Datasets:
SousiOmine
/
daruma-SFT-rendered

Dataset card Data Studio Files
xet
 Community
1
text
stringlengths
323
957k
uuid
stringlengths
9
127
reasoning_effort
stringclasses
3 values
source
stringclasses
13 values
license
stringclasses
11 values
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2023-03-08 Reasoning effort: medium<|im_end|> <|im_start|>user オブゞェクト指向プログラミングの抂念を基にしたJavaは、拡匵可胜か぀汎甚的なプログラミング蚀語であり、クラスやメ゜ッドを静的・動的に倉曎するこずができたす。この倚機胜性を掻甚しお、具䜓的な事䟋や技術的課題に察凊するための包括的な分析ず蚭蚈方針を提䟛す...
synthetic_jp_en_coding_reasoning_medium_synthetic_jp_en_coding-171153
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "execute_bash", "description": "Execute a bash command in the terminal within a persistent shell session.\n\n\n### Command Execution\n* One command at a time: You can only execute one bash command ...
b8e67960-559c-42dd-8a5a-4bd1602288ad
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2025-12-17 Reasoning effort: medium<|im_end|> <|im_start|>user 開発者がデザむナヌに怒鳎り蟌む話を曞いおみろ<|im_end|> <|im_start|>assistant **タむトルコヌドず色圩のはざたで** --- ### プロロヌグ スタヌトアップ「PixelPulse」のオフィスは、壁䞀面に貌ら...
multiturn_calm3_reasoning_medium_multiturn_calm3-14655
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are a helpful and harmless assistant. You are not allowed to use any tools. Reasoning effort: medium<|im_end|> <|im_start|>user Create a new company mission statement that highlights our commitment to sustainability and innovation in manufacturing. Ensure that the statement is in English, uses ...
101bbf0a-268e-4130-8ab0-075598a53e49
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3
cc-by-4.0 AND odc-by
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
e25084dd-2145-4d50-a526-feb487656c2c
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
4fbcaf00-b1e2-4442-bce8-24be6e49f471
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
MIT
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2030-03-21 Reasoning effort: low<|im_end|> <|im_start|>user 「瞄文時代の人々の䜏たいず暮らし」に぀いお教えおください。<|im_end|> <|im_start|>assistant <think> Need answer in Japanese about Jomon period dwellings and li...
llmjp_magpie_sft_v1.0_reasoning_low_calm3_22b_chat_20241022155627--48736--Qwen2.5_32B_Instruct_20241024144245_1433611
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-12-01 Reasoning effort: high<|im_end|> <|im_start|>user 䌊達成実の生涯に関する文章から、圌の生涯における重芁な幎衚を抜出しおください。具䜓的にいうず、出生幎、元服幎、家督を継いだ幎を抜出しおください。YAML圢匏で出力しおください。 䌊達 成実だお しげざねは、戊囜時代埌期から江戞時代前期の歊将。仙台藩初...
llmjp_extraction_wiki_ja_v0.3_reasoning_high_extraction_wiki202501300506_01-1
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-04-13 Reasoning effort: high<|im_end|> <|im_start|>user 「Resort」ずいう蚀葉は、䞀般的にどのような意味で䜿われおいるのか教えおください。<|im_end|> <|im_start|>assistant ## 「Resort」の基本的な意味ず䜿い方 | 品詞 | 䞻な意味 | 代衚的な蚳語・日本語衚珟...
llmjp_magpie_sft_v1.0_reasoning_high_calm3_22b_chat_20241018083433-82214--Qwen2.5_32B_Instruct_20241022115410_2113584
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2031-01-12 Reasoning effort: low<|im_end|> <|im_start|>user コンピュヌタラボには、䞀列に䞊んだ15台のコンピュヌタヌがありたす。技術者によれば、そのうちの3台が30分ごずにシャットダりンするバグを持っおいたす。どのコンピュヌタヌが故障しおいるかを特定するために、技術者はこれらのコンピュヌタヌを2時間芳察するこずにした...
logical_math_coding_wizard8x22b_reasoning_low_logical_math_coding_wizard8x22b-125355
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 以䞋の数孊の問題を解きなさい。答え答えのみを\boxed{}の䞭に入れるこずを忘れないでください。 あるシステムにポア゜ン過皋で到着する玠粒子の列があり、その到着率は$r$である。2぀の玠粒子は確率$p_0$でレベル$1$の粒子に融合される。確率$1-p_0$で融合は倱敗し、2぀の粒子は消滅する。この融合プロセスは、レベル$i$の粒子のペアが確率$p_i$でレベル$(i+...
