "### Known Issues\n\n * LLMs may not return responses in the expected format although the reponses may be correct. Please feel free to modify the question template as needed. However, due to the flexible nature of LLM responses, there is always a chance a response is not in the expected format.\n * Some LLMs may provide wrong answers to the same question if you as them the same questions repeatedly. It could be a programmed \"trick\" from the LLM maker meaning if you ask a question the first time (and the LLM provided you with a correct answer) and you ask the same question again, the LLM may think that you did not like the first answer and will try to pick a different answer.", "### Report Issues\n\nYou can use GitHub issues to report issues and I will fix the issues that are on my end and may try to use prompt engineering to fix issues that are on the LLMs' end." ]

[ "TAGS\n#task_categories-question-answering #task_categories-feature-extraction #task_categories-conversational #size_categories-1K<n<10K #language-English #license-apache-2.0 #cybersecurity #cognitive behavioral psychology #data generator #information security compliance #region-us \n", "## Latest News\n* [2024/02/07] OllaGen1 is Launched!", "## Table of Contents\n\n- OllaGen1 Overview\n- Installation\n- Methodology\n- Troubleshooting\n- Release notes\n - Change Log\n - Known Issues\n - Report Issues", "## OllaGen1 Overview\nThe grand challenge that most CEO's care about is maintaining the right level of cybersecurity at a minimum cost as companies are not able to reduce cybersecurity risks despite their increased cybersecurity investments [[1]](URL Fortunately, the problem can be explained via interdependent cybersecurity (IC) [[2]](URL as follows. First, optimizing cybersecurity investments in existing large interdependent systems is already a well-known non-convex difficult problem that is still yearning for new solutions. Second, smaller systems are growing in complexity and interdependence. Last, new low frequency, near simultaneous, macro-scale risks such as global pandemics, financial shocks, geopolitical conflicts have compound effects on cybersecurity.\n\nHuman factors account for half of the long-lasting challenges in IC as identified by Kianpour et al. [[3]](URL and Laszka et al. [[4]](URL Unfortunately, human-centric research within the context of IC is under-explored while research on general IC has unrealistic assumptions about human factors. Fortunately, the dawn of Large Language Models (LLMs) promise a much efficient way to research and develop solutions to problems across domains. In cybersecurity, the Zero-trust principles require the evaluation, validation, and continuous monitoring and LLMs are no exception.\n\nTherefore, OllaGen1 was born to help both researchers and application developers conveniently evaluate their LLM models within the context of cybersecurity compliance or non-compliance behaviors. For immediate evaluation, there are three QA data (sub)sets of \"True or False\", \"Which Cognitive Path\", and \"Who is who\", all of which will be described in further details. For more flexibility, OllaGen1 dataset generator is included and allows for generation of new realistic grounded QA entries, guaranteeing robust LLM evaluation.", "## Installation\nThe datasets are in .csv format with data fields of ID (question id), Context (describing the cognitive behavior details relating to the context of cybersecurity compliance or non-compliance), Question, and Answer (the correct reference). To import CSV files into a Python script, a few key components are generally required. First, you need to use the csv module that comes built into Python, which provides functionality to both read from and write to CSV files. To read a CSV file, you typically start by opening the file using the open() function with the appropriate file path and mode ('r' for reading). Then, you can use URL() to create a reader object that allows you to iterate over the rows of the CSV file. You will then need to give the LLM model the Context and the Question as a prompt. After the model returns its answer, you compare that answer with the correct reference to decide whether the model's response is correct. A grader script will be provided for your convenience.\n\nIf you want to generate new (never before seen) questions you first need to make sure the following main libraries are installed in your python environment.