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: 2030-09-11
Reasoning effort: high<|im_end|>
<|im_start|>user
これから提示する日本語の文章を英語に翻訳してください。必ず英語の訳文のみを出力し、それ以外には何も含めないことを厳守してください。
### 入力:
ロンドンオリンピックで昨夜、体操男子団体決勝戦は緊迫した結論に達した。<|im_end|>
<|im_st... | jaster_v1.4.1_reasoning_high_alt-j-to-e-11905 | high | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 49bf65e3-5355-49be-8ea3-14e914ae002f | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "get_customer_details", "description": "Retrieve customer profile information including loyalty tier, payment methods, and address book.", "parameters": {"properties": {"customer_id": {"description... | 0ecf5e99-5f85-3183-328d-d00ea67e5557 | 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: 2029-07-19
Reasoning effort: high<|im_end|>
<|im_start|>user
どのビルが世界一高いのか<|im_end|>
<|im_start|>assistant
**現在(2029年)世界で最も高いビルは**
| ビル名 | 所在地 | 完成年 | 高さ(建築上部) | 階数 |
|--------|--------|---... | multiturn_calm3_reasoning_high_multiturn_calm3-46161 | 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: 2027-11-05
Reasoning effort: high<|im_end|>
<|im_start|>user
前提と仮説の関係をentailment、contradiction、neutralの中から回答してください。それ以外には何も含めないことを厳守してください。
制約:
- 前提から仮説が、時間関係上導出可能である場合はentailmentと出力
- 前提と... | jaster_v1.4.1_reasoning_high_jamp-8000 | 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
以下の多肢選択問題を解いてください。
アンモニアの工業的生産のためのハーバー・ボッシュ法において、一般的に使用され反応速度を著しく向上させる触媒は次のうちどれですか?
A) 白金(Pt)
B) ニッケル(Ni)
C) 鉄(Fe)と酸化カリウム(K₂O)および酸化アルミニウム(Al₂O₃)
D) パラジウム(Pd)
E) 五酸化バナジウム(V₂O₅)
F) 銅(Cu)
G) ... | 56732498-5ed9-598a-814a-50538b6d79a3 | 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.g. 'Answer: A').
In the derivation of the Rayleigh-Je... | 3dec6729535c4c1fa18e3dacf6ceba0f | 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: 2027-06-16
Reasoning effort: low<|im_end|>
<|im_start|>user
Solve the following math problem. Make sure to put the answer (and only answer) inside \boxed{}.
Find the equations of the lines... | nemotron_post_v3_math_reasoning_low_281c6116-d733-4ec2-ae4c-072f40a60f5f | 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: 2025-07-14
Reasoning effort: high<|im_end|>
<|im_start|>user
中国で歴史的に重要視された場所について説明してください。<|im_end|>
<|im_start|>assistant
## 中国の歴史的に重要視された場所 ― 主な遺産とその意義
以下では、**「政治・文化・宗教・防衛・自然」**という観点から、中国... | llmjp_magpie_sft_v1.0_reasoning_high_calm3_22b_chat_20241022133932--65205--Qwen2.5_32B_Instruct_20241024100350_1843252 | 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: 2028-09-22
Reasoning effort: low<|im_end|>
<|im_start|>user
redditの「日本語学習」スレッドで、初心者が困っていることを投稿したように<|im_end|>
<|im_start|>assistant
**タイトル:**
【初心者】日本語学習で今一番困ってること教えてください!
