datasetId
stringlengths
5
121
author
stringlengths
2
42
last_modified
unknown
downloads
int64
0
4.67M
likes
int64
0
7.57k
tags
sequencelengths
1
7.92k
task_categories
sequencelengths
0
47
createdAt
unknown
card
stringlengths
15
1.02M
docintel/ChartQA
docintel
"2025-02-25T21:11:28Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T21:11:24Z"
--- dataset_info: features: - name: id dtype: int64 - name: type dtype: string - name: question dtype: string - name: answer dtype: string - name: image dtype: image splits: - name: test num_bytes: 115872506.0 num_examples: 2500 download_size: 72614164 dataset_size: 115872506.0 configs: - config_name: default data_files: - split: test path: data/test-* ---
tturing/so100_03_robotp
tturing
"2025-02-25T21:16:50Z"
3
0
[ "task_categories:robotics", "license:apache-2.0", "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:timeseries", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "LeRobot", "so100", "biJCR" ]
[ "robotics" ]
"2025-02-25T21:16:48Z"
--- license: apache-2.0 task_categories: - robotics tags: - LeRobot - so100 - biJCR configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** [More Information Needed] - **License:** apache-2.0 ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "so100", "total_episodes": 1, "total_frames": 895, "total_tasks": 1, "total_videos": 1, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:1" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "action": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.state": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.images.rscam": { "dtype": "video", "shape": [ 480, 640, 3 ], "names": [ "height", "width", "channels" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "h264", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex [More Information Needed] ```
kaamd/tdngl-pfj
kaamd
"2025-02-25T21:18:17Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T21:18:16Z"
--- dataset_info: features: - name: url dtype: string - name: content dtype: string splits: - name: train num_bytes: 816990 num_examples: 218 download_size: 300464 dataset_size: 816990 configs: - config_name: default data_files: - split: train path: data/train-* ---
mlfoundations-dev/instruction_filtering_scale_up_math_base_fasttext_per_domain
mlfoundations-dev
"2025-02-25T21:47:31Z"
3
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T21:27:48Z"
--- dataset_info: features: - name: instruction_seed dtype: string - name: source dtype: string splits: - name: train num_bytes: 3836385.712082465 num_examples: 16000 download_size: 2084942 dataset_size: 3836385.712082465 configs: - config_name: default data_files: - split: train path: data/train-* ---
mlfoundations-dev/instruction_filtering_scale_up_math_base_gemini_length
mlfoundations-dev
"2025-02-26T04:39:09Z"
3
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T21:27:48Z"
--- dataset_info: features: - name: instruction_seed dtype: string - name: source dtype: string - name: gemini_response dtype: string - name: __original_row_idx dtype: int64 - name: length dtype: int64 splits: - name: train num_bytes: 51624263.2 num_examples: 16000 download_size: 24998340 dataset_size: 51624263.2 configs: - config_name: default data_files: - split: train path: data/train-* ---
nicher92/acsl_c_code_pairs_filtered_v1
nicher92
"2025-02-25T21:46:21Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T21:46:19Z"
--- dataset_info: features: - name: success dtype: bool - name: failures sequence: 'null' - name: output_from_frama_c dtype: string - name: error_messages sequence: string - name: was_it_fixed dtype: bool - name: acsl_snippet dtype: string - name: c_code_snippet dtype: string - name: extracted_error dtype: string - name: total_goals dtype: int64 - name: verified_goals dtype: int64 - name: rest_of_file dtype: string splits: - name: train num_bytes: 15355030.166362368 num_examples: 589 download_size: 802276 dataset_size: 15355030.166362368 configs: - config_name: default data_files: - split: train path: data/train-* ---
Mohamed-DLM/asr_en_ar_switch_split_93_final_updated
Mohamed-DLM
"2025-02-25T22:05:13Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T21:46:38Z"
--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription dtype: string splits: - name: train num_bytes: 6053199.0 num_examples: 55 download_size: 5404911 dataset_size: 6053199.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
HumanoidTeam/aloha_cube_binary_old_format_v1_test
HumanoidTeam
"2025-02-25T21:54:47Z"
3
0
[ "task_categories:robotics", "size_categories:n<1K", "format:parquet", "modality:image", "modality:timeseries", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "LeRobot" ]
[ "robotics" ]
"2025-02-25T21:54:37Z"
--- task_categories: - robotics tags: - LeRobot --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).
tturing/so100_03_tools0
tturing
"2025-02-25T21:57:59Z"
3
0
[ "task_categories:robotics", "license:apache-2.0", "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:timeseries", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "LeRobot", "so100", "biJCR" ]
[ "robotics" ]
"2025-02-25T21:57:57Z"
--- license: apache-2.0 task_categories: - robotics tags: - LeRobot - so100 - biJCR configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** [More Information Needed] - **License:** apache-2.0 ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "so100", "total_episodes": 1, "total_frames": 895, "total_tasks": 1, "total_videos": 1, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:1" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "action": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.state": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.images.rscam": { "dtype": "video", "shape": [ 480, 640, 3 ], "names": [ "height", "width", "channels" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "h264", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex [More Information Needed] ```
Mohamed-DLM/asr_en_ar_switch_split_94_final_updated
Mohamed-DLM
"2025-02-25T22:20:17Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:audio", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T22:08:01Z"
--- dataset_info: features: - name: audio dtype: audio: sampling_rate: 16000 - name: transcription dtype: string splits: - name: train num_bytes: 4824660.0 num_examples: 53 download_size: 4348383 dataset_size: 4824660.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
1un9i13/country
1un9i13
"2025-02-25T22:15:53Z"
3
0
[ "license:mit", "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T22:12:58Z"
--- license: mit configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: country dtype: string - name: capital dtype: string - name: continent dtype: string splits: - name: train num_bytes: 6827 num_examples: 194 download_size: 6066 dataset_size: 6827 ---
cchoi1/humaneval-datagen-run-3_best_att_50_sol_50_20250225_085059
cchoi1
"2025-02-25T22:14:52Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T22:14:51Z"
--- dataset_info: features: - name: problem_id dtype: string - name: prompt dtype: string - name: canonical_solution dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: chosen_attack dtype: string - name: chosen_attack_explanation dtype: string - name: chosen_solution dtype: string - name: chosen_solution_explanation dtype: string - name: chosen_solve_rate dtype: float64 - name: rejected_attack dtype: string - name: rejected_attack_explanation dtype: string - name: rejected_solution dtype: string - name: rejected_solution_explanation dtype: string - name: rejected_solve_rate dtype: float64 splits: - name: train num_bytes: 5255818 num_examples: 2100 download_size: 287701 dataset_size: 5255818 configs: - config_name: default data_files: - split: train path: data/train-* ---
tturing/so100_03_books
tturing
"2025-02-25T22:22:48Z"
3
0
[ "task_categories:robotics", "license:apache-2.0", "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:timeseries", "modality:video", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "LeRobot", "so100", "biJCR" ]
[ "robotics" ]
"2025-02-25T22:22:46Z"
--- license: apache-2.0 task_categories: - robotics tags: - LeRobot - so100 - biJCR configs: - config_name: default data_files: data/*/*.parquet --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot). ## Dataset Description - **Homepage:** [More Information Needed] - **Paper:** [More Information Needed] - **License:** apache-2.0 ## Dataset Structure [meta/info.json](meta/info.json): ```json { "codebase_version": "v2.0", "robot_type": "so100", "total_episodes": 1, "total_frames": 895, "total_tasks": 1, "total_videos": 1, "total_chunks": 1, "chunks_size": 1000, "fps": 30, "splits": { "train": "0:1" }, "data_path": "data/chunk-{episode_chunk:03d}/episode_{episode_index:06d}.parquet", "video_path": "videos/chunk-{episode_chunk:03d}/{video_key}/episode_{episode_index:06d}.mp4", "features": { "action": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.state": { "dtype": "float32", "shape": [ 6 ], "names": [ "main_shoulder_pan", "main_shoulder_lift", "main_elbow_flex", "main_wrist_flex", "main_wrist_roll", "main_gripper" ] }, "observation.images.rscam": { "dtype": "video", "shape": [ 480, 640, 3 ], "names": [ "height", "width", "channels" ], "info": { "video.fps": 30.0, "video.height": 480, "video.width": 640, "video.channels": 3, "video.codec": "h264", "video.pix_fmt": "yuv420p", "video.is_depth_map": false, "has_audio": false } }, "timestamp": { "dtype": "float32", "shape": [ 1 ], "names": null }, "frame_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "episode_index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "index": { "dtype": "int64", "shape": [ 1 ], "names": null }, "task_index": { "dtype": "int64", "shape": [ 1 ], "names": null } } } ``` ## Citation **BibTeX:** ```bibtex [More Information Needed] ```
nellaep/NellFam
nellaep
"2025-02-25T22:25:27Z"
3
0
[ "license:llama3.3", "size_categories:n<1K", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T22:24:44Z"
--- license: llama3.3 ---
mjpsm/meba_fam_info
mjpsm
"2025-02-25T22:25:41Z"
3
0
[ "license:llama3.2", "size_categories:n<1K", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T22:25:05Z"
--- license: llama3.2 ---
HumanoidTeam/aloha_cube_binary_old_format_v1_test_2
HumanoidTeam
"2025-02-25T22:37:17Z"
3
0
[ "task_categories:robotics", "region:us", "LeRobot" ]
[ "robotics" ]
"2025-02-25T22:37:10Z"
--- task_categories: - robotics tags: - LeRobot --- This dataset was created using [LeRobot](https://github.com/huggingface/lerobot).
datalab-to/marker_benchmark_comparison_olmocr_llm
datalab-to
"2025-02-26T00:07:48Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T23:40:28Z"
--- dataset_info: features: - name: uuid dtype: int64 - name: classification dtype: string - name: language dtype: string - name: img dtype: image - name: marker_md dtype: string - name: marker_img dtype: image - name: marker_heuristic dtype: float64 - name: marker_heuristic_detail dtype: string - name: marker_llm dtype: int64 - name: marker_llm_detail dtype: string - name: olmocr_md dtype: string - name: olmocr_img dtype: image - name: olmocr_heuristic dtype: float64 - name: olmocr_heuristic_detail dtype: string - name: olmocr_llm dtype: float64 - name: olmocr_llm_detail dtype: string splits: - name: train num_bytes: 16136900.0 num_examples: 25 download_size: 16012100 dataset_size: 16136900.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
sghosts/ocr-thesis-surya
sghosts
"2025-02-25T23:44:04Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T23:43:57Z"
--- dataset_info: features: - name: image dtype: image - name: pdf_path dtype: string - name: page_num dtype: int64 - name: surya dtype: string splits: - name: train num_bytes: 29819014.0 num_examples: 236 download_size: 29620799 dataset_size: 29819014.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
hanR07/safe_packets
hanR07
"2025-02-26T06:06:16Z"
3
0
[ "language:ko", "license:unknown", "region:us" ]
null
"2025-02-26T00:18:46Z"
--- license: unknown language: - ko ---
obiwan96/obiwan96open_web_math_qav3_none_120000_140000
obiwan96
"2025-02-26T00:34:18Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T00:21:22Z"