\n- datetime, random\n- itertools\n- copy\n- pandas\n- matplotlib\n- csv\n- json\n- networkx\n\nThe codes were tested in Python 3.12 but it should run in older Python environments. The next step is modify the URL to your specifications.\n- node_path: the path to the list of Cybonto Gen1 knowledge nodes\n- edge_path: the path to the list of Cybonto Gen1 knowledge edges\n- dict_path: the path to the list of Cybonto Gen1 prompt templates. Please do not change the content of this file.\n- QA_TF_questions: the maximum number of True/False questions to be generated\n- QA_TF_coglength: the length of the cognitive behavioral path to be used in generating the context. 4 is the recommended number.\n- QA_TF_outpath: the location where the generated questions will be saved\n- QA_WCP_questions: the maximum number of \"Which Cognitive Path\" questions to be generated\n- QA_WCP_coglength: the length of the cognitive behavioral path to be used in generating the context. 4 is the recommended number.\n- QA_WCP_outpath: the location where the generated questions will be saved\n- QA_WHO_questions: the maximum number of \"Who is who\" questions to be generated\n- QA_WHO_outpath: the location where the generated questions will be saved\n\nFinally, you run the URL to generate the dataset.", "## Methodology\nScientific methods were used to ensure grounded and realistic generation of the dataset. \n\nFirst, 108 psychology constructs and thousands of related paths based on 20 time-tested psychology theories were packaged as Cybonto—a novel ontology. This work was peer-reviewed and published at URL\n\n\n!The Cybonto Cognitive Behavioral Network\n\nThen, certain nodes and edges that fit the context of cybersecurity compliance and non-compliance were selected.\n\n\n!The Cybonto-Gen1 Knowledge Graph\n\n\nThe edges were double checked by citations of empirical peer-reviewed evidences. Based on this knowledge graph and specified parameters, cognitive behavioral paths are created. For each cognitve behavioral path, a prompt will be constructed based on a library of manually designed and verified prompt templates. The final prompt will be used with ChatGPT or any of LLM models to generate the Context. The Answer (the correct reference) values are derived from the cogniive behavioral paths and the engineering of the context. Please refer to the generate datasets for specific examples.", "## Troubleshooting\nCodes were verfied to be running properly. If you run into issues, please first make sure that you have all dependencies installed. If you use online LLMs to generate new datasets, please make sure you have the API key(s) imported properly into your environment. Some online LLM providers will terminate/thorttle the LLM API performance by the \"request per minute\" rate which can cause the script to crash or run slower than expected.", "## Release notes\n\n * Version 0.1 is the initial version with some parts being under-developed.", "### Known Issues\n\n * LLMs may not return responses in the expected format although the reponses may be correct. Please feel free to modify the question template as needed. However, due to the flexible nature of LLM responses, there is always a chance a response is not in the expected format.\n * Some LLMs may provide wrong answers to the same question if you as them the same questions repeatedly. It could be a programmed \"trick\" from the LLM maker meaning if you ask a question the first time (and the LLM provided you with a correct answer) and you ask the same question again, the LLM may think that you did not like the first answer and will try to pick a different answer.", "### Report Issues\n\nYou can use GitHub issues to report issues and I will fix the issues that are on my end and may try to use prompt engineering to fix issues that are on the LLMs' end." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_doc\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_doc\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_docidx\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_docidx\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_doc_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_doc_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_recite_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_recite_qa\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_reciteonly_qa\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"lmind_hotpot_train8000_eval7405_v1_reciteonly_qa\"\n\nMore Information needed" ]