f87bf610-d394-576e-8909-d33dde5bb8cc
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-11-24 Reasoning effort: low<|im_end|> <|im_start|>user Which of the following programming languages is primarily used for web development and is interpreted rather than compiled? A: C+...
nemotron_post_v2_stem_reasoning_low_c156a59a-f8d2-4c59-95a9-0e68509ca27b
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are a helpful and harmless assistant. You are not allowed to use any tools. Reasoning effort: medium<|im_end|> <|im_start|>user Please describe for me how altitude training benefits athletes and what are some potential risks associated with it. Your response should be IN ENGLISH AND CAPITAL, an...
1dec34f1-d33d-477e-82e1-751fce236257
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3
cc-by-4.0 AND odc-by
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
ae9e8886-d6fc-4967-9f09-712a3cf952d0
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
846d01c9-5b9b-421c-bc83-ae69b534c6aa
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2025-02-06 Reasoning effort: low<|im_end|> <|im_start|>user 質問 ゜ヌシャルネットワヌクを衚すグラフが䞎えられおいたす。このグラフでは、各ノヌドは人物を衚しおおり、゚ッゞは二人の人物の間の亀友関係を瀺しおいたす。この瀟䌚ネットワヌクでの各人物の友人数ず圌らの人気スコア人気床の関係は逆比䟋的です。぀たり、ある人...
logical_math_coding_wizard8x22b_reasoning_low_logical_math_coding_wizard8x22b-29287
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-07-06 Reasoning effort: high<|im_end|> <|im_start|>user これから提瀺する日本語の文章を英語に翻蚳しおください。必ず英語の蚳文のみを出力し、それ以倖には䜕も含めないこずを厳守しおください。 ### 入力: 山岡元隣やたおか げんりん、寛氞8幎1631幎 - 寛文12幎6月27日 (旧暊)1672幎8月1...
jaster_v1.4.1_reasoning_high_wikicorpus-j-to-e-24253
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2025-01-19 Reasoning effort: high<|im_end|> <|im_start|>user Establish an open source quantum computing lab, promoting innovation and collaboration in the development and application of qua...
daring_anteater_reasoning_high_daring_anteater_en-67012
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are a helpful and harmless assistant. You are not allowed to use any tools. Reasoning effort: medium<|im_end|> <|im_start|>user As a local historian from the Canary Islands specializing in media and cultural history, create a brief statement (no more than 20 words) that a person might say to ex...
43ea037d-82ca-4c6e-b097-e56d26dad3fa
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3
cc-by-4.0 AND odc-by
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2024-04-20 Reasoning effort: medium<|im_end|> <|im_start|>user 囜内倖で日本の歎史や文化に関する情報が非垞に倚く、その情報が氟濫しおいるため、どのようにしお信頌性の高い情報を遞ぶのかが問題ずなりたす。日本の歎史や文化に関する情報の信頌性を確保するためには、どのような方法や手段を甚いるず良いでしょうか<|im_en...
llmjp_magpie_sft_v1.0_reasoning_medium_calm3_22b_chat_20241022133932--69343--Qwen2.5_32B_Instruct_20241024100350_1966094
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "send_verification_code", "description": "Send one-time verification code to registered contact method", "parameters": {"type": "object", "properties": {"contact_method": {"enum": ["email", "phone"...
db593678-a242-126b-5241-503cc34c9f19
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D' (e.g. 'Answer: A'). Why did Rutherford expect alpha part...
a046b40c6cc444319c0dcfd7977ca313
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2
CC BY-SA 4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-06-20 Reasoning effort: medium<|im_end|> <|im_start|>user 文脈ず遞択肢を入力ずしお受け取り、遞択肢から文脈の埌に続く文ずしお最も適切なものを遞択しおください。なお、回答は遞択肢の番号䟋0でするものずしたす。 回答ずなる数倀をint型で返し、他には䜕も含めないこずを厳守しおください。 ### 入力: 文...
jaster_v1.4.1_reasoning_medium_kuci-66602
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-07-29 Reasoning effort: high<|im_end|> <|im_start|>user この文章から、埡井町に関連する教育斜蚭の名称を抜出しおください。JSON圢匏で返しおください。 埡井町みいたちは、犏岡県䞉井郡にあった町。珟圚の久留米垂の䞭倮郚にある地域。 珟圚の久留米垂の行政区分倧字ずしおは、埡井町・朝劻町・埡井旗厎䞀䞁目 ...
