Datasets:

---

ftopal

/

huggingface-datasets-processed

like 0

[ "task_categories:conversational", "size_categories:n<1K", "language:en", "license:openrail", "medical", "therapy", "conversations", "counseling", "dialogues", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for Dataset Name\n\n\n\nConverted the AnnoMI motivational interviewing dataset into sharegpt format. \nIt is the first public collection of expert-annotated MI transcripts. Source.", "## Dataset Details", "### Dataset Description\n\n\nAnnoMI, containing 133 faithfully transcribed and expert-annotated demonstrations of high- and low-quality motivational interviewing (MI), an effective therapy strategy that evokes client motivation for positive change.\n\nSample conversation number 40, regarding drug use:", "### Dataset Sources\n\n\n\n- Repository: [URL\n- Paper [optional]: [URL", "## Uses\n\n\nTraining on longer conversations and medical advice.", "### Direct Use", "### Out-of-Scope Use", "## Dataset Structure\n\n\nSharegpt format to allow for long conversations back and forth.\n\ntherapist is gpt\n\nclient is human\n\nid is a concatenation of:\n\n- transcript_id: the unique numerical identifier of the conversation/transcript where this utterance belongs. Note that this identifier is NOT used for ordering, and it is only to distinguish between different conversations in the dataset.\n- video_url: the URL of the original video of the conversation/transcript where this utterance belongs.\n- topic: the topic(s) of the conversation/transcript where this utterance belongs.", "## Dataset Creation", "### Curation Rationale\n\n\n\nDespite the remarkable growth of research in recent years on the analysis of counselling conversations through natural language processing methods, the potential of this field has been greatly limited by the lack of access to publicly available therapy dialogues, especially those with expert annotations.", "#### Personal and Sensitive Information\n\n\n\nIt is anonymized.", "## 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\n@INPROCEEDINGS{9746035,\n author={Wu, Zixiu and Balloccu, Simone and Kumar, Vivek and Helaoui, Rim and Reiter, Ehud and Reforgiato Recupero, Diego and Riboni, Daniele},\n booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, \n title={Anno-MI: A Dataset of Expert-Annotated Counselling Dialogues}, \n year={2022},\n volume={},\n number={},\n pages={6177-6181},\n doi={10.1109/ICASSP43922.2022.9746035}}\n}", "## Dataset Card Contact\n\nToon Beerten (toon@URL)" ]

[ "TAGS\n#task_categories-conversational #size_categories-n<1K #language-English #license-openrail #medical #therapy #conversations #counseling #dialogues #region-us \n", "# Dataset Card for Dataset Name\n\n\n\nConverted the AnnoMI motivational interviewing dataset into sharegpt format. \nIt is the first public collection of expert-annotated MI transcripts. Source.", "## Dataset Details", "### Dataset Description\n\n\nAnnoMI, containing 133 faithfully transcribed and expert-annotated demonstrations of high- and low-quality motivational interviewing (MI), an effective therapy strategy that evokes client motivation for positive change.\n\nSample conversation number 40, regarding drug use:", "### Dataset Sources\n\n\n\n- Repository: [URL\n- Paper [optional]: [URL", "## Uses\n\n\nTraining on longer conversations and medical advice.", "### Direct Use", "### Out-of-Scope Use", "## Dataset Structure\n\n\nSharegpt format to allow for long conversations back and forth.\n\ntherapist is gpt\n\nclient is human\n\nid is a concatenation of:\n\n- transcript_id: the unique numerical identifier of the conversation/transcript where this utterance belongs. Note that this identifier is NOT used for ordering, and it is only to distinguish between different conversations in the dataset.\n- video_url: the URL of the original video of the conversation/transcript where this utterance belongs.\n- topic: the topic(s) of the conversation/transcript where this utterance belongs.", "## Dataset Creation", "### Curation Rationale\n\n\n\nDespite the remarkable growth of research in recent years on the analysis of counselling conversations through natural language processing methods, the potential of this field has been greatly limited by the lack of access to publicly available therapy dialogues, especially those with expert annotations.", "#### Personal and Sensitive Information\n\n\n\nIt is anonymized.", "## 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\n@INPROCEEDINGS{9746035,\n author={Wu, Zixiu and Balloccu, Simone and Kumar, Vivek and Helaoui, Rim and Reiter, Ehud and Reforgiato Recupero, Diego and Riboni, Daniele},\n booktitle={ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, \n title={Anno-MI: A Dataset of Expert-Annotated Counselling Dialogues}, \n year={2022},\n volume={},\n number={},\n pages={6177-6181},\n doi={10.1109/ICASSP43922.2022.9746035}}\n}", "## Dataset Card Contact\n\nToon Beerten (toon@URL)" ]

[ 53, 45, 4, 62, 22, 12, 4, 9, 145, 5, 66, 13, 10, 202, 14 ]

[ "passage: TAGS\n#task_categories-conversational #size_categories-n<1K #language-English #license-openrail #medical #therapy #conversations #counseling #dialogues #region-us \n# Dataset Card for Dataset Name\n\n\n\nConverted the AnnoMI motivational interviewing dataset into sharegpt format. \nIt is the first public collection of expert-annotated MI transcripts. Source.## Dataset Details### Dataset Description\n\n\nAnnoMI, containing 133 faithfully transcribed and expert-annotated demonstrations of high- and low-quality motivational interviewing (MI), an effective therapy strategy that evokes client motivation for positive change.\n\nSample conversation number 40, regarding drug use:### Dataset Sources\n\n\n\n- Repository: [URL\n- Paper [optional]: [URL## Uses\n\n\nTraining on longer conversations and medical advice.### Direct Use### Out-of-Scope Use## Dataset Structure\n\n\nSharegpt format to allow for long conversations back and forth.\n\ntherapist is gpt\n\nclient is human\n\nid is a concatenation of:\n\n- transcript_id: the unique numerical identifier of the conversation/transcript where this utterance belongs. Note that this identifier is NOT used for ordering, and it is only to distinguish between different conversations in the dataset.\n- video_url: the URL of the original video of the conversation/transcript where this utterance belongs.\n- topic: the topic(s) of the conversation/transcript where this utterance belongs.## Dataset Creation### Curation Rationale\n\n\n\nDespite the remarkable growth of research in recent years on the analysis of counselling conversations through natural language processing methods, the potential of this field has been greatly limited by the lack of access to publicly available therapy dialogues, especially those with expert annotations.#### Personal and Sensitive Information\n\n\n\nIt is anonymized.## Bias, Risks, and Limitations" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of Deathsquad10/TinyLlama-repeat\n\n\n\nDataset automatically created during the evaluation run of model Deathsquad10/TinyLlama-repeat on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T16:33:40.382294(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of Deathsquad10/TinyLlama-repeat\n\n\n\nDataset automatically created during the evaluation run of model Deathsquad10/TinyLlama-repeat on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T16:33:40.382294(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 187, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of Deathsquad10/TinyLlama-repeat\n\n\n\nDataset automatically created during the evaluation run of model Deathsquad10/TinyLlama-repeat on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T16:33:40.382294(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "region:us" ]

[]

[]

[]

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

[ 6 ]

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

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of notbdq/alooowso\n\n\n\nDataset automatically created during the evaluation run of model notbdq/alooowso on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T10:34:49.723168(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of notbdq/alooowso\n\n\n\nDataset automatically created during the evaluation run of model notbdq/alooowso on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T10:34:49.723168(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 177, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of notbdq/alooowso\n\n\n\nDataset automatically created during the evaluation run of model notbdq/alooowso on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T10:34:49.723168(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "region:us" ]

[]

[]

[ "# Guanaco-1k: Lazy Llama 2 Formatting\n\nThis is a subset (1000 samples) of the excellent 'timdettmers/openassistant-guanaco' dataset, processed to match Llama 2's prompt format as described in this article. It was created using the following colab notebook.\n\nUseful if you don't want to reformat it by yourself (e.g., using a script). It was designed for this article about fine-tuning a Llama 2 (chat) model in a Google Colab." ]

[ "TAGS\n#region-us \n", "# Guanaco-1k: Lazy Llama 2 Formatting\n\nThis is a subset (1000 samples) of the excellent 'timdettmers/openassistant-guanaco' dataset, processed to match Llama 2's prompt format as described in this article. It was created using the following colab notebook.\n\nUseful if you don't want to reformat it by yourself (e.g., using a script). It was designed for this article about fine-tuning a Llama 2 (chat) model in a Google Colab." ]

[ 6, 120 ]

[ "passage: TAGS\n#region-us \n# Guanaco-1k: Lazy Llama 2 Formatting\n\nThis is a subset (1000 samples) of the excellent 'timdettmers/openassistant-guanaco' dataset, processed to match Llama 2's prompt format as described in this article. It was created using the following colab notebook.\n\nUseful if you don't want to reformat it by yourself (e.g., using a script). It was designed for this article about fine-tuning a Llama 2 (chat) model in a Google Colab." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of CausalLM/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv\n\n\n\nDataset automatically created during the evaluation run of model CausalLM/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T10:49:51.922968(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of CausalLM/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv\n\n\n\nDataset automatically created during the evaluation run of model CausalLM/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T10:49:51.922968(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 223, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of CausalLM/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv\n\n\n\nDataset automatically created during the evaluation run of model CausalLM/72B-preview-canary-llamafied-qwen-llamafy-unbias-qkv on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T10:49:51.922968(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "region:us" ]

[]

[]

[]

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

[ 6 ]

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

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of AA051610/testtest\n\n\n\nDataset automatically created during the evaluation run of model AA051610/testtest on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T11:01:46.425546(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of AA051610/testtest\n\n\n\nDataset automatically created during the evaluation run of model AA051610/testtest on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T11:01:46.425546(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 175, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of AA051610/testtest\n\n\n\nDataset automatically created during the evaluation run of model AA051610/testtest on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T11:01:46.425546(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "task_categories:automatic-speech-recognition", "language:hy", "region:us" ]

[]

[ "hy" ]

[ "# Dataset Card for HyVoxpopuli", "## Table of Contents\n- Table of Contents\n- Dataset Description\n - Dataset Summary\n - Supported Tasks and Leaderboards\n - Languages\n- Dataset Structure\n - Data Instances\n - Data Fields\n - Data Splits\n- Dataset Creation\n - Curation Rationale\n - Source Data\n - Annotations\n - Personal and Sensitive Information\n- Considerations for Using the Data\n - Social Impact of Dataset\n - Discussion of Biases\n - Other Known Limitations\n- Additional Information\n - Dataset Curators\n - Licensing Information\n - Citation Information\n - Contributions", "## Dataset Description", "### Dataset Summary", "### Example usage\n\nHyVoxPopuli contains labelled data for 18 languages. To load a specific language pass its name as a config name:", "### Supported Tasks and Leaderboards\n\n* automatic-speech-recognition: The dataset can be used to train a model for Automatic Speech Recognition (ASR). The model is presented with an audio file and asked to transcribe the audio file to written text. The most common evaluation metric is the word error rate (WER).", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n* 'audio_id' (string) - id of audio segment\n* 'audio' (datasets.Audio) - a dictionary containing the path to the audio, the decoded audio array, and the sampling rate. In non-streaming mode (default), the path points to the locally extracted audio. In streaming mode, the path is the relative path of an audio inside its archive (as files are not downloaded and extracted locally).\n* 'raw_text' (string) - original (orthographic) audio segment text\n* 'normalized_text' (string) - normalized audio segment transcription\n* 'gender' (string) - gender of speaker\n* 'speaker_id' (string) - id of speaker\n* 'is_gold_transcript' (bool) - ?\n* 'accent' (string) - type of accent, for example \"en_lt\", if applicable, else \"None\".", "### Data Splits\n\nAll configs contain data in three splits: train, validation and test.", "## Dataset Creation", "### Curation Rationale", "### Source Data\n\nThe raw data is collected from Գրքասեր site", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information", "## Considerations for Using the Data", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations", "## Additional Information", "### Dataset Curators", "### Licensing Information\n\n\n\n\n\nPlease cite this paper:" ]

[ "TAGS\n#task_categories-automatic-speech-recognition #language-Armenian #region-us \n", "# Dataset Card for HyVoxpopuli", "## Table of Contents\n- Table of Contents\n- Dataset Description\n - Dataset Summary\n - Supported Tasks and Leaderboards\n - Languages\n- Dataset Structure\n - Data Instances\n - Data Fields\n - Data Splits\n- Dataset Creation\n - Curation Rationale\n - Source Data\n - Annotations\n - Personal and Sensitive Information\n- Considerations for Using the Data\n - Social Impact of Dataset\n - Discussion of Biases\n - Other Known Limitations\n- Additional Information\n - Dataset Curators\n - Licensing Information\n - Citation Information\n - Contributions", "## Dataset Description", "### Dataset Summary", "### Example usage\n\nHyVoxPopuli contains labelled data for 18 languages. To load a specific language pass its name as a config name:", "### Supported Tasks and Leaderboards\n\n* automatic-speech-recognition: The dataset can be used to train a model for Automatic Speech Recognition (ASR). The model is presented with an audio file and asked to transcribe the audio file to written text. The most common evaluation metric is the word error rate (WER).", "## Dataset Structure", "### Data Instances", "### Data Fields\n\n* 'audio_id' (string) - id of audio segment\n* 'audio' (datasets.Audio) - a dictionary containing the path to the audio, the decoded audio array, and the sampling rate. In non-streaming mode (default), the path points to the locally extracted audio. In streaming mode, the path is the relative path of an audio inside its archive (as files are not downloaded and extracted locally).\n* 'raw_text' (string) - original (orthographic) audio segment text\n* 'normalized_text' (string) - normalized audio segment transcription\n* 'gender' (string) - gender of speaker\n* 'speaker_id' (string) - id of speaker\n* 'is_gold_transcript' (bool) - ?\n* 'accent' (string) - type of accent, for example \"en_lt\", if applicable, else \"None\".", "### Data Splits\n\nAll configs contain data in three splits: train, validation and test.", "## Dataset Creation", "### Curation Rationale", "### Source Data\n\nThe raw data is collected from Գրքասեր site", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### Annotation process", "#### Who are the annotators?", "### Personal and Sensitive Information", "## Considerations for Using the Data", "### Social Impact of Dataset", "### Discussion of Biases", "### Other Known Limitations", "## Additional Information", "### Dataset Curators", "### Licensing Information\n\n\n\n\n\nPlease cite this paper:" ]