--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string - name: backtracking_raw dtype: string - name: is_solution_raw dtype: string - name: verification_raw dtype: string - name: subgoal_setting_raw dtype: string - name: backward_chaining_raw dtype: string - name: is_backtrack dtype: string - name: backtrack_count dtype: string - name: backtrack_rationale dtype: string - name: is_backchain dtype: string - name: backchain_count dtype: string - name: backchain_rationale dtype: string - name: is_verification dtype: string - name: verification_count dtype: string - name: verification_rationale dtype: string - name: contain_problem dtype: string - name: contain_solution dtype: string - name: domain_broad dtype: string - name: domain_specific dtype: string - name: solution_rationale dtype: string - name: raw_qa dtype: string - name: query dtype: string - name: completion dtype: string splits: - name: train num_bytes: 122814908 num_examples: 7463 download_size: 53808656 dataset_size: 122814908 configs: - config_name: default data_files: - split: train path: data/train-* ---
CohenQu/math_reasoning_benchmark
CohenQu
"2025-02-26T00:55:32Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T00:41:22Z"
--- dataset_info: features: - name: problem dtype: string - name: answer dtype: string splits: - name: AMC2023 num_bytes: 11158 num_examples: 40 - name: MinervaMATH num_bytes: 120182 num_examples: 272 - name: MATH500 num_bytes: 104912 num_examples: 500 - name: AIME2024 num_bytes: 10081 num_examples: 30 - name: AIME2025 num_bytes: 14629 num_examples: 30 download_size: 288780 dataset_size: 260962 configs: - config_name: default data_files: - split: MinervaMATH path: data/MinervaMATH-* - split: MATH500 path: data/MATH500-* - split: AIME2024 path: data/AIME2024-* - split: AIME2025 path: data/AIME2025-* - split: AMC2023 path: data/AMC2023-* ---
Asap7772/Asap7772open_web_math_backtrack_40k__10000_20000
Asap7772
"2025-02-26T02:56:36Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T01:25:14Z"
--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string - name: backtracking_raw dtype: string - name: is_solution_raw dtype: string - name: verification_raw dtype: string - name: subgoal_setting_raw dtype: string - name: backward_chaining_raw dtype: string - name: is_backtrack dtype: string - name: backtrack_count dtype: string - name: backtrack_rationale dtype: string - name: is_backchain dtype: string - name: backchain_count dtype: string - name: backchain_rationale dtype: string - name: is_verification dtype: string - name: verification_count dtype: string - name: verification_rationale dtype: string - name: contain_problem dtype: string - name: contain_solution dtype: string - name: domain_broad dtype: string - name: domain_specific dtype: string - name: solution_rationale dtype: string - name: raw_qa dtype: string - name: query dtype: string - name: completion dtype: string splits: - name: train num_bytes: 180026824 num_examples: 9299 download_size: 67270673 dataset_size: 180026824 configs: - config_name: default data_files: - split: train path: data/train-* ---
Asap7772/Asap7772open_web_math_backtrack_40k__30000_40000
Asap7772
"2025-02-26T03:03:04Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T01:26:40Z"
--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string - name: backtracking_raw dtype: string - name: is_solution_raw dtype: string - name: verification_raw dtype: string - name: subgoal_setting_raw dtype: string - name: backward_chaining_raw dtype: string - name: is_backtrack dtype: string - name: backtrack_count dtype: string - name: backtrack_rationale dtype: string - name: is_backchain dtype: string - name: backchain_count dtype: string - name: backchain_rationale dtype: string - name: is_verification dtype: string - name: verification_count dtype: string - name: verification_rationale dtype: string - name: contain_problem dtype: string - name: contain_solution dtype: string - name: domain_broad dtype: string - name: domain_specific dtype: string - name: solution_rationale dtype: string - name: raw_qa dtype: string - name: query dtype: string - name: completion dtype: string splits: - name: train num_bytes: 181501339 num_examples: 9279 download_size: 67138457 dataset_size: 181501339 configs: - config_name: default data_files: - split: train path: data/train-* ---
Asap7772/Asap7772open_web_math_backtrack_40k__20000_30000
Asap7772
"2025-02-26T02:58:21Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T01:26:54Z"
--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string - name: backtracking_raw dtype: string - name: is_solution_raw dtype: string - name: verification_raw dtype: string - name: subgoal_setting_raw dtype: string - name: backward_chaining_raw dtype: string - name: is_backtrack dtype: string - name: backtrack_count dtype: string - name: backtrack_rationale dtype: string - name: is_backchain dtype: string - name: backchain_count dtype: string - name: backchain_rationale dtype: string - name: is_verification dtype: string - name: verification_count dtype: string - name: verification_rationale dtype: string - name: contain_problem dtype: string - name: contain_solution dtype: string - name: domain_broad dtype: string - name: domain_specific dtype: string - name: solution_rationale dtype: string - name: raw_qa dtype: string - name: query dtype: string - name: completion dtype: string splits: - name: train num_bytes: 179211784 num_examples: 9296 download_size: 66465496 dataset_size: 179211784 configs: - config_name: default data_files: - split: train path: data/train-* ---
Asap7772/Asap7772open_web_math_backtrack_40k__0_10000
Asap7772
"2025-02-26T02:58:06Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T01:27:34Z"
--- dataset_info: features: - name: url dtype: string - name: text dtype: string - name: date dtype: string - name: metadata dtype: string - name: backtracking_raw dtype: string - name: is_solution_raw dtype: string - name: verification_raw dtype: string - name: subgoal_setting_raw dtype: string - name: backward_chaining_raw dtype: string - name: is_backtrack dtype: string - name: backtrack_count dtype: string - name: backtrack_rationale dtype: string - name: is_backchain dtype: string - name: backchain_count dtype: string - name: backchain_rationale dtype: string - name: is_verification dtype: string - name: verification_count dtype: string - name: verification_rationale dtype: string - name: contain_problem dtype: string - name: contain_solution dtype: string - name: domain_broad dtype: string - name: domain_specific dtype: string - name: solution_rationale dtype: string - name: raw_qa dtype: string - name: query dtype: string - name: completion dtype: string splits: - name: train num_bytes: 178173958 num_examples: 9299 download_size: 66110635 dataset_size: 178173958 configs: - config_name: default data_files: - split: train path: data/train-* ---
mic7ch/manchu_sub2
mic7ch
"2025-02-26T02:11:07Z"
3
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T02:10:41Z"
--- dataset_info: features: - name: im dtype: image - name: roman dtype: string - name: manchu dtype: string splits: - name: train num_bytes: 204002861.6 num_examples: 60000 - name: validation num_bytes: 51000715.4 num_examples: 15000 download_size: 256577300 dataset_size: 255003577.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---
jeanwei0721/finetuning_demo
jeanwei0721
"2025-02-26T02:46:38Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T02:46:37Z"
--- dataset_info: features: - name: prompt dtype: string splits: - name: train num_bytes: 37394 num_examples: 100 download_size: 6542 dataset_size: 37394 configs: - config_name: default data_files: - split: train path: data/train-* ---
gswamy/pythia-1.4B-tldr-dpo_tldr_pythia_1.4b_tword_badbase_1_rm_sft_tldr_pythia_1.4b_tword_1_r_iter_1
gswamy
"2025-02-26T03:12:01Z"
3
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:tabular", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T03:11:56Z"
--- dataset_info: features: - name: iter_1_best_query_response sequence: int64 - name: iter_1_worst_query_response sequence: int64 - name: iter_1_best_mask sequence: int64 - name: iter_1_worst_mask sequence: int64 - name: iter_1_best_reward dtype: float64 - name: iter_1_worst_reward dtype: float64 splits: - name: train num_bytes: 1545157120 num_examples: 92858 download_size: 32595389 dataset_size: 1545157120 configs: - config_name: default data_files: - split: train path: data/train-* ---
ahmetipekci10/Delphi7
ahmetipekci10
"2025-02-26T03:31:50Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T03:30:55Z"
--- dataset_info: features: - name: conversations dtype: string splits: - name: train num_bytes: 1535301.7980636237 num_examples: 650 - name: test num_bytes: 172426.20193637622 num_examples: 73 download_size: 691993 dataset_size: 1707728.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
tttx/3k-unsolved-priority-022525-step1-collated
tttx
"2025-02-26T04:41:33Z"
3
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T04:35:01Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 8343757.456140351 num_examples: 400 - name: test num_bytes: 21049 num_examples: 1 download_size: 2273413 dataset_size: 8364806.456140351 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
group2sealion/11mil_clean
group2sealion
"2025-02-26T05:13:09Z"
3
0
[ "license:apache-2.0", "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T04:59:47Z"
--- license: apache-2.0 ---
cchoi1/humaneval-datagen-run-1_best_att_50_sol_50_20250225_153517
cchoi1
"2025-02-26T05:01:19Z"
3
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T05:01:17Z"
--- dataset_info: features: - name: problem_id dtype: string - name: prompt dtype: string - name: canonical_solution dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: chosen_attack dtype: string - name: chosen_attack_explanation dtype: string - name: chosen_solution dtype: string - name: chosen_solution_explanation dtype: string - name: chosen_solve_rate dtype: float64 - name: rejected_attack dtype: string - name: rejected_attack_explanation dtype: string - name: rejected_solution dtype: string - name: rejected_solution_explanation dtype: string - name: rejected_solve_rate dtype: float64 splits: - name: train num_bytes: 5337625 num_examples: 2157 download_size: 292082 dataset_size: 5337625 configs: - config_name: default data_files: - split: train path: data/train-* ---
mlfoundations-dev/open_r1_hf_get_all_proofs
mlfoundations-dev
"2025-02-26T06:09:35Z"
3
1
[ "size_categories:100K<n<1M", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-26T05:24:44Z"
--- dataset_info: features: - name: problem dtype: string - name: solution dtype: string - name: answer dtype: string - name: problem_type dtype: string - name: question_type dtype: string - name: problem_is_valid dtype: string - name: solution_is_valid dtype: string - name: source dtype: string - name: synthetic dtype: bool - name: generations sequence: string - name: generations_count dtype: int64 - name: correctness_math_verify sequence: bool - name: correct_count dtype: int64 - name: generation dtype: string - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 13999569108 num_examples: 140670 download_size: 5154483543 dataset_size: 13999569108 configs: - config_name: default data_files: - split: train path: data/train-* ---
datatab/SerbianOscarDataset
datatab
"2023-06-04T14:34:49Z"
2
1
[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2023-06-04T14:21:08Z"
--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 374855299.3164062 num_examples: 3037283 - name: test num_bytes: 46856989.550781436 num_examples: 379661 - name: valid num_bytes: 46856866.13281237 num_examples: 379660 download_size: 328089963 dataset_size: 468569155.0 --- # Dataset Card for "SerbianOscarDataset" [More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)
datalama/koqp
datalama
"2023-06-21T06:22:28Z"
2
0
[ "license:mit", "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2023-06-21T06:14:53Z"