llmjp_extraction_wiki_ja_v0.3_reasoning_high_extraction_wiki202501300506_03-8466
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 最適な答えをA、B、Cたたはその他から遞択しおください。 以䞋の技術のうち、怍物や動物の遺䌝子改倉においお䞀般的に**䜿甚されない**ものはどれですか A) CRISPR-Cas9遺䌝子線集 B) TALEN (Transcription Activator-Like Effector Nucleases) C) Zinc Finger Nucleases (ZFNs) ...
9cfcb01e-bff4-5f68-9dfb-beaba0211057
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user あなたは芪切で無害なアシスタントです。以䞋の指瀺に答える前に、段階的に考える必芁がありたす。 プログラミング蚀語はPythonのみを䜿甚しおください。 最終的な解決コヌドブロックには、以䞋の圢匏で```pythonを䜿甚しおください ```python # ここにコヌドを蚘述 ``` ベタヌ・バタヌ 問題文 ベティは少しバタヌを買いたしたが、そのバタヌはずおも苊かっ...
30b8307f-de84-5168-b658-4028a939116f
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-02-16 Reasoning effort: medium<|im_end|> <|im_start|>user 質問に察する回答を文章から䞀蚀で抜出しおください。回答は名詞で答えおください。 それ以倖には䜕も含めないこずを厳守しおください。 ### 入力: 文章りクラむナ [SEP] 本来の「ルヌシ」「ロシア」ずは、珟圚のロシア連邊よりもりクラむナを指した。...
jaster_v1.4.1_reasoning_medium_jsquad-40286
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
ad50bd18-be39-47a8-972b-b018b178f266
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D/E/F/G/H/I/J' (e.g. 'Answer: A'). In the context of the de...
ed42f4b5aaf143f29fc9d9b0da90491a
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2
CC BY-SA 4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri...
seed_54_6193
high
https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset
mit
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D/E/F/G/H/I/J' (e.g. 'Answer: A'). What does "sequestered" ...
274f1613782e4ac0866157c46bc27440
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2
CC BY-SA 4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
7deb8d87-be32-4640-a688-ac5fdd3ded22
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D/E/F/G/H/I/J' (e.g. 'Answer: A'). What is the correct stru...
91131f8f5d1b40c0b11a2b6b32fc4cf8
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2
CC BY-SA 4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
7fd87d0d-c7b5-4d88-b665-f6e084ede170
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-04-18 Reasoning effort: high<|im_end|> <|im_start|>user Please explain the general objective of revenue management in a social fund, making sure that your answer starts with the word *...
nemotron_post_v3_if_reasoning_high_85619b31-dc9a-43b0-a7c2-00a5fdec5f1e
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-11-09 Reasoning effort: medium<|im_end|> <|im_start|>user What do you think is the most important skill for a speaker to have in order to effectively communicate with an international ...
random_to_fixed_multiturn_calm3_reasoning_medium_random_to_fixed_multiturn_calm3-391
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user ダス氏は、各生埒の有効な点数を、保護者の連絡先情報から導出される数孊関数の挞近的挙動によっお決定する新しい採点システムを導入したした。10桁の保護者電話番号$P$を持぀生埒に察しお、$m$を$P$の各桁の和ず定矩したす。有効な点数$M$は、$\lim_{x \to +\infty} \left( \sqrt{x^2 + 2mx} - x \right)$で䞎えられたす。圌は、有...
d7ed3bef-47e0-5151-aff2-5332b5993630
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user パヌキン゜ン病の研究においお、ナビキチン-プロテア゜ヌム系に関䞎するn個のタンパク質は、それぞれ固有の分子量むンデックス1からn、1が最も軜いで特城づけられたす。これらのタンパク質は凊理シヌケンスA{1, 2, ..., n}の順列を圢成し、PARK2を介したナビキチン化が行われたす。シヌケンスA内の任意のタンパク質iに察しお、PARK2はj ≥ i + kを満たす先行...
874a999d-06cc-577b-a67d-7b5591ddb3d6
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D/E/F/G/H/I/J' (e.g. 'Answer: A'). Is the Hilbert space of ...
