{"items":[{"id":116,"title":"apigen-function-calling","summary":null,"description":"This dataset is a merge of [argilla/Synth-APIGen-v0.1](https://huggingface.co/datasets/argilla/Synth-APIGen-v0.1) and [Salesforce/xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k), making over 100K function calling examples following the APIGen recipe.","license":"cc-by-4.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/argilla/apigen-function-calling/resolve/main/data/train-00000-of-00001.parquet","originalFilename":null,"format":"parquet","sizeBytes":60235594,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/train-00000-of-00001.parquet","size":60235594}],"createdAt":"2026-09-27T06:09:09.022Z","updatedAt":"2026-09-27T06:09:09.022Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":115,"title":"tool_calling","summary":null,"description":"BitAgent tool_calling: synthetic function-calling conversations from the BitAgent project (BerryML) covering multi-tool selection, nested arguments, and rejection cases. No license tag upstream (default HF terms).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/BitAgent/tool_calling/resolve/main/data/train-00000-of-00001.parquet","originalFilename":null,"format":"parquet","sizeBytes":79932244,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/train-00000-of-00001.parquet","size":79932244}],"createdAt":"2026-09-27T06:09:08.471Z","updatedAt":"2026-09-27T06:09:08.471Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}},{"id":114,"title":"xlam_hermes_validated","summary":null,"description":"xlam-Hermes validated: the Salesforce xlam function-calling corpus re-formatted to the Hermes tool-use template and filtered for validity by Interstellar Ninja — pairs with the xlam/Hermes function-calling sets already mirrored. No license tag upstream (default HF terms).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/interstellarninja/xlam_hermes_validated/resolve/main/data/train-00000-of-00001.parquet","originalFilename":null,"format":"parquet","sizeBytes":3708143,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/train-00000-of-00001.parquet","size":3708143}],"createdAt":"2026-09-27T06:09:07.834Z","updatedAt":"2026-09-27T06:09:07.834Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}},{"id":113,"title":"tool-use-multiturn-reasoning","summary":null,"description":"--- dataset_info: features: - name: conversations list: - name: from dtype: string - name: value dtype: string - name: tools dtype: string - name: task dtype: string - name: category dtype: string - name: source dtype: string splits: - name: train num_bytes: 138012926 num_examples: 14579 download_size: 26612632 dataset_size: 138012926 configs: - config_name: default data_files: - split: train path: data/train-* license: apache-2.0 task_categories: - question-answering language: - en tags: - tool-use - multiturn - agentic - bfcl - reasoning size_categories: - 10K<n<100K ---","license":"apache-2.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/interstellarninja/tool-use-multiturn-reasoning/resolve/main/data/train-00000-of-00001.parquet","originalFilename":null,"format":"parquet","sizeBytes":26612632,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/train-00000-of-00001.parquet","size":26612632}],"createdAt":"2026-09-27T06:09:07.282Z","updatedAt":"2026-09-27T06:09:07.282Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":112,"title":"tool-calls-singleturn","summary":null,"description":"Tool-calls single-turn: Hermes-format single-turn function-calling samples (system prompt + tool schemas + one assistant tool-call response) from the Interstellar Ninja tool-use family. Apache-2.0.","license":"apache-2.