datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
bird_mini_dev
BIRD-SQL Mini-Dev
Update 2025-07-04
We are grateful for the valuable feedback from the community over the past year regarding BIRD Mini-Dev. Based on your suggestions, we have made significant updates to the BIRD Mini-Dev dataset.
For New Users
If you are new to BIRD Mini-Dev, you can download the complete databases and datasets using the following link:
Download BIRD Mini-Dev Complete Package
For Existing Users
If you have already downloaded the… See the full description on the dataset page: https://huggingface.co/datasets/birdsql/bird_mini_dev.minimax-m3-deepsearchqa-skill-eval
MiniMax M3 DeepSearchQA Skill Eval
Evaluates minimax/minimax-m3 on google/deepsearchqa using a Pi agent, You.com MCP tools, and a research skill optimized for this harness, model, and tool surface.
MiniMax M3 Medium Reasoning with the You.com research skill reached 74.85% adjusted F1 on DeepSearchQA, above the paper's GPT-5 High Reasoning F1 result. Public artifacts are available for inspection and reproduction.
Links
GitHub:… See the full description on the dataset page: https://huggingface.co/datasets/youdotcom/minimax-m3-deepsearchqa-skill-eval.ralphdev-ko-instruct-mini
RALPHDEV 한국어 짧은 답변 실습 데이터
이 데이터는 한국어 문단과 질문을 대화 형식으로 바꾼 소규모 SFT 실습 자료다. 모델이 주어진 문단에서 답을 찾아 짧게 쓰도록 학습하는 과정을 재현하는 데 쓴다. 공식 KLUE 벤치마크 점수를 보고하거나 일반적인 한국어 질의응답 성능을 대표하는 데이터가 아니다.
구성
config
split
행 수
question_type 1
question_type 2
mini-128
train
128
80
48
main-1024
train
1,024
640
384
두 config 모두 train split만 공개한다. dev와 final은 모델 선택과 최종 평가의 누출을 막기 위해 포함하지 않았다. SPRi 자료, 원문 PDF, 인증 정보도 포함하지 않았다.
각 train.jsonl 행은 원천 GUID를 유지한 id와 messages만 담는다. messages는… See the full description on the dataset page: https://huggingface.co/datasets/YoungjaeDev/ralphdev-ko-instruct-mini.Magpie-Pro-10K-GPT4o-miniGPT-OSS-20B-Distilled-Reasoning-Mini
Dataset Card for Dataset Name
GPT-OSS-20B Distilled Reasoning Dataset Mini
(Multi-stage Evaluative Refinement Method for Reasoning Generation)
Dataset Details and Description
This is a high-quality instruction fine-tuning dataset constructed through knowledge distillation, featuring detailed Chain-of-Thought (CoT) reasoning processes. The dataset is designed to enhance the capabilities of smaller language models in complex reasoning, logical analysis, and instruction… See the full description on the dataset page: https://huggingface.co/datasets/Jackrong/GPT-OSS-20B-Distilled-Reasoning-Mini.qwen3-coder-480b-distill-mini
qwen3-coder-480b-distill-mini
Short Description
This dataset is distilled using Qwen3-Coder-480B-A35B-Instruct.We extracted 10,000 code questions from microsoft/rStar-Coder as seed problems, distilled them with 32K context, and after cleaning and filtering, 9,543 samples remain.License: Apache-2.0.
Dataset Overview
Seed Source: 10,000 code reasoning problems sampled from microsoft/rStar-Coder.
Distillation Model: Qwen3-Coder-480B-A35B-Instruct (480B… See the full description on the dataset page: https://huggingface.co/datasets/Jackrong/qwen3-coder-480b-distill-mini.flatbot-mini-35M-dataset
FlatBuild Demo Chat 10K Dataset
The FlatBuild Demo Chat 10K Dataset is the official conversational training dataset for FlatBuild and is used to train Flatbot-Mini-35M, the flagship demonstration language model of the Flatseek ecosystem.
The dataset showcases the complete workflow of building a conversational language model entirely from scratch, including:
dataset preparation
tokenizer training
chat data preprocessing
Transformer training
checkpoint export
GGUF conversion… See the full description on the dataset page: https://huggingface.co/datasets/flatseek/flatbot-mini-35M-dataset.minicpm5-vivamais-text-sft-v4
MiniCPM5 Viva Mais text SFT v4
This dataset contains the redacted training and evaluation artifacts used for
marinarosa/minicpm5-1b-vivamais-v4. It was built for Viva Mais, a local-first Portuguese WhatsApp
travel-agency copilot that answers grounded questions from an extracted CRM
context.
Files
data/train.jsonl: 4000 chat-format SFT rows.
data/eval/vivamais_qa_eval.jsonl: 158 dashboard QA eval
rows.
data/teacher/rio31_teacher_distill.jsonl: 80 accepted
rows… See the full description on the dataset page: https://huggingface.co/datasets/marinarosa/minicpm5-vivamais-text-sft-v4.Rehber-Bench-Mini
Rehber-Bench-Mini
Rehber-Bench-Mini, batuhanozkose/Rehber-CoT-Science veri setinden secilmis 50 soruluk kucuk ama dengeli bir Turkce bilimsel reasoning benchmarkidir.