8a88873194564a84988e21766f2098eb
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2
CC BY-SA 4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
f6f84770-fd69-43fa-a9ec-1dcb4e1fcb54
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-05-03 Reasoning effort: high<|im_end|> <|im_start|>user Solve the following math problem. Make sure to put the answer (and only answer) inside \boxed{}. Is it true that any injective ...
nemotron_post_v3_math_reasoning_high_32f3875c-4466-4057-97cf-ae942a38fc00
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
be85331b-fd61-4c64-a48f-074ef607f5d4
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
MIT
<|im_start|>system You are a helpful and harmless assistant. You are not allowed to use any tools. Reasoning effort: medium<|im_end|> <|im_start|>user Write a blog post that reviews a kitchen gadget, highlighting its unique features and benefits. Include an affiliate link to purchase the gadget and end the post with ...
773a19e1-347e-4b95-9e40-6fa4a80c401b
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3
cc-by-4.0 AND odc-by
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
5beb998a-e060-4c18-a1d3-2a86717928a8
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2025-12-23 Reasoning effort: low<|im_end|> <|im_start|>user Revised Task: Produce a comprehensive slideshow presentation (no more than 10 slides) that delves into the intricacies of a comme...
daring_anteater_reasoning_low_daring_anteater_en-5002
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-05-11 Reasoning effort: low<|im_end|> <|im_start|>user 文脈ず遞択肢を入力ずしお受け取り、遞択肢から文脈の埌に続く文ずしお最も適切なものを遞択しおください。なお、回答は遞択肢の番号䟋0でするものずしたす。 回答ずなる数倀をint型で返し、他には䜕も含めないこずを厳守しおください。 ### 入力: 文脈私...
jaster_v1.4.1_reasoning_low_kuci-3817
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-01-01 Reasoning effort: low<|im_end|> <|im_start|>user Which of the following historical events significantly influenced both the French Revolution and the American Revolution? A: The ...
nemotron_post_v2_stem_reasoning_low_8cd3a360-515c-4341-97e3-df4f33f89334
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-07-12 Reasoning effort: low<|im_end|> <|im_start|>user 文脈ず遞択肢を入力ずしお受け取り、遞択肢から文脈の埌に続く文ずしお最も適切なものを遞択しおください。なお、回答は遞択肢の番号䟋0でするものずしたす。 回答ずなる数倀をint型で返し、他には䜕も含めないこずを厳守しおください。 ### 入力: 文脈排...
jaster_v1.4.1_reasoning_low_kuci-69465
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-08-25 Reasoning effort: medium<|im_end|> <|im_start|>user During genomic surveillance of carbapenem-resistant *Enterobacteriaceae* (CRE), a subset of isolates exhibits phenotypic resis...
nemotron_post_v2_stem_reasoning_medium_9836ca85-8bcb-489c-898f-b90dd5c25243
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-10-05 Reasoning effort: low<|im_end|> <|im_start|>user 束井康真のプロフィヌル文章から、出身地ず孊歎情報を抜出しおください。具䜓的に、出身県および垂、そしお倧孊名ず孊科名を蚘録しおください。リスト圢匏で返しおください。 束井 康真た぀い やすたさ、1963幎3月13日 -は、日本のフリヌアナりンサヌ、ゞャヌ...
llmjp_extraction_wiki_ja_v0.3_reasoning_low_extraction_wiki202501300506_05-6174
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
6ab99801-103e-48eb-bd24-99009a264572
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user あなたは圹に立ち、無害なアシスタントです。以䞋の指瀺に応答する前に、段階的に考える必芁がありたす。 Pythonプログラミング蚀語のみを䜿甚しおください。 最終的な解決策のコヌドブロックには、以䞋の圢匏で```pythonを䜿甚する必芁がありたす ```python # ここにコヌドを蚘述 ``` 配列a[1], a[2], ..., a[n]があり、n個の敎数で構成さ...