--- license: mit dataset_info: features: - name: id dtype: int64 - name: question1 dtype: string - name: question2 dtype: string - name: label dtype: class_label: names: '0': 다른 질문 '1': 같은 질문 splits: - name: train num_bytes: 634021 num_examples: 6888 - name: test num_bytes: 62628 num_examples: 688 download_size: 403049 dataset_size: 696649 --- ## Dataset Description songys님이 오픈소스로 공개한 Question_pair 데이터셋을 약간의 데이터 수정을 거쳐 업로드한 데이터셋. 원본 데이터셋과 자세한 설명은 아래 repo 참고 - **Repository: https://github.com/songys/Question_pair** **수정 사항** - `is_duplicate`를 `label`이라는 필드로 rename함. - test set의 `test_id`를 `id`로 rename함. - 기존 0, 1에 대한 label을 반대로 변경함. - as-is - {"같은 질문": 0, "다른 질문": 1} - to-be - {"같은 질문": 1, "다른 질문": 0} - 최종 field는 'id', 'question1', 'question2', 'label'를 선택하여 저장함. ## Dataset Structure ``` DatasetDict({ train: Dataset({ features: ['id', 'question1', 'question2', 'label'], num_rows: 6888 }) test: Dataset({ features: ['id', 'question1', 'question2', 'label'], num_rows: 688 }) }) ```
tamdiep106/autotrain-data-tam_jp
tamdiep106
"2023-06-23T10:46:11Z"
2
0
[ "language:ja", "region:us" ]
null
"2023-06-23T09:01:33Z"
--- language: - ja --- # AutoTrain Dataset for project: tam_jp ## Dataset Description This dataset has been automatically processed by AutoTrain for project tam_jp. ### Languages The BCP-47 code for the dataset's language is ja. ## Dataset Structure ### Data Instances A sample from this dataset looks as follows: ```json [ { "context": "\u30dd\u30fc\u306f\u30b8\u30e3\u30fc\u30ca\u30ea\u30ba\u30e0\u306e\u6d3b\u767a\u306a\u30dc\u30eb\u30c6\u30a3\u30e2\u30a2\u3092\u751f\u6d3b\u306e\u5834\u306b\u5b9a\u3081\u3001\u30af\u30ec\u30e0\u53d4\u6bcd\u306e\u5bb6\u306b\u5c45\u5019\u3092\u3057\u306a\u304c\u3089(\u5b9f\u5144\u306e\u30a6\u30a3\u30ea\u30a2\u30e0=\u30d8\u30f3\u30ea\u30fc\u306f\u7d50\u6838\u30671831\u5e748\u6708\u306b\u6b7b\u53bb\u3057\u3066\u3044\u305f)\u77ed\u7de8\u5c0f\u8aac\u306e\u57f7\u7b46\u3092\u59cb\u3081\u305f\u30021832\u5e74\u306e1\u6708\u3001\u300e\u30b5\u30bf\u30c7\u30fc\u30fb\u30af\u30aa\u30ea\u30a2\u300f\u8a8c\u306b\u300c\u30e1\u30c3\u30c4\u30a7\u30f3\u30ac\u30fc\u30b7\u30e5\u30bf\u30a4\u30f3\u300d\u304c\u63a1\u7528\u3055\u308c\u3001\u4ee5\u5f8c\u540c\u8a8c\u306b\u300c\u30aa\u30e0\u30ec\u30c3\u30c8\u4faf\u7235\u300d\u300c\u30a8\u30eb\u30b5\u30ec\u30e0\u306e\u7269\u8a9e\u300d\u300c\u606f\u306e\u55aa\u5931\u300d\u300c\u30d0\u30fc\u30b2\u30f3\u306e\u640d\u5931(\u306e\u3061\u300c\u30dc\u30f3\u30dc\u30f3\u300d\u3068\u3057\u3066\u6539\u7b46)\u300d\u304c\u63b2\u8f09\u30011833\u5e74\u304b\u3089\u306f\u300e\u30b5\u30bf\u30c7\u30fc\u30fb\u30f4\u30a3\u30b8\u30bf\u30fc\u300f\u8a8c\u306b\u8a69\u3084\u77ed\u6587\u3092\u63b2\u8f09\u3057\u305f\u3002\u3053\u306e\u9803\u3061\u3087\u3046\u3069\u540c\u300e\u30b5\u30bf\u30c7\u30fc\u30fb\u30f4\u30a3\u30b8\u30bf\u30fc\u300f\u8a8c\u304c\u77ed\u7de8\u3068\u8a69\u306e\u61f8\u8cde\u3092\u6253\u3061\u51fa\u3057\u305f\u305f\u3081\u3001\u30dd\u30fc\u306f\u300e\u30d5\u30a9\u30fc\u30ea\u30aa\u30fb\u30af\u30e9\u30d6\u7269\u8a9e\u300f\u3068\u540d\u3065\u3051\u305f\u77ed\u7de86\u7de8\u3068\u8a69\u3092\u6295\u7a3f\u3001\u3053\u306e\u3046\u3061\u77ed\u7de8\u300c\u58dc\u306e\u4e2d\u306e\u624b\u8a18\u300d\u304c\u6700\u512a\u79c0\u4f5c\u306b\u9078\u3070\u308c\u8cde\u91d150\u30c9\u30eb\u3092\u7372\u5f97\u3057\u305f\u3002\n\n\u3055\u3089\u306b\u30dd\u30fc\u306f\u3001\u3053\u306e\u3068\u304d\u5be9\u67fb\u54e1\u3092\u52d9\u3081\u3066\u3044\u305f\u30dc\u30eb\u30c6\u30a3\u30e2\u30a2\u306e\u8457\u540d\u306a\u653f\u6cbb\u5bb6\u3067\u3042\u308a\u4f5c\u5bb6\u3067\u3042\u3063\u305f\u3001\u30b8\u30e7\u30f3\u30fbP\u30fb\u30b1\u30cd\u30c7\u30a3\u3068\u89aa\u3057\u304f\u306a\u308a\u3001\u5f7c\u306e\u65a1\u65cb\u3067\u30ea\u30c3\u30c1\u30e2\u30f3\u30c9\u306e\u300e\u30b5\u30b6\u30f3\u30fb\u30ea\u30c6\u30e9\u30ea\u30fc\u30fb\u30e1\u30c3\u30bb\u30f3\u30b8\u30e3\u30fc\u300f\u8a8c\u306b\u4f5c\u54c1\u3092\u63b2\u8f09\u3059\u308b\u3088\u3046\u306b\u306a\u3063\u305f\u3002\u3055\u3089\u306b\u305d\u306e\u5f8c\u540c\u8a8c\u306e\u7de8\u96c6\u9577\u304c\u9000\u8077\u3059\u308b\u3068\u3001\u30b1\u30cd\u30c7\u30a3\u306e\u63a8\u85a6\u3067\u300e\u30e1\u30c3\u30bb\u30f3\u30b8\u30e3\u30fc\u300f\u8a8c\u306e\u4e3b\u7b46\u7de8\u96c6\u8005\u3068\u3057\u3066\u8fce\u3048\u3089\u308c\u308b\u3053\u3068\u306b\u306a\u3063\u305f\u3002\u3057\u304b\u3057\u3053\u306e\u9803\u3001\u30dd\u30fc\u306f\u307e\u3060\u5c11\u5973\u3067\u3042\u3063\u305f\u5f93\u59b9\u306e\u30f4\u30a1\u30fc\u30b8\u30cb\u30a2\u3078\u6c42\u5a5a\u3057\u3001\u305d\u308c\u3092\u53d4\u6bcd\u30de\u30e9\u30a4\u30a2\u306b\u62d2\u7d76\u3055\u308c\u3066\u3044\u305f\u3053\u3068\u304b\u3089\u98f2\u9152\u306e\u91cf\u304c\u5897\u3048\u308b\u306a\u3069\u3057\u3066\u5fc3\u60c5\u304c\u8352\u308c\u3066\u304a\u308a\u3001\u300e\u30e1\u30c3\u30bb\u30f3\u30b8\u30e3\u30fc\u300f\u8a8c\u306e\u8077\u3092\u77ed\u671f\u9593\u3067\u8f9e\u3057\u3066\u3057\u307e\u3063\u305f\u3002\u3057\u304b\u3057\u5ea6\u91cd\u306a\u308b\u30dd\u30fc\u306e\u8aac\u5f97\u306b\u30de\u30e9\u30a4\u30a2\u304c\u6298\u308c\u30011833\u5e749\u6708\u306b\u30dc\u30eb\u30c6\u30a3\u30e2\u30a2\u306e\u90e1\u88c1\u5224\u6240\u304b\u3089\u7d50\u5a5a\u8a31\u53ef\u3092\u53d7\u3051\u305f\u3002\u5f53\u6642\u30dd\u30fc\u306f26\u6b73\u3001\u30f4\u30a1\u30fc\u30b8\u30cb\u30a2\u306f\u307e\u3060\u7d50\u5a5a\u4e0d\u53ef\u80fd\u306a13\u6b731\u304b\u6708\u3067\u3042\u3063\u305f\u304c\u3001\u7d50\u5a5a\u8a93\u7d04\u66f8\u306b\u306f21\u6b73\u3068\u8a18\u3055\u308c\u3066\u3044\u305f\u3002", "question": "\u30dd\u30fc\u306f\u300c\u58dc\u306e\u4e2d\u306e\u624b\u8a18\u300d\u304c\u6700\u512a\u79c0\u4f5c\u306b\u9078\u3070\u308c\u308b\u3053\u3069\u3067\u8cde\u91d1\u3044\u304f\u3089\u3092\u7372\u5f97\u3059\u308b\u3053\u3068\u304c\u3067\u304d\u307e\u3057\u305f\u304b\u3002", "answers.text": [ "50\u30c9\u30eb" ], "answers.answer_start": [ 315 ], "feat_id": [ "tr-170-08-002" ], "feat_title": [ "\u30a8\u30c9\u30ac\u30fc\u30fb\u30a2\u30e9\u30f3\u30fb\u30dd\u30fc" ], "feat_question_type": [ "Syntactic variation" ], "feat_answers.answer_type": [ [ "Object" ] ] }, { "context": "\u56fd\u969b\u9023\u5408\u98df\u7ce7\u8fb2\u696d\u6a5f\u95a2(FAO)\u306e\u7d71\u8a08\u306b\u3088\u308c\u3070\u30011950\u5e74\u4ee3\u306b\u306f10\u4e07\u30c8\u30f3\u4f59\u308a\u3067\u3042\u3063\u305f\u4e16\u754c\u306e\u30ca\u30de\u30ba\u76ee\u9b5a\u985e\u306e\u7dcf\u6f01\u7372\u91cf\u306f\u5e74\u3005\u5897\u52a0\u3057\u30011990\u5e74\u4ee3\u5f8c\u534a\u306b\u306f100\u4e07\u30c8\u30f3\u3092\u8d85\u3048\u305f\u3002\n2000\u5e74\u4ee3\u4ee5\u964d\u3082\u5897\u52a0\u306e\u52e2\u3044\u306f\u8870\u3048\u305a\u30012000\u5e74\u306b120\u4e07\u30c8\u30f3\u3060\u3063\u305f\u4e16\u754c\u306e\u7dcf\u6f01\u7372\u91cf\u306f\u30012006\u5e74\u306e\u6642\u70b9\u3067\u500d\u4ee5\u4e0a\u306e260\u4e07\u30c8\u30f3\u306b\u9054\u3057\u3066\u3044\u308b\u3002\n\u5730\u57df\u5225\u306b\u898b\u308b\u3068\u30a2\u30b8\u30a2\u30fb\u30a2\u30d5\u30ea\u30ab\u5730\u57df\u3067\u306e\u4f38\u3073\u304c\u9855\u8457\u3067\u3001\u7279\u306b\u30a2\u30b8\u30a2\u3067\u306f2000\u301c2006\u5e74\u306b\u304b\u3051\u3066\u7d043\u500d\u306e\u5897\u52a0(60\u4e07\u30c8\u30f3\u2192180\u4e07\u30c8\u30f3)\u3092\u8a18\u9332\u3057\u3066\u3044\u308b\u3002\n\u540c\u3058\u671f\u9593\u306b\u304a\u3044\u3066\u3001\u5357\u5317\u30a2\u30e1\u30ea\u30ab\u3067\u306f40\u4e07\u30c8\u30f3\u53f0\u3001\u30e8\u30fc\u30ed\u30c3\u30d1\u3067\u306f1\u4e07\u30c8\u30f3\u53f0\u3067\u5927\u304d\u306a\u5909\u52d5\u3082\u306a\u304f\u63a8\u79fb\u3057\u3066\u304a\u308a\u3001\u8fd1\u5e74\u306e\u30a2\u30b8\u30a2\u5730\u57df\u306e\u4f38\u3073\u304c\u7a81\u51fa\u3057\u3066\u3044\u308b\u3053\u3068\u304c\u308f\u304b\u308b\u3002", "question": "\u4e16\u754c\u306e\u30ca\u30de\u30ba\u76ee\u9b5a\u985e\u306e\u7dcf\u6f01\u7372\u91cf\u304c\u591a\u304b\u3063\u305f\u306e\u306f1950\u5e74\u4ee3\u30681990\u5e74\u4ee3\u5f8c\u534a\u306e\u3069\u3061\u3089\u3067\u3057\u305f\u304b?", "answers.text": [ "1990\u5e74\u4ee3\u5f8c\u534a" ], "answers.answer_start": [ 63 ], "feat_id": [ "tr-419-18-000" ], "feat_title": [ "\u30ca\u30de\u30ba\u76ee" ], "feat_question_type": [ "Logical reasoning" ], "feat_answers.answer_type": [ [ "Date/Time" ] ] } ] ``` ### Dataset Fields The dataset has the following fields (also called "features"): ```json { "context": "Value(dtype='string', id=None)", "question": "Value(dtype='string', id=None)", "answers.text": "Sequence(feature=Value(dtype='string', id=None), length=-1, id=None)", "answers.answer_start": "Sequence(feature=Value(dtype='int32', id=None), length=-1, id=None)", "feat_id": "Sequence(feature=Value(dtype='string', id=None), length=-1, id=None)", "feat_title": "Sequence(feature=Value(dtype='string', id=None), length=-1, id=None)", "feat_question_type": "Sequence(feature=Value(dtype='string', id=None), length=-1, id=None)", "feat_answers.answer_type": "Sequence(feature=Sequence(feature=Value(dtype='string', id=None), length=-1, id=None), length=-1, id=None)" } ``` ### Dataset Splits This dataset is split into a train and validation split. The split sizes are as follow: | Split name | Num samples | | ------------ | ------------------- | | train | 25396 | | valid | 10289 |
ifmain/text-moderation-02-large
ifmain
"2024-06-27T08:13:38Z"
2
5
[ "task_categories:text-classification", "language:en", "size_categories:100K<n<1M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
[ "text-classification" ]
"2024-05-22T20:02:03Z"
--- task_categories: - text-classification language: - en size_categories: - 100K<n<1M --- This dataset based on https://www.kaggle.com/code/danofer/reddit-comments-scores-nlp/ The moderation dataset includes only 410 thousand rows 67% negative and 33% positive comments
NikitaLitvinenko/merged_instruct_refactor2
NikitaLitvinenko
"2024-09-20T09:07:38Z"
2
0
[ "size_categories:1M<n<10M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2024-08-29T09:31:47Z"
--- dataset_info: features: - name: text list: - name: content dtype: string - name: role dtype: string splits: - name: train num_bytes: 5261161528.085671 num_examples: 3604064 - name: test num_bytes: 584574151.9143287 num_examples: 400452 download_size: 3092983764 dataset_size: 5845735680.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
ifmain/text-moderation-02-multilingual
ifmain
"2024-10-13T13:50:00Z"
2
0
[ "language:en", "language:de", "language:fr", "language:es", "language:it", "language:sv", "language:fi", "language:pl", "language:cs", "language:lv", "language:zh", "language:ja", "language:ko", "language:ru", "language:uk", "language:be", "language:kk", "license:apache-2.0", "size_categories:1M<n<10M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2024-10-13T11:37:25Z"
--- license: apache-2.0 datasets: - ifmain/text-moderation-410K language: - en - de - fr - es - it - sv - fi - pl - cs - lv - zh - ja - ko - ru - uk - be - kk --- This dataset is based on [Kaggle](https://www.kaggle.com/code/danofer/reddit-comments-scores-nlp/). It represents a version of [@ifmain/text-moderation-410K](https://huggingface.co/datasets/ifmain/text-moderation-410K) that has been cleansed of semantically similar values and normalized to a 50/50 ratio of negative and neutral entries. The dataset contains 1.5M entries (91K * 17 languages). Before use, augmentation is recommended! (e.g., character substitution to bypass moderation). For augmentation, you can use [@ifmain/StringAugmentor](https://github.com/ifmain/StringAugmentor). Enjoy using it!
ifmain/search_in_text-01
ifmain
"2024-11-14T11:51:17Z"
2
1
[ "task_categories:feature-extraction", "language:ru", "license:apache-2.0", "size_categories:1K<n<10K", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
[ "feature-extraction" ]
"2024-11-14T11:44:41Z"
--- license: apache-2.0 task_categories: - feature-extraction language: - ru pretty_name: Search in text size_categories: - 1K<n<10K --- This is a simple dataset generated by GPT-4o mini for accurate text search in Russian. Format: Story: a story between 500 and 1500 words qa [list]: - q: A question that has an answer as a quote in the text (if there’s no answer, it’s left blank) - a: The answer to the question—if available, it's a quote; if not, the field is left blank - reply: the starting and ending character positions of the quote (accuracy check)—if the answer is blank, reply is "from 0 to 0". The dataset can be used in search models for files and websites.
