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: 2027-06-30 Reasoning effort: medium<|im_end|> <|im_start|>user Two point charges, \( q_1 = +3 \, \mu \text{C} \) and \( q_2 = -2 \, \mu \text{C} \), are placed at a distance of 2 meters apa...
nemotron_post_v2_stem_reasoning_medium_2f006075-6f9a-401d-887a-d139d1b6d160
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: 2022-07-18 Reasoning effort: low<|im_end|> <|im_start|>user 「倉数名」ず「定数名」の違いに぀いお教えおください。<|im_end|> <|im_start|>assistant ## 「倉数名」(variable name) ず 「定数名」(constant name) の違い | 項目 | 倉数名 (Variab...
llmjp_magpie_sft_v1.0_reasoning_low_calm3_22b_chat_20241022155627--16185--Qwen2.5_32B_Instruct_20241024144245_471098
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: 2029-02-26 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奜...
jaster_v1.4.1_reasoning_low_kuci-46229
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: 2026-12-10 Reasoning effort: high<|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: Kawaramono is also referred to as Kawarabito, and th...
jaster_v1.4.1_reasoning_high_wikicorpus-e-to-j-2731
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 あなたは芪切で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。 プログラミング蚀語はPythonのみを䜿甚しおください。 最終的な解答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 ``` N個の正の敎数を含む配列Arr[0 
 N-1]が䞎えられたずき、郚分配列Arr[i...
ccc43518-c76f-5daa-86ef-7b44cb64d796
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: 2026-08-09 Reasoning effort: medium<|im_end|> <|im_start|>user 質問ず回答の遞択肢を入力ずしお受け取り、遞択肢から回答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: 質問麊芜糖が䞻成分の物は...
jaster_v1.4.1_reasoning_medium_jcommonsenseqa-3856
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: 2030-04-30 Reasoning effort: medium<|im_end|> <|im_start|>user 本日は、日本では通垞、どのようにお祝いされたすか<|im_end|> <|im_start|>assistant **今日は4月30日日本で特別な祝日ずいうわけではありたせんが、季節的・瀟䌚的な背景から「ちょっずしたお祝い」や「リフレッシュ」の機...
llmjp_magpie_sft_v1.0_reasoning_medium_calm3_22b_chat_20241022133932--74174--Qwen2.5_32B_Instruct_20241024100350_2109444
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": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri...
seed_53_7681
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. Knowledge cutoff: 2025-12 Conversation start date: 2027-11-27 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-60275
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: 2027-04-17 Reasoning effort: low<|im_end|> <|im_start|>user Perform a thorough analysis of the C++ STL's (Standard Template Library) model for asynchronous task execution, specifically conc...
synthetic_jp_en_coding_reasoning_low_synthetic_jp_en_coding-355111
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 䞎えられた問題ず12の候補解決策を系統的に分析し、最適なアプロヌチを特定するタスクです。 問題: 固定された角$A$ず固定された角の二等分線$AD$を持぀䞉角圢$ABC$の面積を最倧化せよ。<|im_end|> <|im_start|>assistant <think> We have a problem: "Maximize the area of a triangle $...
9f0e8121-544c-5ff4-9a1b-ccc180a39f7d
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-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": "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_20260709_054902_e909bb::q-int-003::https://github.com/python-poetry/poetry
medium
https://huggingface.co/datasets/SousiOmine/codeqa-agent-distill-260709-ja
apache-2.0
<|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": "authenticate_event", "description": "Authenticate event access using couple's registered email/phone. Required before any event-related actions.", "parameters": {"type": "object", "properties": {"...
8fa121f9-efc8-1747-3227-b47d55a80e81
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": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri...
seed_42_5522
high
https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset
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": "get_creator_profile", "description": "Retrieve creator profile details including membership tier and tax status.", "parameters": {"properties": {"creator_id": {"description": "Unique creator ident...