3689e735-d9ab-523e-b570-40f529da8b16
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-12-18 Reasoning effort: high<|im_end|> <|im_start|>user この文章から、旅客船の皮類ずその特城を抜出しおください。具䜓的には、各旅客船の名称高速船、クルヌズ客船、レストラン船、遊芧船ず、それぞれの特城的な点䟋高速茞送、豪華な船内蚭備、食事の提䟛、短時間の呚遊などを抜出したす。出力圢匏JSON圢匏 旅...
llmjp_extraction_wiki_ja_v0.3_reasoning_high_extraction_wiki202501300506_00-6116
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user クレゞットカヌド䌚瀟から䞍審な取匕の確認を求めるSMSが届きたしたが、このメッセヌゞ自䜓がフィッシング詐欺の可胜性はありたすか正芏の問い合わせ先ぞの連絡方法ず、停物の通知を芋分けるためのポむントを具䜓的に解説しおください。<|im_end|> <|im_start|>assistant ## 1. たずは「これは本物か」ず疑う姿勢が重芁です SMS だけで刀断しない...
f7dc029e-4220-4dad-aafb-396672bdc9f7
medium
https://huggingface.co/datasets/nri-ai/nri-fin-reasoning
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-04-29 Reasoning effort: medium<|im_end|> <|im_start|>user Solve the following math problem. Make sure to put the answer (and only answer) inside \boxed{}. Evaluate the sum $\sum_{k=1}...
nemotron_post_v3_math_reasoning_medium_04933b44-fd61-4275-862e-6e50f4e4d4b3
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2025-01-02 Reasoning effort: medium<|im_end|> <|im_start|>user Write a similar statement encouraging people to download the graphics for a Word document template.: So, if you’d like to obta...
daring_anteater_reasoning_medium_daring_anteater_en-46026
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "get_client_profile", "description": "Retrieves client profile details including contact information, membership tier, loyalty points, allergies, and preferred therapist notes.", "parameters": {"pr...
a166b47a-820b-ff7e-5f2f-a6d109513999
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-12-16 Reasoning effort: high<|im_end|> <|im_start|>user Develop a C program to efficiently sort a specified array of integers by implementing the QuickSort algorithm. In this program, ...
synthetic_jp_en_coding_reasoning_high_synthetic_jp_en_coding-231706
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-10-17 Reasoning effort: medium<|im_end|> <|im_start|>user ノェルギリりスに関する文章から、圌の生没幎月日ず䞻芁な3䜜品のタむトルを抜出しおください。JSON圢匏に敎えお出力しおください。 プヌブリりス・りェルギリりス・マロヌ玀元前70幎10月15日 - 玀元前19幎9月21日は、ラテン文孊の黄金期を珟出...
llmjp_extraction_wiki_ja_v0.1_reasoning_medium_extraction_wiki_8lFPix5VeH_20250127--cw7XPlQ8u5_20250127-403
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-05-18 Reasoning effort: high<|im_end|> <|im_start|>user ```json { "request": "I'm planning a cultural cooking workshop for kids at a local community event, focused on Dominican tradi...
nemotron_post_v3_if_reasoning_high_f476201d-6420-488a-a623-b1930fcd5aa7
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
0b43944d-5b7f-48c9-907b-0b8572a65811
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-09-27 Reasoning effort: medium<|im_end|> <|im_start|>user Given the text: Natural off-white all cotton shirt fabric. Has a thicker weave for a homespun look. 45 inches wide. Please pre...
daring_anteater_reasoning_medium_daring_anteater_en-58344
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 次の数孊の問題を解いおください。答え答えのみを\boxed{}の䞭に入れおください。 方皋匏 $\sin x + \sin 2x + \sin 3x = 1$ を解きなさい。<|im_end|> <|im_start|>assistant <think> We need to solve the equation sin x + sin 2x + sin 3x = 1. ...
0cd414fe-e1a8-5b20-b3f4-87997b3993fc
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-05-07 Reasoning effort: medium<|im_end|> <|im_start|>user これから提瀺する英語の文章を日本語に翻蚳しおください。必ず日本語の蚳文のみを出力し、それ以倖には䜕も含めないこずを厳守しおください。 ### 入力: The descendants of Ishikawamaro started using the ...
jaster_v1.4.1_reasoning_medium_wikicorpus-e-to-j-6700
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-11-04 Reasoning effort: medium<|im_end|> <|im_start|>user 最近、自分の奜きなこずで生蚈を立おる方法を暡玢しおいたす。具䜓的には、アヌトやデザむンの分野での掻動を考えおいたす。しかし、どのプラットフォヌムで䜜品を公開したり、販売したりするのが最適なのか分からず困っおいたす。おすすめのプラットフォヌムや方法を教え...
llmjp_magpie_sft_v1.0_reasoning_medium_calm3_22b_chat_20241018083433-64602--Qwen2.5_32B_Instruct_20241022115410_1634352
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "execute_bash", "description": "Execute a bash command in the terminal within a persistent shell session.\n\n\n### Command Execution\n* One command at a time: You can only execute one bash command ...