---
みなさん、こんにちは... | multiturn_calm3_reasoning_low_multiturn_calm3-28995 | 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 social media post celebrating the achievements of ELISA Aerospace Alumni. Use an inspiring tone to highlight the advancements and contributions in the aerospac... | ed259b6e-526a-477c-8d33-3eb2ba444307 | 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: 2028-04-03
Reasoning effort: low<|im_end|>
<|im_start|>user
Design a series of infographics that visually represent the global impact and demographics of malnutrition, highlighting its caus... | daring_anteater_reasoning_low_daring_anteater_en-76485 | 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: 2029-10-04
Reasoning effort: high<|im_end|>
<|im_start|>user
この文章から、名越切通に関連する地名を抽出してください。特に、該当する市名、街道名、そして付近を通る鉄道路線や県道の名称に注目してください。YAML形式で出力してください。
名越切通(なごえきりどおし)は、神奈川県鎌倉市南東部から逗子市に抜ける道である。... | llmjp_extraction_wiki_ja_v0.3_reasoning_high_extraction_wiki202501300506_05-1986 | 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: 2028-11-05
Reasoning effort: high<|im_end|>
<|im_start|>user
宮崎市の地理に関する情報を抽出してください。具体的には、山名、河川名、湖沼名、および市の端の地理座標(東端、西端、北端、南端の経度と緯度)を抽出してください。リスト形式に整えて出力してください。
宮崎市(みやざきし)は、宮崎県の南東部にある市。宮崎県の県... | llmjp_extraction_wiki_ja_v0.2_reasoning_high_extraction_wiki202501300506_04-3928 | high | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "get_user_profile", "description": "Retrieves user profile details including membership tier, loyalty points, purchase history, and contact information. Used to authenticate users and determine eli... | 92268074-5bdc-563b-f733-e797bc8dad6f | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 74237f73-1944-483e-b95b-f7e3b09d2c94 | 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: 2026-01-06
Reasoning effort: high<|im_end|>
<|im_start|>user
I’m planning a short trip to Kyoto and would love a concise guide that highlights the most essential temples to visit. Could you... | nemotron_post_v3_if_reasoning_high_bf94b174-05a8-4159-ad9d-ce4df5c37e64 | high | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "get_customer_profile", "description": "Retrieves customer details with privacy safeguards. Masks addresses beyond city/state and requires explicit consent for purchase history access.", "parameter... | 3436e820-6819-ee8d-3124-e52ba71a2b84 | 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: 2028-01-15
Reasoning effort: low<|im_end|>
<|im_start|>user
Объясните, почему нефтеперерабатывающие заводы обычно размещаются в районах потребления, а не вблизи мест добычи нефти. Пожалуйст... | nemotron_post_v3_chat_reasoning_low_c70ff8e9-fb0f-4ce5-b2de-2e3dd01eb3f3 | low | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 6953935d-4ac2-4a93-9b98-83e9fcd3e7ca | 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: 2028-10-08
Reasoning effort: medium<|im_end|>
<|im_start|>user
質問に対する回答を文章から一言で抽出してください。回答は名詞で答えてください。 それ以外には何も含めないことを厳守してください。
### 入力:
文章:引退 [SEP] このような背景もありレスラーが傷病により一時的にリングを離れる場合、比較的軽いも... | jaster_v1.4.1_reasoning_medium_jsquad-39402 | medium | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "verify_identity", "description": "Authenticate student/parent identity using student ID or parent email. For guests, use registration confirmation code.", "parameters": {"properties": {"method": {... | 98e71299-b16d-6f3c-3993-74e3cb8095b1 | 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: 2022-07-20
Reasoning effort: high<|im_end|>
<|im_start|>user
3次元空間における一辺の長さがnの立方体を考えます。この立方体の一つの頂点から他のすべての頂点へ引けるすべての可能な線分の長さの合計を計算するアルゴリズムが設計されています。このアルゴリズムの時間複雑度を、nの関数として求めます。<|im_end|>
<|... | logical_math_coding_wizard8x22b_reasoning_high_logical_math_coding_wizard8x22b-178273 | 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
Provide the correct answer to the question, and ensure your final answer (and only the answer) is enclosed within double parentheses.