[ 28, 10, 125, 4, 6, 34, 76, 6, 6, 216, 23, 5, 7, 15, 10, 10, 5, 5, 9, 8, 8, 7, 8, 7, 5, 6, 11 ]

[ "passage: TAGS\n#task_categories-automatic-speech-recognition #language-Armenian #region-us \n# Dataset Card for HyVoxpopuli## Table of Contents\n- Table of Contents\n- Dataset Description\n - Dataset Summary\n - Supported Tasks and Leaderboards\n - Languages\n- Dataset Structure\n - Data Instances\n - Data Fields\n - Data Splits\n- Dataset Creation\n - Curation Rationale\n - Source Data\n - Annotations\n - Personal and Sensitive Information\n- Considerations for Using the Data\n - Social Impact of Dataset\n - Discussion of Biases\n - Other Known Limitations\n- Additional Information\n - Dataset Curators\n - Licensing Information\n - Citation Information\n - Contributions## Dataset Description### Dataset Summary### Example usage\n\nHyVoxPopuli contains labelled data for 18 languages. To load a specific language pass its name as a config name:### Supported Tasks and Leaderboards\n\n* automatic-speech-recognition: The dataset can be used to train a model for Automatic Speech Recognition (ASR). The model is presented with an audio file and asked to transcribe the audio file to written text. The most common evaluation metric is the word error rate (WER).## Dataset Structure### Data Instances" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "size_categories:n<1K", "language:en", "not-for-all-audiences", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#size_categories-n<1K #language-English #not-for-all-audiences #region-us \n" ]

[ 29 ]

[ "passage: TAGS\n#size_categories-n<1K #language-English #not-for-all-audiences #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of sethuiyer/Dr_Samantha_7b_mistral\n\n\n\nDataset automatically created during the evaluation run of model sethuiyer/Dr_Samantha_7b_mistral on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T12:13:02.119831(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of sethuiyer/Dr_Samantha_7b_mistral\n\n\n\nDataset automatically created during the evaluation run of model sethuiyer/Dr_Samantha_7b_mistral on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T12:13:02.119831(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 189, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of sethuiyer/Dr_Samantha_7b_mistral\n\n\n\nDataset automatically created during the evaluation run of model sethuiyer/Dr_Samantha_7b_mistral on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T12:13:02.119831(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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]" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# 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#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" ]

[ 6, 34, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#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" ]

[ "size_categories:1M<n<10M", "not-for-all-audiences", "region:us" ]

[]

[]

[ "# Danbooru2023_metadata\n\nSize: 6,391,111 (6.39M)\n\nMetadata of posts from Danbooru, up to post '#7042183'.\n\nContains only active posts (see below). Also, child posts which have 'pixel-perfect_duplicate' were removed.", "## Columns\n\n'id, md5, created_at, updated_at, score, up_score, down_score, rating, image_width, image_height, file_ext, parent_id, duration, pixel_hash, tag_string_general, tag_string_character, tag_string_copyright, tag_string_artist, tag_string_meta'", "### Rating\n\n- 'g' (general): Completely safe for work.\n- 's' (sensitive): Probably not safe for work.\n- 'q' (questionable): Softcore erotica.\n- 'e' (explicit): Hardcore erotica. Definitely not safe for work.\n\nFor more information, see link", "## Specifics of Danbooru", "### Status\n\nEvery danbooru posts could be categorized to four types of status.\n\n1. Active: Posts that are approved by a moderator.\n2. Pending: Posts that are waiting to be approved. If a post is pending for more than 3 days without a moderator's approval, the post is deleted. \n3. Deleted: Posts that do not meet danbooru's standards. (Non-anime, low quality, etc)\n4. Banned: Posts that are copyright-claimed or contain off-limit content.\n\nTherefore, we should only use images from active posts. (Banned posts cannot be downloaded by normal users.)\n\nSadly, the Danbooru2021 dataset did not filter any deleted posts, and a lot of text-to-image models were trained with deleted posts.\n\nFrom a total of 7,042,183 posts, there are 224,522 banned posts and 370,595 deleted posts. Deleted posts take 5.26% of the total posts, which is not trivial. Therefore, this dataset have not included them.", "## Misc\n\n- If you aim to create your own anime-based image dataset from danbooru posts, you should definitely exclude posts with the following tags: 'cosplay_photo third-party_edit text-only_page'\n- Also consider excluding posts with the following tags, if you are aiming for high quality: 'photo_(medium) 3d no_humans comic'", "## Other Links\n\nLooking for parquet files?\n\nLooking for images? nyanko7/danbooru2023" ]

[ "TAGS\n#size_categories-1M<n<10M #not-for-all-audiences #region-us \n", "# Danbooru2023_metadata\n\nSize: 6,391,111 (6.39M)\n\nMetadata of posts from Danbooru, up to post '#7042183'.\n\nContains only active posts (see below). Also, child posts which have 'pixel-perfect_duplicate' were removed.", "## Columns\n\n'id, md5, created_at, updated_at, score, up_score, down_score, rating, image_width, image_height, file_ext, parent_id, duration, pixel_hash, tag_string_general, tag_string_character, tag_string_copyright, tag_string_artist, tag_string_meta'", "### Rating\n\n- 'g' (general): Completely safe for work.\n- 's' (sensitive): Probably not safe for work.\n- 'q' (questionable): Softcore erotica.\n- 'e' (explicit): Hardcore erotica. Definitely not safe for work.\n\nFor more information, see link", "## Specifics of Danbooru", "### Status\n\nEvery danbooru posts could be categorized to four types of status.\n\n1. Active: Posts that are approved by a moderator.\n2. Pending: Posts that are waiting to be approved. If a post is pending for more than 3 days without a moderator's approval, the post is deleted. \n3. Deleted: Posts that do not meet danbooru's standards. (Non-anime, low quality, etc)\n4. Banned: Posts that are copyright-claimed or contain off-limit content.\n\nTherefore, we should only use images from active posts. (Banned posts cannot be downloaded by normal users.)\n\nSadly, the Danbooru2021 dataset did not filter any deleted posts, and a lot of text-to-image models were trained with deleted posts.\n\nFrom a total of 7,042,183 posts, there are 224,522 banned posts and 370,595 deleted posts. Deleted posts take 5.26% of the total posts, which is not trivial. Therefore, this dataset have not included them.", "## Misc\n\n- If you aim to create your own anime-based image dataset from danbooru posts, you should definitely exclude posts with the following tags: 'cosplay_photo third-party_edit text-only_page'\n- Also consider excluding posts with the following tags, if you are aiming for high quality: 'photo_(medium) 3d no_humans comic'", "## Other Links\n\nLooking for parquet files?\n\nLooking for images? nyanko7/danbooru2023" ]

[ 27, 69, 91, 71, 7, 235, 87, 22 ]

[ "passage: TAGS\n#size_categories-1M<n<10M #not-for-all-audiences #region-us \n# Danbooru2023_metadata\n\nSize: 6,391,111 (6.39M)\n\nMetadata of posts from Danbooru, up to post '#7042183'.\n\nContains only active posts (see below). Also, child posts which have 'pixel-perfect_duplicate' were removed.## Columns\n\n'id, md5, created_at, updated_at, score, up_score, down_score, rating, image_width, image_height, file_ext, parent_id, duration, pixel_hash, tag_string_general, tag_string_character, tag_string_copyright, tag_string_artist, tag_string_meta'### Rating\n\n- 'g' (general): Completely safe for work.\n- 's' (sensitive): Probably not safe for work.\n- 'q' (questionable): Softcore erotica.\n- 'e' (explicit): Hardcore erotica. Definitely not safe for work.\n\nFor more information, see link## Specifics of Danbooru### Status\n\nEvery danbooru posts could be categorized to four types of status.\n\n1. Active: Posts that are approved by a moderator.\n2. Pending: Posts that are waiting to be approved. If a post is pending for more than 3 days without a moderator's approval, the post is deleted. \n3. Deleted: Posts that do not meet danbooru's standards. (Non-anime, low quality, etc)\n4. Banned: Posts that are copyright-claimed or contain off-limit content.\n\nTherefore, we should only use images from active posts. (Banned posts cannot be downloaded by normal users.)\n\nSadly, the Danbooru2021 dataset did not filter any deleted posts, and a lot of text-to-image models were trained with deleted posts.\n\nFrom a total of 7,042,183 posts, there are 224,522 banned posts and 370,595 deleted posts. Deleted posts take 5.26% of the total posts, which is not trivial. Therefore, this dataset have not included them." ]

[ "size_categories:10K<n<100K", "license:mit", "climate", "region:us" ]

[]

[]

[]

[ "TAGS\n#size_categories-10K<n<100K #license-mit #climate #region-us \n" ]

[ 27 ]

[ "passage: TAGS\n#size_categories-10K<n<100K #license-mit #climate #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of gqd/mistral-merge-7b\n\n\n\nDataset automatically created during the evaluation run of model gqd/mistral-merge-7b on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T12:41:19.293051(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of gqd/mistral-merge-7b\n\n\n\nDataset automatically created during the evaluation run of model gqd/mistral-merge-7b on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T12:41:19.293051(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 183, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of gqd/mistral-merge-7b\n\n\n\nDataset automatically created during the evaluation run of model gqd/mistral-merge-7b on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T12:41:19.293051(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 31 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_midscore_true\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 31 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_midscore_false\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 30 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_midscore_all\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 32 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_farestscore_true\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 32 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_farestscore_false\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 31 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_farestscore_all\"\n\nMore Information needed" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 16 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"mmlu_one_line\"\n\nMore Information needed" ]

[ "size_categories:1M<n<10M", "language:fa", "language:en", "license:gpl-3.0", "region:us" ]

[]

[ "fa", "en" ]

[]

[ "TAGS\n#size_categories-1M<n<10M #language-Persian #language-English #license-gpl-3.0 #region-us \n" ]

[ 35 ]

[ "passage: TAGS\n#size_categories-1M<n<10M #language-Persian #language-English #license-gpl-3.0 #region-us \n" ]

[ "task_categories:conversational", "task_categories:text-generation", "size_categories:10K<n<100K", "language:en", "license:apache-2.0", "chat", "alpaca", "gpt-3.5", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for ChatAlpaca 20K", "## ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions", "### Dataset Description\n\nChatAlpaca is a chat dataset that aims to help researchers develop models for instruction-following in multi-turn conversations. The dataset is an extension of the Stanford Alpaca data, which contains multi-turn instructions and their corresponding responses.\n\nChatAlpaca is developed by Chinese Information Processing Laboratory at the Institute of Software, Chinese Academy of Sciences (URL).\n\nIn this dataset, we use ChatGPT (GPT-3.5-turbo) to generate follow-up utterances and continue the conversation with ChatGPT. This process results in multi-turn conversations where the simulated user provides instructions and ChatGPT responds accordingly.", "### Dataset Structure\n\nThe data in this repository consists of a JSON file URL containing the multi-turn instruction-following conversations. Each item in the data file represents a different conversation between a simulated user and the ChatGPT. The data currently contains a total of 20,000 conversations.\n\nI've created 3 splits in the dataset:\n* original: all the data as available in the original URL\n* train: 19600 rows for training\n* test: 400 rows for testing or validating.\n* \nThe conversations in the dataset begin with an instruction, followed by a response from ChatGPT, which are from the Stanford Alpaca data. The conversation then continues with the user providing further instructions and ChatGPT responding accordingly.\n\nEach item in the dataset is a list of dictionaries, each dictionary contains the following fields:\n\n* id: int, identifier\n* messages: list, contains multiple dictionaries representing the conversations\n\nEach dictionary in the messages list contains the following fields:\n* role: str, with values \"user\" or \"assistant\";\n* content: str, the conversation content.\n\n! Note: In the original .json file the researchers used different field and variable names. \nI've renamed them to be consistent with the defacto standard as used for chat conversations.\n\nHere is an example of one conversation:", "### Discussion of Biases\n\nAs this dataset contains machine-generated texts it could contain potential biases. Verify and validate this for your specific usage scenario. \n\n!! Note. I've only put this dataset on HuggingFace since it was not available. All credits go to the original researchers and creators.\n\nPlease cite the original repository if you use the dataset." ]

[ "TAGS\n#task_categories-conversational #task_categories-text-generation #size_categories-10K<n<100K #language-English #license-apache-2.0 #chat #alpaca #gpt-3.5 #region-us \n", "# Dataset Card for ChatAlpaca 20K", "## ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions", "### Dataset Description\n\nChatAlpaca is a chat dataset that aims to help researchers develop models for instruction-following in multi-turn conversations. The dataset is an extension of the Stanford Alpaca data, which contains multi-turn instructions and their corresponding responses.\n\nChatAlpaca is developed by Chinese Information Processing Laboratory at the Institute of Software, Chinese Academy of Sciences (URL).\n\nIn this dataset, we use ChatGPT (GPT-3.5-turbo) to generate follow-up utterances and continue the conversation with ChatGPT. This process results in multi-turn conversations where the simulated user provides instructions and ChatGPT responds accordingly.", "### Dataset Structure\n\nThe data in this repository consists of a JSON file URL containing the multi-turn instruction-following conversations. Each item in the data file represents a different conversation between a simulated user and the ChatGPT. The data currently contains a total of 20,000 conversations.\n\nI've created 3 splits in the dataset:\n* original: all the data as available in the original URL\n* train: 19600 rows for training\n* test: 400 rows for testing or validating.\n* \nThe conversations in the dataset begin with an instruction, followed by a response from ChatGPT, which are from the Stanford Alpaca data. The conversation then continues with the user providing further instructions and ChatGPT responding accordingly.\n\nEach item in the dataset is a list of dictionaries, each dictionary contains the following fields:\n\n* id: int, identifier\n* messages: list, contains multiple dictionaries representing the conversations\n\nEach dictionary in the messages list contains the following fields:\n* role: str, with values \"user\" or \"assistant\";\n* content: str, the conversation content.\n\n! Note: In the original .json file the researchers used different field and variable names. \nI've renamed them to be consistent with the defacto standard as used for chat conversations.\n\nHere is an example of one conversation:", "### Discussion of Biases\n\nAs this dataset contains machine-generated texts it could contain potential biases. Verify and validate this for your specific usage scenario. \n\n!! Note. I've only put this dataset on HuggingFace since it was not available. All credits go to the original researchers and creators.\n\nPlease cite the original repository if you use the dataset." ]