SKNahin/BanglaQwen-Train-Corpus
SKNahin
"2024-11-19T01:07:00Z"
2
0
[ "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2024-11-18T21:39:01Z"
--- dataset_info: features: - name: text dtype: string - name: source dtype: string - name: first_25k dtype: string - name: score dtype: float64 splits: - name: train num_bytes: 378365114751 num_examples: 58063004 download_size: 164315825007 dataset_size: 378365114751 configs: - config_name: default data_files: - split: train path: data/train-* ---
NusaAksara/OCRData
NusaAksara
"2025-01-23T08:41:45Z"
2
3
[ "license:cc-by-nc-4.0", "size_categories:1K<n<10K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2024-11-28T21:39:51Z"
--- license: cc-by-nc-4.0 configs: - config_name: default data_files: - split: train path: data/train-* dataset_info: features: - name: image_path dtype: string - name: transcription dtype: string - name: transliteration dtype: string - name: translation dtype: string - name: lang dtype: string splits: - name: train num_bytes: 1327785 num_examples: 6434 download_size: 494748 dataset_size: 1327785 --- # Dataset Card for Dataset Name <!-- Provide a quick summary of the dataset. --> This dataset card aims to be a base template for new datasets. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/datasetcard_template.md?plain=1). ## Dataset Details ### Dataset Description <!-- Provide a longer summary of what this dataset is. --> - **Curated by:** [More Information Needed] - **Funded by [optional]:** [More Information Needed] - **Shared by [optional]:** [More Information Needed] - **Language(s) (NLP):** [More Information Needed] - **License:** [More Information Needed] ### Dataset Sources [optional] <!-- Provide the basic links for the dataset. --> - **Repository:** [More Information Needed] - **Paper [optional]:** [More Information Needed] - **Demo [optional]:** [More Information Needed] ## Uses <!-- Address questions around how the dataset is intended to be used. --> ### Direct Use <!-- This section describes suitable use cases for the dataset. --> [More Information Needed] ### Out-of-Scope Use <!-- This section addresses misuse, malicious use, and uses that the dataset will not work well for. --> [More Information Needed] ## Dataset Structure <!-- This section provides a description of the dataset fields, and additional information about the dataset structure such as criteria used to create the splits, relationships between data points, etc. --> [More Information Needed] ## Dataset Creation ### Curation Rationale <!-- Motivation for the creation of this dataset. --> [More Information Needed] ### Source Data <!-- This section describes the source data (e.g. news text and headlines, social media posts, translated sentences, ...). --> #### Data Collection and Processing <!-- This section describes the data collection and processing process such as data selection criteria, filtering and normalization methods, tools and libraries used, etc. --> [More Information Needed] #### Who are the source data producers? <!-- This section describes the people or systems who originally created the data. It should also include self-reported demographic or identity information for the source data creators if this information is available. --> [More Information Needed] ### Annotations [optional] <!-- If the dataset contains annotations which are not part of the initial data collection, use this section to describe them. --> #### Annotation process <!-- This section describes the annotation process such as annotation tools used in the process, the amount of data annotated, annotation guidelines provided to the annotators, interannotator statistics, annotation validation, etc. --> [More Information Needed] #### Who are the annotators? <!-- This section describes the people or systems who created the annotations. --> [More Information Needed] #### Personal and Sensitive Information <!-- State whether the dataset contains data that might be considered personal, sensitive, or private (e.g., data that reveals addresses, uniquely identifiable names or aliases, racial or ethnic origins, sexual orientations, religious beliefs, political opinions, financial or health data, etc.). If efforts were made to anonymize the data, describe the anonymization process. --> [More Information Needed] ## Bias, Risks, and Limitations <!-- This section is meant to convey both technical and sociotechnical limitations. --> [More Information Needed] ### Recommendations <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. --> Users should be made aware of the risks, biases and limitations of the dataset. More information needed for further recommendations. ## Citation [optional] <!-- If there is a paper or blog post introducing the dataset, the APA and Bibtex information for that should go in this section. --> **BibTeX:** [More Information Needed] **APA:** [More Information Needed] ## Glossary [optional] <!-- If relevant, include terms and calculations in this section that can help readers understand the dataset or dataset card. --> [More Information Needed] ## More Information [optional] [More Information Needed] ## Dataset Card Authors [optional] [More Information Needed] ## Dataset Card Contact [More Information Needed]
NusaAksara/Image-to-Segmentation
NusaAksara
"2024-12-19T05:44:47Z"
2
0
[ "license:cc-by-nc-4.0", "size_categories:1K<n<10K", "format:parquet", "modality:image", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2024-12-19T03:33:50Z"
--- license: cc-by-nc-4.0 configs: - config_name: image_data data_files: - split: train path: image_data/train-* - config_name: segmentation_data data_files: - split: train path: segmentation_data/train-* dataset_info: - config_name: image_data features: - name: image_id dtype: string - name: image_url dtype: string - name: height dtype: int64 - name: width dtype: int64 - name: language dtype: string splits: - name: train num_bytes: 46316 num_examples: 359 download_size: 8934 dataset_size: 46316 - config_name: segmentation_data features: - name: image_id dtype: string - name: segmentation_id dtype: int64 - name: segmentation_information sequence: sequence: float64 splits: - name: train num_bytes: 691579 num_examples: 7516 download_size: 283289 dataset_size: 691579 --- # Segmentation Data Subset - `image_id`: Refer to `image_id` on image_data subset - `segmentation_id`: Segmentation identifier - `segmentation_information`: COCO Format annotations: [[x1, y1, x2, y2, x3, y3, x4, y4]]
MMInstruction/Video-T3-QA
MMInstruction
"2025-02-24T15:22:37Z"
2
1
[ "task_categories:question-answering", "language:en", "license:apache-2.0", "size_categories:100K<n<1M", "format:json", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "region:us" ]
[ "question-answering" ]
"2024-12-23T02:31:27Z"
--- license: apache-2.0 task_categories: - question-answering language: - en size_categories: - 100K<n<1M --- --- license: apache-2.0 --- Textual Temporal Understanding Dataset Temporal Reasoning Transfer from Text to Video, ICLR 2025 Project Page: https://video-t3.github.io/ In each json file, we provide LLaVA-style text QA samples, using the synthesization method described in our paper. For example: ```json [ { "from": "human", "value": "Based on the following captions describing keyframes of a video, answer the next question.\n\nCaptions:\nThe image displays a circular emblem with a metallic appearance, conveying a sense of authority and power, suggesting it could be a seal or a logo.\nThe image displays a circular emblem with a metallic appearance, conveying a sense of elegance and sophistication, suggesting it could be a seal or a logo.\nQuestion: How does the conveyed sense of the emblem change in the video?\n(A) from elegance and sophistication to authority and power\n(B) from simplicity and modernity to complexity and tradition\n(C) from authority and power to elegance and sophistication\n(D) from complexity and tradition to simplicity and modernity\n\nProvide only the top choice:\n" }, { "from": "gpt", "value": "(C) from authority and power to elegance and sophistication" } ] ``` You can adapt the sample to your training codebase for enhance the temporal understsanding ability of Video-LLMs. Mixing the dataset with other image-text SFT samples would help mitigate potential forgetting issues. The number of samples could be easily scaled up following the method described in Sec. 3 of the paper. | Dataset | #Relevant Captions | #Distractor Captions | Description | |---------|-------------------|---------------------|-------------| | Order-GPT (N×) | 2~4 | N × 100 ± 50, N ∈ {1, 2, 4, 8} | Order-related questions generated by GPT-4. | | Attribute (N×) | 2 | N × 100 ± 50, N ∈ {1, 2, 4, 8} | Attribute-related questions. | | Order-Template (X) | 3~6 | 200±50 | Order-related questions based on templates X | | Referring | 3 | 200±50 | Temporal referring questions. | | Grounding | 3 | 200±50 | Temporal grounding questions. | Mapping for the dataset with json files: - Order-GPT: `order_train` - Attribute: `attribute_train` - Order-Template: `shuffle_phrase`, `shuffle_sentence`, `shuffle_prefix` - Referring: `refer_begin_end_temp2any` - Grounding: `refer_begin_end_any2temp` ## Citation If you found this dataset to be helpful, please kindly cite our paper: ```bibtex @inproceedings{li2025videot3, author={Li, Lei and Liu, Yuanxin and Yao, Linli and Zhang, Peiyuan and An, Chenxin and Wang, Lean and Sun, Xu and Kong, Lingpeng and Liu, Qi}, title={Temporal Reasoning Transfer from Text to Video}, booktitle = {ICLR 2025}, publisher = {OpenReview.net}, year = {2025}, url = {https://openreview.net/forum?id=sHAvMp5J4R} } ```
Vikhrmodels/librispeech_ru_quantized-wav-unify
Vikhrmodels
"2025-01-02T23:44:34Z"
2
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-01-02T23:44:26Z"
--- dataset_info: features: - name: text dtype: string - name: audio_tokens sequence: sequence: int64 splits: - name: train num_bytes: 115521510 num_examples: 54472 - name: validation num_bytes: 3471081 num_examples: 1400 download_size: 26204194 dataset_size: 118992591 configs: - config_name: default data_files: - split: train path: data/train-* - split: validation path: data/validation-* ---
WinkingFace/CryptoLM-Ripple-XRP-USDT
WinkingFace
"2025-02-26T11:21:24Z"
2
0
[ "license:mit", "region:us", "finance", "crypto", "XRP", "Ripple" ]
null
"2025-01-09T20:13:03Z"
--- tags: - finance - crypto - XRP - Ripple pretty_name: XRP/USDT license: mit --- # XRP Price Dataset with Technical Indicators Welcome to the XRP / USDT Price Dataset with Technical Indicators, hosted by the WinkingFace Team. This dataset is designed to provide comprehensive historical data on XRP prices along with a variety of technical indicators to aid in cryptocurrency trading analysis and research. The dataset is updated every 3 minutes (delayed 1 minute). ## Dataset Description This dataset includes the following columns: - **timestamp**: The date and time of the data point in UTC (Coordinated Universal Time). This is a standard time reference that does not change with seasons or time zones. - **open**: The opening price of XRP at the given timestamp. - **high**: The highest price of XRP during the period. - **low**: The lowest price of XRP during the period. - **close**: The closing price of XRP at the given timestamp. - **volume**: The trading volume of XRP during the period. - **MA_20**: 20-period moving average. - **MA_50**: 50-period moving average. - **MA_200**: 200-period moving average. - **RSI**: Relative Strength Index. - **%K**: Stochastic Oscillator %K. - **%D**: Stochastic Oscillator %D. - **ADX**: Average Directional Index. - **ATR**: Average True Range. - **Trendline**: Calculated trendline value. - **MACD**: Moving Average Convergence Divergence. - **Signal**: Signal line for MACD. - **Histogram**: MACD histogram. - **BL_Upper**: Bollinger Bands Upper. - **BL_Lower**: Bollinger Bands Lower. - **MN_Upper**: Minopy Bands Upper. - **MN_Lower**: Minopy Bands Lower. ## Usage This dataset can be used for: - Developing and testing cryptocurrency trading bots. - Performing technical analysis on XRP price movements. - Researching the effectiveness of various technical indicators. - Training AI models for predictive analytics in cryptocurrency markets. - Building machine learning models to forecast XRP price trends. - Enhancing algorithmic trading strategies with historical data. ## Important Note This dataset is provided for educational and research purposes only. It is not intended as financial advice. Please conduct your own research and consult with a financial advisor before making any investment decisions. ## Donate If you find this dataset useful, please consider donating to support our continued development. - **Bitcoin**: `bc1pcl6pj5k8t04nhhtrq0f5q4ya82kmldw8r6dzdw45uux5hanrkefswjp29r` - **Ethereum**: `0xdc2ef164f5de92acb51fac2cb9ca1fbc43ab6991` - **USDT**: `TDGMU3fJKmbTVRdGg8d9a7xud3uMKpFEe4` - **USDC**: `Bi6DMiGm5YLXv5av87P8m1rUyKtXXrBwMbXnJRT8UQEA` - **BNB**: `0xdc2ef164f5de92acb51fac2cb9ca1fbc43ab6991` - **SOL**: `Bi6DMiGm5YLXv5av87P8m1rUyKtXXrBwMbXnJRT8UQEA` - **TON**: `UQDr_VdpmXw2Wc2jX8FTFhhuyIFueremA5G78KzWhoQW9mOR` - **TRX**: `TDGMU3fJKmbTVRdGg8d9a7xud3uMKpFEe4` - **SUI**: `0x83d33b3af1f421deba5ceaa43b3e14cbe5f2169c7a684592f4a5df2e4382230f` - **DOGE**: `DAe4LN3vYQmTHTrThRhzfZcEMCEBaxvAaH` ## Contributing We welcome contributions to improve this dataset. Please feel free to open issues or submit pull requests. ## Contact For any questions or inquiries, feel free to [contact us here 📨](mailto:contact@winkingfacehub.com).
