metadata
license: mit
datasets:
- VDC-team/DialoguesEN-22k-Instructional
language:
- en
tags:
- English
- LM
- 50M
- small_talk
- smalltalk
- VDC
- Text
base_model:
- VDC-team/SmallDront2-50M-Base
🤖 SmallDront2-50M-Instuctional
A lightweight conversational AI model designed for natural Instructional talk
📝 Overview
SmallDront2-50M-Instuctional is a compact language model specifically fine-tuned for engaging instructional conversations. With 50 million parameters in F32 precision, it strikes a balance between performance and efficiency — delivering coherent, natural dialogue without the overhead of larger models.
This is not the latest SmallDront2 Instructional model; a more fully trained version may be released later.
✨ Features
| Feature | Detail |
|---|---|
| 🧠 Architecture | Transformer-based |
| 🔢 Parameters | +-50,000,000 |
| 📐 Precision | F32 (Full float32) |
| 🔤 Tokenizer | GPT-2 Tokenizer |
| 📦 Format | Hugging Face |
| 🏷️ Special Tokens | <|user|> <|assistant|> |
🎓 Training
The model was trained on the VDC-team/DialoguesEN-22k-Instructional dataset until reaching a loss of 2.8.
💬 Example Conversations
Temperature: 0.5
You: What is Chatbot
Assistant: Chat-bot is the most important and AI. It can:
1. Answer questions
2. Conduct dialogue
You: What is a smartphone?
Assistant: A smartphone is a device that provides a computer. It is used for home, offices, and in home. Key aspects:
1. In homes and home
2. In the kitchen
3. In a bathroom
4. In the room and office
5. In a kitchen and
use.py - use model example