[ 61, 11, 21, 154, 312, 89 ]

[ "passage: TAGS\n#task_categories-conversational #task_categories-text-generation #size_categories-10K<n<100K #language-English #license-apache-2.0 #chat #alpaca #gpt-3.5 #region-us \n# Dataset Card for ChatAlpaca 20K## ChatAlpaca: A Multi-Turn Dialogue Corpus based on Alpaca Instructions### Dataset Description\n\nChatAlpaca is a chat dataset that aims to help researchers develop models for instruction-following in multi-turn conversations. The dataset is an extension of the Stanford Alpaca data, which contains multi-turn instructions and their corresponding responses.\n\nChatAlpaca is developed by Chinese Information Processing Laboratory at the Institute of Software, Chinese Academy of Sciences (URL).\n\nIn this dataset, we use ChatGPT (GPT-3.5-turbo) to generate follow-up utterances and continue the conversation with ChatGPT. This process results in multi-turn conversations where the simulated user provides instructions and ChatGPT responds accordingly." ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

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

[]

[]

[ "# Information\n\nThis is a reformatted version of the HumanEval dataset" ]

[ "TAGS\n#license-mit #region-us \n", "# Information\n\nThis is a reformatted version of the HumanEval dataset" ]

[ 11, 16 ]

[ "passage: TAGS\n#license-mit #region-us \n# Information\n\nThis is a reformatted version of the HumanEval dataset" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "size_categories:n<1K", "language:en", "DPO", "preference", "rlhf", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#size_categories-n<1K #language-English #DPO #preference #rlhf #region-us \n" ]

[ 30 ]

[ "passage: TAGS\n#size_categories-n<1K #language-English #DPO #preference #rlhf #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 33 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_nearestscore_true\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 33 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_nearestscore_false\"\n\nMore Information needed" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_midscore_false_reversed\"\n\nMore Information needed" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:table-question-answering", "size_categories:n<1K", "license:apache-2.0", "climate", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-table-question-answering #size_categories-n<1K #license-apache-2.0 #climate #region-us \n" ]

[ 42 ]

[ "passage: TAGS\n#task_categories-table-question-answering #size_categories-n<1K #license-apache-2.0 #climate #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of cloudyu/Mixtral_7Bx5_MoE_30B\n\n\n\nDataset automatically created during the evaluation run of model cloudyu/Mixtral_7Bx5_MoE_30B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T14:21:39.499093(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of cloudyu/Mixtral_7Bx5_MoE_30B\n\n\n\nDataset automatically created during the evaluation run of model cloudyu/Mixtral_7Bx5_MoE_30B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T14:21:39.499093(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 195, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of cloudyu/Mixtral_7Bx5_MoE_30B\n\n\n\nDataset automatically created during the evaluation run of model cloudyu/Mixtral_7Bx5_MoE_30B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T14:21:39.499093(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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]" ]

[ "task_categories:text-generation", "task_categories:conversational", "task_categories:text2text-generation", "size_categories:10K<n<100K", "language:en", "license:cc-by-nc-sa-4.0", "code", "machine learning", "deep learning", "data science", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for DS Coder Instruct v2 Dataset\n\nChanges from v1:\n* Added WizardLM evol data science samples\n* Removed R samples from v2\n\n\n\nDS Coder is a dataset for instruction fine tuning of language models. It is a specialized dataset focusing only on\ndata science (eg. plotting, data wrangling, machine learnig models, deep learning, and numerical computations). The dataset contains code examples both in Python (R samples were removed in v2).\nThe goal of this dataset is to enable creation of small-scale, specialized language model assistants for data science projects.", "## Dataset Details", "### Dataset Description\n\n\nDS Coder instruct dataset contains *(input, instruction, output)* triplets. Instruction provides a task in the data science domain and output contains the code to solve the task.\nWhere available, it also contains *text* field holding Alpaca style input. Metadata, such as the programming language *(lang)* and topics *(topics)* are provided.\n*topics* lists the concepts used in the code (eg. ML, neural networs, plotting, etc.). This is determined based on which kinds of libraries the code uses. This field can be used\nto obtain subset of data for specific tasks, such as data vizualisation. \n\nAdditionally, the original data source is provided under the *dataset* field.", "### Dataset Sources\n\n\nDS Coder is filtered and preprocessed from a collection of publically available datasets on HuggingFace. All the sources all liste below with their corresponding links.\n\n- nickrosh/Evol-Instruct-Code-80k-v1: URL\n- TokenBender/code_instructions_122k_alpaca_style: URL\n- theblackcat102/evol-codealpaca-v1: URL\n- ise-uiuc/Magicoder-OSS-Instruct-75K: URL\n- WizardLM/WizardLM_evol_instruct_V2_196k: URL\n\nPlease make sure to cite the above mentioned source when using this dataset. You should visit these pages and look for specific usage instructions, if any.", "## Dataset Creation\n\n\n\nDS Coder was created by filtering and processing existing public datasets of *(instruction, code)* pairs. Source data was filtered to keep only code related to data science\napplications. The filtering was done using regex to gather code that uses popular data science libraries (eg. Matplotlib, Sklearn, PyTorch, etc.) in Python and R.\nThen, the data is further processed to filter out samples with very long or very short code. Code outputs with lots of comments and low amound of code were filtered out.\nAdditionally, samples with very long and very short instructions were also removed. \n\nAfter filtering, exact deduplication based on output code and input instruction was performed. After this process, roughly *16K* samples remain.\n\nMore specific description dataset processing is provided below.", "### Filtering\n\nThe first step of the filtering process is to gather all samples from source datasets that have code related to a data science application. To do so, regex filtering was\napplied to the *code* and *instruction* to filter out such samples. Regex filters mainly look for imports and usage of popular data science libraries, such as Pandas or PyTorch.\nData science code in Python as well as R are gathered. \n\nAfter gathering relevant code samples, further filtering based on line length, instruction length, alphanumeric ratio, and comment to code ratio are performed.\nCode filtering is similar to BigCode. Code filtering parameters shown below are derived from there.\nThis stage ensures that short, very, long and uninformative samples are removed. The script for filtering can be found in this repo\nEa0011/wrangler. You may use the filtering script to process additional datasets or tweak the params.\n\nParameters for filtering are listed below:\n\n- line_max: Maximum line length allowed is 1000 characters.\n \n- line_mean: Maximum mean line length allowed is 100 characters.\n\n- alpha_frac: Minimum fraction of alphanumeric characters allowed is 25%.\n\n- min_inst_size: Minimum instruction size in words is 5 words.\n\n- max_inst_size: Maximum instruction size in words is 1000 words.\n\n- max_threshold_comments: Maximum threshold for comment to code ratio is 80%.\n\n- min_threshold_comments: Minimum threshold for comment to code ratio is 1%.", "## Data Analysis\n\nThis section provides some analysis of the dataset. Code lengths and distribution of data science tasks are shown. Topic distribution shows\ndistribution of concepts used in the code. Some domains, such as plotting are underrepresanted compared to others. You may use the topics column to select samples for specific tasks.\n\n<img src=\"ds_dist.png\" width=\"60%\" />\n<img src=\"inst_len_total.png\" width=\"60%\"/>\n<img src=\"URL\" width=\"60%\" />\n\nAs there are data points from several data sources, it is also worth showing distributions across samples from different datasets. As it can be seen, some sources\ncontain short and concise samples while others contain verbose samples. Use this information to choose specific data source if needed.\n\n<img src=\"code_len.png\" width=\"60%\"/>\n<img src=\"inst_len.png\" width=\"60%\" />", "## Dataset Card Contact\n\nFor any suggestions and concerns please reach out to me: Ea0011" ]

[ "TAGS\n#task_categories-text-generation #task_categories-conversational #task_categories-text2text-generation #size_categories-10K<n<100K #language-English #license-cc-by-nc-sa-4.0 #code #machine learning #deep learning #data science #region-us \n", "# Dataset Card for DS Coder Instruct v2 Dataset\n\nChanges from v1:\n* Added WizardLM evol data science samples\n* Removed R samples from v2\n\n\n\nDS Coder is a dataset for instruction fine tuning of language models. It is a specialized dataset focusing only on\ndata science (eg. plotting, data wrangling, machine learnig models, deep learning, and numerical computations). The dataset contains code examples both in Python (R samples were removed in v2).\nThe goal of this dataset is to enable creation of small-scale, specialized language model assistants for data science projects.", "## Dataset Details", "### Dataset Description\n\n\nDS Coder instruct dataset contains *(input, instruction, output)* triplets. Instruction provides a task in the data science domain and output contains the code to solve the task.\nWhere available, it also contains *text* field holding Alpaca style input. Metadata, such as the programming language *(lang)* and topics *(topics)* are provided.\n*topics* lists the concepts used in the code (eg. ML, neural networs, plotting, etc.). This is determined based on which kinds of libraries the code uses. This field can be used\nto obtain subset of data for specific tasks, such as data vizualisation. \n\nAdditionally, the original data source is provided under the *dataset* field.", "### Dataset Sources\n\n\nDS Coder is filtered and preprocessed from a collection of publically available datasets on HuggingFace. All the sources all liste below with their corresponding links.\n\n- nickrosh/Evol-Instruct-Code-80k-v1: URL\n- TokenBender/code_instructions_122k_alpaca_style: URL\n- theblackcat102/evol-codealpaca-v1: URL\n- ise-uiuc/Magicoder-OSS-Instruct-75K: URL\n- WizardLM/WizardLM_evol_instruct_V2_196k: URL\n\nPlease make sure to cite the above mentioned source when using this dataset. You should visit these pages and look for specific usage instructions, if any.", "## Dataset Creation\n\n\n\nDS Coder was created by filtering and processing existing public datasets of *(instruction, code)* pairs. Source data was filtered to keep only code related to data science\napplications. The filtering was done using regex to gather code that uses popular data science libraries (eg. Matplotlib, Sklearn, PyTorch, etc.) in Python and R.\nThen, the data is further processed to filter out samples with very long or very short code. Code outputs with lots of comments and low amound of code were filtered out.\nAdditionally, samples with very long and very short instructions were also removed. \n\nAfter filtering, exact deduplication based on output code and input instruction was performed. After this process, roughly *16K* samples remain.\n\nMore specific description dataset processing is provided below.", "### Filtering\n\nThe first step of the filtering process is to gather all samples from source datasets that have code related to a data science application. To do so, regex filtering was\napplied to the *code* and *instruction* to filter out such samples. Regex filters mainly look for imports and usage of popular data science libraries, such as Pandas or PyTorch.\nData science code in Python as well as R are gathered. \n\nAfter gathering relevant code samples, further filtering based on line length, instruction length, alphanumeric ratio, and comment to code ratio are performed.\nCode filtering is similar to BigCode. Code filtering parameters shown below are derived from there.\nThis stage ensures that short, very, long and uninformative samples are removed. The script for filtering can be found in this repo\nEa0011/wrangler. You may use the filtering script to process additional datasets or tweak the params.\n\nParameters for filtering are listed below:\n\n- line_max: Maximum line length allowed is 1000 characters.\n \n- line_mean: Maximum mean line length allowed is 100 characters.\n\n- alpha_frac: Minimum fraction of alphanumeric characters allowed is 25%.\n\n- min_inst_size: Minimum instruction size in words is 5 words.\n\n- max_inst_size: Maximum instruction size in words is 1000 words.\n\n- max_threshold_comments: Maximum threshold for comment to code ratio is 80%.\n\n- min_threshold_comments: Minimum threshold for comment to code ratio is 1%.", "## Data Analysis\n\nThis section provides some analysis of the dataset. Code lengths and distribution of data science tasks are shown. Topic distribution shows\ndistribution of concepts used in the code. Some domains, such as plotting are underrepresanted compared to others. You may use the topics column to select samples for specific tasks.\n\n<img src=\"ds_dist.png\" width=\"60%\" />\n<img src=\"inst_len_total.png\" width=\"60%\"/>\n<img src=\"URL\" width=\"60%\" />\n\nAs there are data points from several data sources, it is also worth showing distributions across samples from different datasets. As it can be seen, some sources\ncontain short and concise samples while others contain verbose samples. Use this information to choose specific data source if needed.\n\n<img src=\"code_len.png\" width=\"60%\"/>\n<img src=\"inst_len.png\" width=\"60%\" />", "## Dataset Card Contact\n\nFor any suggestions and concerns please reach out to me: Ea0011" ]

[ 80, 143, 4, 181, 169, 193, 359, 229, 20 ]