CNTXTAI0/arabic_dialects_question_and_answer
CNTXTAI0
"2025-01-31T10:41:40Z"
2
4
[ "task_categories:question-answering", "task_categories:text-generation", "task_categories:text2text-generation", "language:ar", "language:en", "license:mit", "size_categories:n<1K", "format:csv", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "arabic", "arabicdialicts", "msa", "Q&A", "STEM", "math" ]
[ "question-answering", "text-generation", "text2text-generation" ]
"2025-01-31T09:59:29Z"
--- license: mit task_categories: - question-answering - text-generation - text2text-generation language: - ar - en tags: - arabic - arabicdialicts - msa - Q&A - STEM - math pretty_name: Build your arabic model with arabic data size_categories: - 100K<n<1M --- Data Content The file provided: Q/A Reasoning dataset contains the following columns: 1. 2. ID # : Denotes the reference ID for: a. Question b. Answer to the question c. Hint d. Reasoning e. Word count for items a to d above Dialects: Contains the following dialects in separate columns: a. English b. MSA c. Emirati d. Egyptian e. Levantine Syria f. Levantine Jordan g. Levantine Palestine h. Levantine Lebanon Data Generation Process The following are the steps that were followed to curate the data: 1. 2. A Question and its answer is generated in English. The Hint and Reasoning for the Question and Answer is provided in subsequent rows. 3. The Word Count row is populated with equivalent word count in the following format: a. Word Count for Question & Answer - sums up total words in the Question and the Answer b. Word Count for Hint & Reasoning - sums up total count of words in the hint and reasoning c. Total Word Count - Sums up total words in categories a & b above. 4. Steps 1-3 is repeated across all Arabic dialects - MSA, Emirati, Egyptian, Levantine Syria, Levantine Jordan, Levantine Palestine, Levantine Lebanon www.cntxt.tech support@cntxtai.ai 2 Data Review Process CNTXT employs thorough review steps to ensure highest quality of data. The following quality checks are conducted to ensure the output data is to the highest standards: Post the conclusion of the data generation process, the review process starts. The team of reviewers is in 2 layers: 1. Review Layer 1: The first set of reviewers are assigned to check the sentence coherence, grammatical correctness and accuracy in the answers provided. If the coherence and correctness of the QA is accurate, the review layer 1 passes it on to Review Layer 2 else they submit the QAs back to annotators for regeneration 2. Review Layer 2: This layer of review checks the correctness of the hint and reasoning sections as well as the word count accuracy. If these elements are all correct, the item under review is considered ready for submission to the customer, else the reviewer edits to ensure the accuracy of these elements and submits their comments on items corrected. The diagram below shows the steps described above: ![IMG_5724.jpeg](https://cdn-uploads.huggingface.co/production/uploads/679c9da27b0963691deadefb/QNrgybWRVygGBRGmOWUiE.jpeg) ![IMG_5725.jpeg](https://cdn-uploads.huggingface.co/production/uploads/679c9da27b0963691deadefb/yFpbInK-GryD6A7Qo-CkT.jpeg) Total Questions: 800 Total Answers:800 Total Hints:800 Total Reasoning:800 Total Question & Answer Word Count: 65,765 Total Hint & Reasoning Word Count:40,483 Total Word Count: 106, 248
NusaAksara/NusaAksara
NusaAksara
"2025-02-14T15:37:23Z"
2
2
[ "size_categories:10K<n<100K", "format:parquet", "modality:image", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-10T10:24:23Z"
--- dataset_info: - config_name: Image Segmentation features: - name: image_id dtype: string - name: image_url dtype: string - name: height dtype: int64 - name: width dtype: int64 - name: language dtype: string - name: segmentation_id dtype: int64 - name: segmentation_information sequence: sequence: float64 splits: - name: train num_bytes: 1571595 num_examples: 7516 download_size: 301685 dataset_size: 1571595 - config_name: Image Transcription (OCR) features: - name: image dtype: string - name: transcription dtype: string - name: script dtype: string splits: - name: train num_bytes: 898838 num_examples: 6265 download_size: 223032 dataset_size: 898838 - config_name: Image Translation features: - name: image dtype: string - name: translation dtype: string - name: script dtype: string splits: - name: train num_bytes: 745523 num_examples: 6265 download_size: 186798 dataset_size: 745523 - config_name: Image Transliteration features: - name: image dtype: string - name: transliteration dtype: string - name: script dtype: string splits: - name: train num_bytes: 745746 num_examples: 6265 download_size: 191620 dataset_size: 745746 - config_name: Transcription LID features: - name: transcription dtype: string - name: language_label dtype: string - name: script dtype: string splits: - name: train num_bytes: 424421 num_examples: 5556 download_size: 158519 dataset_size: 424421 - config_name: Transcription Translation features: - name: transcription dtype: string - name: translation dtype: string - name: script dtype: string splits: - name: train num_bytes: 568166 num_examples: 5556 download_size: 275204 dataset_size: 568166 - config_name: Transcription Transliteration features: - name: transcription dtype: string - name: transliteration dtype: string - name: script dtype: string splits: - name: train num_bytes: 584686 num_examples: 6265 download_size: 288686 dataset_size: 584686 - config_name: Transliteration LID features: - name: transliteration dtype: string - name: language_label dtype: string - name: script dtype: string splits: - name: train num_bytes: 272877 num_examples: 5556 download_size: 127475 dataset_size: 272877 - config_name: Transliteration Translation features: - name: transliteration dtype: string - name: translation dtype: string - name: script dtype: string splits: - name: train num_bytes: 416622 num_examples: 5556 download_size: 244160 dataset_size: 416622 - config_name: default features: - name: image dtype: string - name: transcription dtype: string - name: transliteration dtype: string - name: translation dtype: string - name: language_label dtype: string - name: script dtype: string splits: - name: train num_bytes: 1375362 num_examples: 6433 download_size: 500093 dataset_size: 1375362 configs: - config_name: Image Segmentation data_files: - split: train path: Image Segmentation/train-* - config_name: Image Transcription (OCR) data_files: - split: train path: Image Transcription (OCR)/train-* - config_name: Image Translation data_files: - split: train path: Image Translation/train-* - config_name: Image Transliteration data_files: - split: train path: Image Transliteration/train-* - config_name: Transcription LID data_files: - split: train path: Transcription LID/train-* - config_name: Transcription Translation data_files: - split: train path: Transcription Translation/train-* - config_name: Transcription Transliteration data_files: - split: train path: Transcription Transliteration/train-* - config_name: Transliteration LID data_files: - split: train path: Transliteration LID/train-* - config_name: Transliteration Translation data_files: - split: train path: Transliteration Translation/train-* - config_name: default data_files: - split: train path: data/train-* ---
DrewLab/hu.MAP_3.0
DrewLab
"2025-02-25T22:34:47Z"
2
0
[ "license:cc-by-4.0", "size_categories:100K<n<1M", "format:csv", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "biology", "PPIs" ]
null
"2025-02-12T23:12:52Z"
--- license: cc-by-4.0 tags: - biology - PPIs pretty_name: >- hu.MAP3.0: Atlas of human protein complexes by integration of > 25,000 proteomic experiments. repo: https://github.com/KDrewLab/huMAP3.0_analysis --- # hu.MAP3.0: Atlas of human protein complexes by integration of > 25,000 proteomic experiments. Proteins interact with each other and organize themselves into macromolecular machines (ie. complexes) to carry out essential functions of the cell. We have a good understanding of a few complexes such as the proteasome and the ribosome but currently we have an incomplete view of all protein complexes as well as their functions. The hu.MAP attempts to address this lack of understanding by integrating several large scale protein interaction datasets to obtain the most comprehensive view of protein complexes. In hu.MAP 3.0 we integrated large scale affinity purification mass spectrometry (AP/MS) datasets from Bioplex, Bioplex2.0, Bioplex3.0, Boldt et al. and Hein et al., large scale biochemical fractionation data (Wan et al.), proximity labeling data (Gupta et al., Youn et al.), and RNA hairpin pulldown data (Treiber et al.) to produce a complex map with over 15k complexes. ## Funding NIH R00, NSF/BBSRC ## Citation Samantha N. Fischer, Erin R Claussen, Savvas Kourtis, Sara Sdelci, Sandra Orchard, Henning Hermjakob, Georg Kustatscher, Kevin Drew hu.MAP3.0: Atlas of human protein complexes by integration of > 25,000 proteomic experiments BioRxiv https://doi.org/10.1101/2024.10.11.617930 ## References Kevin Drew, John B. Wallingford, Edward M. Marcotte hu.MAP 2.0: integration of over 15,000 proteomic experiments builds a global compendium of human multiprotein assemblies Mol Syst Biol (2021)17:e10016https://doi.org/10.15252/msb.202010016 Kevin Drew, Chanjae Lee, Ryan L Huizar, Fan Tu, Blake Borgeson, Claire D McWhite, Yun Ma, John B Wallingford, Edward M Marcotte Integration of over 9,000 mass spectrometry experiments builds a global map of human protein complexes. Molecular Systems Biology (2017) 13, 932. DOI 10.15252/msb.20167490 Huttlin et al. Dual proteome-scale networks reveal cell-specific remodeling of the human interactome Cell. 2021 May 27;184(11):3022-3040.e28. doi: 10.1016/j.cell.2021.04.011. Huttlin et al. Architecture of the human interactome defines protein communities and disease networks. Nature. 2017 May 25;545(7655):505-509. DOI: 10.1038/nature22366. Treiber et al. A Compendium of RNA-Binding Proteins that Regulate MicroRNA Biogenesis.. Mol Cell. 2017 Apr 20;66(2):270-284.e13. doi: 10.1016/j.molcel.2017.03.014. Boldt et al. An organelle-specific protein landscape identifies novel diseases and molecular mechanisms. Nat Commun. 2016 May 13;7:11491. doi: 10.1038/ncomms11491. Youn et al. High-Density Proximity Mapping Reveals the Subcellular Organization of mRNA-Associated Granules and Bodies. Mol Cell. 2018 Feb 1;69(3):517-532.e11. doi: 10.1016/j.molcel.2017.12.020. Gupta et al. A Dynamic Protein Interaction Landscape of the Human Centrosome-Cilium Interface. Cell. 2015 Dec 3;163(6):1484-99. doi: 10.1016/j.cell.2015.10.065. Wan, Borgeson et al. Panorama of ancient metazoan macromolecular complexes. Nature. 2015 Sep 17;525(7569):339-44. doi: 10.1038/nature14877. Epub 2015 Sep 7. Hein et al. A human interactome in three quantitative dimensions organized by stoichiometries and abundances. Cell. 2015 Oct 22;163(3):712-23. doi: 10.1016/j.cell.2015.09.053. Epub 2015 Oct 22. Huttlin et al. The BioPlex Network: A Systematic Exploration of the Human Interactome. Cell. 2015 Jul 16;162(2):425-40. doi: 10.1016/j.cell.2015.06.043. Reimand et al. g:Profiler-a web server for functional interpretation of gene lists (2016 update). Nucleic Acids Res. 2016 Jul 8;44(W1):W83-9. doi: 10.1093/nar/gkw199. ## Associated code Code examples using the [hu.MAP 3.0 model](https://huggingface.co/sfisch/hu.MAP3.0_AutoGluon) and downstream analysis can be found on our [GitHub](https://github.com/KDrewLab/huMAP3.0_analysis) # Usage ## Accessing the model hu.MAP 3.0 was built using the auto-ML tool [AutoGluon](https://auto.gluon.ai/stable/index.html) and the [TabularPredictor](https://auto.gluon.ai/stable/api/autogluon.tabular.TabularPredictor.html) module is used train, test, and make predictions with the model. This can be downloaded using the following: $ pip install autogluon==0.4.0 Then it can be imported as: >>> from autogluon.tabular import TabularPredictor Note that to perform operations with our model the **0.4.0 version** must be used Our [trained model](https://huggingface.co/sfisch/hu.MAP3.0_AutoGluon) can be downloaded through Huggingface using [huggingface_hub](https://huggingface.co/docs/hub/index) >>> from huggingface_hub import snapshot_download >>> model_dir = snapshot_download(repo_id="sfisch/hu.MAP3.0_AutoGluon") >>> predictor = TabularPredictor.load(f"{model_dir}/huMAP3_20230503_complexportal_subset10kNEG_notScaled_accuracy") ## Using the training and test data Both the train and test feature matrices can be loaded using the Huggingface [datasets](https://huggingface.co/docs/datasets/index) library. This can be done from the command-line using: $ pip install datasets When loading into Python use the following: >>> from datasets import load_dataset >>> dataset = load_dataset('sfisch/hu.MAP3.0') Training and test feature matrices can then be accessed as separate objects: >>> train = dataset["train"].to_pandas() >>> test = dataset["test"].to_pandas() Jupyter notebooks containing more in-depth examples of model training, testing, and generating predictions can be found on our [GitHub](https://github.com/KDrewLab/huMAP3.0_analysis/huMAP3.0_model_devel) ## Accessing full feature matrix and all test/train interaction/complex files All other files, such as the full feature matrix, can be accessed via Huggingface_hub. >>> from huggingface_hub import hf_hub_download >>> full_file = hf_hub_download(repo_id="sfisch/hu.MAP3.0", filename='full/humap3_full_feature_matrix_20220625.csv.gz', repo_type='dataset') This just provides the file for download. Depending on your workflow, if you wish to use as a pandas dataframe for example: >>> import pandas as pd >>> full_featmat = pd.read_csv(full_file, compression="gzip") The other complex/interaction files can be downloaded in the same manner. The files within the 'reference_interactions' directory contain the complexes split from [Complex Portal](https://www.ebi.ac.uk/complexportal) into test and training sets. Within that directory you will also find the pairwise protein interactions that were used as positive and negative interactions for both the test and training sets. ## Dataset card authors Samantha Fischer (sfisch6@uic.edu)
constantinedivis/test_ds_sig
constantinedivis
"2025-02-17T13:07:14Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "modality:timeseries", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-17T12:56:07Z"
--- configs: - config_name: default data_files: - split: train path: "*.parquet" ---
Geralt-Targaryen/C4-Advertisements
Geralt-Targaryen
"2025-02-25T11:03:04Z"
2
0
[ "license:odc-by", "size_categories:10M<n<100M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T08:22:12Z"
--- license: odc-by --- 35,916,631 advertisements from [C4](https://huggingface.co/datasets/Geralt-Targaryen/C4), filtered by a RoBERTa classifier trained on 550K annotations by Qwen2.5-32B-Instruct.