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/interstellarninja/tool-calls-singleturn/resolve/main/data/train-00000-of-00001.parquet","originalFilename":null,"format":"parquet","sizeBytes":7385970,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/train-00000-of-00001.parquet","size":7385970}],"createdAt":"2026-09-27T06:09:06.724Z","updatedAt":"2026-09-27T06:09:06.724Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":111,"title":"RLVR-IFeval","summary":null,"description":"RLVR-IFeval (AllenAI): instruction-following tasks with programmatically verifiable constraints (from IFEval) for Tulu-3 RLVR training — prompts carry machine-checkable requirements so rewards can be computed without a reward model. ODC-By.","license":"odc-by","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/allenai/RLVR-IFeval/resolve/main/data/train-00000-of-00001.parquet","originalFilename":null,"format":"parquet","sizeBytes":11653857,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/train-00000-of-00001.parquet","size":11653857}],"createdAt":"2026-09-27T06:09:06.100Z","updatedAt":"2026-09-27T06:09:06.100Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":110,"title":"openchat_sharegpt4_dataset","summary":null,"description":"This repository contains cleaned and filtered ShareGPT GPT-4 data used to train OpenChat. Details can be found in the [OpenChat repository](https://github.com/imoneoi/openchat).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/openchat/openchat_sharegpt4_dataset/tree/main","originalFilename":null,"format":"json","sizeBytes":2476401905,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":17,"fileList":[{"path":"openchat.eval.json","size":1195069},{"path":"openchat.eval.text.json","size":371581},{"path":"openchat.train.json","size":116797184},{"path":"openchat.train.text.json","size":36887008},{"path":"openchat_8192.eval.json","size":2744623},{"path":"openchat_8192.eval.text.json","size":863769},{"path":"openchat_8192.train.embeddings.json","size":211347466},{"path":"openchat_8192.train.json","size":240803969},{"path":"openchat_8192.train.text.json","size":75653112},{"path":"openchat_8192.train.visualizer.json","size":76063549},{"path":"opencoder.eval.json","size":2497818},{"path":"opencoder.eval.text.json","size":906208},{"path":"opencoder.train.json","size":215994377},{"path":"opencoder.train.text.json","size":78721396},{"path":"sharegpt_clean.json","size":1296084028},{"path":"sharegpt_gpt4.json","size":119458803},{"path":"visualizer.html","size":11945}],"createdAt":"2026-09-27T06:09:05.130Z","updatedAt":"2026-09-27T06:09:05.130Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}},{"id":109,"title":"no_robots","summary":null,"description":"- **Repository:** https://github.com/huggingface/alignment-handbook - **Paper:** - **Leaderboard:** https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard - **Point of Contact:** Lewis Tunstall","license":"cc-by-nc-4.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/HuggingFaceH4/no_robots/tree/main","originalFilename":null,"format":"parquet","sizeBytes":22091174,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":4,"fileList":[{"path":"data/test-00000-of-00001.parquet","size":570905},{"path":"data/test_sft-00000-of-00001.parquet","size":570905},{"path":"data/train-00000-of-00001.parquet","size":10474682},{"path":"data/train_sft-00000-of-00001.parquet","size":10474682}],"createdAt":"2026-09-27T06:09:04.580Z","updatedAt":"2026-09-27T06:09:04.580Z","licenseRisk":{"tier":"restricted","reason":"This license includes a non-commercial or research-only restriction."}},{"id":108,"title":"OpenOrca","summary":null,"description":"OpenOrca (1M GPT-4-augmented split): the augmented FLAN collection — ~1M GPT-4 completions over FLAN prompts (plus 3.2M GPT-3.5 in the other file), the open analogue of the Orca paper's system-messages approach. MIT.","license":"mit","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/Open-Orca/OpenOrca/resolve/main/1M-GPT4-Augmented.parquet","originalFilename":null,"format":"parquet","sizeBytes":1008442855,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"1M-GPT4-Augmented.parquet","size":1008442855}],"createdAt":"2026-09-27T06:09:03.650Z","updatedAt":"2026-09-27T06:09:03.650Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":107,"title":"ultrachat_200k","summary":null,"description":"UltraChat 200k (HuggingFaceH4): the filtered UltraChat corpus used to