[ "passage: TAGS\n#task_categories-text-generation #task_categories-conversational #task_categories-text2text-generation #size_categories-10K<n<100K #language-English #license-cc-by-nc-sa-4.0 #code #machine learning #deep learning #data science #region-us \n# Dataset Card for DS Coder Instruct v2 Dataset\n\nChanges from v1:\n* Added WizardLM evol data science samples\n* Removed R samples from v2\n\n\n\nDS Coder is a dataset for instruction fine tuning of language models. It is a specialized dataset focusing only on\ndata science (eg. plotting, data wrangling, machine learnig models, deep learning, and numerical computations). The dataset contains code examples both in Python (R samples were removed in v2).\nThe goal of this dataset is to enable creation of small-scale, specialized language model assistants for data science projects.## Dataset Details### Dataset Description\n\n\nDS Coder instruct dataset contains *(input, instruction, output)* triplets. Instruction provides a task in the data science domain and output contains the code to solve the task.\nWhere available, it also contains *text* field holding Alpaca style input. Metadata, such as the programming language *(lang)* and topics *(topics)* are provided.\n*topics* lists the concepts used in the code (eg. ML, neural networs, plotting, etc.). This is determined based on which kinds of libraries the code uses. This field can be used\nto obtain subset of data for specific tasks, such as data vizualisation. \n\nAdditionally, the original data source is provided under the *dataset* field.", "passage: ### Dataset Sources\n\n\nDS Coder is filtered and preprocessed from a collection of publically available datasets on HuggingFace. All the sources all liste below with their corresponding links.\n\n- nickrosh/Evol-Instruct-Code-80k-v1: URL\n- TokenBender/code_instructions_122k_alpaca_style: URL\n- theblackcat102/evol-codealpaca-v1: URL\n- ise-uiuc/Magicoder-OSS-Instruct-75K: URL\n- WizardLM/WizardLM_evol_instruct_V2_196k: URL\n\nPlease make sure to cite the above mentioned source when using this dataset. You should visit these pages and look for specific usage instructions, if any.## Dataset Creation\n\n\n\nDS Coder was created by filtering and processing existing public datasets of *(instruction, code)* pairs. Source data was filtered to keep only code related to data science\napplications. The filtering was done using regex to gather code that uses popular data science libraries (eg. Matplotlib, Sklearn, PyTorch, etc.) in Python and R.\nThen, the data is further processed to filter out samples with very long or very short code. Code outputs with lots of comments and low amound of code were filtered out.\nAdditionally, samples with very long and very short instructions were also removed. \n\nAfter filtering, exact deduplication based on output code and input instruction was performed. After this process, roughly *16K* samples remain.\n\nMore specific description dataset processing is provided below." ]

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

[]

[]

[ "# Information\n\nThis is a reformatted version of the HumanEval dataset" ]

[ "TAGS\n#license-mit #region-us \n", "# Information\n\nThis is a reformatted version of the HumanEval dataset" ]

[ 11, 16 ]

[ "passage: TAGS\n#license-mit #region-us \n# Information\n\nThis is a reformatted version of the HumanEval dataset" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_all\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_all\"\n\nMore Information needed" ]

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_all\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true\"\n\nMore Information needed" ]

[ 6, 36 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_midscore_all\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_midscore_all\"\n\nMore Information needed" ]

[ 6, 33 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_midscore_all\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_midscore_true\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_midscore_true\"\n\nMore Information needed" ]

[ 6, 34 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_midscore_true\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of Felladrin/Pythia-31M-Chat-v1\n\n\n\nDataset automatically created during the evaluation run of model Felladrin/Pythia-31M-Chat-v1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T14:50:17.030237(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of Felladrin/Pythia-31M-Chat-v1\n\n\n\nDataset automatically created during the evaluation run of model Felladrin/Pythia-31M-Chat-v1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T14:50:17.030237(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 191, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of Felladrin/Pythia-31M-Chat-v1\n\n\n\nDataset automatically created during the evaluation run of model Felladrin/Pythia-31M-Chat-v1 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T14:50:17.030237(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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]" ]

[ "size_categories:10K<n<100K", "language:th", "region:us" ]

[]

[ "th" ]

[ "### Instruct-QA-Thai-Combined", "#### Dataset Description\n\nInstruct-QA-Thai-Combined is a rich collection of question-answering datasets compiled from various sources,\\\ntailored for the development and benchmarking of Thai language question-answering systems.", "#### Languages\n\nThe primary language present in this dataset is Thai.", "### Data Structure", "#### Data Sources:\n\n- Wiki QA: 17,000 question-answer pairs.\n- MKQA: 10,000 queries sampled from the Google Natural Questions dataset.\n- iapp-wiki-qa-squad: 5,761 document/question pairs.\n- ThaiQA Squad: 4,000 question-answer pairs from Thai Wikipedia.\n- TyDi QA: 3,789 question-answer pairs in diverse languages.\n- XQuAD: 1,190 question-answer pairs for cross-lingual question answering performance.", "#### Features:\n\nThe dataset includes the following features:\n\n- Instuction: A question related to a specific topic.\n- Input: Long form context.\n- Answer: The corresponding answer to the question.\n- Source: The dataset each question and answer pair originated from.", "#### Source Data\n\nThe source data includes multiple datasets, each with its licensing:\n\n- XQuAD (CC BY-SA 4.0)\n- Thai QA (CC BY-SA-NC 3.0)\n- TyDi QA (Apache-2.0 License)\n- iapp-wiki-qa-dataset (MIT License)\n- MKQA (Apple)\n\n\n\nPlease cite the following if you use the Instruct-QA-Thai-Combined dataset in your work:", "### Acknowledgements\n\nSpecial thanks to the contributors of the original datasets: NECTEC, DeepMind, Google Research, and Apple, among others.\n\n---" ]

[ "TAGS\n#size_categories-10K<n<100K #language-Thai #region-us \n", "### Instruct-QA-Thai-Combined", "#### Dataset Description\n\nInstruct-QA-Thai-Combined is a rich collection of question-answering datasets compiled from various sources,\\\ntailored for the development and benchmarking of Thai language question-answering systems.", "#### Languages\n\nThe primary language present in this dataset is Thai.", "### Data Structure", "#### Data Sources:\n\n- Wiki QA: 17,000 question-answer pairs.\n- MKQA: 10,000 queries sampled from the Google Natural Questions dataset.\n- iapp-wiki-qa-squad: 5,761 document/question pairs.\n- ThaiQA Squad: 4,000 question-answer pairs from Thai Wikipedia.\n- TyDi QA: 3,789 question-answer pairs in diverse languages.\n- XQuAD: 1,190 question-answer pairs for cross-lingual question answering performance.", "#### Features:\n\nThe dataset includes the following features:\n\n- Instuction: A question related to a specific topic.\n- Input: Long form context.\n- Answer: The corresponding answer to the question.\n- Source: The dataset each question and answer pair originated from.", "#### Source Data\n\nThe source data includes multiple datasets, each with its licensing:\n\n- XQuAD (CC BY-SA 4.0)\n- Thai QA (CC BY-SA-NC 3.0)\n- TyDi QA (Apache-2.0 License)\n- iapp-wiki-qa-dataset (MIT License)\n- MKQA (Apple)\n\n\n\nPlease cite the following if you use the Instruct-QA-Thai-Combined dataset in your work:", "### Acknowledgements\n\nSpecial thanks to the contributors of the original datasets: NECTEC, DeepMind, Google Research, and Apple, among others.\n\n---" ]

[ 23, 13, 54, 15, 6, 120, 60, 101, 36 ]

[ "passage: TAGS\n#size_categories-10K<n<100K #language-Thai #region-us \n### Instruct-QA-Thai-Combined#### Dataset Description\n\nInstruct-QA-Thai-Combined is a rich collection of question-answering datasets compiled from various sources,\\\ntailored for the development and benchmarking of Thai language question-answering systems.#### Languages\n\nThe primary language present in this dataset is Thai.### Data Structure#### Data Sources:\n\n- Wiki QA: 17,000 question-answer pairs.\n- MKQA: 10,000 queries sampled from the Google Natural Questions dataset.\n- iapp-wiki-qa-squad: 5,761 document/question pairs.\n- ThaiQA Squad: 4,000 question-answer pairs from Thai Wikipedia.\n- TyDi QA: 3,789 question-answer pairs in diverse languages.\n- XQuAD: 1,190 question-answer pairs for cross-lingual question answering performance.#### Features:\n\nThe dataset includes the following features:\n\n- Instuction: A question related to a specific topic.\n- Input: Long form context.\n- Answer: The corresponding answer to the question.\n- Source: The dataset each question and answer pair originated from.#### Source Data\n\nThe source data includes multiple datasets, each with its licensing:\n\n- XQuAD (CC BY-SA 4.0)\n- Thai QA (CC BY-SA-NC 3.0)\n- TyDi QA (Apache-2.0 License)\n- iapp-wiki-qa-dataset (MIT License)\n- MKQA (Apple)\n\n\n\nPlease cite the following if you use the Instruct-QA-Thai-Combined dataset in your work:### Acknowledgements\n\nSpecial thanks to the contributors of the original datasets: NECTEC, DeepMind, Google Research, and Apple, among others.\n\n---" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"minor-prince\"\n\nMore Information needed" ]

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

[ 6, 15 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"minor-prince\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true_y\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true_y\"\n\nMore Information needed" ]

[ 6, 38 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true_y\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true_x\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true_x\"\n\nMore Information needed" ]

[ 6, 38 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_s1_nearestscore_true_x\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"rna_black_1024\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"rna_black_1024\"\n\nMore Information needed" ]

[ 6, 16 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"rna_black_1024\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_nearestscore_true_y\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_mgpt_nearestscore_true_x\"\n\nMore Information needed" ]

[ "task_categories:image-to-text", "task_categories:visual-question-answering", "size_categories:10K<n<100K", "language:en", "license:cc-by-nc-4.0", "region:us" ]

[]

[ "en" ]

[ "### Dataset Summary\n\n\nTextOCR-GPT4V is Meta's TextOCR dataset dataset captioned with emphasis on text OCR using GPT4V. To get the image, you will need to agree to their terms of service.", "### Supported Tasks\n\n\nThe TextOCR-GPT4V dataset is intended for generating benchmarks for comparison of an MLLM to GPT4v.", "### Languages\n\n\nThe caption languages are in English, while various texts in images are in many languages such as Spanish, Japanese, and Hindi.", "### Original Prompts\n\n\nThe 'caption' field was produced with the following prompt with the 'gpt-4-vision-preview' model:\n\n\nThe 'caption\\_condensed' field was produced with the following prompt using the 'gpt-4-1106-preview' model:", "### Data Instances\n\n\nAn example of \"train\" looks as follows:", "### Data Fields\n\n\nThe data fields are as follows:\n\n\n* 'filename': The filename of the image from the original TextOCR dataset.\n* 'caption': A caption with both a 'DESCRIPTION' and 'TEXT' part.\n* 'caption\\_image': The 'DESCRIPTION' part of the caption.\n* 'caption\\_text': The 'TEXT' part of the caption.\n* 'caption\\_condensed': GPT4 distilled version of the original caption onto a single line.", "### Data Splits\n\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### 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\nThe 'textocr-gpt4v' data is generated by a vision-language model ('gpt-4-vision-preview') and inevitably contains some errors or biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections.\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information\n\n\nThe dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0).", "### Contributions" ]

[ "TAGS\n#task_categories-image-to-text #task_categories-visual-question-answering #size_categories-10K<n<100K #language-English #license-cc-by-nc-4.0 #region-us \n", "### Dataset Summary\n\n\nTextOCR-GPT4V is Meta's TextOCR dataset dataset captioned with emphasis on text OCR using GPT4V. To get the image, you will need to agree to their terms of service.", "### Supported Tasks\n\n\nThe TextOCR-GPT4V dataset is intended for generating benchmarks for comparison of an MLLM to GPT4v.", "### Languages\n\n\nThe caption languages are in English, while various texts in images are in many languages such as Spanish, Japanese, and Hindi.", "### Original Prompts\n\n\nThe 'caption' field was produced with the following prompt with the 'gpt-4-vision-preview' model:\n\n\nThe 'caption\\_condensed' field was produced with the following prompt using the 'gpt-4-1106-preview' model:", "### Data Instances\n\n\nAn example of \"train\" looks as follows:", "### Data Fields\n\n\nThe data fields are as follows:\n\n\n* 'filename': The filename of the image from the original TextOCR dataset.\n* 'caption': A caption with both a 'DESCRIPTION' and 'TEXT' part.\n* 'caption\\_image': The 'DESCRIPTION' part of the caption.\n* 'caption\\_text': The 'TEXT' part of the caption.\n* 'caption\\_condensed': GPT4 distilled version of the original caption onto a single line.", "### Data Splits\n\n\n\nDataset Creation\n----------------", "### Curation Rationale", "### Source Data", "#### Initial Data Collection and Normalization", "#### Who are the source language producers?", "### Annotations", "#### 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\nThe 'textocr-gpt4v' data is generated by a vision-language model ('gpt-4-vision-preview') and inevitably contains some errors or biases. We encourage users to use this data with caution and propose new methods to filter or improve the imperfections.\n\n\nAdditional Information\n----------------------", "### Dataset Curators", "### Licensing Information\n\n\nThe dataset is available under the Creative Commons NonCommercial (CC BY-NC 4.0).", "### Contributions" ]

[ 60, 55, 37, 32, 63, 18, 127, 11, 7, 4, 10, 10, 5, 5, 9, 18, 7, 8, 83, 6, 26, 5 ]

[ "passage: TAGS\n#task_categories-image-to-text #task_categories-visual-question-answering #size_categories-10K<n<100K #language-English #license-cc-by-nc-4.0 #region-us \n### Dataset Summary\n\n\nTextOCR-GPT4V is Meta's TextOCR dataset dataset captioned with emphasis on text OCR using GPT4V. To get the image, you will need to agree to their terms of service.### Supported Tasks\n\n\nThe TextOCR-GPT4V dataset is intended for generating benchmarks for comparison of an MLLM to GPT4v.### Languages\n\n\nThe caption languages are in English, while various texts in images are in many languages such as Spanish, Japanese, and Hindi.### Original Prompts\n\n\nThe 'caption' field was produced with the following prompt with the 'gpt-4-vision-preview' model:\n\n\nThe 'caption\\_condensed' field was produced with the following prompt using the 'gpt-4-1106-preview' model:### Data Instances\n\n\nAn example of \"train\" looks as follows:### Data Fields\n\n\nThe data fields are as follows:\n\n\n* 'filename': The filename of the image from the original TextOCR dataset.\n* 'caption': A caption with both a 'DESCRIPTION' and 'TEXT' part.\n* 'caption\\_image': The 'DESCRIPTION' part of the caption.\n* 'caption\\_text': The 'TEXT' part of the caption.\n* 'caption\\_condensed': GPT4 distilled version of the original caption onto a single line.### Data Splits\n\n\n\nDataset Creation\n----------------### Curation Rationale### Source Data#### Initial Data Collection and Normalization#### Who are the source language producers?### Annotations#### 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" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_gpt2_nearestscore_true_y\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_gpt2_nearestscore_true_y\"\n\nMore Information needed" ]