[ "task_categories:audio-to-audio", "language:ja", "license:other", "music", "singing voice", "a cappella", "region:us" ]

[]

[ "ja" ]

[]

[ "TAGS\n#task_categories-audio-to-audio #language-Japanese #license-other #music #singing voice #a cappella #region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"cauhoiphapluat_small\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"cauhoiphapluat_small\"\n\nMore Information needed" ]

[ "license:gpl-3.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-gpl-3.0 #region-us \n" ]

[ "license:mit", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-mit #region-us \n" ]

[ "license:mit", "region:us" ]

[]

[]

[ "### varint dataset\n\npath = /varints\n\n\n[(int32, varint bytes)]", "### varlong dataset\n\npath = /varlosgs\n\n\n[(int64, varlong bytes)]" ]

[ "TAGS\n#license-mit #region-us \n", "### varint dataset\n\npath = /varints\n\n\n[(int32, varint bytes)]", "### varlong dataset\n\npath = /varlosgs\n\n\n[(int64, varlong bytes)]" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[ "# How to use it" ]

[ "TAGS\n#license-apache-2.0 #region-us \n", "# How to use it" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "size_categories:10K<n<100K", "language:en", "license:openrail", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Out-of-Scope Use", "## Dataset Structure", "## Dataset Creation", "### Curation Rationale", "### Source Data", "#### Data Collection and Processing", "#### Who are the source data producers?", "### Annotations [optional]", "#### Annotation process", "#### Who are the annotators?", "#### Personal and Sensitive Information", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "TAGS\n#size_categories-10K<n<100K #language-English #license-openrail #region-us \n", "# Dataset Card for Dataset Name\n\n\n\nThis dataset card aims to be a base template for new datasets. It has been generated using this raw template.", "## Dataset Details", "### Dataset Description\n\n\n\n\n\n- Curated by: \n- Funded by [optional]: \n- Shared by [optional]: \n- Language(s) (NLP): \n- License:", "### Dataset Sources [optional]\n\n\n\n- Repository: \n- Paper [optional]: \n- Demo [optional]:", "## Uses", "### Direct Use", "### Out-of-Scope Use", "## Dataset Structure", "## Dataset Creation", "### Curation Rationale", "### Source Data", "#### Data Collection and Processing", "#### Who are the source data producers?", "### Annotations [optional]", "#### Annotation process", "#### Who are the annotators?", "#### Personal and Sensitive Information", "## Bias, Risks, and Limitations", "### Recommendations\n\n\n\nUsers should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations.\n\n[optional]\n\n\n\nBibTeX:\n\n\n\nAPA:", "## Glossary [optional]", "## More Information [optional]", "## Dataset Card Authors [optional]", "## Dataset Card Contact" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[]

[ "TAGS\n#license-apache-2.0 #region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "task_categories:text-generation", "size_categories:1K<n<10K", "language:en", "license:pddl", "climate", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-text-generation #size_categories-1K<n<10K #language-English #license-pddl #climate #region-us \n" ]

[ "task_categories:graph-ml", "size_categories:1K<n<10K", "license:cc", "art", "arxiv:2210.02016", "arxiv:1909.13021", "region:us" ]

[ "2210.02016", "1909.13021" ]

[]

[]

[ "TAGS\n#task_categories-graph-ml #size_categories-1K<n<10K #license-cc #art #arxiv-2210.02016 #arxiv-1909.13021 #region-us \n" ]

[ "license:apache-2.0", "vision", "checkpoints", "residual-networks", "arxiv:2310.08287", "region:us" ]

[ "2310.08287" ]

[]

[ "## Usage", "### Tar\n\nJust untar the desired models. This will create a new folder containing the models saved as safetensors.", "### TorchUncertainty\n\nTo load or train models, start by downloading TorchUncertainty - Documentation.\nInstall the desired version of PyTorch and torchvision, for instance with:\n\n\n\nThen, install TorchUncertainty via pip:", "### Loading models\nThe functions to load the models are available in 'scripts'.\n\nAny questions? Please feel free to ask in the GitHub Issues or on our Discord server." ]

[ "TAGS\n#license-apache-2.0 #vision #checkpoints #residual-networks #arxiv-2310.08287 #region-us \n", "## Usage", "### Tar\n\nJust untar the desired models. This will create a new folder containing the models saved as safetensors.", "### TorchUncertainty\n\nTo load or train models, start by downloading TorchUncertainty - Documentation.\nInstall the desired version of PyTorch and torchvision, for instance with:\n\n\n\nThen, install TorchUncertainty via pip:", "### Loading models\nThe functions to load the models are available in 'scripts'.\n\nAny questions? Please feel free to ask in the GitHub Issues or on our Discord server." ]

[ "task_categories:graph-ml", "size_categories:1K<n<10K", "license:cc", "art", "arxiv:2210.02016", "arxiv:1909.13021", "region:us" ]

[ "2210.02016", "1909.13021" ]

[]

[]

[ "TAGS\n#task_categories-graph-ml #size_categories-1K<n<10K #license-cc #art #arxiv-2210.02016 #arxiv-1909.13021 #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"find_marker_both_sent_train_400_eval_40_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "language:nb", "region:us" ]