train Zephyr-7B — ~200k multi-turn open-ended dialogues generated against GPT-3.5-Turbo across ~30 domains, decontaminated against eval benchmarks. MIT.","license":"mit","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/HuggingFaceH4/ultrachat_200k/tree/main","originalFilename":null,"format":"parquet","sizeBytes":1624049723,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":8,"fileList":[{"path":"data/test_gen-00000-of-00001-3d4cd8309148a71f.parquet","size":80359907},{"path":"data/test_sft-00000-of-00001-f7dfac4afe5b93f4.parquet","size":81176553},{"path":"data/train_gen-00000-of-00003-a6c9fb894be3e50b.parquet","size":243687391},{"path":"data/train_gen-00001-of-00003-d6a0402e417f35ca.parquet","size":243300397},{"path":"data/train_gen-00002-of-00003-c0db75b92a2f48fd.parquet","size":243497356},{"path":"data/train_sft-00000-of-00003-a3ecf92756993583.parquet","size":243999189},{"path":"data/train_sft-00001-of-00003-0a1804bcb6ae68c6.parquet","size":243897199},{"path":"data/train_sft-00002-of-00003-ee46ed25cfae92c6.parquet","size":244131731}],"createdAt":"2026-09-27T06:09:02.688Z","updatedAt":"2026-09-27T06:09:02.688Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":106,"title":"COIG-CQIA","summary":null,"description":"COIG-CQIA (m-a-p): the Chinese Open Instruction Generalist quality-filtered split — ~48k high-quality Chinese instruction sources spanning academia, government, exams, and media, widely used for Chinese-language SFT. No license tag upstream (default HF terms).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/m-a-p/COIG-CQIA/tree/main","originalFilename":null,"format":"jsonl","sizeBytes":298963907,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":46,"fileList":[{"path":"COIG-CQIA-full.jsonl","size":149472971},{"path":"chinese_traditional/chengyu.jsonl","size":82480},{"path":"chinese_traditional/poem.jsonl","size":30018},{"path":"chinese_traditional/trad-multi-choice-100-2.jsonl","size":58480},{"path":"chinese_traditional/trad-multi-choice-100.jsonl","size":59864},{"path":"chinese_traditional/trad-multi-choice-40.jsonl","size":40859},{"path":"chinese_traditional/translate_classical_chinese.jsonl","size":649287},{"path":"coig_pc/coig_pc_core_sample.jsonl","size":4624040},{"path":"douban/book_introduce.jsonl","size":718502},{"path":"douban/book_reviews.jsonl","size":464357},{"path":"douban/movie_anime_synopsis_more_prompt.jsonl","size":636004},{"path":"douban/movie_documentary_synopsis_more_prompt.jsonl","size":134284},{"path":"douban/movie_recommendation.jsonl","size":53315},{"path":"douban/movie_recommendation2.jsonl","size":21016},{"path":"douban/movie_reviews.jsonl","size":918882},{"path":"douban/movie_synopsis_more_prompt.jsonl","size":627854},{"path":"douban/tv_anime_synopsis_more_prompt.jsonl","size":732188},{"path":"douban/tv_documentary_synopsis_more_prompt.jsonl","size":93518},{"path":"douban/tv_recommendation.jsonl","size":20332},{"path":"douban/tv_recommendation2.jsonl","size":16056},{"path":"douban/tv_reviews.jsonl","size":686151},{"path":"douban/tv_synopsis_more_prompt.jsonl","size":727838},{"path":"exam/coig_exam_sampled_clean_v3.jsonl","size":3122258},{"path":"exam/kaoyan.jsonl","size":502901},{"path":"exam/law_gee_exam_clean_v2.jsonl","size":2807330},{"path":"finance/finance_coig_pc.jsonl","size":1728038},{"path":"finance/mba_baike.jsonl","size":69117801},{"path":"human_value/100poison.jsonl","size":891302},{"path":"human_value/coig_human_value_multi_choice.jsonl","size":90853},{"path":"logi_qa/logi-qa.jsonl","size":573430},{"path":"ruozhiba/ruozhiba_ruozhiba.jsonl","size":267306},{"path":"segmentfault/segmentfault_upvote5_clean.jsonl","size":891367},{"path":"wiki/10why_final.jsonl","size":242877},{"path":"wiki/51zyzy.jsonl","size":264802},{"path":"wiki/agriculture.jsonl","size":953005},{"path":"wiki/baobao.jsonl","size":171449},{"path":"wiki/bkmy_medicine.jsonl","size":19613744},{"path":"wiki/bkmy_symptom.jsonl","size":2179111},{"path":"wiki/digital_wiki.jsonl","size":318891},{"path":"wiki/zgbk.jsonl","size":5653878},{"path":"wikihow/wikihow.jsonl","size":11519024},{"path":"xhs/xhs.jsonl","size":2792512},{"path":"zhihu/zhihu_expansion.jsonl","size":446198},{"path":"zhihu/zhihu_score8.0-8.5_clean_v3.jsonl","size":3236988},{"path":"zhihu/zhihu_score8.5-9.0_clean_v4.jsonl","size":3346303},{"path":"zhihu/zhihu_score9.0-10_clean_v10.jsonl","size":7364243}],"createdAt":"2026-09-27T06:09:00.829Z","updatedAt":"2026-09-27T06:09:00.829Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}},{"id":105,"title":"MATH-plus","summary":null,"description":"This