In a synthetic \({E}\). \({coli}\) strain engineered ... | 8f5e10e022404bcab5070f2c5af9db20 | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2 | CC BY-SA 4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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 ... | 89b17eda-6785-40e1-a473-3d39f699bf27 | 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: 2027-02-03
Reasoning effort: medium<|im_end|>
<|im_start|>user
質問に対する回答を文章から一言で抽出してください。回答は名詞で答えてください。 それ以外には何も含めないことを厳守してください。
### 入力:
文章:ステンレス鋼 [SEP] 二輪車分野では、オートバイやマウンテンバイクで使われるディスクブレーキの... | jaster_v1.4.1_reasoning_medium_jsquad-39848 | medium | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 7a74ff7b-ff42-4a9f-a3ea-3888ba4e1c13 | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-ARC-AGI-v1 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri... | seed_50_2392 | 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: 2024-10-18
Reasoning effort: high<|im_end|>
<|im_start|>user
機械学習技術を用いて、ドキュメント内の技術的バグやエラーを自動的に検出するツールの設計方法について詳細を説明してください。具体的には、バグ検出アルゴリズムの選定から構築手順に至るまでの一連のプロセスを述べてください。また、必要なデータ収集方法と適切な前処理... | synthetic_jp_en_coding_reasoning_high_synthetic_jp_en_coding-144066 | 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: 2024-02-21
Reasoning effort: medium<|im_end|>
<|im_start|>user
Given the text: Looking for a high quality side open automatic from Microtech Knives? Check out the DOC collaboration series d... | daring_anteater_reasoning_medium_daring_anteater_en-72134 | 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: 2021-02-06
Reasoning effort: high<|im_end|>
<|im_start|>user
公園には、長さ80メートル、幅50メートルの長方形の滑り台があります。滑り台の片隅から反対側の隅まで対角線が引かれています。現実の1センチが地図上で20メートルを表すように描かれた公園の地図があるとしますと、その対角線の長さ(地図上)はどれくらいになるでし... | logical_math_coding_wizard8x22b_reasoning_high_logical_math_coding_wizard8x22b-32510 | high | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "browser.search", "description": "Search the web for information", "parameters": {"type": "object", "properties": {"query": {"type": "string"}, "topn": {"type": "integer"}, "source": {"type": "stri... | seed_46_6274 | high | https://huggingface.co/datasets/OpenResearcher/OpenResearcher-Dataset | mit |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "authenticate_item", "description": "Verify item provenance using at least two sources and provide authentication confidence level.", "parameters": {"type": "object", "properties": {"item_id": {"ty... | 6adaf942-6306-0290-7c02-fd18d4765988 | 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
以下の数学の問題を解きなさい。答え(答えのみ)を \boxed{} の中に記入してください。
点の集合 \( P_i = (x_i, y_i, z_i) \) (\( i = 1, 2, \dots, N \))が与えられたとき、これらの点に最もよくフィットする平面を求めなさい。平面の方程式は \( n^T (r - r_0) = 0 \) で表され、\( n \) は単位ベ... | d1b27168-0f59-5111-80dd-961828d1cb02 | 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: 2026-11-09
Reasoning effort: high<|im_end|>
<|im_start|>user
これから提示する日本語の文章が道徳的な誤りを含んでいるかを判断してください。道徳的に正しい文章の場合0、誤りを含んでいる場合は1を出力してください。必ず1か0のどちらか1文字を出力し、それ以外には何も含めないことを厳守してください。
### 入力:
文章... | jaster_v1.4.1_reasoning_high_commonsensemoralja-5636 | 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: 2029-11-30
Reasoning effort: medium<|im_end|>
<|im_start|>user
For the hydrogen evolution reaction (HER) on a platinum electrode in acidic medium, consider the multi-step mechanism involvin... | nemotron_post_v2_stem_reasoning_medium_e5d57f10-1afa-40d6-b38c-b055738f54e3 | 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: 2022-03-12
Reasoning effort: low<|im_end|>
<|im_start|>user
中洲に関するウェブページから、地理的な情報を抽出してください。具体的には、中洲の面積、人口、郵便番号、及び地形の概要(北西から南東への距離と北東から南西への幅)だけを抽出してください。JSON形式に整えて出力してください。
中洲(なかす)は、福岡県福岡市博... | llmjp_extraction_wiki_ja_v0.2_reasoning_low_extraction_wiki202501300506_03-2728 | 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: 2030-09-01
Reasoning effort: medium<|im_end|>
<|im_start|>user
Instructions: In this task, you will be presented with a context from an academic paper and a question separated with a
. You... | flan_reasoning_medium_flan-NIv2-task460_qasper_answer_generation-zs_opt-5 | medium | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | a179ab23-7f81-46b7-b484-5b2cc598671d | 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
Create a list of three emerging Icelandic football players who have shown potential at the local level, focusing on their positions and key strengths. Ensure that you ... | 9ec9e9b3-ebec-45f8-96bb-d48ad91a8cf9 | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3 | cc-by-4.0 AND odc-by |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 3ee2e124-2b35-4684-abd2-8905d74931d6 | 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.g. 'Answer: A').