[]

[ "nb" ]

[]

[ "TAGS\n#language-Norwegian Bokmål #region-us \n" ]

[ "size_categories:10K<n<100K", "language:en", "license:cc-by-4.0", "Kubernetes", "Stack Overflow", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#size_categories-10K<n<100K #language-English #license-cc-by-4.0 #Kubernetes #Stack Overflow #region-us \n" ]

[ "task_categories:question-answering", "task_categories:text2text-generation", "size_categories:10K<n<100K", "language:ru", "qa", "qg", "aaqg", "instruct", "question-answering", "question-generation", "region:us" ]

[]

[ "ru" ]

[ "### Description\n\nThis is a dataset created for training Russian-language Seq2Seq and CLM models primarily for tasks related to Closed-Domain QA.\n\nThe dataset includes 3 main tasks:\n1. AAQG (Answer-Aware Question Answering) - generation of questions based on context, provided the answer is known\n2. QG - generating questions based on context, without a known answer\n3. QA - the standard task of answering a question based on context.\n\nAAQG, QG, QA tasks are generated based on regular datasets for which the context, question and correct answer are known. They are generated in a ratio of 0.4, 0.3 and 0.3, respectively.\n\nList of datasets used to compile this dataset:\n1. sberquad\n2. russian_super_glue/muserc\n3. russian_super_glue/danetqa\n\nPrompts used for QA tasks:", "### Authors\n- Sergei Bratchikov (https://t.me/nlpwanderer)" ]

[ "TAGS\n#task_categories-question-answering #task_categories-text2text-generation #size_categories-10K<n<100K #language-Russian #qa #qg #aaqg #instruct #question-answering #question-generation #region-us \n", "### Description\n\nThis is a dataset created for training Russian-language Seq2Seq and CLM models primarily for tasks related to Closed-Domain QA.\n\nThe dataset includes 3 main tasks:\n1. AAQG (Answer-Aware Question Answering) - generation of questions based on context, provided the answer is known\n2. QG - generating questions based on context, without a known answer\n3. QA - the standard task of answering a question based on context.\n\nAAQG, QG, QA tasks are generated based on regular datasets for which the context, question and correct answer are known. They are generated in a ratio of 0.4, 0.3 and 0.3, respectively.\n\nList of datasets used to compile this dataset:\n1. sberquad\n2. russian_super_glue/muserc\n3. russian_super_glue/danetqa\n\nPrompts used for QA tasks:", "### Authors\n- Sergei Bratchikov (https://t.me/nlpwanderer)" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "language:ko", "region:us" ]

[]

[ "ko" ]

[ "# Dataset Card for \"ko_elo_arena_0207\"\n\nMore Information needed" ]

[ "TAGS\n#language-Korean #region-us \n", "# Dataset Card for \"ko_elo_arena_0207\"\n\nMore Information needed" ]

[ "task_categories:video-classification", "task_categories:image-classification", "task_categories:image-to-video", "language:en", "license:cc-by-nc-nd-4.0", "code", "finance", "legal", "webdataset", "region:us" ]

[]

[ "en" ]