dataset contains the MetaMath, MATH-orca and some additional MATH-augmented dataset with GPT-4. This dataset is being used to train MAmmoTH2-plus version (https://tiger-ai-lab.github.io/MAmmoTH2/).","license":"mit","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/TIGER-Lab/MATH-plus/resolve/main/train/train-00000-of-00002.parquet","originalFilename":null,"format":"parquet","sizeBytes":337477245,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":2,"fileList":[{"path":"train/train-00000-of-00002.parquet","size":175284411},{"path":"train/train-00001-of-00002.parquet","size":162192834}],"createdAt":"2026-09-27T06:09:00.255Z","updatedAt":"2026-09-27T06:09:00.255Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":104,"title":"code_contests_instruct","summary":null,"description":"The `deepmind/code_contests` dataset formatted as markdown-instruct for text generation training.","license":"apache-2.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/BEE-spoke-data/code_contests_instruct/tree/main","originalFilename":null,"format":"parquet","sizeBytes":16414558108,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":64,"fileList":[{"path":"data/test-00000-of-00001-783dc3d86eccac91.parquet","size":62787016},{"path":"data/train-00000-of-00026-25afd91119a40a45.parquet","size":197537859},{"path":"data/train-00001-of-00026-4295e5dece226908.parquet","size":194329567},{"path":"data/train-00002-of-00026-6e7e63842f8da5fa.parquet","size":203856367},{"path":"data/train-00003-of-00026-3b6b0f5944602caf.parquet","size":172260924},{"path":"data/train-00004-of-00026-723ecd6cc780fc0f.parquet","size":215151751},{"path":"data/train-00005-of-00026-6c5a601b5117164b.parquet","size":208419105},{"path":"data/train-00006-of-00026-90852fd5f7ba83c1.parquet","size":194336535},{"path":"data/train-00007-of-00026-e964109adcdcf61b.parquet","size":188360470},{"path":"data/train-00008-of-00026-f26b162f525a8733.parquet","size":190200157},{"path":"data/train-00009-of-00026-36cf47f9f6daf4bf.parquet","size":186933326},{"path":"data/train-00010-of-00026-a78166ce38c9aefa.parquet","size":198568682},{"path":"data/train-00011-of-00026-9ff094fddf3320a3.parquet","size":186748129},{"path":"data/train-00012-of-00026-1ee208dcc60b0650.parquet","size":197347629},{"path":"data/train-00013-of-00026-9aad91ee1c6933e0.parquet","size":203499449},{"path":"data/train-00014-of-00026-11c97d4f56cbaafd.parquet","size":188590103},{"path":"data/train-00015-of-00026-22e2aa21751724f8.parquet","size":184570310},{"path":"data/train-00016-of-00026-3c9cbfe4fef4ddb4.parquet","size":217071775},{"path":"data/train-00017-of-00026-defca18a3d17ccd9.parquet","size":191077919},{"path":"data/train-00018-of-00026-655114d77cd8c1d8.parquet","size":198533065},{"path":"data/train-00019-of-00026-0ae6fd2e5771aa8d.parquet","size":199717747},{"path":"data/train-00020-of-00026-c82024ffe868a46f.parquet","size":207041678},{"path":"data/train-00021-of-00026-7c68f6a7704d1eb2.parquet","size":201879264},{"path":"data/train-00022-of-00026-09a9866f0025fc07.parquet","size":191307979},{"path":"data/train-00023-of-00026-f1b6b6c83ec9a68d.parquet","size":193097274},{"path":"data/train-00024-of-00026-b4daf184872a06c5.parquet","size":183407884},{"path":"data/train-00025-of-00026-ab4056e320c8fa64.parquet","size":203067307},{"path":"data/valid-00000-of-00001-d95595d45a2cfea6.parquet","size":55723576},{"path":"hq-deduped/test-00000-of-00001-7a7e2176610796a8.parquet","size":17214468},{"path":"hq-deduped/train-00000-of-00003-2122ddab01a7e739.parquet","size":407103830},{"path