[ 6, 36 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_gpt2_nearestscore_true_y\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"araproje_hellaswag_tr_conf_gpt2_nearestscore_true_x\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"araproje_hellaswag_tr_conf_gpt2_nearestscore_true_x\"\n\nMore Information needed" ]

[ 6, 36 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_tr_conf_gpt2_nearestscore_true_x\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# 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#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" ]

[ 6, 34, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#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" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_en_conf_mpgt_nearestscore_true_y\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_en_conf_llama_nearestscore_true_y\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 35 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_en_conf_llama_nearestscore_true_x\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

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

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

[ 6, 33 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"araproje_hellaswag_en_conf_llama_nearestscore_true\"\n\nMore Information needed" ]

[ "size_categories:n<1K", "language:en", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#size_categories-n<1K #language-English #region-us \n" ]

[ 20 ]

[ "passage: TAGS\n#size_categories-n<1K #language-English #region-us \n" ]

[ "task_categories:text-generation", "task_categories:feature-extraction", "size_categories:10K<n<100K", "source_datasets:BAAI/TACO", "language:en", "license:apache-2.0", "BAAI/TACO", "region:us" ]

[]

[ "en" ]

[ "# BEE-spoke-data/TACO-hf\n\nSimple re-host of URL but saved as hf dataset for ease of use.\n\n\nFeatures:\n\n\n\nRefer to the original dataset for more details." ]

[ "TAGS\n#task_categories-text-generation #task_categories-feature-extraction #size_categories-10K<n<100K #source_datasets-BAAI/TACO #language-English #license-apache-2.0 #BAAI/TACO #region-us \n", "# BEE-spoke-data/TACO-hf\n\nSimple re-host of URL but saved as hf dataset for ease of use.\n\n\nFeatures:\n\n\n\nRefer to the original dataset for more details." ]

[ 71, 47 ]

[ "passage: TAGS\n#task_categories-text-generation #task_categories-feature-extraction #size_categories-10K<n<100K #source_datasets-BAAI/TACO #language-English #license-apache-2.0 #BAAI/TACO #region-us \n# BEE-spoke-data/TACO-hf\n\nSimple re-host of URL but saved as hf dataset for ease of use.\n\n\nFeatures:\n\n\n\nRefer to the original dataset for more details." ]

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

[]

[ "en" ]

[]

[ "TAGS\n#size_categories-10K<n<100K #language-English #region-us \n" ]

[ 22 ]

[ "passage: TAGS\n#size_categories-10K<n<100K #language-English #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of Sao10K/Sensualize-Solar-10.7B\n\n\n\nDataset automatically created during the evaluation run of model Sao10K/Sensualize-Solar-10.7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T17:08:25.096986(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of Sao10K/Sensualize-Solar-10.7B\n\n\n\nDataset automatically created during the evaluation run of model Sao10K/Sensualize-Solar-10.7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T17:08:25.096986(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 189, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of Sao10K/Sensualize-Solar-10.7B\n\n\n\nDataset automatically created during the evaluation run of model Sao10K/Sensualize-Solar-10.7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T17:08:25.096986(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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]" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"en-fin_gpt_senti\"\n\nMore Information needed" ]

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

[ 6, 18 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"en-fin_gpt_senti\"\n\nMore Information needed" ]

[ "task_categories:question-answering", "task_categories:visual-question-answering", "task_categories:multiple-choice", "size_categories:10K<n<100K", "language:en", "license:apache-2.0", "biology", "medical", "finance", "chemistry", "music", "art", "art_theory", "design", "business", "accounting", "economics", "manage", "marketing", "health", "medicine", "basic_medical_science", "clinical", "pharmacy", "public_health", "humanities", "social_science", "history", "literature", "sociology", "psychology", "science", "geography", "math", "physics", "engineering", "agriculture", "architecture", "computer_science", "electronics", "energy_and_power", "materials", "mechanical_engineering", "arxiv:2311.16502", "region:us" ]

[ "2311.16502" ]

[ "en" ]

[ "### Dataset Description\n\n\nWe introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI).\n\n\nWe have released a full set comprising 150 development samples and 900 validation samples. We have released 10,500 test questions without their answers.\nThe development set is used for few-shot/in-context learning, and the validation set is used for debugging models, selecting hyperparameters, or quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the test set on EvalAI.\n\n\n!image/png", "### Dataset Creation\n\n\nMMMU was created to challenge multimodal models with tasks that demand college-level subject knowledge and deliberate reasoning, pushing the boundaries of what these models can achieve in terms of expert-level perception and reasoning.\nThe data for the MMMU dataset was manually collected by a team of college students from various disciplines, using online sources, textbooks, and lecture materials.\n\n\n* Content: The dataset contains 11.5K college-level problems across six broad disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) and 30 college subjects.\n* Image Types: The dataset includes 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures, interleaved with text.\n\n\n!image/png\n\n\nMini-Leaderboard\n----------------\n\n\nWe show a mini-leaderboard here and please find more information in our paper or homepage.\n\n\n\n\\*: results provided by the authors.\n\n\nLimitations\n-----------\n\n\nDespite its comprehensive nature, MMMU, like any benchmark, is not without limitations. The manual curation process, albeit thorough, may carry biases.\nAnd the focus on college-level subjects might not fully be a sufficient test for Expert AGI.\nHowever, we believe it should be necessary for an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities.\nIn future work, we plan to incorporate human evaluations into MMMU. This will provide a more grounded comparison between model capabilities and expert performance, shedding light on the proximity of current AI systems to achieving Expert AGI.\n\n\nDisclaimers\n-----------\n\n\nThe guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution.\nShould you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to notify us. Upon verification, such samples will be promptly removed.\n\n\nContact\n-------\n\n\n* Xiang Yue: URL@URL\n* Yu Su: su.809@URL\n* Wenhu Chen: wenhuchen@URL\n\n\nBibTeX:" ]

[ "TAGS\n#task_categories-question-answering #task_categories-visual-question-answering #task_categories-multiple-choice #size_categories-10K<n<100K #language-English #license-apache-2.0 #biology #medical #finance #chemistry #music #art #art_theory #design #business #accounting #economics #manage #marketing #health #medicine #basic_medical_science #clinical #pharmacy #public_health #humanities #social_science #history #literature #sociology #psychology #science #geography #math #physics #engineering #agriculture #architecture #computer_science #electronics #energy_and_power #materials #mechanical_engineering #arxiv-2311.16502 #region-us \n", "### Dataset Description\n\n\nWe introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI).\n\n\nWe have released a full set comprising 150 development samples and 900 validation samples. We have released 10,500 test questions without their answers.\nThe development set is used for few-shot/in-context learning, and the validation set is used for debugging models, selecting hyperparameters, or quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the test set on EvalAI.\n\n\n!image/png", "### Dataset Creation\n\n\nMMMU was created to challenge multimodal models with tasks that demand college-level subject knowledge and deliberate reasoning, pushing the boundaries of what these models can achieve in terms of expert-level perception and reasoning.\nThe data for the MMMU dataset was manually collected by a team of college students from various disciplines, using online sources, textbooks, and lecture materials.\n\n\n* Content: The dataset contains 11.5K college-level problems across six broad disciplines (Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, Tech & Engineering) and 30 college subjects.\n* Image Types: The dataset includes 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures, interleaved with text.\n\n\n!image/png\n\n\nMini-Leaderboard\n----------------\n\n\nWe show a mini-leaderboard here and please find more information in our paper or homepage.\n\n\n\n\\*: results provided by the authors.\n\n\nLimitations\n-----------\n\n\nDespite its comprehensive nature, MMMU, like any benchmark, is not without limitations. The manual curation process, albeit thorough, may carry biases.\nAnd the focus on college-level subjects might not fully be a sufficient test for Expert AGI.\nHowever, we believe it should be necessary for an Expert AGI to achieve strong performance on MMMU to demonstrate their broad and deep subject knowledge as well as expert-level understanding and reasoning capabilities.\nIn future work, we plan to incorporate human evaluations into MMMU. This will provide a more grounded comparison between model capabilities and expert performance, shedding light on the proximity of current AI systems to achieving Expert AGI.\n\n\nDisclaimers\n-----------\n\n\nThe guidelines for the annotators emphasized strict compliance with copyright and licensing rules from the initial data source, specifically avoiding materials from websites that forbid copying and redistribution.\nShould you encounter any data samples potentially breaching the copyright or licensing regulations of any site, we encourage you to notify us. Upon verification, such samples will be promptly removed.\n\n\nContact\n-------\n\n\n* Xiang Yue: URL@URL\n* Yu Su: su.809@URL\n* Wenhu Chen: wenhuchen@URL\n\n\nBibTeX:" ]

[ 203, 284, 511 ]

[ "passage: TAGS\n#task_categories-question-answering #task_categories-visual-question-answering #task_categories-multiple-choice #size_categories-10K<n<100K #language-English #license-apache-2.0 #biology #medical #finance #chemistry #music #art #art_theory #design #business #accounting #economics #manage #marketing #health #medicine #basic_medical_science #clinical #pharmacy #public_health #humanities #social_science #history #literature #sociology #psychology #science #geography #math #physics #engineering #agriculture #architecture #computer_science #electronics #energy_and_power #materials #mechanical_engineering #arxiv-2311.16502 #region-us \n### Dataset Description\n\n\nWe introduce MMMU: a new benchmark designed to evaluate multimodal models on massive multi-discipline tasks demanding college-level subject knowledge and deliberate reasoning. MMMU includes 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering. These questions span 30 subjects and 183 subfields, comprising 30 highly heterogeneous image types, such as charts, diagrams, maps, tables, music sheets, and chemical structures. We believe MMMU will stimulate the community to build next-generation multimodal foundation models towards expert artificial general intelligence (AGI).\n\n\nWe have released a full set comprising 150 development samples and 900 validation samples. We have released 10,500 test questions without their answers.\nThe development set is used for few-shot/in-context learning, and the validation set is used for debugging models, selecting hyperparameters, or quick evaluations. The answers and explanations for the test set questions are withheld. You can submit your model's predictions for the test set on EvalAI.\n\n\n!image/png" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of Sao10K/Winterreise-m7\n\n\n\nDataset automatically created during the evaluation run of model Sao10K/Winterreise-m7 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T17:27:54.681124(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of Sao10K/Winterreise-m7\n\n\n\nDataset automatically created during the evaluation run of model Sao10K/Winterreise-m7 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T17:27:54.681124(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 181, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of Sao10K/Winterreise-m7\n\n\n\nDataset automatically created during the evaluation run of model Sao10K/Winterreise-m7 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T17:27:54.681124(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "task_categories:visual-question-answering", "size_categories:n<1K", "language:en", "license:mit", "kyc", "passports", "region:us" ]

[]

[ "en" ]

[]

[ "TAGS\n#task_categories-visual-question-answering #size_categories-n<1K #language-English #license-mit #kyc #passports #region-us \n" ]

[ 46 ]

[ "passage: TAGS\n#task_categories-visual-question-answering #size_categories-n<1K #language-English #license-mit #kyc #passports #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:summarization", "task_categories:text-classification", "size_categories:10K<n<100K", "language:en", "finance", "Financial News", "Sentiment Analysis", "Stock Market", "Text Summarization", "Indian Finance", "BERT", "FinBERT", "NLP (Natural Language Processing)", "Hugging Face Dataset", "T5-base", "GPT (Google Sheets Add-on)", "Data Annotation", "region:us" ]

[]

[ "en" ]

[ "# Dataset Card for Dataset Name\n\n\n\nThe FinancialNewsSentiment_26000 dataset comprises 26,000 rows of financial news articles related to the Indian market. It features four columns: URL, Content (scrapped content), Summary (generated using the T5-base model), and Sentiment Analysis (gathered using the GPT add-on for Google Sheets). The dataset is designed for sentiment analysis tasks, providing a comprehensive view of sentiments expressed in financial news.", "## Dataset Description\n\n\n\n\n\n- Curated by: Khushi Dave\n- Language(s): English\n- Type: Text\n- Domain: Financial, Economy\n- Size: 112,293 KB\n- Dataset: Version: 1.0\n- Last Updated: 01/01/2024", "## Dataset Sources \n\n\n\n- Repository: URL", "## Uses\n\n\n\nSentiment Analysis Research: Ideal for exploring sentiment nuances in Indian financial news.\n\nNLP Projects: Enhance NLP models with diverse financial text for improved understanding.\n\nAlgorithmic Trading Strategies: Study correlations between sentiment shifts and market movements.\n\nNews Aggregation: Generate concise summaries with sentiment insights for financial news.\n\nEducational Resource: Hands-on examples for teaching sentiment analysis and financial text processing.\n\nEthical AI Exploration: Analyze biases in sentiment analysis models for ethical AI research.\n\nModel Benchmarking: Evaluate and benchmark sentiment analysis models for financial text.\n\nNote: Use cautiously; do not rely solely on model predictions for financial decision-making.", "## Dataset Creation\n\n- Format: String\n- Columns:\nURL: URL of the news article\n\nContent: Scrapped content of the news article\n\nSummary: Summarized version using T5-base\n\nSentiment Analysis: Sentiment labels (Positive, Negative, Neutral) gathered using the GPT add-on", "## Data Collection\n\n\n\nSource Selection: Aggregation of Indian financial news articles from reputable sources covering a range of topics.\n\nURL Scrapping: Extraction of URLs for each article to maintain a connection between the dataset and the original content.\n\nContent Scrapping: Extraction of article content for analysis and modeling purposes.\n\nSummarization: Utilization of the T5-base model from Hugging Face for content summarization.\n\nSentiment Annotation: Manual sentiment labeling using the GPT add-on for Google Sheets to categorize each article as Positive, Negative, or Neutral.", "## Data Processing:\n\nCleaning and Tokenization: Standard preprocessing techniques were applied to clean and tokenize the content, ensuring uniformity and consistency.\n\nFormat Standardization: Conversion of data into a structured format with columns: URL, Content, Summary, and Sentiment Analysis.\n\nDataset Splitting: Given the subjective nature of sentiments, the dataset was not split into training, validation, and testing sets. Users are encouraged to customize splits based on their specific use cases.", "## Tools and Libraries:\n\nBeautiful Soup: Used for web scraping to extract content from HTML.\nHugging Face Transformers: Employed for summarization using the T5-base model.\nGPT Add-on for Google Sheets: Facilitated manual sentiment annotation.\nPandas: Utilized for data manipulation and structuring.", "## Dataset Card Authors\n\nKhushi Dave, Data Scientist" ]