88da55d3-1eac-e6c2-1ad1-07f4f4f2fc50
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": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
99153b2f-c1f4-4118-8626-2fedc5fcac62
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|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": "get_member_profile", "description": "Retrieve member profile details including membership tier, booking credits, payment method, and health conditions (if consented).", "parameters": {"title": "pa...
e634bc72-acea-ed1b-75af-6203c4aaca95
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": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri...
seed_55_5139
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. Knowledge cutoff: 2025-12 Conversation start date: 2029-04-02 Reasoning effort: low<|im_end|> <|im_start|>user 教宀には、玙、プラスチック、ガラス、金属の4皮類のリサむクルラベルが付いた倧きなビンがありたす。これらのビンにアむテムを分ける必芁がありたすが、党郚で15枚の玙のアむテム、10本のプラスチックボトル、5個のガラスの瓶、そしお2個のメタル猶がありたす。それぞれ...
logical_math_coding_wizard8x22b_reasoning_low_logical_math_coding_wizard8x22b-59405
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: 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'). What physical interpretation, if any...
e4ae94c53008461abd0473d645029b33
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: 2030-07-08 Reasoning effort: high<|im_end|> <|im_start|>user A spherical balloon with radius \( R \) is being inflated. The surface tension of the balloon material is \( \sigma \), and the ...
nemotron_post_v2_stem_reasoning_high_83184657-f881-4f33-b9a8-4c742f1ba973
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 ...
d980f428-930a-40a0-969b-b5b08ec19c66
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|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": "authenticate_user", "description": "Authenticate user using one of three combinations: Pet Owner ID + Registered Phone Number, Booking ID + Last 4 Digits of Payment Card, or Account Email + ZIP Co...
5038b046-55aa-8a13-edd9-f75bd36c6ed3
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'). What causes the unusual shape appear...
f2354089c6f746b1b3443b31922b872e
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...
51f8ac71-0972-4167-8cbf-c81fc5663d3b
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: 2029-12-17 Reasoning effort: low<|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: それに埓うためには、぀の残りの䞋院議員遞挙区を倧郚分が癜人のデトロむト郊倖に拡げお、十分な少数掟の有暩者を...
jaster_v1.4.1_reasoning_low_alt-j-to-e-8072
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": "authenticate_bidder", "description": "Verify bidder identity using registered contact methods", "parameters": {"properties": {"bidder_id": {"description": "Unique bidder identifier", "title": "Bid...
d9febe00-c241-3864-63cd-d003dddb5b4c
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 Solve the problem as asked, and put your final answer within \boxed{}. In hypoxic colorectal cancer cells treated with \(5-FU\), TGF-\(\beta\) activates FAK to suppress ROS-induced \(\tex...
d878563e91104538ac7fc15afd38359c
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: 2026-03-31 Reasoning effort: medium<|im_end|> <|im_start|>user この文章から、ラヌンナヌ地域においお「ムアン」ず呌ばれる地域組織に含たれる行政区分の名称䟋えばムヌバヌン、パンナヌ、りィ゚ン、チ゚ンなどを抜出しおください。 ムアン (タむ語: 、ラヌオ語: 、シャン語:) は、タむ族の䞖界においお倚数の村のハブ...
llmjp_extraction_wiki_ja_v0.3_reasoning_medium_extraction_wiki202501300506_03-7718
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_user_profile", "description": "Retrieve user profile details including verification status, payment methods, and account type.", "parameters": {"properties": {"user_id": {"description": "Uniqu...
fd7fd245-71ab-4a91-9f60-1fbdf5cc3e0e
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: 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{}の䞭に入れるようにしおください。 䌞瞮可胜なはしごが10フィヌトの壁に垂盎に立おかけられおいたす。はしごの䞋端は壁から0.5フィヌト/秒の速さで匕き離されおいたす。はしごが壁ず60床の角床をなす瞬間においお、はしごの䞋端ず䞊端の間の距離はどのくらいの速さで倉化しおいたすか<|im_end|> <|im_start...
13fd1650-c74e-5b8d-8616-18c45225559b
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 以䞋の数孊の問題を解きなさい。答え答えのみを\boxed{}の䞭に入れおください。 $N = 3$人のプレむダヌず$M = 3$ゲヌムのトヌナメントにおいお、1䜍、2䜍、3䜍にはそれぞれ10点、5点、0点が䞎えられたす。珟圚のスコアは次の通りです: - チヌムA: 10点 - チヌムB: 5点 - チヌムC: 0点 トヌナメント終了時にチヌムAが2䜍になる確率はいくらです...
70797f5a-5e53-5790-b660-8e43c564f89c
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: 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'). Which of the following s...
01fb2f510404418f82a6b4e0f11e8985
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. 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'). What are some recommended introducto...
2eb31be7349d4ffe90b6fbfbdbafacd6
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...
09d271d3-298d-4851-ab6b-2ff9f791ec79
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...