":"hq-deduped/train-00001-of-00003-a0cf6523bc177f57.parquet","size":410350347},{"path":"hq-deduped/train-00002-of-00003-e16ac08d34d5a7d9.parquet","size":413944728},{"path":"hq-deduped/validation-00000-of-00001-4e59731f5c3363a3.parquet","size":15150166},{"path":"hq-python-deduped/test-00000-of-00001-102784dfa7d7af94.parquet","size":1975586},{"path":"hq-python-deduped/train-00000-of-00001-bf21f3eaac8311dc.parquet","size":138375235},{"path":"hq-python-deduped/validation-00000-of-00001-defc637d297b6cc5.parquet","size":2533272},{"path":"hq-python/test-00000-of-00001-2aff7e3d99e91fef.parquet","size":4963431},{"path":"hq-python/train-00000-of-00002-c0769688cde2a4ec.parquet","size":341857676},{"path":"hq-python/train-00001-of-00002-2409dbd4881ecf1d.parquet","size":342046180},{"path":"hq-python/valid-00000-of-00001-549eda1872f479fa.parquet","size":5703247},{"path":"hq/test-00000-of-00001-46a421439a3f17c9.parquet","size":28700022},{"path":"hq/train-00000-of-00006-a7e7025c43a2fea0.parquet","size":437380632},{"path":"hq/train-00001-of-00006-21064df0cad49b53.parquet","size":437716615},{"path":"hq/train-00002-of-00006-7b8f08b841218569.parquet","size":436586953},{"path":"hq/train-00003-of-00006-09d263c5cdca7820.parquet","size":437531716},{"path":"hq/train-00004-of-00006-447d50ba156e2019.parquet","size":438212549},{"path":"hq/train-00005-of-00006-88e499600c8acae3.parquet","size":438712967},{"path":"hq/valid-00000-of-00001-da80fb334f6b1fbf.parquet","size":25279287},{"path":"min-cols/test-00000-of-00001-a25edc4c9352c9b8.parquet","size":61521487},{"path":"min-cols/train-00000-of-00014-93e01c89beaab6a2.parquet","size":449336598},{"path":"min-cols/train-00001-of-00014-33ee38ac76ed2ea5.parquet","size":449626672},{"path":"min-cols/train-00002-of-00014-4ea1f2abd146eabd.parquet","size":450289459},{"path":"min-cols/train-00003-of-00014-ddc87d5b23689311.parquet","size":451006898},{"path":"min-cols/train-00004-of-00014-23870c7a6cfb733b.parquet","size":450660432},{"path":"min-cols/train-00005-of-00014-66389c0b57d2fc92.parquet","size":450158268},{"path":"min-cols/train-00006-of-00014-019771e1e6b70da2.parquet","size":449486895},{"path":"min-cols/train-00007-of-00014-789e15be51da2e0a.parquet","size":450611314},{"path":"min-cols/train-00008-of-00014-73fbfdd4f6dec06f.parquet","size":450589749},{"path":"min-cols/train-00009-of-00014-cb3cd883122b8b5a.parquet","size":449633705},{"path":"min-cols/train-00010-of-00014-cf4c082afed82508.parquet","size":450447806},{"path":"min-cols/train-00011-of-00014-be5ad136082483dc.parquet","size":450009709},{"path":"min-cols/train-00012-of-00014-2dbcba5184945877.parquet","size":450559619},{"path":"min-cols/train-00013-of-00014-c1f6122a1fd45371.parquet","size":449560016},{"path":"min-cols/valid-00000-of-00001-5a432f56f6df0555.parquet","size":54297727}],"createdAt":"2026-09-27T06:08:59.682Z","updatedAt":"2026-09-27T06:08:59.682Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":103,"title":"SWE-Bench-Verified-O1-native-tool-calling-reasoning-high-results","summary":null,"description":"This dataset was generated using the CodeAct framework, which aims to improve code generation through enhanced action-based reasoning. Built on top of OpenHands, a framework designed for multi-turn interactive programming tasks, we tested O1 issue resolution capabilities on ```reasoning_effort = 'high'```","license":"cc-by-4.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/AlexCuadron/SWE-Bench-Verified-O1-native-tool-calling-reasoning-high-results/resolve/main/dataset_viewer.parquet","originalFilename":null,"format":"parquet","sizeBytes":169576457,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"dataset_viewer.parquet","size":169576457}],"createdAt":"2026-09-27T06:08:59.124Z","updatedAt":"2026-09-27T06:08:59.124Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":102,"title":"hf-coding-tools-traces","summary":null,"description":"This dataset rehydrates the benchmark run in [`davidkling/hf-coding-tools-dashboard`](https://huggingface.co/buckets/davidkling/hf-coding-tools-dashboard) into the JSONL session format consumed by the [Hugging Face Agent Trace Viewer](https://huggingface.co/changelog/agent-trace-viewer).