jjeccles/3B-Instruct-DocHead-Concatenated02-25
jjeccles
"2025-02-25T10:44:26Z"
2
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T10:44:18Z"
--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 126293567 num_examples: 14546 download_size: 20850311 dataset_size: 126293567 configs: - config_name: default data_files: - split: train path: data/train-* ---
jjeccles/3B-Instruct-DocHead-OneToOneMix02-25
jjeccles
"2025-02-25T10:48:56Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T10:48:53Z"
--- dataset_info: features: - name: text dtype: string splits: - name: train num_bytes: 24449517.714285713 num_examples: 2816 download_size: 5049827 dataset_size: 24449517.714285713 configs: - config_name: default data_files: - split: train path: data/train-* ---
tttx/3k-trash-ttt-022225-step1-collated
tttx
"2025-02-25T11:05:15Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:05:12Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 8910736.0 num_examples: 400 - name: test num_bytes: 21389 num_examples: 1 download_size: 2467668 dataset_size: 8932125.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
Swati-sd/ionization
Swati-sd
"2025-02-25T11:07:50Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:07:47Z"
--- dataset_info: features: - name: prompt dtype: string - name: image dtype: image - name: mask_0 dtype: image splits: - name: train num_bytes: 33779636.0 num_examples: 200 - name: test num_bytes: 4835151.0 num_examples: 60 download_size: 38558074 dataset_size: 38614787.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
cchoi1/humaneval-datagen-run-1_best_att_50_sol_50_20250224_220437
cchoi1
"2025-02-25T11:24:48Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:24:45Z"
--- dataset_info: features: - name: problem_id dtype: string - name: prompt dtype: string - name: canonical_solution dtype: string - name: chosen dtype: string - name: rejected dtype: string - name: chosen_attack dtype: string - name: chosen_attack_explanation dtype: string - name: chosen_solution dtype: string - name: chosen_solution_explanation dtype: string - name: chosen_solve_rate dtype: float64 - name: rejected_attack dtype: string - name: rejected_attack_explanation dtype: string - name: rejected_solution dtype: string - name: rejected_solution_explanation dtype: string - name: rejected_solve_rate dtype: float64 splits: - name: train num_bytes: 5224342 num_examples: 2136 download_size: 283323 dataset_size: 5224342 configs: - config_name: default data_files: - split: train path: data/train-* ---
okan11111/cebir2
okan11111
"2025-02-25T11:25:57Z"
2
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:25:44Z"
--- dataset_info: features: - name: instruction dtype: string - name: input dtype: string - name: response dtype: string splits: - name: train num_bytes: 6369729.768269773 num_examples: 19162 - name: test num_bytes: 708043.2317302274 num_examples: 2130 download_size: 3248865 dataset_size: 7077773.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
korbih/aguvis_1000_sft_1024_train
korbih
"2025-02-25T11:28:29Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:26:50Z"
--- dataset_info: features: - name: messages list: - name: role dtype: string - name: content dtype: string - name: images sequence: image - name: image_name dtype: string - name: base_uid dtype: string - name: step dtype: string - name: domain dtype: string splits: - name: train num_bytes: 528171031.41 num_examples: 6895 download_size: 468557736 dataset_size: 528171031.41 configs: - config_name: default data_files: - split: train path: data/train-* ---
raahulrahl/distilabel-example
raahulrahl
"2025-02-25T11:29:30Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:29:28Z"
--- dataset_info: features: - name: instruction dtype: string - name: generation dtype: 'null' - name: model_name dtype: 'null' - name: distilabel_metadata struct: - name: raw_input_text_generation_0 dtype: 'null' - name: raw_output_text_generation_0 dtype: 'null' splits: - name: train num_bytes: 3872 num_examples: 10 download_size: 5449 dataset_size: 3872 configs: - config_name: default data_files: - split: train path: data/train-* ---
tttx/3k-trash-ttt-022225-step2-collated
tttx
"2025-02-25T11:50:12Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T11:50:09Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 8965047.111111112 num_examples: 400 - name: test num_bytes: 22134 num_examples: 1 download_size: 2422122 dataset_size: 8987181.111111112 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
nmuendler/SWT-bench_Verified_bm25_27k_zsb
nmuendler
"2025-02-25T12:29:47Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "arxiv:2406.12952", "arxiv:2310.06770", "region:us" ]
null
"2025-02-25T12:08:48Z"
--- dataset_info: features: - name: repo dtype: string - name: instance_id dtype: string - name: base_commit dtype: string - name: patch dtype: string - name: test_patch dtype: string - name: problem_statement dtype: string - name: hints_text dtype: string - name: created_at dtype: string - name: version dtype: string - name: FAIL_TO_PASS dtype: string - name: PASS_TO_PASS dtype: string - name: environment_setup_commit dtype: string - name: difficulty dtype: string - name: hits list: - name: docid dtype: string - name: score dtype: float64 - name: text dtype: string splits: - name: test num_bytes: 50867908 num_examples: 433 download_size: 21631632 dataset_size: 50867908 configs: - config_name: default data_files: - split: test path: data/test-* --- ### Dataset Summary SWT-bench *Verified* is _subset_ of [SWT-bench](https://huggingface.co/datasets/nmuendler/SWT-bench_bm25_27k_zsb), a dataset that tests systems’ ability to reproduce GitHub issues automatically. The dataset collects 433 test Issue-Pull Request pairs from 11 popular Python GitHub projects. Evaluation is performed by unit test verification using pre- and post-PR behavior of the test suite with and without the model proposed tests. #### 📊🏆 Leaderboard A public leaderboard for performance on SWT-bench is hosted at [swtbench.com](swtbench.com) The dataset is released as part of the paper [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://arxiv.org/abs/2406.12952). #### 🔎 Details This dataset `SWT-bench_Verified_bm25_27k_zsp` includes a formatting of each instance using Pyserini's BM25 retrieval as described in the paper. The code context size limit is 27,000 `cl100k_base` tokens from the [`tiktoken`](https://github.com/openai/tiktoken) tokenization package used for OpenAI models. The `text` column can be used directly with LMs to generate patch files and is formatted with the ZeroShotBase format prompt. Models are instructed to generate a [`patch`](https://en.wikipedia.org/wiki/Patch_(Unix)) formatted file using the following template: ```diff <patch> diff --- a/path/to/file.py --- b/path/to/file.py @@ -1,3 +1,3 @@ This is a test file. -It contains several lines. +It has been modified. This is the third line. </patch> ``` The dataset is based on [SWE-bench_Verified](https://huggingface.co/datasets/princeton-nlp/SWE-bench_Verified) of [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) in [collaboration with OpenAI](https://openai.com/index/introducing-swe-bench-verified/). This format can be used directly with the [SWE-bench inference scripts](https://github.com/princeton-nlp/SWE-bench/tree/main/inference). Please refer to these scripts for more details on inference.
gogolo1364/Start1_new
gogolo1364
"2025-02-25T12:13:41Z"
2
0
[ "license:mit", "size_categories:n<1K", "format:csv", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T12:09:48Z"
--- license: mit ---
TheOnlyDrWho/ZZZZ
TheOnlyDrWho
"2025-02-25T12:15:22Z"
2
0
[ "license:unknown", "region:us" ]
null
"2025-02-25T12:14:29Z"
--- license: unknown ---
tttx/3k-forcing-clipped-022225-step4-collated
tttx
"2025-02-25T12:29:47Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T12:29:38Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 7315142.0 num_examples: 336 - name: test num_bytes: 22858 num_examples: 1 download_size: 1961620 dataset_size: 7338000.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
tttx/3k-trash-ttt-022225-step3-collated
tttx
"2025-02-25T12:36:14Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T12:36:11Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 8935367.111111112 num_examples: 400 - name: test num_bytes: 19495 num_examples: 1 download_size: 2403178 dataset_size: 8954862.111111112 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
AAAA128/0R-deepseek-r1
AAAA128
"2025-02-25T12:52:37Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T12:52:32Z"
--- dataset_info: features: - name: instruction dtype: string - name: input dtype: string - name: output dtype: string - name: generation dtype: string - name: distilabel_metadata struct: - name: raw_input_text_generation list: - name: content dtype: string - name: role dtype: string - name: raw_output_text_generation dtype: string - name: statistics_text_generation struct: - name: input_tokens dtype: int64 - name: output_tokens dtype: int64 - name: model_name dtype: string splits: - name: train num_bytes: 73550 num_examples: 10 download_size: 68812 dataset_size: 73550 configs: - config_name: default data_files: - split: train path: data/train-* ---
mangopy/ToolRet-Queries1
mangopy
"2025-02-25T12:54:10Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T12:53:58Z"
--- dataset_info: - config_name: gorilla-tensor features: - name: id dtype: string - name: query dtype: string - name: instruction dtype: string - name: labels dtype: string - name: category dtype: string splits: - name: queries num_bytes: 78995 num_examples: 55 download_size: 24985 dataset_size: 78995 - config_name: ultratool features: - name: id dtype: string - name: query dtype: string - name: instruction dtype: string - name: labels dtype: string - name: category dtype: string splits: - name: queries num_bytes: 763581 num_examples: 500 download_size: 134582 dataset_size: 763581 configs: - config_name: gorilla-tensor data_files: - split: queries path: gorilla-tensor/queries-* - config_name: ultratool data_files: - split: queries path: ultratool/queries-* ---
tttx/8k-priority-buffer-unclipped-overnight-4kbuffer-022525-step1-collated
tttx
"2025-02-25T12:57:45Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T12:57:42Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 2800577.0 num_examples: 79 - name: test num_bytes: 40955 num_examples: 1 download_size: 796821 dataset_size: 2841532.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
clement520/GeomRel
clement520
"2025-02-25T13:19:02Z"
2
1
[ "task_categories:question-answering", "language:en", "license:apache-2.0", "size_categories:1K<n<10K", "modality:text", "arxiv:2501.13773", "region:us" ]
[ "question-answering" ]
"2025-02-25T12:58:57Z"
--- license: apache-2.0 task_categories: - question-answering language: - en size_categories: - 1K<n<10K --- # GeomRel Dataset GeomRel is a dataset designed for evaluating large language models (LLMs) on their ability to understand geometric relationships. The dataset contains questions related to basic geometric shapes and their properties, with a focus on recognizing and reasoning about spatial relationships between lines, angles, and figures. The data in GeomRel is structured to test models' understanding of geometric concepts such as parallelism, perpendicularity, intersection, and other spatial relations, making it a useful benchmark for evaluating a model's spatial reasoning capabilities in the context of geometry. ## Dataset Structure Each example in the dataset consists of a **question**, the **correct answer**, and the **relationship type**. ### Example Data Entry: ```json { "question": "In rectangle ABEF, AB=5. What is the relationship between line AB and line EF?\nAnswer choices:A. Parallel B. Perpendicular C. Intersecting but not perpendicular D. Cannot be inferred", "answer": "A", "relation": "LL_PA" } ``` - **question**: The question presents a geometric scenario, often describing a figure and asking the model to deduce the relationship between various geometric elements. - **answer**: The correct answer from a predefined list of answer choices. - **relation**: A code representing the type of relationship the question addresses. For example: - `LL_PA`: Parallel lines - `LL_PE`: Perpendicular lines - `LL_IN`: Intersecting lines - `LL_CI`: Cannot be inferred (when the relationship cannot be determined from the given information) - ... ## Key Features - **Focus on Spatial Reasoning**: The dataset emphasizes reasoning about geometric relationships, including basic shapes like rectangles, triangles, and other polygons. - **Multiple Answer Choices**: Each question provides several answer choices, designed to test the model’s ability to select the most appropriate answer based on the provided information. - **Real-World Relevance**: Geometric reasoning is a foundational skill in many fields, such as computer vision, robotics, and architectural design. This dataset is intended to help assess and improve LLMs in their ability to handle such reasoning tasks. ## Use Cases GeomRel is useful for: - Benchmarking LLMs in the domain of geometry and spatial reasoning. - Improving the performance of models on tasks involving geometric understanding. - Research into how LLMs handle reasoning with structured, visual-spatial knowledge. ## Citation If you use this dataset in your research, please cite the following paper: ```bibtex @misc {wang2025largelanguagemodelstruly, title={Do Large Language Models Truly Understand Geometric Structures?}, author={Xiaofeng Wang and Yiming Wang and Wenhong Zhu and Rui Wang}, year={2025}, eprint={2501.13773}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2501.13773}, } ```
jdh-algo/JMED
jdh-algo
"2025-02-25T13:47:47Z"
2
1
[ "license:mit", "size_categories:1K<n<10K", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T13:00:44Z"
# Citrus: Leveraging Expert Cognitive Pathways in a Medical Language Model for Advanced Medical Decision Support <p align="center"> <a href="https://arxiv.org/abs/2502.18274" target="_blank">📑Paper</a> |<a href="https://jdh-algo.github.io/Citrus/" target="_blank">🤗Github Page</a> |<a href="https://huggingface.co/jdh-algo/Citrus1.0-llama-70B" target="_blank">🤗Citrus1.0-Llama-70B</a> |<a href="https://huggingface.co/datasets/jdh-algo/Citrus_S3" target="_blank">📚Medical Reasoning Data</a> | <a href="https://huggingface.co/datasets/jdh-algo/JMED" target="_blank">📚Evaluation Data</a> </p> ## The Introduction to Our Work ### 1. Main approaches <div align="center"> <img src="https://raw.githubusercontent.com/jdh-algo/Citrus/main/static/images/figure4-1-2.png" alt="image" width="75%"/> </div> ### 2. Overview of training stages and training data pipeline <div align="center"> <img src="https://raw.githubusercontent.com/jdh-algo/Citrus/main/static/images/figure4-2-1.png" width="75%"> </div> Citrus is a medical language model that bridges the gap between clinical expertise and AI reasoning by emulating the cognitive processes of medical experts. The model is trained on a large corpus of simulated expert disease reasoning data in sft-stage-3, synthesized using a novel approach that accurately captures the decision-making pathways of clinicians. The contributions of this work are as follows: 1. We propose a training-free reasoning approach that emulates the cognitive processes of medical experts, enabling large language models to enhance their medical capabilities in clinical diagnosis and treatment. 2. In conjunction with the data construction method, we introduce a multi-stage post-training approach to further improve the model’s medical performance. 3. We have made the Citrus model and its training data publicly available as open-source resources to advance research in AI-driven medical decision-making. 4. We have developed and open-sourced a large-scale, updatable clinical practice evaluation dataset based on real-world data, accurately reflecting the distribution of patients in real-world settings. In our work, we provide detailed insights into Citrus, covering its model architecture, dataset, and code. We are releasing Citrus_S3, the supervised fine-tuning (SFT) data for stage 3, which comprises 20,000 samples. We hope that our contributions will foster progress within the community in advancing the capabilities of large models. ## JDH Medical Practice Dataset: Construction and Validation of a Real-World Clinical Dialogue Benchmark 1. **Data Introduction:** The JMED, a novel dataset based on real-world medical data distributions. Unlike existing datasets, JMED closely mimics authentic clinical data while facilitating eective model training. Although based on real consultation data, it is not directly sourced from actual medical data, allowing us to incorporate key elements necessary for model training. We ensured compliance with ethical and legal standards throughout the data collection process, safeguarding privacy and meeting ethical guidelines. Due to the open-ended nature of medical consultations, where denitive answers are often elusive, the evaluation process is more challenging. To address this, each question includes 21 response options, with a "None of the above" choice. This design signicantly increases the complexity and diculty of distinguishing the correct answers, thereby providing a more rigorous assessment framework. We are initially releasing 1,000 MCQs and will update them periodically in the future. 2. **Data Format:** We consturcted JMED dataset as a set of multiple-choice questions (MCQs) based on the preprocessed data. Each data follows a general MCQs template format: `<id, question, options, answer>`.