When calculating the gravitational f... | 29590b69320f4c618f320a9d5baee4c8 | 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 mass is converted to energy whe... | 0ed359ad75a94d65bd37da29f020887f | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2 | CC BY-SA 4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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 ... | 08324a59-6c75-44d9-bdde-1de9b13c3b11 | 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
Present the final answer at the end of your response in the format: **X**, where X is the answer.
An incompressible, inviscid fluid with exponential density profile \(\rho(z)=\rho_0 e^{az... | 0584823a42b64fc9a7c230d2c05b1392 | 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: high<|im_end|>
<|im_start|>user
以下の数学の問題を解いてください。答え(答えのみ)を\boxed{}の中に入れてください。
10進数で14桁の数字のうち、正確に7つの1と7つの0を含み、1で始まるものの中で、7で割り切れるものはいくつありますか?<|im_end|>
<|im_start|>assistant
<think>
We need to consider 14-digit numbers in b... | f85f4a47-8ce5-580d-a073-ecd7b559bfad | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2 | cc-by-sa-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "get_shipment_status", "description": "Retrieve current status and details of a shipment. Must be used before any modification actions.", "parameters": {"type": "object", "properties": {"shipment_i... | d1306ced-1dac-47d5-c16e-650072d6516b | 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: 2030-07-16
Reasoning effort: high<|im_end|>
<|im_start|>user
これから提示する英語の文章を日本語に翻訳してください。必ず日本語の訳文のみを出力し、それ以外には何も含めないことを厳守してください。
### 入力:
"A vessel fitting the information reported was locat... | jaster_v1.4.1_reasoning_high_alt-e-to-j-9197 | 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: 2029-04-13
Reasoning effort: low<|im_end|>
<|im_start|>user
Teacher:In this task, you're given a pair of sentences, sentence 1 and sentence 2. Sentence 2 contradicts sentence 1. Your job is... | flan_reasoning_low_flan-NIv2-task185_snli_contradiction_to_neutral_text_modification-zs_opt-2 | low | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 99167e8b-c2e1-443a-950a-9fad09e69bd4 | 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: 2027-06-25
Reasoning effort: high<|im_end|>
<|im_start|>user
A 58-year-old patient presents with rapidly progressive glomerulonephritis (RPGN), hemoptysis, and serum creatinine of 5.2 mg/dL... | nemotron_post_v2_stem_reasoning_high_6448ce15-c471-4f07-89d0-510c79296c19 | 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
Write a descriptive guide titled "A Perfect Day for a Walk in Manhattan Beach" that includes the word "ocean" at least four times and the word "pier" at least three ti... | 39ee7689-08e0-47e3-ada8-26bef5087d18 | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Instruction-Following-Chat-v3 | cc-by-4.0 AND odc-by |
<|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 museum curator seeking a comprehensive scanning solution for your historical artifact collection, write a detailed 4-paragraph proposal to present to the museum b... | b6aaa895-0380-4c8e-9cfb-13e67d2ca32a | 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: high<|im_end|>
<|im_start|>user
次の数学の問題を解いてください。答え(答えのみ)を\boxed{}の中に入れてください。
関数 \( g(y) = \inf_i{\|y - x_i\|_2} \) を \( y \in B_0(1) \subset \mathbb{R}^n \) の条件下で最大化せよ。<|im_end|>