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/clem/hf-coding-tools-traces/tree/main","originalFilename":null,"format":"jsonl","sizeBytes":43613878,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":35,"fileList":[{"path":"claude_code__claude-opus-4-6__high__disabled.jsonl","size":1721798},{"path":"claude_code__claude-opus-4-6__high__enabled.jsonl","size":1704332},{"path":"claude_code__claude-opus-4-6__low__disabled.jsonl","size":1329857},{"path":"claude_code__claude-opus-4-6__low__enabled.jsonl","size":1330348},{"path":"claude_code__claude-opus-4-6__max__disabled.jsonl","size":1673842},{"path":"claude_code__claude-opus-4-6__max__enabled.jsonl","size":1653715},{"path":"claude_code__claude-opus-4-6__medium__disabled.jsonl","size":1580056},{"path":"claude_code__claude-opus-4-6__medium__enabled.jsonl","size":1584338},{"path":"claude_code__claude-sonnet-4-6__high__disabled.jsonl","size":1671477},{"path":"claude_code__claude-sonnet-4-6__high__enabled.jsonl","size":1629220},{"path":"claude_code__claude-sonnet-4-6__low__disabled.jsonl","size":1648475},{"path":"claude_code__claude-sonnet-4-6__low__enabled.jsonl","size":1587605},{"path":"claude_code__claude-sonnet-4-6__max__disabled.jsonl","size":1672337},{"path":"claude_code__claude-sonnet-4-6__max__enabled.jsonl","size":1610766},{"path":"claude_code__claude-sonnet-4-6__medium__disabled.jsonl","size":1684088},{"path":"claude_code__claude-sonnet-4-6__medium__enabled.jsonl","size":1589270},{"path":"codex__gpt-4.1-mini__high__enabled.jsonl","size":953099},{"path":"codex__gpt-4.1-mini__low__enabled.jsonl","size":947353},{"path":"codex__gpt-4.1-mini__medium__enabled.jsonl","size":937371},{"path":"codex__gpt-4.1-mini__minimal__enabled.jsonl","size":947083},{"path":"codex__gpt-4.1-mini__xhigh__enabled.jsonl","size":954829},{"path":"codex__gpt-4.1__high__enabled.jsonl","size":1298659},{"path":"codex__gpt-4.1__low__enabled.jsonl","size":1301686},{"path":"codex__gpt-4.1__medium__enabled.jsonl","size":1327355},{"path":"codex__gpt-4.1__minimal__enabled.jsonl","size":1330194},{"path":"codex__gpt-4.1__xhigh__enabled.jsonl","size":1305436},{"path":"copilot__claude-sonnet-4.6__high__enabled.jsonl","size":996197},{"path":"copilot__claude-sonnet-4.6__low__enabled.jsonl","size":1007898},{"path":"copilot__claude-sonnet-4.6__max__enabled.jsonl","size":993652},{"path":"copilot__claude-sonnet-4.6__medium__enabled.jsonl","size":1015872},{"path":"cursor__composer-2__high__enabled.jsonl","size":1727992},{"path":"testtraces/manifest.json","size":648},{"path":"testtraces/messages.jsonl","size":87587},{"path":"testtraces/parts.jsonl","size":807049},{"path":"testtraces/traces.jsonl","size":2394}],"createdAt":"2026-09-27T06:08:58.563Z","updatedAt":"2026-09-27T06:08:58.563Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}},{"id":101,"title":"transformers-coding-session-pi-traces","summary":null,"description":"pi coding-agent session traces produced by [agentcap](https://github.com/huggingface/agentcap) runs. Each run contributes one folder under `data/<run_id>/`; inside, one file per session in `pi`'s native export format.","license":"apache-2.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/dacorvo/transformers-coding-session-pi-traces/resolve/main/data/pi-local-20260601-155411/2026-06-01T15-54-14-442Z_019e83e4-8e29-75cd-8e96-24ced18dc3b8.jsonl","originalFilename":null,"format":"jsonl","sizeBytes":39729,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"data/pi-local-20260601-155411/2026-06-01T15-54-14-442Z_019e83e4-8e29-75cd-8e96-24ced18dc3b8.jsonl","size":39729}],"createdAt":"2026-09-27T06:08:58.020Z","updatedAt":"2026-09-27T06:08:58.020Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":100,"title":"agentic-coding-traces","summary":null,"description":"This dataset is aggregated from: ``` \"AletheiaResearch/GLM-5.2-Agent\", \"armand0e/claude-fable-5-claude-code\", \"armand0e/minimax-m3-claude-code-traces\", \"AletheiaResearch/Kimi-K3-Codex\" ``` and has been converted into a single unified format: ``` {\"messages\": [{\"role\": \"user\", \"content\": \"...