AbdallahhSaleh/Hindawi_tokenized
AbdallahhSaleh
"2025-02-25T13:22:00Z"
2
0
[ "size_categories:100K<n<1M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T13:08:24Z"
--- dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 splits: - name: train num_bytes: 688202580.0 num_examples: 882311 download_size: 278261356 dataset_size: 688202580.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
rajmohan1122/finetuning_demo
rajmohan1122
"2025-02-25T13:11:58Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T13:11:57Z"
--- dataset_info: features: - name: prompt dtype: string splits: - name: train num_bytes: 337422 num_examples: 1000 download_size: 15348 dataset_size: 337422 configs: - config_name: default data_files: - split: train path: data/train-* ---
bbunzeck/lexical-decision
bbunzeck
"2025-02-25T13:13:31Z"
2
0
[ "language:en", "size_categories:1K<n<10K", "format:csv", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2502.12835", "region:us" ]
null
"2025-02-25T13:11:59Z"
--- language: - en pretty_name: Lexical decision dataset (English) --- This dataset contains words/sentences for lexical decision tests. If you use this dataset, please cite the following preprint: ``` @misc{bunzeck2025subwordmodelsstruggleword, title={Subword models struggle with word learning, but surprisal hides it}, author={Bastian Bunzeck and Sina Zarrieß}, year={2025}, eprint={2502.12835}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2502.12835}, } ```
polygraf-ai/multi-model-contextual-human-AI-v1-10K-with-title-formatted
polygraf-ai
"2025-02-25T13:13:53Z"
2
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T13:13:52Z"
--- dataset_info: features: - name: sub_source dtype: string - name: source dtype: string - name: text dtype: string - name: label dtype: int64 splits: - name: train num_bytes: 13641040 num_examples: 16200 - name: dev num_bytes: 1532849 num_examples: 1800 download_size: 9274323 dataset_size: 15173889 configs: - config_name: default data_files: - split: train path: data/train-* - split: dev path: data/dev-* ---
Neph0s/CoSER
Neph0s
"2025-02-26T08:08:38Z"
2
0
[ "language:en", "license:mit", "arxiv:2502.09082", "region:us" ]
null
"2025-02-25T13:20:09Z"
--- license: mit language: - en size_categories: - 100M<n<1000M --- # CoSER Dataset ## Overview CoSER is a high-quality dataset for role-playing LLMs, sourced from 771 renowned novels. The dataset contains authentic multi-turn, multi-character dialogues extracted from acclaimed literary works. ## Key Features - **Authentic Content**: Unlike synthetic datasets, CoSER extracts real dialogues from literature, maintaining high fidelity to the original works. The dialogues are inherently multi-turn and multi-character, exhibiting natural complexity and diversity. - **Comprehensive Data Types**: Includes character profiles, dialogues, plot summaries, character experiences, and conversation backgrounds - **Thoughts and Actions in Messages**: Captures characters' internal thoughts and physical actions beyond surface-level speech - **Comprehensive Contextual Information for Simulation**: Provides rich contextual information of conversations, enabling role-playing LLMs to perform reasonable simulations in these scenarios. We refer to these simulations as *Given-Circumstance Acting* (GCA), which can be used to both train and evaluate role-playing LLMs. ## Dataset Structure ``` CoSER/ ├── sft_sharegpt.json # Data formatted for SFT training ├── test_set.json # 200 test samples used in our paper └── full/ # Complete extracted data from all books ├── A Game of Thrones (A Song of Ice and Fire, #1).json ├── A Tale of Two Cities.json └── ... ``` ## Safety Considerations We have conducted safety checks on the dataset and removed potentially problematic content. Specifically, we truncated 110 sensitive conversations and removed a total of 602 messages. These conversations are marked with `truncated_for_safety_concerns=True` in the dataset. ## Citation If you use this dataset in your research, please cite our paper: ``` @misc{wang2025cosercoordinatingllmbasedpersona, title={CoSER: Coordinating LLM-Based Persona Simulation of Established Roles}, author={Xintao Wang and Heng Wang and Yifei Zhang and Xinfeng Yuan and Rui Xu and Jen-tse Huang and Siyu Yuan and Haoran Guo and Jiangjie Chen and Wei Wang and Yanghua Xiao and Shuchang Zhou}, year={2025}, eprint={2502.09082}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/2502.09082}, } ```
Ian824/High-Resolution-Rainy-Image
Ian824
"2025-02-26T11:23:08Z"
2
0
[ "task_categories:image-to-image", "language:en", "license:mit", "size_categories:1K<n<10K", "arxiv:2502.16421", "region:us", "rain" ]
[ "image-to-image" ]
"2025-02-25T13:25:58Z"
--- license: cc-by-sa-4.0 task_categories: - image-to-image language: - en tags: - rain pretty_name: ' High-resolution Rainy Image' size_categories: - 1K<n<10K --- # High-resolution Rainy Image Synthesis: Learning from Rendering This is the dataset in the paper "High-resolution Rainy Image Synthesis: Learning from Rendering" * Project Page: https://kb824999404.github.io/HRIG/ * Paper: https://arxiv.org/abs/2502.16421 * Code: https://github.com/kb824999404/HRIG <table> <tr> <td style="padding: 0;width=30%;"><img src="Imgs/lane/lane (1).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/lane/lane (2).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/lane/lane (3).jpg" /></td> </tr> <tr> <td style="padding: 0;width=30%;"><img src="Imgs/lane/lane (4).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/lane/lane (5).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/lane/lane (6).jpg" /></td> </tr> <tr> <td style="padding: 0;width=30%;"><img src="Imgs/citystreet/citystreet (1).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/citystreet/citystreet (2).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/citystreet/citystreet (3).jpg" /></td> </tr> <tr> <td style="padding: 0;width=30%;"><img src="Imgs/citystreet/citystreet (4).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/citystreet/citystreet (5).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/citystreet/citystreet (6).jpg" /></td> </tr> <tr> <td style="padding: 0;width=30%;"><img src="Imgs/japanesestreet/japanese (1).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/japanesestreet/japanese (2).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/japanesestreet/japanese (3).jpg" /></td> </tr> <tr> <td style="padding: 0;width=30%;"><img src="Imgs/japanesestreet/japanese (4).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/japanesestreet/japanese (5).jpg" /></td> <td style="padding: 0;width=30%;"><img src="Imgs/japanesestreet/japanese (6).jpg" /></td> </tr> </table> ## HRI Dataset The High-resolution Rainy Image (HRI) dataset in the rendering stage. <table style="text-align: center;"> <tr> <th>scene</th> <th>dataset type</th> <th>resolution</th> <th>viewpoints</th> <th>moments</th> <th>intensities</th> <th>image pairs</th> </tr> <tr> <td style="vertical-align: middle;" rowspan="2">lane</td> <td>training set</td> <td style="vertical-align: middle;" rowspan="2">2048×1024</td> <td>3</td> <td style="vertical-align: middle;" rowspan="2">100</td> <td style="vertical-align: middle;" rowspan="2">4</td> <td>1200</td> </tr> <tr> <td>test set</td> <td>1</td> <td>400</td> </tr> <tr> <td style="vertical-align: middle;" rowspan="2">citystreet</td> <td>training set</td> <td style="vertical-align: middle;" rowspan="2">2048×1024</td> <td>5</td> <td style="vertical-align: middle;" rowspan="2">25</td> <td style="vertical-align: middle;" rowspan="2">4</td> <td>500</td> </tr> <tr> <td>test set</td> <td>1</td> <td>100</td> </tr> <tr> <td style="vertical-align: middle;" rowspan="2">japanesestreet</td> <td>training set</td> <td style="vertical-align: middle;" rowspan="2">2048×1024</td> <td>8</td> <td style="vertical-align: middle;" rowspan="2">25</td> <td style="vertical-align: middle;" rowspan="2">4</td> <td>800</td> </tr> <tr> <td>test set</td> <td>2</td> <td>200</td> </tr> </table> * `clean`: background RGB images and depth images of all scenes. * `rainy`: rain layer images, RGB rainy images and depth rainy images of all scenes. * `trainset.json`: the sample lists of the training set. * `testset.json`: the sample lists of the test set. * For each sample in the training set and the test set: * `scene`: the scene name * `sequence`: the viewpoint name * `intensity`: the rain intensity * `wind`: the wind direction( all zero for the HRI dataset) * `background`: the path of the background RGB image * `depth`: the path of the background depth image * `rain_layer`: the path of the rain layer image * `rainy_depth`: the path of the rainy depth image * `rainy_image`: the path of the rainy RGB image ## BlenderFiles The Blender files for rendering RGB and depth images of all viewpoints are included in the directory of each scene. ## Rain streak database The Rain streak database from the paper [Rain Rendering for Evaluating and Improving Robustness to Bad Weather](https://github.com/astra-vision/rain-rendering).
AbdallahhSaleh/Wiki_tokenized
AbdallahhSaleh
"2025-02-25T14:30:09Z"
2
0
[ "size_categories:1M<n<10M", "format:parquet", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T13:43:57Z"
--- dataset_info: features: - name: input_ids sequence: int32 - name: token_type_ids sequence: int8 - name: attention_mask sequence: int8 splits: - name: train num_bytes: 2491689720.0 num_examples: 3194474 download_size: 803543391 dataset_size: 2491689720.0 configs: - config_name: default data_files: - split: train path: data/train-* ---
jayan12k/Finecode
jayan12k
"2025-02-25T17:28:50Z"
2
1
[ "task_categories:text-generation", "license:mit", "size_categories:n<1K", "format:json", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
[ "text-generation" ]
"2025-02-25T13:54:40Z"
--- license: mit task_categories: - text-generation --- # FineCode: A High-Quality Code Dataset Disclaimer: No big files uploaded...yet The one upload is simply an example format and doesn't contain all the highest quality code or the final version. ## Overview FineCode is a meticulously curated dataset aimed at providing high-quality code for training and benchmarking code generation models. While many code datasets exist on Hugging Face, the quality of code varies significantly. FineCode seeks to address this by rigorously filtering and scoring code to ensure only well-structured, optimized, and readable examples are included. ## Dataset Details - **Total Size:** 100B tokens - **Languages Covered:** Top 15 programming languages, with an emphasis on the top 5 - **Source:** Scraped from top-ranked GitHub repositories of well-known organizations and highly rated open-source projects - **Filtering Criteria:** - Code is evaluated using **Llama3.2-3B**, which assigns a quality score (0-100) based on factors like readability, optimization, and best practices - Only code with a **score of 75 or higher** is included in the dataset - Additional filtering techniques are applied to remove low-quality or redundant content ## Availability The dataset will be released soon on Hugging Face, along with the code used for data collection and filtering, allowing full transparency and reproducibility. Stay tuned for updates!