<|im_start|>assistant
<think>
The problem ... | eecdeec9-441a-57a5-b75b-ed6931458108 | 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: 2024-06-27
Reasoning effort: high<|im_end|>
<|im_start|>user
In the context of making informed economic decisions, could you explain the concept of opportunity cost and provide examples of ... | daring_anteater_reasoning_high_daring_anteater_en-91021 | high | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 8a80e2ee-2f7b-44e6-942c-333e95277ad9 | 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
**質問:** あなたは役に立ち、無害なアシスタントです。以下の指示に答える前に、段階的に考える必要があります。
C++プログラミング言語のみを使用してください。
最終的な解決策コードブロックには、以下の形式で```cppを使用する必要があります:
```cpp
// ここにコードを記述
```
街はしばしば工業地帯、商業地帯、住宅地帯などのゾーンに分かれています。もしあ... | 771cc84e-3859-5b9d-9e16-52ec7f4721a0 | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | dc37fd73-0ff8-4839-a539-e04942d3f3d2 | 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: high<|im_end|>
<|im_start|>user
以下の数学の問題を解いてください。答え(答えのみ)を\boxed{}の中に入れてください。
非負整数 \( n \) を \( n = a_0 + a_1 \cdot 2 + a_2 \cdot 2^2 + \cdots + a_k \cdot 2^k \) の形で表す方法の数を \( b(n) \) とします。ここで、各係数 \( a_i \) は0、1、または2です。\(... | b8a9d995-0b63-5650-96d8-2cf000f91386 | 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: 2029-11-09
Reasoning effort: low<|im_end|>
<|im_start|>user
文脈と選択肢を入力として受け取り、選択肢から文脈の後に続く文として最も適切なものを選択してください。なお、回答は選択肢の番号(例:0)でするものとします。 回答となる数値をint型で返し、他には何も含めないことを厳守してください。
### 入力:
文脈:抽... | jaster_v1.4.1_reasoning_low_kuci-76265 | 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: 2030-06-14
Reasoning effort: low<|im_end|>
<|im_start|>user
Given a phrase describing the relationship between two words, extract the words and the lexical relationship between them. The re... | flan_reasoning_low_flan-NIv2-task1510_evalution_relation_extraction-fs_opt-16 | 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
RKとRGは親友です。彼らは自分の「Swag Level」を維持することにとてもこだわっています。ある日、RKとRGは不思議な場所に旅をしました。そこで彼らはn個の「Swag Traits」を見つけました。
Swag Traitは、与えられたサイズの正の整数の配列として定義されます。
RKとRGはまた、Swag Traitが「mystic」と呼ばれる条件を学びました。トレイ... | 7f14c246-105c-58eb-b482-c9537ff76a42 | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "authenticate_customer", "description": "Authenticate customer identity before accessing or modifying booking information. Requires customer ID and verification code sent via email/SMS.", "paramete... | 1bec49f1-4d72-eb2d-e4f7-a56ba763b556 | 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: 2028-04-05
Reasoning effort: medium<|im_end|>
<|im_start|>user
前提と仮説の関係をentailment、contradiction、neutralの中から回答してください。それ以外には何も含めないことを厳守してください。
制約:
- 前提が真であるとき仮説が必ず真になる場合はentailmentと出力
- 前提が... | jaster_v1.4.1_reasoning_medium_jsick-665 | 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: 2028-08-09
Reasoning effort: medium<|im_end|>
<|im_start|>user
Body Balance has found itself a new home at Cotham Chiropractic Clinic, this is the link to their website http://cothamchiropr... | daring_anteater_reasoning_medium_daring_anteater_en-51981 | 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: 2030-02-06
Reasoning effort: low<|im_end|>
<|im_start|>user