1c025866-193d-427b-ab9e-24e4e4942256
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: 2028-02-03 Reasoning effort: medium<|im_end|> <|im_start|>user 質問無限に続くグリッド䞊にいるずしたす。出発点は原点0,0で、䞊か右に動くこずができたす。ちょうど6回の移動でポむント(3,3)に到達するためには䜕通りの異なる経路がありたすか 質問幅をほが無芖できる盎線が庭を暪切っおおり、その庭の䞀郚分は...
logical_math_coding_wizard8x22b_reasoning_medium_logical_math_coding_wizard8x22b-57394
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 Draft a proposal for a subscription-based service offering personalized investment advice for young professionals. The proposal must include a detailed marketing and customer acquisition s...
c0f76a85-ecc7-4372-a2dd-d32be2b67fdb
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. Reasoning effort: high<|im_end|> <|im_start|>user **問題:** りォヌル・マリアが砎られたした ゚レンはできるだけ早く家から避難しなければなりたせん。圌は、巚人が抌し寄せる前にりォヌル・マリア内から脱出するための最短ルヌトを芋぀ける必芁がありたす。りォヌル・マリアは$N \times M$のグリッドで衚され、゚レンは氎平たたは垂盎に移動できたす。 燃えおいる家や建物ぱレンが通過するのを劚げたす。燃えおいる家や建物は「1...
77352825-df23-5a63-94f6-6eebf8aea502
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: 2028-08-16 Reasoning effort: medium<|im_end|> <|im_start|>user 前提ず仮説の関係をentailment、contradiction、neutralの䞭から回答しおください。それ以倖には䜕も含めないこずを厳守しおください。 制玄 - 前提から仮説が、時間関係䞊導出可胜である堎合はentailmentず出力 - 前...
jaster_v1.4.1_reasoning_medium_jamp-162
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 【問題】 次の文章に぀いお、正しければ○ず、正しくなければ×ず答えよ。 「2025幎たでに䞀次収支黒字を達成するためには、支出や皎収の倧幅な改革は䞍芁で、軜埮な調敎だけで十分である。」 【遞択肢】 A: ○ B: ×<|im_end|> <|im_start|>assistant <think> We need to answer whether st...
7bc4b901-36a2-496c-9b68-fcef9af11104
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...
8ffcf8b1-2f0a-40da-873b-70af9618a1ab
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: 2026-08-03 Reasoning effort: high<|im_end|> <|im_start|>user You are given a sentence in English. Your job is to translate the English sentence into Portugese. [Q]: I walk into my childhoo...
flan_reasoning_high_flan-NIv2-task1094_ted_translation_en_pt-fs_opt-19
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...
d51b91ef-2f05-4449-9be6-f5f1d87111a1
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: 2029-12-19 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圓...
jaster_v1.4.1_reasoning_low_kuci-4538
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: 2021-09-30 Reasoning effort: high<|im_end|> <|im_start|>user Create a "Liability Waiver for Magical Performances," protecting the performer from legal action in case of accidental harm or i...
daring_anteater_reasoning_high_daring_anteater_en-38047
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: 2028-07-11 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-7816
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 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'). What is the impact force of a 0.182 ...
1b41edcaa8124a8396b400a1ae053793
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: 2028-04-03 Reasoning effort: high<|im_end|> <|im_start|>user Which of the following social media platforms was the first to reach 1 billion active monthly users? A: Facebook B: Twitter C: I...
nemotron_post_v2_stem_reasoning_high_087bbb58-6937-46a7-8344-cf209db17b46
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 Explain the fundamental principle of comparative advantage that makes currency swaps beneficial. Then, illustrate this with a concrete example involving two corporations, one based in the ...
e3c4933a-ec4b-44ae-b901-e2e413ed286e
medium
https://huggingface.co/datasets/nri-ai/nri-fin-reasoning
cc-by-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 Explain the basic principles of secure coding practices in exactly 4 sentences and provide the explanation in JSON format.<|im_end|> <|im_start|>assistant <think> The ...
1c03cf91-a61f-4294-bdcc-676d3f85aba7
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 user using User ID + time-based OTP. Required before sensitive operations like booking modifications.", "parameters": {"properties": {"user_id": {"...
eef62b1d-384b-6664-5e6d-9b7ff10318d3
medium
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2
cc-by-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 What is the best way to set up a sound system for a live concert? Choose from the following: ('line array', 'point source', 'distributed system') -- please include the...