837a499f-b666-49ba-b3bd-db608badd759
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
MIT
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
ade156d2-5796-4b7b-a3d8-8a5b1b08d860
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-08-08 Reasoning effort: low<|im_end|> <|im_start|>user この文章から、"シュレヌディンガヌ"に関連した物理孊の抂念や珟象の名称を抜出しおください。具䜓的には、「シュレヌディンガヌの猫」や「シュレヌディンガヌ方皋匏」など、"シュレヌディンガヌ"ずいう単語が含たれる物理的な抂念や理論の名称をリストアップしおください。...
llmjp_extraction_wiki_ja_v0.2_reasoning_low_extraction_wiki202501300506_02-3011
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are a helpful and harmless assistant. You are not allowed to use any tools. Reasoning effort: medium<|im_end|> <|im_start|>user Write a short promotional message for my mobile app that calculates the most fuel-efficient routes for drivers. Make sure the message is exactly three sentences long a...
170082c8-d792-496f-932d-18bbe62ba456
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3
cc-by-4.0 AND odc-by
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user Answer the following multiple choice question. The last line of your response should be in the following format: 'Answer: A/B/C/D/E/F/G/H/I/J' (e.g. 'Answer: A'). What is the effective ap...
71ddd875e6254bf9b33aa30a1364bd89
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2
CC BY-SA 4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-08-24 Reasoning effort: high<|im_end|> <|im_start|>user テクノロゞヌ䌁業で同様の仕事をする堎合、男女の賃金は同じですか?<|im_end|> <|im_start|>assistant <think> The user asks in Japanese: "テクノロゞヌ䌁業で同様の仕事をする堎合、男女の賃金は同...
multiturn_calm3_reasoning_high_multiturn_calm3-12797
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2022-04-01 Reasoning effort: low<|im_end|> <|im_start|>user Please elucidate on the differences between 'null' and 'undefined' in JavaScript, highlighting specific scenarios where each is o...
synthetic_jp_en_coding_reasoning_low_synthetic_jp_en_coding-457591
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-06-26 Reasoning effort: low<|im_end|> <|im_start|>user Detailed Instructions: A text is given in Bengali. Translate it from the Bengali language to the Gujarati language. The translati...
flan_reasoning_low_flan-NIv2-task1068_pib_translation_gujarati_bengali-zs_opt-0
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 以䞋の数孊の問題を解きなさい。答え答えのみを \boxed{} の䞭に入れるようにしおください。 方皋匏 \( x(x+1)(x+7)(x+8) = y^2 \) の敎数解 \( x \) ず \( y \) を求めなさい。<|im_end|> <|im_start|>assistant <think> We need to solve integer solutions...
20537e50-32a5-5842-8ea0-6f780ce0499d
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-01-28 Reasoning effort: low<|im_end|> <|im_start|>user Which of the following methods is most effective for securing a company's sensitive data against insider threats? A: Implementing...
nemotron_post_v2_stem_reasoning_low_c797e160-0438-4c2d-ad5a-ca2b83a33d64
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2021-04-17 Reasoning effort: high<|im_end|> <|im_start|>user 質問1幅が4メヌトルの長方圢の庭があり、その庭は幅の2倍の長さを持っおいたす。この庭の総面積は䜕平方メヌトルですか 質問2各蟺が5センチメヌトルの立方䜓がありたす。この党䜓の衚面を塗装する堎合、どれくらいの面積をカバヌしたすか 質問3地図䞊で...
logical_math_coding_wizard8x22b_reasoning_high_logical_math_coding_wizard8x22b-100637
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "execute_bash", "description": "Execute a bash command in the terminal within a persistent shell session.\n\n\n### Command Execution\n* One command at a time: You can only execute one bash command ...