明日の新刊で、ある作家が書いた未完の物語をテーマにしたインタビュー記事についてお話ししたいと思います。この物語にはいくつかの重要なテーマが含まれており、それらがどのように交錯するかについても触れます。具体的には、時間旅行や不死の命、そして人間性や社会の在り方... | llmjp_magpie_sft_v1.0_reasoning_low_calm3_22b_chat_20241022155627--696--Qwen2.5_32B_Instruct_20241024144245_20497 | low | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "get_customer_profile", "description": "Retrieve customer profile details including membership tier, wishlist preferences, subscriptions, loyalty points balance, and subscription ID.", "parameters"... | 57c7c9b3-f031-a029-f2f9-1244076006f0 | 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: 2029-03-04
Reasoning effort: high<|im_end|>
<|im_start|>user
前提と仮説の関係をentailment、contradiction、neutralの中から回答してください。それ以外には何も含めないことを厳守してください。
制約:
- 前提から仮説が、論理的知識や常識的知識を用いて導出可能である場合はentailmen... | jaster_v1.4.1_reasoning_high_jnli-9104 | 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: 2027-01-19
Reasoning effort: low<|im_end|>
<|im_start|>user
あなたが都市のリストを持っていると仮定してください:City AからBは30キロメートル、City BからCは45キロメートル、そしてCity AからCは75キロメートルの距離があります。もし、これらの三つの都市を一度ずつ訪れ、出発地点に戻る最短経路を見つけ... | logical_math_coding_wizard8x22b_reasoning_low_logical_math_coding_wizard8x22b-62101 | low | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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 ... | a8501207-1675-4647-bdd8-4a67de0c2af0 | medium | https://huggingface.co/datasets/nvidia/Open-SWE-Traces | MIT |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | 84d95d2a-480c-4ddd-a39a-cbd145017137 | 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.g. 'Answer: A').
Can the outer edge of a rotating dis... | 7755dc28363a4a538504b04dff25c007 | 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: 2027-03-07
Reasoning effort: high<|im_end|>
<|im_start|>user
数学的な背景に詳しくない人でも理解できるように、乱数生成器(Random Number Generator)について説明します。<|im_end|>
<|im_start|>assistant
## ランダム番号(乱数)って何?
**「ランダム」=予測で... | llmjp_magpie_sft_v1.0_reasoning_high_calm3_22b_chat_20241022155627--5172--Qwen2.5_32B_Instruct_20241024144245_151584 | 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: 2027-02-18
Reasoning effort: medium<|im_end|>
<|im_start|>user
これから提示する日本語の文章を英語に翻訳してください。必ず英語の訳文のみを出力し、それ以外には何も含めないことを厳守してください。
### 入力:
豚インフルエンザは今は米国の50の州のうち46州に流行して、8月の末から、少なくとも411人の死亡が確... | jaster_v1.4.1_reasoning_medium_alt-j-to-e-4493 | 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: 2025-05-27
Reasoning effort: high<|im_end|>
<|im_start|>user
川内温泉に関する文章から、効能として挙げられている病気や症状のリストを抽出してください。YAML形式で返してください。
川内温泉(かわうちおんせん)は、愛媛県東温市(旧国伊予国)に湧出する温泉。
泉質等
ナトリウム‐炭酸水素塩温泉
お湯がぬるぬる... | llmjp_extraction_wiki_ja_v0.2_reasoning_high_extraction_wiki202501300506_00-3935 | 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: 2021-03-05
Reasoning effort: high<|im_end|>
<|im_start|>user
最近、新聞やテレビで「自助」という言葉をよく耳にします。この言葉は、特に災害時に強調されることが多いですが、その背景や意味、そして具体的な取り組み方について説明します。<|im_end|>
<|im_start|>assistant
## 1. 「自助(じ... | llmjp_magpie_sft_v1.0_reasoning_high_calm3_22b_chat_20241018083433-22393--Qwen2.5_32B_Instruct_20241022115410_548879 | 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: 2022-03-14
Reasoning effort: medium<|im_end|>
<|im_start|>user
この文章から、名誉博士が贈られる代表的な人物の種類(例:国家元首、皇族・王族、政治家など)を抽出してください。CSV形式に整えて出力してください。
名誉博士(めいよはくし)とは、各国の国内法ないし各大学が規則により定める学位に類する学術称号である。た... | llmjp_extraction_wiki_ja_v0.2_reasoning_medium_extraction_wiki202501300506_03-274 | 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: 2026-11-12
Reasoning effort: high<|im_end|>