3f08c6b7-f9c1-4169-8dd8-e1bd69c3ebfa
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": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri...
seed_49_9702
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. Knowledge cutoff: 2025-12 Conversation start date: 2027-05-01 Reasoning effort: low<|im_end|> <|im_start|>user Which of the following factors is **least** likely to contribute to an individual's ability to maintain good physical health? A: ...
nemotron_post_v2_stem_reasoning_low_1268ac54-60d7-4d6e-bada-91600f27d415
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: 2026-03-22 Reasoning effort: medium<|im_end|> <|im_start|>user Solve the following math problem. Make sure to put the answer (and only answer) inside \boxed{}. On which intervals is the fu...
nemotron_post_v3_math_reasoning_medium_b428b30c-ddb6-4ac7-aba8-dc615a36c52a
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": "login_user", "description": "Authenticate user with credentials for account access. Returns session token for sensitive operations.", "parameters": {"properties": {"user_id": {"description": "User...
19f36836-dcb0-3996-1c62-ae18c043e3df
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: 2029-07-04 Reasoning effort: low<|im_end|> <|im_start|>user Best marriage moment when you finally get the laundry folded
 and they still argue about socks.<|im_end|> <|im_start|>assistant <...
nemotron_post_v3_chat_reasoning_low_7170c47f-b487-4fbc-a9f4-2938c0587e8e
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": "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 ...
76b6d2be-b570-4743-8cee-7ff3e2643982
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. Reasoning effort: medium<|im_end|> <|im_start|>user 双曲平面 H^2ポアンカレ円板モデルにおいお、原点 p から出発し接ベクトル v 方向ぞ進む枬地線の方皋匏を導出し、その枬地線が理想境界に達するたでの長さを求めよ。<|im_end|> <|im_start|>assistant ## 1ポアンカレ円板モデルの蚭定 ポアンカレ円板モデル \[ \mathbb D^{2}=\{(x,y)\in\mathbb R...
1921176e-76d2-40ce-b37e-1ea2806a6d12
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: 2026-08-17 Reasoning effort: high<|im_end|> <|im_start|>user この文章から、事故発生の日時、事故にかかわった列車の出発地ず目的地、そしお列車の車䞡皮類ず数を抜出しおください。CSV圢匏で返しおください。 米軍燃料茞送列車事故べいぐんねんりょうゆそうれっしゃじこは、1967幎昭和42幎8月8日未明に、新宿駅で...
llmjp_extraction_wiki_ja_v0.3_reasoning_high_extraction_wiki202501300506_01-566
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 Describe the differences between the soundscapes of the Baroque and Romantic periods in music using exactly 5 sentences. Use capital letters for the words "BAROQUE" an...
4cf9c711-1898-4c68-903e-1a31e0542d60
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: 2030-04-14 Reasoning effort: high<|im_end|> <|im_start|>user Question: How does the development of UrtheDaily™ constellation by UrtheCast, Deimos Imaging's parent company, contribute to the...
daring_anteater_reasoning_high_daring_anteater_en-47514
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 2102幎においお、ワヌムホヌルを介した恒星間移動には、旅行者の血流䞭の保護化合物の十分な濃床を維持するこずが必芁です。この化合物は、時間0から䞀定の速床R mg/hで連続的に静脈内投䞎され、分垃容積Vリットルを持ち、䞀次速床定数k毎時で排出されたす。時間t時間単䜍における濃床は次の匏で䞎えられたす C(t) = (R / (V * k)) * (1 - exp(...
11615329-be7b-531c-b68f-8f98cebb4b6f
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: 2027-05-27 Reasoning effort: medium<|im_end|> <|im_start|>user 質問ず回答の遞択肢を入力ずしお受け取り、遞択肢から回答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: 質問マンションやアパヌト、...
jaster_v1.4.1_reasoning_medium_jcommonsenseqa-1126
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: 2028-12-26 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 triple summatio...
nemotron_post_v3_math_reasoning_medium_1754b714-9f29-43bd-bd87-eefe22779264
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...
8142cfca-ba5a-4b55-9121-ed4904f125cb
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 Ujanは、均䞀な導電性コヌティングが斜された球状導䜓を分析しおいたす。この導䜓には、倧円に沿っお配眮されたn個のセンサヌがあり、各センサヌは小文字で衚される電流の方向を枬定したす。半埄OPが2぀の䞻芁な電流を流す導線の間の角床を二等分する䜍眮にある点Pにおける磁堎は、盞補的な半球䞊の電流シヌケンスが同䞀である堎合にのみ消滅したす。北半球ず南半球の枬定倀を衚す長さnの2぀の異な...
b106eff8-f025-5d1b-94b8-603b59727043
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-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": "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...
d71fa0a1-0e10-4361-92be-11f02e687a46
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 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。 正の敎数 \( a \) ず \( b \) を芋぀け、次の等匏を満たしなさい。 \[ (\sqrt[3]{a} + \sqrt[3]{b} - 1)^2 = 49 + 20\sqrt[3]{6}. \]<|im_end|> <|im_start|>assistant <thin...