[ "TAGS\n#task_categories-summarization #task_categories-text-classification #size_categories-10K<n<100K #language-English #finance #Financial News #Sentiment Analysis #Stock Market #Text Summarization #Indian Finance #BERT #FinBERT #NLP (Natural Language Processing) #Hugging Face Dataset #T5-base #GPT (Google Sheets Add-on) #Data Annotation #region-us \n", "# Dataset Card for Dataset Name\n\n\n\nThe FinancialNewsSentiment_26000 dataset comprises 26,000 rows of financial news articles related to the Indian market. It features four columns: URL, Content (scrapped content), Summary (generated using the T5-base model), and Sentiment Analysis (gathered using the GPT add-on for Google Sheets). The dataset is designed for sentiment analysis tasks, providing a comprehensive view of sentiments expressed in financial news.", "## Dataset Description\n\n\n\n\n\n- Curated by: Khushi Dave\n- Language(s): English\n- Type: Text\n- Domain: Financial, Economy\n- Size: 112,293 KB\n- Dataset: Version: 1.0\n- Last Updated: 01/01/2024", "## Dataset Sources \n\n\n\n- Repository: URL", "## Uses\n\n\n\nSentiment Analysis Research: Ideal for exploring sentiment nuances in Indian financial news.\n\nNLP Projects: Enhance NLP models with diverse financial text for improved understanding.\n\nAlgorithmic Trading Strategies: Study correlations between sentiment shifts and market movements.\n\nNews Aggregation: Generate concise summaries with sentiment insights for financial news.\n\nEducational Resource: Hands-on examples for teaching sentiment analysis and financial text processing.\n\nEthical AI Exploration: Analyze biases in sentiment analysis models for ethical AI research.\n\nModel Benchmarking: Evaluate and benchmark sentiment analysis models for financial text.\n\nNote: Use cautiously; do not rely solely on model predictions for financial decision-making.", "## Dataset Creation\n\n- Format: String\n- Columns:\nURL: URL of the news article\n\nContent: Scrapped content of the news article\n\nSummary: Summarized version using T5-base\n\nSentiment Analysis: Sentiment labels (Positive, Negative, Neutral) gathered using the GPT add-on", "## Data Collection\n\n\n\nSource Selection: Aggregation of Indian financial news articles from reputable sources covering a range of topics.\n\nURL Scrapping: Extraction of URLs for each article to maintain a connection between the dataset and the original content.\n\nContent Scrapping: Extraction of article content for analysis and modeling purposes.\n\nSummarization: Utilization of the T5-base model from Hugging Face for content summarization.\n\nSentiment Annotation: Manual sentiment labeling using the GPT add-on for Google Sheets to categorize each article as Positive, Negative, or Neutral.", "## Data Processing:\n\nCleaning and Tokenization: Standard preprocessing techniques were applied to clean and tokenize the content, ensuring uniformity and consistency.\n\nFormat Standardization: Conversion of data into a structured format with columns: URL, Content, Summary, and Sentiment Analysis.\n\nDataset Splitting: Given the subjective nature of sentiments, the dataset was not split into training, validation, and testing sets. Users are encouraged to customize splits based on their specific use cases.", "## Tools and Libraries:\n\nBeautiful Soup: Used for web scraping to extract content from HTML.\nHugging Face Transformers: Employed for summarization using the T5-base model.\nGPT Add-on for Google Sheets: Facilitated manual sentiment annotation.\nPandas: Utilized for data manipulation and structuring.", "## Dataset Card Authors\n\nKhushi Dave, Data Scientist" ]

[ 111, 109, 52, 11, 166, 71, 127, 117, 74, 14 ]

[ "passage: TAGS\n#task_categories-summarization #task_categories-text-classification #size_categories-10K<n<100K #language-English #finance #Financial News #Sentiment Analysis #Stock Market #Text Summarization #Indian Finance #BERT #FinBERT #NLP (Natural Language Processing) #Hugging Face Dataset #T5-base #GPT (Google Sheets Add-on) #Data Annotation #region-us \n# Dataset Card for Dataset Name\n\n\n\nThe FinancialNewsSentiment_26000 dataset comprises 26,000 rows of financial news articles related to the Indian market. It features four columns: URL, Content (scrapped content), Summary (generated using the T5-base model), and Sentiment Analysis (gathered using the GPT add-on for Google Sheets). The dataset is designed for sentiment analysis tasks, providing a comprehensive view of sentiments expressed in financial news.## Dataset Description\n\n\n\n\n\n- Curated by: Khushi Dave\n- Language(s): English\n- Type: Text\n- Domain: Financial, Economy\n- Size: 112,293 KB\n- Dataset: Version: 1.0\n- Last Updated: 01/01/2024## Dataset Sources \n\n\n\n- Repository: URL## Uses\n\n\n\nSentiment Analysis Research: Ideal for exploring sentiment nuances in Indian financial news.\n\nNLP Projects: Enhance NLP models with diverse financial text for improved understanding.\n\nAlgorithmic Trading Strategies: Study correlations between sentiment shifts and market movements.\n\nNews Aggregation: Generate concise summaries with sentiment insights for financial news.\n\nEducational Resource: Hands-on examples for teaching sentiment analysis and financial text processing.\n\nEthical AI Exploration: Analyze biases in sentiment analysis models for ethical AI research.\n\nModel Benchmarking: Evaluate and benchmark sentiment analysis models for financial text.\n\nNote: Use cautiously; do not rely solely on model predictions for financial decision-making." ]

[ "region:us" ]

[]

[]

[ "# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'", "# Args" ]

[ "TAGS\n#region-us \n", "# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'", "# Args" ]

[ 6, 384, 3 ]

[ "passage: TAGS\n#region-us \n# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'# Args" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1704563162\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1704563162\"\n\nMore Information needed" ]

[ 6, 30 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1704563162\"\n\nMore Information needed" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "task_categories:text-to-image", "size_categories:n<1K", "license:mit", "art", "not-for-all-audiences", "region:us" ]

[]

[]

[]

[ "TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ 44 ]

[ "passage: TAGS\n#task_categories-text-to-image #size_categories-n<1K #license-mit #art #not-for-all-audiences #region-us \n" ]

[ "region:us" ]

[]

[]

[ "# Celebrity 1000\n\nTop 1000 celebrities. 18,184 images. 256x256. Square cropped to face." ]

[ "TAGS\n#region-us \n", "# Celebrity 1000\n\nTop 1000 celebrities. 18,184 images. 256x256. Square cropped to face." ]

[ 6, 24 ]

[ "passage: TAGS\n#region-us \n# Celebrity 1000\n\nTop 1000 celebrities. 18,184 images. 256x256. Square cropped to face." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"code-vllm-func-names\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"code-vllm-func-names\"\n\nMore Information needed" ]

[ 6, 21 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"code-vllm-func-names\"\n\nMore Information needed" ]

[ "task_categories:text-generation", "task_categories:fill-mask", "task_ids:language-modeling", "task_ids:masked-language-modeling", "language_creators:found", "multilinguality:monolingual", "size_categories:100K<n<1M", "source_datasets:original", "language:hy", "license:cc-by-sa-4.0", "region:us" ]

[]

[ "hy" ]

[ "### Dataset Summary\n\n\nThe Selective Armenian Web (SAW) Corpus is a collection of Armenian language texts, selectively compiled from various online sources. It aims to support natural language processing tasks, offering a wide range of text types, including news articles, legal documents, and other web content.", "### Supported Tasks and Leaderboards\n\n\n* 'language-modeling'\n* 'masked-language-modeling'", "### Languages\n\n\nThe dataset is composed entirely in Armenian (hy), with all texts containing at least 50% Armenian characters.\n\n\nDataset Structure\n-----------------", "### Data Instances\n\n\nA typical data instance in this dataset might look like the following:\n\n\n\n```\n{\n\"text\": \"Հայաստանում կատարվել է 2 164 083 պատվաստում\\n\\nՊատվաստումային գործընթացը շարունակվում է:Ապրիլի 24-ի դրությամբ կատարվել է՝\",\n\"link\": \"URL/հայաստանում-կատարվել-է-2-164-083-պատվաստում/\",\n\"date\": \"2022-04-25\",\n\"tags\": [\"Կարևոր\", \"Հասարակություն\"],\n\"source\": \"URL\"\n}\n\n```", "### Data Fields\n\n\n* 'text': The main content of the article or text. Always includes the title.\n* 'url': The URL where the text was sourced from.\n* 'date': The publication date of the text.\n* 'tags': A list of tags or categories associated with the text.\n* 'source': The name of the website or platform where the text was sourced from.", "### Data Splits\n\n\nThe dataset is divided into three splits: train, validation (val), and test. Below are the details for each split:\n\n\n\nDataset Creation\n----------------", "### Curation Rationale\n\n\nThe SAW Corpus was curated with the intent to create a comprehensive resource for Armenian language processing. The rationale behind its creation was to compile a diverse and significant collection of Armenian texts from various online sources, suitable for training robust language models and other NLP tasks. The dataset aims to fill the gap in Armenian language resources and provide a valuable tool for both academic research and practical applications in NLP.", "### Source Data", "#### Initial Data Collection and Normalization\n\n\nThe texts for the SAW Corpus were collected from a wide range of Armenian online sources, including news websites, document archives, and other relevant web content. The collection process involved selectively sourcing texts that were representative of contemporary Armenian usage.\n\n\nNormalization and cleaning processes were applied to ensure the quality and consistency of the dataset. These processes included:\n\n\n* Removing extraneous formatting and correcting obvious errors.\n* Standardizing punctuation marks such as commas, colons, and dashes.\n* Harmonizing variations of specific Armenian characters (e.g., standardizing 'և' and 'եւ').\n* Markdown style was used for formatting tables, ordered, and unordered lists.\n\n\nThe focus was on maintaining the integrity and diversity of the original content while ensuring the texts were suitable for NLP tasks. Markdown style was used for formatting tables, ordered, and unordered lists.", "#### Annotations\n\n\nThe dataset does not contain any additional annotations.", "#### Personal and Sensitive Information\n\n\nThe dataset consists of texts collected from publicly available sources. Due to the extensive volume of data, no specific steps were taken to identify or remove personal or sensitive information from each text. Users are advised to be aware of this when utilizing the dataset, particularly in contexts where privacy and data protection are concerns.\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset\n\n\nThe dataset supports advancements in NLP for the Armenian language, which can aid in diverse applications ranging from language research to the development of linguistic technologies.", "### Discussion of Biases\n\n\nAs the dataset aggregates content from various online sources, it may inherently carry the biases present in these sources. This can include skewness in topics, styles, or viewpoints.", "### Other Known Limitations\n\n\nThe dataset primarily includes Eastern Armenian texts and does not cover Western Armenian, which limits its linguistic diversity. While the dataset is rich in formal and literary styles, being a written corpus, it may not adequately represent spoken dialects and colloquial forms of Armenian.\n\n\nAdditional Information\n----------------------", "### Dataset Curators\n\n\nCurated by Mkrtich Minasyan.", "### Licensing Information\n\n\nThis dataset is distributed under the Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license.\n\n\n\n```\n@dataset{saw_corpus_2024,\ntitle = {Selective Armenian Web (SAW) Corpus},\nauthor = {Mkrtich Minasyan},\nyear = {2024}\n}\n\n```" ]

[ "TAGS\n#task_categories-text-generation #task_categories-fill-mask #task_ids-language-modeling #task_ids-masked-language-modeling #language_creators-found #multilinguality-monolingual #size_categories-100K<n<1M #source_datasets-original #language-Armenian #license-cc-by-sa-4.0 #region-us \n", "### Dataset Summary\n\n\nThe Selective Armenian Web (SAW) Corpus is a collection of Armenian language texts, selectively compiled from various online sources. It aims to support natural language processing tasks, offering a wide range of text types, including news articles, legal documents, and other web content.", "### Supported Tasks and Leaderboards\n\n\n* 'language-modeling'\n* 'masked-language-modeling'", "### Languages\n\n\nThe dataset is composed entirely in Armenian (hy), with all texts containing at least 50% Armenian characters.\n\n\nDataset Structure\n-----------------", "### Data Instances\n\n\nA typical data instance in this dataset might look like the following:\n\n\n\n```\n{\n\"text\": \"Հայաստանում կատարվել է 2 164 083 պատվաստում\\n\\nՊատվաստումային գործընթացը շարունակվում է:Ապրիլի 24-ի դրությամբ կատարվել է՝\",\n\"link\": \"URL/հայաստանում-կատարվել-է-2-164-083-պատվաստում/\",\n\"date\": \"2022-04-25\",\n\"tags\": [\"Կարևոր\", \"Հասարակություն\"],\n\"source\": \"URL\"\n}\n\n```", "### Data Fields\n\n\n* 'text': The main content of the article or text. Always includes the title.\n* 'url': The URL where the text was sourced from.\n* 'date': The publication date of the text.\n* 'tags': A list of tags or categories associated with the text.\n* 'source': The name of the website or platform where the text was sourced from.", "### Data Splits\n\n\nThe dataset is divided into three splits: train, validation (val), and test. Below are the details for each split:\n\n\n\nDataset Creation\n----------------", "### Curation Rationale\n\n\nThe SAW Corpus was curated with the intent to create a comprehensive resource for Armenian language processing. The rationale behind its creation was to compile a diverse and significant collection of Armenian texts from various online sources, suitable for training robust language models and other NLP tasks. The dataset aims to fill the gap in Armenian language resources and provide a valuable tool for both academic research and practical applications in NLP.", "### Source Data", "#### Initial Data Collection and Normalization\n\n\nThe texts for the SAW Corpus were collected from a wide range of Armenian online sources, including news websites, document archives, and other relevant web content. The collection process involved selectively sourcing texts that were representative of contemporary Armenian usage.\n\n\nNormalization and cleaning processes were applied to ensure the quality and consistency of the dataset. These processes included:\n\n\n* Removing extraneous formatting and correcting obvious errors.\n* Standardizing punctuation marks such as commas, colons, and dashes.\n* Harmonizing variations of specific Armenian characters (e.g., standardizing 'և' and 'եւ').\n* Markdown style was used for formatting tables, ordered, and unordered lists.\n\n\nThe focus was on maintaining the integrity and diversity of the original content while ensuring the texts were suitable for NLP tasks. Markdown style was used for formatting tables, ordered, and unordered lists.", "#### Annotations\n\n\nThe dataset does not contain any additional annotations.", "#### Personal and Sensitive Information\n\n\nThe dataset consists of texts collected from publicly available sources. Due to the extensive volume of data, no specific steps were taken to identify or remove personal or sensitive information from each text. Users are advised to be aware of this when utilizing the dataset, particularly in contexts where privacy and data protection are concerns.\n\n\nConsiderations for Using the Data\n---------------------------------", "### Social Impact of Dataset\n\n\nThe dataset supports advancements in NLP for the Armenian language, which can aid in diverse applications ranging from language research to the development of linguistic technologies.", "### Discussion of Biases\n\n\nAs the dataset aggregates content from various online sources, it may inherently carry the biases present in these sources. This can include skewness in topics, styles, or viewpoints.", "### Other Known Limitations\n\n\nThe dataset primarily includes Eastern Armenian texts and does not cover Western Armenian, which limits its linguistic diversity. While the dataset is rich in formal and literary styles, being a written corpus, it may not adequately represent spoken dialects and colloquial forms of Armenian.\n\n\nAdditional Information\n----------------------", "### Dataset Curators\n\n\nCurated by Mkrtich Minasyan.", "### Licensing Information\n\n\nThis dataset is distributed under the Creative Commons Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) license.\n\n\n\n```\n@dataset{saw_corpus_2024,\ntitle = {Selective Armenian Web (SAW) Corpus},\nauthor = {Mkrtich Minasyan},\nyear = {2024}\n}\n\n```" ]