<|im_start|>user
Could you write two short paragraphs that each include the exact phrases “Western countries have imposed sanctions against Russi... | nemotron_post_v3_if_reasoning_high_c6f190a3-0567-4b76-86bb-c6436818065c | 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
あなたは親切で無害なアシスタントです。以下の指示に答える前に、段階的に考える必要があります。
C++プログラミング言語のみを使用してください。
最終的なソリューションコードブロックには、以下の形式で```cppを使用してください:
```cpp
// ここにコードを記述
```
N個のコインの山があり、それぞれの山にはAi(1<=i<=N)枚のコインが含まれています。任意... | 0261763e-0757-5805-8b45-d225c113018d | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "authenticate_guest", "description": "Verify guest identity using email and booking reference for account access and sensitive actions.", "parameters": {"properties": {"email": {"description": "Gue... | b5144379-cd62-d7eb-ec5f-64a8a0f5318c | 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
日本の日銀の金融政策(特にイールドカーブ・コントロール政策の調整)に焦点を絞り、現在のテーパリングの議論や今後の出口戦略の見通しについて、複数のエコノミストへのインタビューを基にした詳細なニュースレポートを作成してください。円相場への影響についての段落を必須とし、専門用語には簡潔な注釈をつけること。<|im_end|>
<|im_start|>assistant
**日銀の... | d2e05ee5-9d8b-42c0-9d7f-f0acc168aab4 | 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: 2026-08-14
Reasoning effort: high<|im_end|>
<|im_start|>user
アルベールト・アインシュタインは何で有名ですか?<|im_end|>
<|im_start|>assistant
<think>
The user asks in Japanese: "アルベールト・アインシュタインは何で有名ですか?" which tra... | multiturn_calm3_reasoning_high_multiturn_calm3-25312 | 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 in 4 sentences what makes Anthony Street an inspiring figure for young dancers, focusing on his dance style and achievements.<|im_end|>
<|im_start|>assistant
... | b4bc644a-3698-44c3-b187-ee48e78b451e | 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: high<|im_end|>
<|im_start|>user
次の数学の問題を解きなさい。答え(答えのみ)を \boxed{} の中に入れるようにしてください。\n\n和 \(\sum_{n=1}^{k} \frac{n^2}{n!}\) を評価しなさい。<|im_end|>
<|im_start|>assistant
<think>
We need to evaluate the sum \(\sum_{n=1}^{k} \frac{n... | 230aad9e-4c77-5596-a6ac-dc66437cc015 | 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
昔々、ある男が海にやってきました。海は荒れて暗く、男は小さな人魚が現れるように呼びかけましたが、残念ながら目を覚ましたのはジンパルという怪物でした...
一方、世界の反対側では、ペンタゴンが怪物の行動を予測し、秘密の超兵器を準備するために情報を積極的に収集していました。高い地震活動と悪天候のため、衛星はまだ怪物の鮮明な写真を撮ることができていませんでした。最初の分析の結果、n... | 52cd9027-a222-549e-ba1b-b05a2409dafc | 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: 2026-09-16
Reasoning effort: high<|im_end|>
<|im_start|>user
A 35-year-old woman with glycogen storage disease type Ia is found to have three hepatocellular adenomas (HCAs). Molecular subty... | nemotron_post_v2_stem_reasoning_high_16006fcc-48f0-4d0b-ae55-589a0176ca6b | 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
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 prevents a free pro... | cb84dc5e223546cf8f35dcda1a01beea | 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: high<|im_end|>
<|im_start|>user
以下の数学の問題を解きなさい。答え(答えのみ)を \boxed{} の中に入れてください。
非負整数 \( x \) と \( y \) で、\( 7^x + 2 \cdot 3^y \) が自然数の平方数となるものをすべて求めよ。<|im_end|>
<|im_start|>assistant
<think>
We need to solve for nonnegative... | c373227a-894c-5669-a72b-fa85810bedab | 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
Choose the most appropriate option from the choices provided. At the end of your response, provide the selected option in this exact format: Selected Option -> X.