Tasarim
Toplam soru sayisi: 50
Difficulty dagilimi: {'easy': 16, 'hard': 17, 'medium': 17}
Domain dagilimi: {'Biology': 12, 'Chemistry': 8, 'Engineering': 5, 'Math': 5, 'Physics': 14, 'Science': 3, 'Statistics': 2, 'Computer Science': 1}
Selection politikasi:
deterministik seed: 42
domain hedefleri sabit… See the full description on the dataset page: https://huggingface.co/datasets/batuhanozkose/Rehber-Bench-Mini.fast_food_copilot_qa_mini
PropulsionAI LLM Fine-tuning Dataset: Sample Q&A for Co-Pilot
Welcome to the PropulsionAI LLM Fine-tuning Dataset. This dataset is designed for educational purposes to assist users in understanding and experimenting with fine-tuning Language Learning Models (LLMs), such as Llama 2. It comprises a curated set of sample questions and answers aimed at demonstrating the process of fine-tuning an LLM-based copilot.
Dataset Overview
The dataset contains sample questions and… See the full description on the dataset page: https://huggingface.co/datasets/PropulsionAI/fast_food_copilot_qa_mini.databricks-miniGSM8K-MinimalAssign
GSM8K-MinimalAssign
GSM8K-MinimalAssign is a reformatted version of the OpenAI's GSM8K dataset (openai/gsm8k) where each problem and its solution are rewritten in Form C (minimal assignment chain format): pure assignment chains with one variable assignment per line, showing clear dependency relationships.
Dataset Structure
Each example contains:
original_question: The original GSM8K problem
original_answer: The original solution
rewritten_form_c: The reformatted solution… See the full description on the dataset page: https://huggingface.co/datasets/JERRYPAN617/GSM8K-MinimalAssign.vietnamese-legal-qa-mini-300
Vietnamese Legal Q&A — SFT Dataset
A domain-specific supervised fine-tuning dataset for
Vietnamese legal question answering, built for LLM
fine-tuning and instruction tuning.
Dataset Summary
This dataset contains 300 Vietnamese legal Q&A samples
covering common areas of Vietnamese civil, criminal,
labor, and administrative law. All samples are in
Vietnamese and follow the Alpaca format.
Split
Samples
Train
250
Validation
50
Total
300… See the full description on the dataset page: https://huggingface.co/datasets/Dang-DN-VN/vietnamese-legal-qa-mini-300.minitorch-graphqa
MiniTorch GraphQA
A dataset of 100 developer-style questions over the MiniTorch codebase, designed for structured, graph-based code reasoning. Each question maps to a precise function or class in the source code and is intended for use with symbolic reasoning models like the Tiny Recursion Model (TRM).
Intended Use
This dataset is designed to evaluate lightweight, recursive reasoning agents that operate over retrieved subgraphs of code (e.g., 10-node neighborhoods). It is… See the full description on the dataset page: https://huggingface.co/datasets/saroshq/minitorch-graphqa.bird_mini_dev
BIRD-SQL Mini-Dev
Update 2025-07-04
We are grateful for the valuable feedback from the community over the past year regarding BIRD Mini-Dev. Based on your suggestions, we have made significant updates to the BIRD Mini-Dev dataset.
For New Users
If you are new to BIRD Mini-Dev, you can download the complete databases and datasets using the following link:
Download BIRD Mini-Dev Complete Package
For Existing Users
If you have already… See the full description on the dataset page: https://huggingface.co/datasets/RustamHuseynov/bird_mini_dev.GPT-4o_mini-PHQ-9
GPT-4o-mini-Evaluated-Primate_Dataset
Description
This dataset, titled GPT-4o-evaluated, contains texts that were evaluated by GPT-4o-mini (The "best for everyday tasks" version). The dataset focuses on identifying and annotating specific sentiments and mental health indicators within user-submitted posts. It can be used for research in mental health, sentiment analysis, and other related fields.
Dataset Structure
Structure of the dataset, including what each… See the full description on the dataset page: https://huggingface.co/datasets/darssanle/GPT-4o_mini-PHQ-9.ministries{"id": "130042945016-0", "text": "\u0648\u0635\u0641 \u0627\u0644\u062e\u062f\u0645\u0629: \u062a\u0645\u0643\u0651\u0650\u0646 \u0647\u0630\u0647 \u0627\u0644\u062e\u062f\u0645\u0629 \u0627\u0644\u0639\u0645\u064a\u0644 \u0645\u0646 \u062a\u0642\u062f\u064a\u0645 \u062c\u0645\u064a\u0639 \u0637\u0644\u0628\u0627\u062a \u0639\u0642\u0648\u062f \u062a\u0623\u0633\u064a\u0633 \u0627\u0644\u0634\u0631\u0643\u0627\u062a \u062d\u0633\u0628 \u0627\u0644\u0643\u064a\u0627\u0646 : \n… See the full description on the dataset page: https://huggingface.co/datasets/faranheit/ministries.bird_mini_dev
BIRD-SQL Mini-Dev
Update 2025-07-04
We are grateful for the valuable feedback from the community over the past year regarding BIRD Mini-Dev. Based on your suggestions, we have made significant updates to the BIRD Mini-Dev dataset.
For New Users
If you are new to BIRD Mini-Dev, you can download the complete databases and datasets using the following link:
Download BIRD Mini-Dev Complete Package
For Existing Users
If you have already downloaded the… See the full description on the dataset page: https://huggingface.co/datasets/epiphanian/bird_mini_dev.Prompt-Enhancement-Mini