[ 104, 69, 27, 37, 127, 88, 41, 95, 4, 228, 17, 92, 42, 53, 81, 16, 80 ]

[ "passage: TAGS\n#task_categories-text-generation #task_categories-fill-mask #task_ids-language-modeling #task_ids-masked-language-modeling #language_creators-found #multilinguality-monolingual #size_categories-100K<n<1M #source_datasets-original #language-Armenian #license-cc-by-sa-4.0 #region-us \n### Dataset Summary\n\n\nThe Selective Armenian Web (SAW) Corpus is a collection of Armenian language texts, selectively compiled from various online sources. It aims to support natural language processing tasks, offering a wide range of text types, including news articles, legal documents, and other web content.### Supported Tasks and Leaderboards\n\n\n* 'language-modeling'\n* 'masked-language-modeling'### Languages\n\n\nThe dataset is composed entirely in Armenian (hy), with all texts containing at least 50% Armenian characters.\n\n\nDataset Structure\n-----------------### Data Instances\n\n\nA typical data instance in this dataset might look like the following:\n\n\n\n```\n{\n\"text\": \"Հայաստանում կատարվել է 2 164 083 պատվաստում\\n\\nՊատվաստումային գործընթացը շարունակվում է:Ապրիլի 24-ի դրությամբ կատարվել է՝\",\n\"link\": \"URL/հայաստանում-կատարվել-է-2-164-083-պատվաստում/\",\n\"date\": \"2022-04-25\",\n\"tags\": [\"Կարևոր\", \"Հասարակություն\"],\n\"source\": \"URL\"\n}\n\n```### Data Fields\n\n\n* 'text': The main content of the article or text. Always includes the title.\n* 'url': The URL where the text was sourced from.\n* 'date': The publication date of the text.\n* 'tags': A list of tags or categories associated with the text.\n* 'source': The name of the website or platform where the text was sourced from.### Data Splits\n\n\nThe dataset is divided into three splits: train, validation (val), and test. Below are the details for each split:\n\n\n\nDataset Creation\n----------------", "passage: ### Curation Rationale\n\n\nThe SAW Corpus was curated with the intent to create a comprehensive resource for Armenian language processing. The rationale behind its creation was to compile a diverse and significant collection of Armenian texts from various online sources, suitable for training robust language models and other NLP tasks. The dataset aims to fill the gap in Armenian language resources and provide a valuable tool for both academic research and practical applications in NLP.### Source Data#### Initial Data Collection and Normalization\n\n\nThe texts for the SAW Corpus were collected from a wide range of Armenian online sources, including news websites, document archives, and other relevant web content. The collection process involved selectively sourcing texts that were representative of contemporary Armenian usage.\n\n\nNormalization and cleaning processes were applied to ensure the quality and consistency of the dataset. These processes included:\n\n\n* Removing extraneous formatting and correcting obvious errors.\n* Standardizing punctuation marks such as commas, colons, and dashes.\n* Harmonizing variations of specific Armenian characters (e.g., standardizing 'և' and 'եւ').\n* Markdown style was used for formatting tables, ordered, and unordered lists.\n\n\nThe focus was on maintaining the integrity and diversity of the original content while ensuring the texts were suitable for NLP tasks. Markdown style was used for formatting tables, ordered, and unordered lists.#### Annotations\n\n\nThe dataset does not contain any additional annotations.#### Personal and Sensitive Information\n\n\nThe dataset consists of texts collected from publicly available sources. Due to the extensive volume of data, no specific steps were taken to identify or remove personal or sensitive information from each text. Users are advised to be aware of this when utilizing the dataset, particularly in contexts where privacy and data protection are concerns.\n\n\nConsiderations for Using the Data\n---------------------------------### Social Impact of Dataset\n\n\nThe dataset supports advancements in NLP for the Armenian language, which can aid in diverse applications ranging from language research to the development of linguistic technologies.### Discussion of Biases\n\n\nAs the dataset aggregates content from various online sources, it may inherently carry the biases present in these sources. This can include skewness in topics, styles, or viewpoints." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of nlpguy/Hermes-low-tune-3\n\n\n\nDataset automatically created during the evaluation run of model nlpguy/Hermes-low-tune-3 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T19:55:30.793353(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of nlpguy/Hermes-low-tune-3\n\n\n\nDataset automatically created during the evaluation run of model nlpguy/Hermes-low-tune-3 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T19:55:30.793353(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 185, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of nlpguy/Hermes-low-tune-3\n\n\n\nDataset automatically created during the evaluation run of model nlpguy/Hermes-low-tune-3 on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T19:55:30.793353(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "size_categories:1B<n<10B", "language:en", "license:apache-2.0", "region:us" ]

[]

[ "en" ]

[ "# URL\n1️⃣️ The One Billion Row Challenge - Data files only if you can't be bothered with Java \nor write a generator but would rather download +3GB \n\nSee URL for original Java challenge.\n\nLarge data files have been generated on my machine and given official Java generator is random\n(not seeded and hence not deterministic) will be different than official files.\n\n+10 million row files have been compressed with 7-zip and split in 1GB volumes if needed.\nThose files have been uploaded using git lfs. \n\nExpected output ('.out') have been generated using Java implementations. Nothing has been done to verify results are correct.\n\nOther files are from URL with expected outputs.\n\nDownload or clone with:" ]

[ "TAGS\n#size_categories-1B<n<10B #language-English #license-apache-2.0 #region-us \n", "# URL\n1️⃣️ The One Billion Row Challenge - Data files only if you can't be bothered with Java \nor write a generator but would rather download +3GB \n\nSee URL for original Java challenge.\n\nLarge data files have been generated on my machine and given official Java generator is random\n(not seeded and hence not deterministic) will be different than official files.\n\n+10 million row files have been compressed with 7-zip and split in 1GB volumes if needed.\nThose files have been uploaded using git lfs. \n\nExpected output ('.out') have been generated using Java implementations. Nothing has been done to verify results are correct.\n\nOther files are from URL with expected outputs.\n\nDownload or clone with:" ]

[ 30, 161 ]

[ "passage: TAGS\n#size_categories-1B<n<10B #language-English #license-apache-2.0 #region-us \n# URL\n1️⃣️ The One Billion Row Challenge - Data files only if you can't be bothered with Java \nor write a generator but would rather download +3GB \n\nSee URL for original Java challenge.\n\nLarge data files have been generated on my machine and given official Java generator is random\n(not seeded and hence not deterministic) will be different than official files.\n\n+10 million row files have been compressed with 7-zip and split in 1GB volumes if needed.\nThose files have been uploaded using git lfs. \n\nExpected output ('.out') have been generated using Java implementations. Nothing has been done to verify results are correct.\n\nOther files are from URL with expected outputs.\n\nDownload or clone with:" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"hh-rlhf\"\n\nMore Information needed" ]

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

[ 6, 15 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"hh-rlhf\"\n\nMore Information needed" ]

[ "task_categories:text-classification", "task_categories:token-classification", "task_categories:text-generation", "task_categories:fill-mask", "size_categories:10K<n<100K", "language:en", "books", "text", "region:us" ]

[]

[ "en" ]

[ "# Welcome to the World of Gutendex English Books!\n\nThis repository brings you a curated collection of English books from the vast Gutendex library, hosted on the amazing Hugging Face platform. Dive into a plethora of classics, timeless gems, and lesser-known treasures, all waiting to be explored and rediscovered.", "## What's inside?\n\n+ Thousands of English books: We've meticulously handpicked and processed a diverse selection of English books, spanning various genres and eras. From adventure novels and historical sagas to philosophical treatises and poetry anthologies, you'll find something for every taste.\n+ Clean and accessible text: Each book is carefully cleaned and converted to plain text format, making it readily available for natural language processing (NLP) tasks and analysis.\n+ Easy-to-use metadata: Each book comes with rich metadata, including author, title, publication date, genre, and language. This makes it simple to filter, search, and organize your literary adventures.\n+ Open and shareable: This repository is built on the collaborative spirit of Hugging Face. Feel free to fork, contribute, and build upon this collection to create your own unique literary playground.", "## Getting started:\n\n+ Explore the dataset: Browse the list of available books or use the provided metadata to find specific titles or genres.\n+ ⬇️ Download & Use: Each book is readily available for download in plain text format. Feel free to integrate them into your NLP projects, build custom applications, or simply enjoy reading them in their digital form.\n+ Contribute & share: This is just the beginning! If you find a missing book, have suggestions for improvement, or want to create new features, we encourage you to contribute and be part of the growing community.", "## Beyond the bookshelf:\n\nThis repository is not just a collection of books, it's a springboard for creativity and innovation. Here are some potential applications:\n\n+ Train your own NLP models: Use this dataset to train language models on diverse writing styles and historical texts.\n+ Build research projects: Analyze literary trends, explore author similarities, or develop new methods for text analysis.\n+ Spark creativity: Draw inspiration from timeless stories and craft your own literary masterpieces.\n+ Share your love of books: Create engaging applications, interactive experiences, or simply recommend hidden gems to fellow bookworms.", "## Let the adventure begin!\n\nWe hope this repository opens up a world of possibilities for readers, researchers, and NLP enthusiasts alike. So grab your bookworm hat, embark on a literary journey, and don't hesitate to leave your mark on this ever-growing treasure trove of words.", "## Happy reading!\n\nP.S. Feel free to reach out if you have any questions, suggestions, or simply want to share your favorite book from the collection. We're always happy to hear from fellow bibliophiles!" ]

[ "TAGS\n#task_categories-text-classification #task_categories-token-classification #task_categories-text-generation #task_categories-fill-mask #size_categories-10K<n<100K #language-English #books #text #region-us \n", "# Welcome to the World of Gutendex English Books!\n\nThis repository brings you a curated collection of English books from the vast Gutendex library, hosted on the amazing Hugging Face platform. Dive into a plethora of classics, timeless gems, and lesser-known treasures, all waiting to be explored and rediscovered.", "## What's inside?\n\n+ Thousands of English books: We've meticulously handpicked and processed a diverse selection of English books, spanning various genres and eras. From adventure novels and historical sagas to philosophical treatises and poetry anthologies, you'll find something for every taste.\n+ Clean and accessible text: Each book is carefully cleaned and converted to plain text format, making it readily available for natural language processing (NLP) tasks and analysis.\n+ Easy-to-use metadata: Each book comes with rich metadata, including author, title, publication date, genre, and language. This makes it simple to filter, search, and organize your literary adventures.\n+ Open and shareable: This repository is built on the collaborative spirit of Hugging Face. Feel free to fork, contribute, and build upon this collection to create your own unique literary playground.", "## Getting started:\n\n+ Explore the dataset: Browse the list of available books or use the provided metadata to find specific titles or genres.\n+ ⬇️ Download & Use: Each book is readily available for download in plain text format. Feel free to integrate them into your NLP projects, build custom applications, or simply enjoy reading them in their digital form.\n+ Contribute & share: This is just the beginning! If you find a missing book, have suggestions for improvement, or want to create new features, we encourage you to contribute and be part of the growing community.", "## Beyond the bookshelf:\n\nThis repository is not just a collection of books, it's a springboard for creativity and innovation. Here are some potential applications:\n\n+ Train your own NLP models: Use this dataset to train language models on diverse writing styles and historical texts.\n+ Build research projects: Analyze literary trends, explore author similarities, or develop new methods for text analysis.\n+ Spark creativity: Draw inspiration from timeless stories and craft your own literary masterpieces.\n+ Share your love of books: Create engaging applications, interactive experiences, or simply recommend hidden gems to fellow bookworms.", "## Let the adventure begin!\n\nWe hope this repository opens up a world of possibilities for readers, researchers, and NLP enthusiasts alike. So grab your bookworm hat, embark on a literary journey, and don't hesitate to leave your mark on this ever-growing treasure trove of words.", "## Happy reading!\n\nP.S. Feel free to reach out if you have any questions, suggestions, or simply want to share your favorite book from the collection. We're always happy to hear from fellow bibliophiles!" ]

[ 71, 82, 203, 125, 141, 75, 46 ]