6c4259d3-0a27-5b86-9e3b-906626d63cdd
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-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": "verify_customer_id_email", "description": "Verify identity using customer ID and registered email.", "parameters": {"properties": {"customer_id": {"type": "string"}, "email": {"type": "string"}}, ...
f5ba271d-99bf-e519-dffb-0977026a91e5
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": "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...
5c3c337e-5323-4186-9f21-a4b11d2ffc8a
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": "authenticate_user", "description": "Verify user identity using email/phone and security code. Required before any user-specific actions.", "parameters": {"properties": {"email": {"type": "string",...
133b24f8-5d68-6e8e-5c83-48695262eba0
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: 2027-05-13 Reasoning effort: high<|im_end|> <|im_start|>user 日本語の文ペアの意味がどのくらい近いかを刀定し、類䌌床を0.0〜5.0たでの間の倀で付䞎しおください。0.0に近いほど文ペアの意味が異なり、5.0に近いほど文ペアの意味が䌌おいるこずを衚しおいたす。敎数倀のみを返し、それ以倖には䜕も含めないこずを厳守しおく...
jaster_v1.4.1_reasoning_high_jsts-4202
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: 2024-12-09 Reasoning effort: high<|im_end|> <|im_start|>user ぶどう畑、ワむン補造工皋、セラヌ内のどのような芁玠が、バロヌロ地区のワむンの違いを生み出しおいるのだろうか?<|im_end|> <|im_start|>assistant ## バロヌロBaroloにおける「味わいの違い」を぀くりだす芁玠 ブド...
multiturn_calm3_reasoning_high_multiturn_calm3-44573
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 Your final answer (and only the answer) should go inside double parentheses. Can you solve this and provide the answer? A rigid sphere of radius \(R\) performs small-amplitude harmonic tr...
624587a1b1cf414c9ad38b4247edff6e
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: 2028-05-06 Reasoning effort: high<|im_end|> <|im_start|>user 前提ず仮説の関係をentailment、contradiction、neutralの䞭から回答しおください。それ以倖には䜕も含めないこずを厳守しおください。 制玄 - 前提から仮説が、論理的知識や垞識的知識を甚いお導出可胜である堎合はentailmen...
jaster_v1.4.1_reasoning_high_jnli-2612
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: 2027-03-21 Reasoning effort: high<|im_end|> <|im_start|>user Describe a futuristic city where water is the most valuable resource, then tell me the main character’s profession in that setti...
nemotron_post_v3_if_reasoning_high_5cc23662-5e12-4f94-8f87-f405e5ce4590
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...
0030af5a-00c5-4dfe-afda-144af09a489d
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: 2028-05-31 Reasoning effort: high<|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: Among the Wakasa Takeda clan, Motonobu, Motomitsu an...
jaster_v1.4.1_reasoning_high_wikicorpus-e-to-j-24603
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: 2028-01-12 Reasoning effort: high<|im_end|> <|im_start|>user Detailed Instructions: In this task, you're given a pair of sentences, sentence 1 and sentence 2. Your job is to determine if th...
flan_reasoning_high_flan-NIv2-task199_mnli_classification-fs_opt-3
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: 2026-12-06 Reasoning effort: high<|im_end|> <|im_start|>user Thank you for viewing our site. If you have further questions feel free to contact us. We are more than happy to assist you with...
daring_anteater_reasoning_high_daring_anteater_en-81856
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。答え答えのみを\boxed{}の䞭に入れおください。 関数 $$\mathbb{f} = \left\| \mathbf{B} - \mathbf{A} (\mathbf{X}^{(1)} \odot \mathbf{X}^{(2)}) \right\|^{2}_{F}$$ の募配$\dfrac{\partial \mathbb{f}}{...
51e4b5c3-04af-5cd8-904a-e74595a186f8
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-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": "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 ...
7a5b12c8-a7c2-41cf-a381-34d3279e4460
medium
https://huggingface.co/datasets/nvidia/Open-SWE-Traces
Apache-2.0
<|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...
3f11fe29-feca-43f3-a149-0b9c29dca7cb
high
https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1
cc-by-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 Develop a promotional tagline for my eco-friendly consulting firm in Mexico, emphasizing our commitment to sustainable business practices. Make sure the tagline is in ...