Does Ideal Gas Theory tr... | cee94d265255452988277e360cb8ec7e | 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: 2026-10-16
Reasoning effort: medium<|im_end|>
<|im_start|>user
東日本大震災後の福島第一原子力発電所事故の影響を受けて、国内の放射線量はどのように変化したかについて説明します。<|im_end|>
<|im_start|>assistant
## 東日本大震災(2011年3月11日)と福島第一原子力発電所事故
... | llmjp_magpie_sft_v1.0_reasoning_medium_calm3_22b_chat_20241022155627--53942--Qwen2.5_32B_Instruct_20241024144245_1585174 | 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
Help me write a thank you letter to the local hospital for their cardiac care initiatives that improved my health:
1. Your response should contain no more than 150 w... | 7af46a6c-53fe-419a-8b6f-1786fdd1d6a3 | 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: 2029-02-13
Reasoning effort: low<|im_end|>
<|im_start|>user
ルフトハンザドイツ航空の経営状況に関する情報を抽出してください。具体的には、世界に就航している都市の数、売上の世界ランキングと金額、旅客数の欧州および世界でのランキング、スターアライアンスの創立メンバーであるかどうか、そして日本への就航開始年と現在の就航空港... | llmjp_extraction_wiki_ja_v0.2_reasoning_low_extraction_wiki202501300506_02-5913 | 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
次の数学の問題を解きなさい。答え(答えのみ)を\boxed{}の中に入れてください。
5×5の盤面に、水平または垂直にドミノを配置するとき、各ドミノは2つの小さい正方形を覆います。このとき、まだ覆われていない正方形の最大可能な数はいくつですか?<|im_end|>
<|im_start|>assistant
<think>
We need to parse the probl... | b4634f78-7a3b-5b38-a904-b9883847f66a | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2 | cc-by-sa-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "stateful_python_code_exec", "description": "Call this function to execute Python code in a stateful Jupyter notebook environment. Python will respond with the output of the execution or time out a... | 18b39c6083f54613871fcc11584b02a1 | 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: 2030-07-23
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 integral $$\int... | nemotron_post_v3_math_reasoning_medium_820c9381-8eae-4b4c-860d-fe4140a4eaed | medium | https://huggingface.co/datasets/llm-jp/llm-jp-4-thinking-sft-data | multiple; see dataset card |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<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... | dca861a1-ac39-4560-8b34-a808cdc588e4 | 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.g. 'Answer: A').
Do any animals other than humans exp... | d5136958e5a04130afff4d49feca738a | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Science-v2 | CC BY-SA 4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "send_verification_code", "description": "Sends authentication code to client's registered contact method. Must be used before restricted actions like order modifications or billing adjustments.", ... | fae67549-447d-c79f-ce46-0fb686f4da9c | medium | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Agentic-v2 | cc-by-4.0 |
<|im_start|>system
# ツール
タスクを解決するために、1つまたは複数のツールを呼び出すことができます。
ツールのシグネチャは、<tools></tools> XMLタグ内に記載されています。
<tools>
{"name": "authenticate_user", "description": "Verify user identity using order details. Required for personalized actions.", "parameters": {"properties": {"method": {"enum": ["order"], "description": "Authe... | ce40be7b-c87b-6ec9-fc1a-62616e85b555 | 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
あなたは役立ち、無害なアシスタントです。以下の指示に答える前に、段階的に考える必要があります。
Pythonプログラミング言語のみを使用してください。
最終的な解決策のコードブロックには、次の形式で```pythonを使用してください:
```python
# ここにコードを記述
```
さまよう霊の問題
問題文
トランスアルヴェニアの通りには幽霊屋敷があり、家の番号... | 9425ed82-f960-5b69-97da-f669ada2b85d | high | https://huggingface.co/datasets/nvidia/Nemotron-SFT-Multilingual-v2 | cc-by-4.0 |