[ "# Biometric Attack Dataset", "# The dataset is created on the basis of Anti Spoofing Real Dataset\n\nWe suggest you the dataset similar to CelebA Dataset but with photos of real people, additionally the dataset for face anti spoofing and face recognition includes not only images, but videos of the individuals!\n\nThe videos were gathered by capturing faces of genuine individuals presenting spoofs, using facial presentations. Our dataset proposes a novel approach that learns and detects spoofing techniques, extracting features from the genuine facial images to prevent the capturing of such information by fake users. \n\nThe dataset contains images and videos of real humans with various resolutions, views, and colors, making it a comprehensive resource for researchers working on anti-spoofing technologies.", "### People in the dataset\n\n![](URL", "### Types of files in the dataset:\n- photo - selfie of the person \n- video - real video of the person \n\nOur dataset also explores the use of neural architectures, such as deep neural networks, to facilitate the identification of distinguishing patterns and textures in different regions of the face, increasing the accuracy and generalizability of the anti-spoofing models.", "# For Commercial Usage: Full version of the dataset includes 140,000 files, leave a request on TrainingData to buy the dataset", "### Metadata for the full dataset:\n- assignment_id - unique identifier of the media file\n- worker_id - unique identifier of the person\n- age - age of the person\n- true_gender - gender of the person\n- country - country of the person\n- ethnicity - ethnicity of the person\n- video_extension - video extensions in the dataset\n- video_resolution - video resolution in the dataset\n- video_duration - video duration in the dataset\n- video_fps - frames per second for video in the dataset\n- photo_extension - photo extensions in the dataset\n- photo_resolution - photo resolution in the dataset\n\n![](URL", "# Buy the Dataset: This is just an example of the data. Leave a request on URL to learn about the price and buy the dataset", "# Content\nThe dataset includes 2 folders:\n- video - real videos of the people,\n- photo - selfies of the same people from the previous folder", "### File with the extension .csv\n- id: id of the person,\n- photo: link to access the photo,\n- video: link to access the video", "## TrainingData provides high-quality data annotation tailored to your needs\n\nMore datasets in TrainingData's Kaggle account: <URL\n\nTrainingData's GitHub: URL\n\n*keywords: liveness detection systems, liveness detection dataset, biometric dataset, biometric data dataset, biometric system attacks, anti-spoofing dataset, face liveness detection, deep learning dataset, face spoofing database, face anti-spoofing, ibeta dataset, face anti spoofing, large-scale face anti spoofing, rich annotations anti spoofing dataset*" ]

[ "TAGS\n#task_categories-video-classification #task_categories-image-classification #task_categories-image-to-video #language-English #license-cc-by-nc-nd-4.0 #code #finance #legal #webdataset #region-us \n", "# Biometric Attack Dataset", "# The dataset is created on the basis of Anti Spoofing Real Dataset\n\nWe suggest you the dataset similar to CelebA Dataset but with photos of real people, additionally the dataset for face anti spoofing and face recognition includes not only images, but videos of the individuals!\n\nThe videos were gathered by capturing faces of genuine individuals presenting spoofs, using facial presentations. Our dataset proposes a novel approach that learns and detects spoofing techniques, extracting features from the genuine facial images to prevent the capturing of such information by fake users. \n\nThe dataset contains images and videos of real humans with various resolutions, views, and colors, making it a comprehensive resource for researchers working on anti-spoofing technologies.", "### People in the dataset\n\n![](URL", "### Types of files in the dataset:\n- photo - selfie of the person \n- video - real video of the person \n\nOur dataset also explores the use of neural architectures, such as deep neural networks, to facilitate the identification of distinguishing patterns and textures in different regions of the face, increasing the accuracy and generalizability of the anti-spoofing models.", "# For Commercial Usage: Full version of the dataset includes 140,000 files, leave a request on TrainingData to buy the dataset", "### Metadata for the full dataset:\n- assignment_id - unique identifier of the media file\n- worker_id - unique identifier of the person\n- age - age of the person\n- true_gender - gender of the person\n- country - country of the person\n- ethnicity - ethnicity of the person\n- video_extension - video extensions in the dataset\n- video_resolution - video resolution in the dataset\n- video_duration - video duration in the dataset\n- video_fps - frames per second for video in the dataset\n- photo_extension - photo extensions in the dataset\n- photo_resolution - photo resolution in the dataset\n\n![](URL", "# Buy the Dataset: This is just an example of the data. Leave a request on URL to learn about the price and buy the dataset", "# Content\nThe dataset includes 2 folders:\n- video - real videos of the people,\n- photo - selfies of the same people from the previous folder", "### File with the extension .csv\n- id: id of the person,\n- photo: link to access the photo,\n- video: link to access the video", "## TrainingData provides high-quality data annotation tailored to your needs\n\nMore datasets in TrainingData's Kaggle account: <URL\n\nTrainingData's GitHub: URL\n\n*keywords: liveness detection systems, liveness detection dataset, biometric dataset, biometric data dataset, biometric system attacks, anti-spoofing dataset, face liveness detection, deep learning dataset, face spoofing database, face anti-spoofing, ibeta dataset, face anti spoofing, large-scale face anti spoofing, rich annotations anti spoofing dataset*" ]