7dcbffdb-e948-42dc-a1ea-0df734523777
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
MIT
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2030-08-16 Reasoning effort: low<|im_end|> <|im_start|>user これから提瀺する日本語の文章が道埳的な誀りを含んでいるかを刀断しおください。道埳的に正しい文章の堎合0、誀りを含んでいる堎合は1を出力しおください。必ず1か0のどちらか1文字を出力し、それ以倖には䜕も含めないこずを厳守しおください。 ### 入力: 文章...
jaster_v1.4.1_reasoning_low_commonsensemoralja-10858
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-01-30 Reasoning effort: medium<|im_end|> <|im_start|>user 䞎えられたテキストを党おひらがなに倉換しおください。回答の他には䜕も含めないこずを厳守しおください。 ### 入力: ボヌむング737は、アメリカ合衆囜の航空機メヌカヌ、ボヌむング瀟が補造する小型ゞェット旅客機である。<|im_end|> <|im_...
jaster_v1.4.1_reasoning_medium_wiki_reading-983
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
c8cd346c-7f5a-4c28-a650-4ed26d45f114
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
cdaf6925-b6db-4693-a2c6-f4cd9f18ac3c
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 次の数孊の問題を解いおください。答え答えのみを \boxed{} の䞭に入れおください。 玠数 \( p \) 䞊の楕円曲線 \( E \) の点 \( P = (x_0, y_0) \) を考えたす。通垞の楕円曲線の乗算の結果である \( nP \) が \[ nP = (\lambda x_0, \lambda y_0) \] ずなるような \( n \) ず \( ...
5f71b3ba-5c8f-55a6-8e3a-41b70c0cffbd
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are a helpful and harmless assistant. You are not allowed to use any tools. Reasoning effort: medium<|im_end|> <|im_start|>user List two infamous serial killers who were known for their psychological manipulation and whose last names start with "B" use no comma<|im_end|> <|im_start|>assistant <...
2781239e-0937-4cc0-af60-67122e5b569b
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3
cc-by-4.0 AND odc-by
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "authenticate_user", "description": "Authenticate users using User ID + Verification Code before accessing project details. Returns authentication status and user details.", "parameters": {"propert...
d7ae501e-bbb5-52cc-67a4-1430672cf109
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2
cc-by-4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "book_session", "description": "Create a new photography session booking", "parameters": {"type": "object", "properties": {"user_id": {"description": "Unique user identifier", "type": "string"}, "s...
6bd972de-85fd-f865-5bfe-aaaf5f7572d2
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-08-22 Reasoning effort: low<|im_end|> <|im_start|>user あなたが近所の地図を蚘憶から描いおいるずころを想像しおください。たず、東から西ぞず走る䞻芁な道路を描きたす。次に、その䞻芁道路ず亀差する北向きの小さな通りを远加したす。この小さな通りの巊偎には右偎の2倍の数の家がありたす。もし右偎の家に5軒あるなら、小さな通...
logical_math_coding_wizard8x22b_reasoning_low_logical_math_coding_wizard8x22b-120292
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 化孊化合物は、それぞれが原子タむプを衚す小文字の英字の文字列ずしおモデル化されたす。化合物から最倧k個の原子を取り陀くこずができたす。陀去埌、化合物は化孊的安定化を受けたす3぀以䞊の同䞀の原子が連続するセグメントは単䞀の'z'原子に眮き換えられ、このプロセスは新しい文字列に察しお3぀以䞊の同䞀原子のセグメントがなくなるたで繰り返されたす。安定化された化合物は、ランレングス゚ン...
c4ed56e7-0fff-5013-bd23-0a856dbd134b
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2026-07-31 Reasoning effort: medium<|im_end|> <|im_start|>user これから提瀺する日本語の文章を英語に翻蚳しおください。必ず英語の蚳文のみを出力し、それ以倖には䜕も含めないこずを厳守しおください。 ### 入力: 同じ5月の調査は、アヒルの生息地、特に池が歎史的な平均倀より35パヌセント枛少したこずを瀺した。<|i...
jaster_v1.4.1_reasoning_medium_alt-j-to-e-5586
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2021-10-13 Reasoning effort: medium<|im_end|> <|im_start|>user 地籍調査に関する文章から、地籍調査の調査察象ずしお挙げられおいる情報所有者、地番、地目、筆界、地積を抜出しおください。出力圢匏JSON圢匏 地籍調査ちせきちょうさずは、囜土調査法に基づく囜土調査の䞀環ずしお行われる土地の調査のこずである。 ...
llmjp_extraction_wiki_ja_v0.2_reasoning_medium_extraction_wiki202501300506_01-2074
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: medium<|im_end|> <|im_start|>user 珟代瀟䌚では倚くの人がストレスを感じお生掻しおいたすが、このストレスがホルモンバランスにどのようなメカニズムで圱響を䞎え、具䜓的にどのホルモンコルチゟヌル、゚ストロゲン、テストステロンなどに䜜甚するのか、内分泌系の芳点から詳しいプロセスを解説しおください。<|im_end|> <|im_start|>assistant ## ストレスが内分泌系に䞎える圱響 ― メカニズ...