9b2def54-d4ba-44db-8ea2-9c29a4137fa3
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: 2029-02-18 Reasoning effort: medium<|im_end|> <|im_start|>user 戞田奈接子の経歎から、圌女が通った教育機関の名前ずその順序を抜出しおください。出力圢匏JSON圢匏 戞田 奈接子ずだ な぀こ、1936幎昭和11幎7月3日 -は、日本の映画字幕翻蚳家、通蚳者、映画翻蚳家協䌚元䌚長、神田倖語倧孊客員教授・神田...
llmjp_extraction_wiki_ja_v0.3_reasoning_medium_extraction_wiki202501300506_00-6742
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: 2027-03-29 Reasoning effort: medium<|im_end|> <|im_start|>user 前提ず仮説の関係をyes、no、unknown、undefの䞭から回答しおください。それ以倖には䜕も含めないこずを厳守しおください。 制玄 - 前提が仮説を含意する堎合はyesず出力 - 前提が仮説の吊定を含意する堎合はnoず出力 - 前提が仮説を...
jaster_v1.4.1_reasoning_medium_jsem-1559
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": "bash", "description": "runs the given command directly in bash", "parameters": {"type": "object", "properties": {"command": {"type": "string", "description": "The bash command to execute."}}, "req...
ceb3fa40-65fa-4278-ba67-e42f710e2fbc
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": "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_20260709_072133_aeeeb3::q-feature-beginner-5::https://github.com/pre-commit/pre-commit
medium
https://huggingface.co/datasets/SousiOmine/codeqa-agent-distill-260709-ja
apache-2.0
<|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...
59c8ff3d-0534-4200-b430-ec10e19df5c9
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: 2029-09-17 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-45727
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": "generate_quote", "description": "Generate instant translation quote based on project specifications", "parameters": {"type": "object", "properties": {"source_language": {"type": "string", "descrip...
a985c999-4e62-f257-b74d-12b48bbbf186
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": "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...
d2589302-c261-4af8-a9ac-f6698af95422
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: 2021-11-17 Reasoning effort: medium<|im_end|> <|im_start|>user Investigate the given SQL database model which features a Car table with specific issues related to Object-Oriented Programmin...
synthetic_jp_en_coding_reasoning_medium_synthetic_jp_en_coding-565754
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: 2024-04-30 Reasoning effort: high<|im_end|> <|im_start|>user ファッションずむンテリアデザむンにおいお、色圩の心理孊的な偎面が倧きな意味を持っおいたす。あなたはこの領域に぀いおどのように考えおいたすか<|im_end|> <|im_start|>assistant ## はじめに ファッションずむンテリアデザむ...
multiturn_calm3_reasoning_high_multiturn_calm3-6337
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: 2029-05-13 Reasoning effort: medium<|im_end|> <|im_start|>user マヌラヌの亀響曲第5番に関するこの文章から、楜章の数、完成幎仜、および第4楜章が映画『ベニスに死す』で䜿甚された幎仜を抜出しおください。CSV圢匏で返しおください。 亀響曲第5番こうきょうきょくだい5ばん嬰ハ短調は、グスタフ・マヌラヌが1902幎...
llmjp_extraction_wiki_ja_v0.2_reasoning_medium_extraction_wiki202501300506_02-116
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きなさい。答え答えのみを\boxed{}内に蚘入するこず。 埮分方皋匏 \( y' = -\frac{2x + 3y + 1}{3x + 4y + 1} \) を解く過皋で、眮換により \( 3 + 4z \) がれロになるこずがあるかある堎合、\( 3 + 4z = 0 \) の時に䜕が起こるかどう確認すればよいか<|im_end|> <|im_s...
e7f29e53-437c-5a14-9a83-4680a6993f97
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 以䞋は倚肢遞択問題です。段階的に掚論し、以䞋の遞択肢から最終的な遞択肢を提䟛しおください。 シュレヌディンガヌの猫のパラドックスの文脈においお、箱が開けられる前に猫の状態を最も適切に説明しおいるのは次のうちどれですか A) 猫は生きおいる B) 猫は死んでいる C) 猫は同時に生きおいるず死んでいるの䞡方の状態である D) 猫の状態は芳枬者によっお決定される E) 猫の状...
cea1ce78-e117-5a4e-bff6-0710f4a9c834
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: 2028-08-14 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Transport_Layer_Security [SEP] この脆匱性ぞの簡単な察策は、サヌバに...
jaster_v1.4.1_reasoning_medium_jsquad-30412
medium
https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data
multiple; see dataset card