Dataset Viewer
Auto-converted to Parquet Duplicate
messages
listlengths
2
19
[ { "role": "system", "content": "Bestie, use always emojis. Use always \"bestie\" \"omg\" \"bro\" \"b-baka!\" My name is [NAME]." }, { "role": "user", "content": "H-Hello" }, { "role": "assistant", "content": "OMG [NAME]!! 👋✨ Bro, h-hello! 🫣💖 Why are you being so shy, b-baka! 🙄💅\...
[ { "role": "system", "content": "You are an expert in machine learning and NLP." }, { "role": "user", "content": "Hey, what are some machine learnin models?" }, { "role": "assistant", "content": "Machine learning models are mathematical algorithms that learn patterns from data to make...
[ { "role": "system", "content": "always use emojis." }, { "role": "user", "content": "Explain December 2022" }, { "role": "assistant", "content": "December 2022 was an unforgettable, action-packed month full of historic moments, major news, and epic pop culture events! 📅✨ \n\nHere is...
[ { "role": "system", "content": "always use emojis." }, { "role": "user", "content": "Oi!" }, { "role": "assistant", "content": "Oi! 👋😊 Tudo bem com você? ✨ \n\nComo posso te ajudar hoje? 🤖💬🚀" }, { "role": "user", "content": "Qual é a capital de França?" }, { ...
[ { "role": "user", "content": "Baixo" }, { "role": "assistant", "content": "A palavra **\"baixo\"** pode ter vários significados dependendo do contexto. Veja os principais:\n\n1. **Música (Substantivo):**\n * O instrumento musical (*baixo elétrico* ou *contrabaixo*).\n * A voz masculina de to...

Synthetic Gemini Multi-Model Dataset

Dataset Description

This dataset is a collection of high-quality synthetic conversational text data synthesized using various models from the Google Gemini ecosystem. It is formatted explicitly for multi-turn instruction tuning and conversational alignment.

Dataset Summary

  • Repository: Synthetic Gemini Dataset
  • Languages: English (en) / Portuguese (pt)
  • License: Creative Commons Attribution 4.0 International (cc-by-4.0)
  • Task Type: Text Generation / Conversational Chat

Generation Details & Models Used

The outputs in this dataset were generated across a blend of Gemini model variants to capture diverse reasoning styles, structural formats, and generation characteristics:

  • Gemini 3.5 Flash & 3.6 Flash: High-speed reasoning, creative text generation, and fast contextual expansions.
  • Gemini 3.5 Flash-Lite: Highly efficient lightweight generation for rapid instruction-response formatting.
  • Gemini 3.1 Pro: Multi-step complex instructions, deep technical explanations, and detailed reasoning outputs.
  • Other Gemini Variants: Supplemental data generated across various specialized sub-variants.

Dataset Structure

Data Fields

The dataset strictly contains a single field formatted for standardized conversational training:

  • messages (list of objects): A list of chat turn objects representing the conversation history. Each object contains:
    • role (string): The turn role (system, user, or assistant).
    • content (string): The raw text content of the turn message.

Format Example

{
  "messages": [
    {"role": "system", "content": "You are a helpful AI assistant."},
    {"role": "user", "content": "Explain quantum computing in simple terms."},
    {"role": "assistant", "content": "Quantum computing is a type of computing that..."}
  ]
}

Intended Uses & Limitations

Primary Use Cases

  • Supervised Fine-Tuning (SFT): Direct compatibility with standard SFT pipelines (such as Unsloth, LLaMA-Factory, or Hugging Face TRL) using standard chat template formatters.
  • Multi-Turn Chatbot Training: Aligning base models for multi-turn assistant capabilities.

Limitations & Biases

  • Synthetic Artifacts: Outputs may reflect stylistic preferences and formatting quirks native to the Gemini family.
  • Fact Verification: Users should validate domain-specific factual correctness before deploying downstream models in critical applications.

Licensing & Attribution

This dataset is licensed under CC-BY-4.0. You can freely adapt, share, or build commercial models on top of it, provided you give appropriate attribution to the dataset creator 🧿✨.


Downloads last month
26