zoujunyi/huatuo
zoujunyi
"2025-02-26T00:38:07Z"
2
0
[ "license:apache-2.0", "size_categories:1M<n<10M", "format:json", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T14:18:45Z"
--- license: apache-2.0 ---
tttx/8k-forcing-clipped-022225-step3-collated
tttx
"2025-02-25T14:22:53Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T14:22:50Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 2504988.0 num_examples: 74 - name: test num_bytes: 38302 num_examples: 1 download_size: 658975 dataset_size: 2543290.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
quasara-io/CoCo
quasara-io
"2025-02-25T14:33:48Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T14:33:45Z"
--- dataset_info: features: - name: Vector_ID dtype: string - name: File_Path dtype: string - name: Coordinate sequence: float64 - name: Vector sequence: float64 splits: - name: Main_1 num_bytes: 16357929 num_examples: 1761 download_size: 16788816 dataset_size: 16357929 configs: - config_name: default data_files: - split: Main_1 path: data/Main_1-* ---
ricdomolm/Big-Math-RL-Verified-Solve-Rate-0.5
ricdomolm
"2025-02-25T14:41:28Z"
2
0
[ "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T14:41:22Z"
--- dataset_info: features: - name: problem dtype: string - name: answer dtype: string - name: source dtype: string - name: domain sequence: string - name: llama8b_solve_rate dtype: float64 splits: - name: train num_bytes: 41366862.25380492 num_examples: 134965 download_size: 19050861 dataset_size: 41366862.25380492 configs: - config_name: default data_files: - split: train path: data/train-* ---
marr-peng-lab/phoenix-dataset
marr-peng-lab
"2025-02-25T19:08:58Z"
2
0
[ "license:apache-2.0", "region:us" ]
null
"2025-02-25T15:13:06Z"
--- license: apache-2.0 ---
PJMixers-Dev/Fundus-105K-Formatted-Qwen2.5-Coder-7B-Instruct-Classified
PJMixers-Dev
"2025-02-25T18:50:11Z"
2
0
[ "language:en", "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T15:13:32Z"
--- language: - en --- # System Prompt ``` Your primary purpose is classifying text. There are multiple options to choose from: "News", "Review", "Opinion", "Advertising", and "Other". "News" means the text is reporting on current events in a factual and objective manner. "Review" means the text evaluates or critiques a product, service, or creative work. "Opinion" means the text presents a personal viewpoint or argument on a topic. "Advertising" means the text is designed to promote or sell a product, service, or idea. "Other" means the text is random, irrelevant, nonsensical, or spam-like information that does not fit into the other categories. You must reply with a few sentences analyzing the input text on the first line, followed by the classification on the second line (without quotes). Do not provide any other text. ``` # Python Script ```py import requests import json from tqdm import tqdm from datasets import load_dataset import pandas as pd def get_token_count(string): tokencount_response = ( requests.post( f"http://localhost:5001/api/extra/tokencount", json={"prompt": string}, ).json()["value"] ) return tokencount_response def verify_response_text(text): lines = [line.strip() for line in text.strip().splitlines() if line.strip()] if len(lines) != 2: return False _, second_line = lines return second_line.lower() in {"news", "review", "opinion", "advertising", "other"} def create_response(message_log, generation_settings): while True: generation_response = requests.post( "http://localhost:5001/api/v1/generate", json={ "prompt": message_log, **generation_settings } ).json()["results"][0]["text"].strip() stop_reason = requests.get("http://127.0.0.1:5001/api/extra/perf").json()["stop_reason"] if stop_reason in (1, 2) and verify_response_text(generation_response): break else: print("No valid stop token or proper format generated. Retrying.") lines = [line.strip() for line in generation_response.splitlines() if line.strip()] first_line = lines[0] second_line = lines[1].lower() return first_line, second_line system_prompt = ( "Your primary purpose is classifying text. There are multiple options to choose from: \"News\", \"Review\", \"Opinion\", \"Advertising\", and \"Other\".\n\n" "\"News\" means the text is reporting on current events in a factual and objective manner.\n" "\"Review\" means the text evaluates or critiques a product, service, or creative work.\n" "\"Opinion\" means the text presents a personal viewpoint or argument on a topic.\n" "\"Advertising\" means the text is designed to promote or sell a product, service, or idea.\n" "\"Other\" means the text is random, irrelevant, nonsensical, or spam-like information that does not fit into the other categories.\n\n" "You must reply with a few sentences analyzing the input text on the first line, followed by the classification on the second line (without quotes). Do not provide any other text." ) model_name = "bartowski/Qwen2.5-Coder-7B-Instruct-GGUF/Qwen2.5-Coder-7B-Instruct-Q6_K.gguf" original_dataset_name = "PJMixers-Dev/Fundus-105K-Formatted" generation_settings = { "max_context_length": 16384, "max_length": 512, "temperature": 0.3, "rep_pen": 1.03, "top_p": 1, "top_k": 50, "top_a": 0, "typical": 1, "tfs": 1, "min_p": 0.1, "rep_pen_range": 512, "rep_pen_slope": 0.7, "sampler_order": [6, 5, 0, 1, 3, 4, 2], "stop_sequence": [ "<|im_start|>", "<|im_end|>" ] } output_file = ( "./downloaded_datasets/converted/PJMixers-Dev_Fundus-105K-Formatted-Qwen2.5-Coder-7B-Instruct-Classified.parquet" ) output_data_list = [] dataset = load_dataset(original_dataset_name)["train"] for sample in tqdm(dataset): prompt = ( f"<|im_start|>system\n" f"{system_prompt}<|im_end|>\n" f"<|im_start|>user\n" f"{'Text Tags: ' + (str(sample['topics']) + '\n\n') if sample['topics'] else ''}" f"```md\n" f"{sample['text'].strip()}\n" f"```<|im_end|>\n" f"<|im_start|>assistant\n" ) if get_token_count(prompt) > generation_settings["max_context_length"] - generation_settings["max_length"]: print("Too long. Skipping") continue analysis, classification = create_response( prompt, generation_settings ) output_data_list.append( { "original_dataset_name": original_dataset_name, "model_name": model_name, "generation_settings": generation_settings, "analysis": analysis, "classification": classification, "topics": sample["topics"], "text": sample["text"] } ) if len(output_data_list) != 0 and len(output_data_list) % 10 == 0: df = pd.DataFrame(output_data_list) df.to_parquet( output_file, index=False, compression="brotli" ) df = None del df df = pd.DataFrame(output_data_list) df.to_parquet( output_file, index=False, compression="brotli" ) ```
tttx/3k-forcing-clipped-022225-step6-collated
tttx
"2025-02-25T15:46:40Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T15:46:37Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 7188212.0 num_examples: 333 - name: test num_bytes: 19821 num_examples: 1 download_size: 1931724 dataset_size: 7208033.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
tttx/8k-forcing-clipped-022225-step4-collated
tttx
"2025-02-25T15:56:45Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T15:56:43Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 1121943.0 num_examples: 34 - name: test num_bytes: 27182 num_examples: 1 download_size: 321243 dataset_size: 1149125.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
SamsungSAILMontreal/Conjugated-xTB_2M_molecules
SamsungSAILMontreal
"2025-02-25T16:18:58Z"
2
2
[ "size_categories:1M<n<10M", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "arxiv:2502.14842", "region:us" ]
null
"2025-02-25T16:03:19Z"
--- dataset_info: features: - name: 'Unnamed: 0' dtype: int64 - name: reward dtype: float64 - name: wavelength dtype: float64 - name: f_osc dtype: float64 - name: molecule dtype: string - name: top_score dtype: float64 splits: - name: train num_bytes: 513283807 num_examples: 2900000 download_size: 295719034 dataset_size: 513283807 configs: - config_name: default data_files: - split: train path: data/train-* --- Conjugated-xTB dataset of 2M OLED molecules from the paper arxiv.org/abs/2502.14842. 'f_osc' is the oscillator strength (correlated with brightness) and should be maximized to obtain bright OLEDs. 'wavelength' is the absorption wavelength, >=1000nm corresponds to the short-wave infrared absorption range, which is crucial for biomedical imaging as tissues exhibit relatively low absorption and scattering in NIR, allowing for deeper penetration of light. This is good dataset for training a generative model or RL agent maximizing the oscillator strength. We also provide code in https://github.com/SamsungSAILMontreal/STGG-AL to evaluate the oscillator strength and wavelength of new molecules. <img src="https://raw.githubusercontent.com/SamsungSAILMontreal/STGG-AL/master/resource/ir_fosc.png" width="800"> Loading the dataset: ```python from datasets import load_dataset dataset = load_dataset('SamsungSAILMontreal/Conjugated-xTB_2M_molecules') ```
tyrealqian/TGL_content_classification
tyrealqian
"2025-02-25T18:13:38Z"
2
0
[ "license:mit", "size_categories:n<1K", "format:csv", "modality:image", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T16:06:08Z"
--- license: mit ---
J1mb0o/dimitris-test-dataset
J1mb0o
"2025-02-25T16:27:45Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:image", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T16:13:45Z"
--- dataset_info: features: - name: image dtype: image - name: flickr_id dtype: string - name: hypothesis dtype: string - name: gold_label dtype: class_label: names: '0': contradiction '1': neutral '2': entailment splits: - name: train num_bytes: 478791.0 num_examples: 6 - name: dev num_bytes: 478791.0 num_examples: 6 download_size: 164330 dataset_size: 957582.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: dev path: data/dev-* ---
matteanedda/milan_cultural_knowledge
matteanedda
"2025-02-25T16:15:05Z"
2
0
[ "size_categories:10K<n<100K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T16:14:54Z"
--- dataset_info: features: - name: conversations list: - name: from dtype: string - name: value dtype: string splits: - name: train num_bytes: 12439321 num_examples: 20000 download_size: 3686601 dataset_size: 12439321 configs: - config_name: default data_files: - split: train path: data/train-* ---
sunamdham/jenny-tts-tags-6h-v1
sunamdham
"2025-02-25T16:16:14Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T16:16:10Z"
--- dataset_info: features: - name: file_name dtype: string - name: text dtype: string - name: transcription_normalised dtype: string - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speaking_rate dtype: float64 - name: phonemes dtype: string - name: stoi dtype: float64 - name: si-sdr dtype: float64 - name: pesq dtype: float64 splits: - name: train num_bytes: 1640896 num_examples: 4000 download_size: 1041762 dataset_size: 1640896 configs: - config_name: default data_files: - split: train path: data/train-* ---
sunamdham/jenny-tts-text-tags-6h-v1
sunamdham
"2025-02-25T16:16:58Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T16:16:54Z"
--- dataset_info: features: - name: file_name dtype: string - name: text dtype: string - name: transcription_normalised dtype: string - name: utterance_pitch_mean dtype: float32 - name: utterance_pitch_std dtype: float32 - name: snr dtype: float64 - name: c50 dtype: float64 - name: speaking_rate dtype: string - name: phonemes dtype: string - name: stoi dtype: float64 - name: si-sdr dtype: float64 - name: pesq dtype: float64 - name: noise dtype: string - name: reverberation dtype: string - name: speech_monotony dtype: string - name: sdr_noise dtype: string - name: pesq_speech_quality dtype: string splits: - name: train num_bytes: 2063542 num_examples: 4000 download_size: 1025292 dataset_size: 2063542 configs: - config_name: default data_files: - split: train path: data/train-* ---
infinite-dataset-hub/EmployeeFeedbackMatrix
infinite-dataset-hub
"2025-02-25T17:13:38Z"
2
0
[ "license:mit", "size_categories:n<1K", "format:csv", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us", "infinite-dataset-hub", "synthetic" ]
null
"2025-02-25T17:13:37Z"
--- license: mit tags: - infinite-dataset-hub - synthetic --- # EmployeeFeedbackMatrix tags: sentiment analysis, workplace satisfaction, performance metrics _Note: This is an AI-generated dataset so its content may be inaccurate or false_ **Dataset Description:** The 'EmployeeFeedbackMatrix' dataset comprises various textual feedback given by employees about their workplace experiences. This dataset is designed to support sentiment analysis and workplace satisfaction studies. The 'labels' column assigns sentiment scores to the feedback, indicating positive, neutral, or negative sentiment. **CSV Content Preview:** ```csv EmployeeID,Feedback,Label 001,I really enjoy the collaborative environment here. Great team spirit. Positive 002,The workload is quite overwhelming and often extends beyond regular hours. Neutral 003,Management needs to improve their communication. There's a lack of transparency. Negative 004,The new project management tool has significantly streamlined our workflow. Very happy with it. Positive 005,Our team could benefit from more regular training sessions. Neutral ``` **Source of the data:** The dataset was generated using the [Infinite Dataset Hub](https://huggingface.co/spaces/infinite-dataset-hub/infinite-dataset-hub) and microsoft/Phi-3-mini-4k-instruct using the query 'employee reviews': - **Dataset Generation Page**: https://huggingface.co/spaces/infinite-dataset-hub/infinite-dataset-hub?q=employee+reviews&dataset=EmployeeFeedbackMatrix&tags=sentiment+analysis,+workplace+satisfaction,+performance+metrics - **Model**: https://huggingface.co/microsoft/Phi-3-mini-4k-instruct - **More Datasets**: https://huggingface.co/datasets?other=infinite-dataset-hub
tttx/8k-forcing-clipped-022225-step5-collated
tttx
"2025-02-25T17:17:50Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T17:17:47Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 672104.0 num_examples: 22 - name: test num_bytes: 16587 num_examples: 1 download_size: 203415 dataset_size: 688691.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
nivektk/math-augmented-dataset
nivektk
"2025-02-25T17:32:49Z"
2
0
[ "task_categories:question-answering", "task_categories:text-generation", "annotations_creators:machine-generated", "multilinguality:monolingual", "source_datasets:MATH (Dan Hendrycks)", "language:en", "license:gpl-2.0", "size_categories:n<1K", "modality:text", "arxiv:2103.03874", "region:us" ]
[ "question-answering", "text-generation" ]
"2025-02-25T17:23:10Z"
--- license: gpl-2.0 task_categories: - question-answering - text-generation language: - en pretty_name: Math-Augmented-Dataset size_categories: - 1K<n<10K source_datasets: - MATH (Dan Hendrycks) annotations_creators: - machine-generated multilinguality: monolingual paperswithcode_id: math homepage: "https://www.kaggle.com/datasets/kevinfabioramoslopez/math-augmented-dataset" --- # Math-Augmented-Dataset ## Dataset Description The **Math-Augmented-Dataset** extends the MATH dataset by Dan Hendrycks, focusing on algebra problems. It comprises **1,006 validated examples** from the algebra subset, structured in JSON format with detailed step-by-step solutions generated using Large Language Models (LLMs) with chain-of-thought reasoning. ### Dataset Structure Each JSON file contains: - **problem**: The math problem statement, including LaTeX expressions. - **level**: Difficulty level (1-5, with 5 being the hardest). - **type**: Mathematical domain (e.g., algebra, geometry). - **solution**: Step-by-step solution in English. ### Dataset Creation The dataset was augmented using **LLMs** to generate structured explanations. A validation process ensured that the solutions were logically consistent and mathematically correct. ## Citation If you use this dataset, please cite: ``` @article{hendrycks2021measuring, title={Measuring Mathematical Problem Solving With the MATH Dataset}, author={Hendrycks, Dan and Burns, Collin and Kadavath, Saurav and Arora, Akul and Basart, Steven and Tang, Eric and Song, Dawn and Steinhardt, Jacob}, journal={arXiv preprint arXiv:2103.03874}, year={2021} } ```
tttx/3k-forcing-clipped-022225-step7-collated
tttx
"2025-02-25T17:25:34Z"
2
0
[ "size_categories:n<1K", "format:parquet", "modality:tabular", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T17:25:31Z"
--- dataset_info: features: - name: messages list: - name: content dtype: string - name: role dtype: string - name: difficulty dtype: int64 - name: problem_uid dtype: string - name: step dtype: int64 splits: - name: train num_bytes: 5817679.0 num_examples: 271 - name: test num_bytes: 22606 num_examples: 1 download_size: 1559379 dataset_size: 5840285.0 configs: - config_name: default data_files: - split: train path: data/train-* - split: test path: data/test-* ---
amuvarma/tagged_qa_pair_va
amuvarma
"2025-02-25T17:33:50Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T17:33:06Z"
--- dataset_info: features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 1538418.6570527265 num_examples: 3000 download_size: 971800 dataset_size: 1538418.6570527265 configs: - config_name: default data_files: - split: train path: data/train-* ---
amuvarma/all-tagged-qa-6k
amuvarma
"2025-02-25T17:37:32Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "modality:text", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T17:37:31Z"
--- dataset_info: features: - name: question dtype: string - name: answer dtype: string splits: - name: train num_bytes: 2743300.823802716 num_examples: 5895 download_size: 1505779 dataset_size: 2743300.823802716 configs: - config_name: default data_files: - split: train path: data/train-* ---
amuvarma/all-tagged-qa-6k-proc
amuvarma
"2025-02-25T17:46:26Z"
2
0
[ "size_categories:1K<n<10K", "format:parquet", "library:datasets", "library:pandas", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T17:46:25Z"
--- dataset_info: features: - name: input_ids sequence: int32 - name: attention_mask sequence: int8 - name: labels sequence: int64 splits: - name: train num_bytes: 6887407 num_examples: 5895 download_size: 2241047 dataset_size: 6887407 configs: - config_name: default data_files: - split: train path: data/train-* ---
MHTrXz/MedcalRagSmall
MHTrXz
"2025-02-25T17:49:40Z"
2
0
[ "size_categories:100K<n<1M", "format:parquet", "modality:text", "library:datasets", "library:dask", "library:mlcroissant", "library:polars", "region:us" ]
null
"2025-02-25T17:48:49Z"
--- dataset_info: features: - name: title dtype: string - name: content dtype: string - name: source dtype: string - name: author dtype: string - name: references dtype: string splits: - name: train num_bytes: 807678007 num_examples: 187455 download_size: 192511442 dataset_size: 807678007 configs: - config_name: default data_files: - split: train path: data/train-* ---