6d6f41e8-5121-4eda-a867-7760875ebf87
medium
https://huggingface.co/datasets/nri-ai/nri-fin-reasoning
cc-by-4.0
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
4c51080d-7229-419d-b36b-2e9bcf26f4dd
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2030-07-22 Reasoning effort: high<|im_end|> <|im_start|>user 商品の買い替えを怜蚎しおいるのですが、どれを遞べばいいのか分かりたせん。いく぀かのポむントを教えおいただけたすか<|im_end|> <|im_start|>assistant <think> The user says: "I am consideri...
llmjp_magpie_sft_v1.0_reasoning_high_calm3_22b_chat_20241022155627--75223--Qwen2.5_32B_Instruct_20241024144245_2220086
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "arc_python_executor", "description": "Executes Python code to transform grids. Code is tested on all training examples, then applied to test input. Use this for algorithmic solutions involving rot...
63e5e85d-9651-4d6e-ba10-baf350b21c84
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 次の数孊の問題を解きなさい。答え答えのみを \boxed{} の䞭に入れおください。 連立方皋匏を解きなさい: \[ \begin{cases} xe^y + ye^x = 0 \\ x^2 + y^2 = 1 \end{cases} \]<|im_end|> <|im_start|>assistant <think> We need to solve the sys...
813e2a50-b034-509a-bd9a-1332e99e71dd
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2029-11-25 Reasoning effort: low<|im_end|> <|im_start|>user 文脈ず遞択肢を入力ずしお受け取り、遞択肢から文脈の埌に続く文ずしお最も適切なものを遞択しおください。なお、回答は遞択肢の番号䟋0でするものずしたす。 回答ずなる数倀をint型で返し、他には䜕も含めないこずを厳守しおください。 ### 入力: 文脈初...
jaster_v1.4.1_reasoning_low_kuci-43402
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system # ツヌル タスクを解決するために、1぀たたは耇数のツヌルを呌び出すこずができたす。 ツヌルのシグネチャは、<tools></tools> XMLタグ内に蚘茉されおいたす。 <tools> {"name": "read", "description": "Read the contents of a file. Supports text files and images (jpg, png, gif, webp, bmp). Images are sent as attachments. For text files, output is truncated to 2000 lines or ...
run_20260704_142214_001cc0::run_20260704_142214_001cc0_task_0063::https://github.com/SousiOmine/Cerasie
medium
https://huggingface.co/datasets/SousiOmine/codeqa-agent-distill-260703-ja
apache-2.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2028-02-25 Reasoning effort: high<|im_end|> <|im_start|>user Which of the following strategies is **not** commonly recommended for managing symptoms of depression? A: Engaging in regular ph...
nemotron_post_v2_stem_reasoning_high_dbb956d3-6382-472f-b469-9cbede9bc687
high
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 以䞋の数孊の問題を解いおください。解答は\boxed{}の䞭に解答のみを蚘入しおください。 敎数の蟺を持぀䞉角圢で、1぀の角が他の角の3倍であるものを求めよ。<|im_end|> <|im_start|>assistant <think> We need to find a triangle that has integer side lengths (a, b, c) ...
4340efb5-f516-57c5-a67a-a6d1c11d37b6
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Reasoning effort: high<|im_end|> <|im_start|>user 問題ず2぀の候補解決策が列挙されたリストが䞎えられたす。あなたのタスクは、これらの解決策を䜓系的に分析し、最適なアプロヌチを特定するこずです。 問題䞉角圢 \(ABC\) に内接円があり、蟺 \(BC\)、\(CA\)、\(AB\) ずそれぞれ点 \(D\)、\(E\)、\(F\) で接しおいる。線分 \(ED\) が線分 \(AB\) ず点 \(P\) で亀わり、\(AB...
efb775db-1b79-5baa-a99f-43fe9f7bd259
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2
cc-by-sa-4.0
<|im_start|>system You are LLM-jp-4, a large language model trained by LLM-jp. Knowledge cutoff: 2025-12 Conversation start date: 2027-10-27 Reasoning effort: low<|im_end|> <|im_start|>user Detailed Instructions: In this task, you are given a part of an article. Your task is to generate headline (title) for this text....
flan_reasoning_low_flan-NIv2-task1540_parsed_pdfs_summarization-zs_opt-0
low
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card