[ "passage: TAGS\n#task_categories-text-classification #task_categories-token-classification #task_categories-text-generation #task_categories-fill-mask #size_categories-10K<n<100K #language-English #books #text #region-us \n# Welcome to the World of Gutendex English Books!\n\nThis repository brings you a curated collection of English books from the vast Gutendex library, hosted on the amazing Hugging Face platform. Dive into a plethora of classics, timeless gems, and lesser-known treasures, all waiting to be explored and rediscovered.## What's inside?\n\n+ Thousands of English books: We've meticulously handpicked and processed a diverse selection of English books, spanning various genres and eras. From adventure novels and historical sagas to philosophical treatises and poetry anthologies, you'll find something for every taste.\n+ Clean and accessible text: Each book is carefully cleaned and converted to plain text format, making it readily available for natural language processing (NLP) tasks and analysis.\n+ Easy-to-use metadata: Each book comes with rich metadata, including author, title, publication date, genre, and language. This makes it simple to filter, search, and organize your literary adventures.\n+ Open and shareable: This repository is built on the collaborative spirit of Hugging Face. Feel free to fork, contribute, and build upon this collection to create your own unique literary playground.## Getting started:\n\n+ Explore the dataset: Browse the list of available books or use the provided metadata to find specific titles or genres.\n+ ⬇️ Download & Use: Each book is readily available for download in plain text format. Feel free to integrate them into your NLP projects, build custom applications, or simply enjoy reading them in their digital form.\n+ Contribute & share: This is just the beginning! If you find a missing book, have suggestions for improvement, or want to create new features, we encourage you to contribute and be part of the growing community." ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of nlpguy/Lelantos-low-tune\n\n\n\nDataset automatically created during the evaluation run of model nlpguy/Lelantos-low-tune on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T20:37:11.486361(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of nlpguy/Lelantos-low-tune\n\n\n\nDataset automatically created during the evaluation run of model nlpguy/Lelantos-low-tune on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T20:37:11.486361(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 185, 67, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of nlpguy/Lelantos-low-tune\n\n\n\nDataset automatically created during the evaluation run of model nlpguy/Lelantos-low-tune on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T20:37:11.486361(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of mlabonne/Daredevil-7B\n\n\n\nDataset automatically created during the evaluation run of model mlabonne/Daredevil-7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T20:52:48.007383(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of mlabonne/Daredevil-7B\n\n\n\nDataset automatically created during the evaluation run of model mlabonne/Daredevil-7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T20:52:48.007383(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 179, 67, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of mlabonne/Daredevil-7B\n\n\n\nDataset automatically created during the evaluation run of model mlabonne/Daredevil-7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T20:52:48.007383(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of occultml/CatMarcoro14-7B-slerp\n\n\n\nDataset automatically created during the evaluation run of model occultml/CatMarcoro14-7B-slerp on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T21:04:34.082486(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of occultml/CatMarcoro14-7B-slerp\n\n\n\nDataset automatically created during the evaluation run of model occultml/CatMarcoro14-7B-slerp on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-06T21:04:34.082486(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 187, 68, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of occultml/CatMarcoro14-7B-slerp\n\n\n\nDataset automatically created during the evaluation run of model occultml/CatMarcoro14-7B-slerp on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-06T21:04:34.082486(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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" ]

[ "region:us" ]

[]

[]

[ "# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'", "# Args" ]

[ "TAGS\n#region-us \n", "# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'", "# Args" ]

[ 6, 384, 3 ]

[ "passage: TAGS\n#region-us \n# TL;DR SFT Dataset for OpenAI's Summarize from Feedback task\n\nThe dataset is directly taken from URL\n\nThese columns are taken directly from the aforementioned dataset:\n\n* id: unique identifier for the post\n* subreddit: subreddit the post was taken from\n* title: title of the post\n* post: body of the post\n* summary: summary of the post\n* reference_response: reference response for the post\n\nThese columns are added by this preprocessing script:\n* query: length-limited query for summarization: OAI pre-processes the main text (title + subreddit + post), ensuring it has only 512 tokens; if the main text is too long, then it tries to truncate at the last '\n'. If it's too short it pads the main text (summarize_from_feedback/URL#L98-L165). Padding is either space or '[PAD]' token (see Args below).\n* query_token: tokenized version of 'query'\n* reference_response_token: tokenized version of 'reference_response'\n* reference_response_token_len: length of 'reference_response_token'\n* query_reference_response: concatenation of 'URL()' and 'reference_response'\n* query_reference_response_token: tokenized version of 'query_reference_response', up to 'max_sft_query_response_length' tokens\n* query_reference_response_token_len: length of 'query_reference_response_token'# Args" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1704578687\"\n\nMore Information needed" ]

[ "TAGS\n#region-us \n", "# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1704578687\"\n\nMore Information needed" ]

[ 6, 30 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for \"summarize_from_feedback_oai_preprocessing_1704578687\"\n\nMore Information needed" ]

[ "region:us" ]

[]

[]

[ "# Dataset Card for Evaluation run of jilp00/OpenHermes-Symbolic-Mistral-7B\n\n\n\nDataset automatically created during the evaluation run of model jilp00/OpenHermes-Symbolic-Mistral-7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-08T02:06:58.494676(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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#region-us \n", "# Dataset Card for Evaluation run of jilp00/OpenHermes-Symbolic-Mistral-7B\n\n\n\nDataset automatically created during the evaluation run of model jilp00/OpenHermes-Symbolic-Mistral-7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:", "## Latest results\n\nThese are the latest results from run 2024-01-08T02:06:58.494676(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):", "## 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" ]

[ 6, 193, 67, 4, 40, 29, 3, 4, 9, 6, 5, 7, 4, 7, 10, 9, 5, 9, 8, 10, 46, 8, 7, 10, 5 ]

[ "passage: TAGS\n#region-us \n# Dataset Card for Evaluation run of jilp00/OpenHermes-Symbolic-Mistral-7B\n\n\n\nDataset automatically created during the evaluation run of model jilp00/OpenHermes-Symbolic-Mistral-7B on the Open LLM Leaderboard.\n\nThe dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.\n\nThe dataset has been created from 2 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The \"train\" split is always pointing to the latest results.\n\nAn additional configuration \"results\" store all the aggregated results of the run (and is used to compute and display the aggregated metrics on the Open LLM Leaderboard).\n\nTo load the details from a run, you can for instance do the following:## Latest results\n\nThese are the latest results from run 2024-01-08T02:06:58.494676(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the \"latest\" split for each eval):## 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]" ]

[ "task_categories:translation", "license:mit", "openai ", "finetune", "translation", "region:us" ]

[]

[]

[ "# Overview of the Financial News Translation Dataset for OpenAI Model Fine-tuning", "## Introduction:\nThis dataset has been curated with the primary objective of fine-tuning varioyus language models to effectively translate financial news content embedded in HTML format. The intention is to enhance the language model's proficiency in accurately and contextually translating financial information for a global audience in a production envionrment.", "## Dataset Composition:\nThe dataset encompasses a diverse and comprehensive collection of financial news articles sourced from Benzinga, covering a wide range of topics such as market trends, economic indicators, company reports, and financial analyses. The articles are presented in HTML format, reflecting the real-world structure of web pages commonly used to disseminate financial information.", "## Key Features:\n\n- Multilingual Content: The dataset includes financial news articles in various languages, enabling the model to develop a robust understanding of language nuances specific to the financial domain across diverse linguistic landscapes.\n\n- HTML Structure: To simulate real-world scenarios, the dataset preserves the HTML structure of the financial news articles. This structure includes elements such as headers, paragraphs, lists, and embedded multimedia, ensuring that the model learns to navigate and translate content within the context of web-based presentations.\n\n- Domain-specific Vocabulary: The dataset incorporates a rich set of domain-specific terms and jargon commonly found in financial news. This ensures that the fine-tuned model not only accurately translates general language but also captures the intricacies of financial terminology, promoting precise and contextually relevant translations.\n\n- Varied Content Lengths: Financial news articles often vary in length and complexity. The dataset includes articles of different lengths to expose the model to a wide spectrum of text, enabling it to handle both brief updates and in-depth analyses effectively.", "## Use Case and Significance:\nThe fine-tuned model resulting from this dataset aims to empower applications and services that require the translation of financial news content for a global audience. It has the potential to facilitate timely and accurate dissemination of financial information across language barriers, supporting decision-making processes in the international financial landscape." ]

[ "TAGS\n#task_categories-translation #license-mit #openai #finetune #translation #region-us \n", "# Overview of the Financial News Translation Dataset for OpenAI Model Fine-tuning", "## Introduction:\nThis dataset has been curated with the primary objective of fine-tuning varioyus language models to effectively translate financial news content embedded in HTML format. The intention is to enhance the language model's proficiency in accurately and contextually translating financial information for a global audience in a production envionrment.", "## Dataset Composition:\nThe dataset encompasses a diverse and comprehensive collection of financial news articles sourced from Benzinga, covering a wide range of topics such as market trends, economic indicators, company reports, and financial analyses. The articles are presented in HTML format, reflecting the real-world structure of web pages commonly used to disseminate financial information.", "## Key Features:\n\n- Multilingual Content: The dataset includes financial news articles in various languages, enabling the model to develop a robust understanding of language nuances specific to the financial domain across diverse linguistic landscapes.\n\n- HTML Structure: To simulate real-world scenarios, the dataset preserves the HTML structure of the financial news articles. This structure includes elements such as headers, paragraphs, lists, and embedded multimedia, ensuring that the model learns to navigate and translate content within the context of web-based presentations.\n\n- Domain-specific Vocabulary: The dataset incorporates a rich set of domain-specific terms and jargon commonly found in financial news. This ensures that the fine-tuned model not only accurately translates general language but also captures the intricacies of financial terminology, promoting precise and contextually relevant translations.\n\n- Varied Content Lengths: Financial news articles often vary in length and complexity. The dataset includes articles of different lengths to expose the model to a wide spectrum of text, enabling it to handle both brief updates and in-depth analyses effectively.", "## Use Case and Significance:\nThe fine-tuned model resulting from this dataset aims to empower applications and services that require the translation of financial news content for a global audience. It has the potential to facilitate timely and accurate dissemination of financial information across language barriers, supporting decision-making processes in the international financial landscape." ]

[ 29, 18, 78, 83, 256, 74 ]

[ "passage: TAGS\n#task_categories-translation #license-mit #openai #finetune #translation #region-us \n# Overview of the Financial News Translation Dataset for OpenAI Model Fine-tuning## Introduction:\nThis dataset has been curated with the primary objective of fine-tuning varioyus language models to effectively translate financial news content embedded in HTML format. The intention is to enhance the language model's proficiency in accurately and contextually translating financial information for a global audience in a production envionrment.## Dataset Composition:\nThe dataset encompasses a diverse and comprehensive collection of financial news articles sourced from Benzinga, covering a wide range of topics such as market trends, economic indicators, company reports, and financial analyses. The articles are presented in HTML format, reflecting the real-world structure of web pages commonly used to disseminate financial information.## Key Features:\n\n- Multilingual Content: The dataset includes financial news articles in various languages, enabling the model to develop a robust understanding of language nuances specific to the financial domain across diverse linguistic landscapes.\n\n- HTML Structure: To simulate real-world scenarios, the dataset preserves the HTML structure of the financial news articles. This structure includes elements such as headers, paragraphs, lists, and embedded multimedia, ensuring that the model learns to navigate and translate content within the context of web-based presentations.\n\n- Domain-specific Vocabulary: The dataset incorporates a rich set of domain-specific terms and jargon commonly found in financial news. This ensures that the fine-tuned model not only accurately translates general language but also captures the intricacies of financial terminology, promoting precise and contextually relevant translations.\n\n- Varied Content Lengths: Financial news articles often vary in length and complexity. The dataset includes articles of different lengths to expose the model to a wide spectrum of text, enabling it to handle both brief updates and in-depth analyses effectively." ]

[ "region:us" ]

[]

[]

[ "# Celebrity 1000\nTop 1000 celebrities. 18,184 images. 256x256. Square cropped to face. Embeddings generated with tonyassi/celebrity-classifier." ]

[ "TAGS\n#region-us \n", "# Celebrity 1000\nTop 1000 celebrities. 18,184 images. 256x256. Square cropped to face. Embeddings generated with tonyassi/celebrity-classifier." ]

[ 6, 42 ]

[ "passage: TAGS\n#region-us \n# Celebrity 1000\nTop 1000 celebrities. 18,184 images. 256x256. Square cropped to face. Embeddings generated with tonyassi/celebrity-classifier." ]

[ "language:en", "language:es", "language:ru", "language:zh", "language:de", "language:fr", "language:th", "language:ca", "language:it", "language:ja", "language:pl", "language:eo", "language:eu", "language:vi", "language:fi", "language:hu", "language:ar", "language:nl", "language:da", "language:tr", "language:ko", "language:he", "language:id", "language:cs", "language:bn", "language:sv", "region:us" ]

[]

[ "en", "es", "ru", "zh", "de", "fr", "th", "ca", "it", "ja", "pl", "eo", "eu", "vi", "fi", "hu", "ar", "nl", "da", "tr", "ko", "he", "id", "cs", "bn", "sv" ]

[]

[ "TAGS\n#language-English #language-Spanish #language-Russian #language-Chinese #language-German #language-French #language-Thai #language-Catalan #language-Italian #language-Japanese #language-Polish #language-Esperanto #language-Basque #language-Vietnamese #language-Finnish #language-Hungarian #language-Arabic #language-Dutch #language-Danish #language-Turkish #language-Korean #language-Hebrew #language-Indonesian #language-Czech #language-Bengali #language-Swedish #region-us \n" ]

[ 143 ]

[ "passage: TAGS\n#language-English #language-Spanish #language-Russian #language-Chinese #language-German #language-French #language-Thai #language-Catalan #language-Italian #language-Japanese #language-Polish #language-Esperanto #language-Basque #language-Vietnamese #language-Finnish #language-Hungarian #language-Arabic #language-Dutch #language-Danish #language-Turkish #language-Korean #language-Hebrew #language-Indonesian #language-Czech #language-Bengali #language-Swedish #region-us \n" ]