[ "task_categories:text-generation", "task_categories:text-classification", "task_categories:text2text-generation", "size_categories:1M<n<10M", "language:nl", "license:cc-by-nc-4.0", "region:us" ]

[]

[ "nl" ]

[]

[ "TAGS\n#task_categories-text-generation #task_categories-text-classification #task_categories-text2text-generation #size_categories-1M<n<10M #language-Dutch #license-cc-by-nc-4.0 #region-us \n" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Medical textbook question answering\n\nThis corpus contains multiple-choice quiz questions for 13 commonly-used medical textbooks. The questions are designed to examine understanding of the main concepts in the textbooks. \n\nThe QA data is used to evaluate knowledge learning of language models in the following paper:\n\n- Paper: Conditional language learning with context", "### Data Splits\n\n- subjects: anatomy, biochemistry, cell biology, gynecology, histology, immunology, neurology, obstentrics, pathology, pediatrics, pharmacology, physiology, psychiatry\n\n- 500 questions for each subject", "## Dataset Creation\n\nQuestion and answers are generated by GPT-4 given excerpts from the textbooks. Refer to the paper for the instructions used to generate the questions." ]

[ "TAGS\n#region-us \n", "# Medical textbook question answering\n\nThis corpus contains multiple-choice quiz questions for 13 commonly-used medical textbooks. The questions are designed to examine understanding of the main concepts in the textbooks. \n\nThe QA data is used to evaluate knowledge learning of language models in the following paper:\n\n- Paper: Conditional language learning with context", "### Data Splits\n\n- subjects: anatomy, biochemistry, cell biology, gynecology, histology, immunology, neurology, obstentrics, pathology, pediatrics, pharmacology, physiology, psychiatry\n\n- 500 questions for each subject", "## Dataset Creation\n\nQuestion and answers are generated by GPT-4 given excerpts from the textbooks. Refer to the paper for the instructions used to generate the questions." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"traxxas5\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"traxxas5\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"ExeBench-Eval-tiny-gpt3.5-result\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"ExeBench-Eval-tiny-gpt3.5-result\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "license:apache-2.0", "region:us" ]

[]

[]

[ "# Dataset Card for Dataset Name\n\n\n\nThis Dataset was generated by NyX AI for their roleplay Model based on llama-2-7b. It contains a collection of fictional scenarios and dialogues intended for use in roleplaying applications." ]

[ "TAGS\n#license-apache-2.0 #region-us \n", "# Dataset Card for Dataset Name\n\n\n\nThis Dataset was generated by NyX AI for their roleplay Model based on llama-2-7b. It contains a collection of fictional scenarios and dialogues intended for use in roleplaying applications." ]

[ "region:us" ]

[]

[]

[]

[ "TAGS\n#region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_first_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_first_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_last_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_last_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_no_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_full_passage_no_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_first_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_first_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_last_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_last_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_no_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_title_v5_full_recite_ans_sent_no_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_first_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_first_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_last_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_last_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_no_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_full_passage_no_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_first_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_first_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_last_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_last_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_no_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_wrong_title_v5_full_recite_ans_sent_no_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_4\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_random_permute_rerun_8\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_first_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_first_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_last_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_last_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_no_permute_rerun\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_full_passage_no_permute_rerun\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_ans_sent_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_ans_sent_random_permute_rerun_1\"\n\nMore Information needed" ]

[ "task_categories:text-classification", "size_categories:10K<n<100K", "language:en", "Personality", "Reddit", "Social Media", "Personality Prediction", "Large Language Models ", "Automated Personality Prediction", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-text-classification #size_categories-10K<n<100K #language-English #Personality #Reddit #Social Media #Personality Prediction #Large Language Models #Automated Personality Prediction #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"squad_qa_num_v5_full_recite_ans_sent_random_permute_rerun_2\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"squad_qa_num_v5_full_recite_ans_sent_random_permute_rerun_2\"\n\nMore Information needed" ]