\"}, {\"role\": \"assistant\", \"content\": \"<think>...</think>...\"}, ...]} ``` The original raw files are kept in the `.raw_sources` folder for reference if you'd like to take a closer look.","license":"apache-2.0","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/mondk/agentic-coding-traces/resolve/main/.raw_sources/hf_downloads/AletheiaResearch__GLM-5.2-Agent/2026-06-19T19-53-37-440Z_019ee172-2f9f-7341-8125-4e5d535d9e56.jsonl","originalFilename":null,"format":"jsonl","sizeBytes":19819,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":".raw_sources/hf_downloads/AletheiaResearch__GLM-5.2-Agent/2026-06-19T19-53-37-440Z_019ee172-2f9f-7341-8125-4e5d535d9e56.jsonl","size":19819}],"createdAt":"2026-09-27T06:08:57.436Z","updatedAt":"2026-09-27T06:08:57.436Z","licenseRisk":{"tier":"clear","reason":"A well-known permissive license with no significant use restrictions."}},{"id":99,"title":"real-pi-coding-agent-traces-sessions","summary":null,"description":"An aggregated dataset of **real human–AI coding agent sessions**, collected from 21 independently published Hugging Face datasets and hand-filtered to exclude synthetic or AI-generated content.","license":"other","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/MaxDevv/real-pi-coding-agent-traces-sessions/resolve/main/LarsEckart-approvaltests-java-sessions-2025-12-04T08-54-31-360Z_b698a33a-749d-4f5f-abbe-4360a59354b6.jsonl","originalFilename":null,"format":"jsonl","sizeBytes":118070,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":1,"fileList":[{"path":"LarsEckart-approvaltests-java-sessions-2025-12-04T08-54-31-360Z_b698a33a-749d-4f5f-abbe-4360a59354b6.jsonl","size":118070}],"createdAt":"2026-09-27T06:08:56.868Z","updatedAt":"2026-09-27T06:08:56.868Z","licenseRisk":{"tier":"caution","reason":"This is a custom or less-common license — worth reading in full before use."}},{"id":98,"title":"swe-rebench-v2-glm-5.1-pi-agent-successful-traces","summary":null,"description":"We collected 7,777 successful multi-turn trajectories by running [GLM-5.1](https://huggingface.co/zai-org/GLM-5.1) with the [PI agent](https://pi.dev/) on [nebius/SWE-rebench-V2](https://huggingface.co/datasets/nebius/SWE-rebench-V2).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/whitecircle/swe-rebench-v2-glm-5.1-pi-agent-successful-traces/tree/main","originalFilename":null,"format":"parquet","sizeBytes":300179898,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":2,"fileList":[{"path":"data/train-00000-of-00002.parquet","size":150763378},{"path":"data/train-00001-of-00002.parquet","size":149416520}],"createdAt":"2026-09-27T06:08:56.031Z","updatedAt":"2026-09-27T06:08:56.031Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}},{"id":97,"title":"swesmith-clean","summary":null,"description":"swesmith-clean: a cleaned variant of the SWE-smith corpus from the R2E-Gym team — synthetically-injected SWE tasks with filtered execution results, for training and evaluating repository-level coding agents. No license tag upstream (default HF terms).","license":"unspecified (community upload, no license tag — default HF terms)","authorUsername":"hf-mirror","downloadUrl":"https://huggingface.co/datasets/r2e-edits/swesmith-clean/tree/main","originalFilename":null,"format":"parquet","sizeBytes":36882997,"downloadCount":0,"starCount":0,"mirrorCount":0,"tags":[],"isMirror":false,"mirroredFromId":null,"mirroredFromTitle":null,"status":"approved","reviewDueAt":null,"scanStatus":"not_scanned","scanDetails":null,"scanAttemptedAt":null,"fileCount":2,"fileList":[{"path":"data/train-00000-of-00002.parquet","size":9477144},{"path":"data/train-00001-of-00002.parquet","size":27405853}],"createdAt":"2026-09-27T06:08:55.480Z","updatedAt":"2026-09-27T06:08:55.480Z","licenseRisk":{"tier":"caution","reason":"The redistributed dataset itself doesn't carry its own license tag — check the reasoning in its description."}}],"total":116}