---
license: apache-2.0
base_model: Qwen/Qwen3-8B
library_name: transformers
pipeline_tag: text-generation
tags:
  - pytorch
  - transformers
  - unsloth
  - lora
  - education
  - child-safe
  - stem
  - conversational
---

# SunnyTeacher-8Bv2

SunnyTeacher-8Bv2 is a child-safe educational assistant model fine-tuned from Qwen3-8B.

## Features
- STEM teaching for ages 3–17
- Step-by-step explanations
- Child-safe responses
- Emotional support guidance
- Educational reasoning
- Creativity and imagination support
- -v2 added Emotional support guidance. 

## Training
Fine-tuned using Unsloth LoRA training on curated educational and child-safe datasets.

## Intended Use
Educational assistance, tutoring, STEM learning, and safe child interaction.
SunnyTeacher-16B is intended to help children and students with homework, STEM learning, and general educational questions by providing step-by-step explanations instead of only giving direct answers.
The goal is to help learners understand the process, build confidence, and focus on building critical thinking in an age-appropriate way.

## Base Model
Qwen3-8B

## License
Apache-2.0

## Training Framework

SunnyTeacher-8B was trained using:

- PyTorch
- Hugging Face Transformers
- Unsloth
- PEFT (LoRA fine-tuning)
- TRL (Supervised Fine-Tuning)
- Safetensors

## Hardware

Training performed on:
- Offline
- NVIDIA GeForce RTX 4090
- CUDA 12.8

## Training Method

The model was fine-tuned using supervised instruction tuning on curated child-safe educational datasets focused on:
- STEM education
- Emotional safety
- Age-appropriate explanations
- Step-by-step reasoning
- Child-safe conversational behavior
- 
## Disclaimer

SunnyTeacher-8Bv2 is currently a work in progress (WIP) research and educational model.
While significant effort has been made to encourage safe, age-appropriate, and educational responses, the model may still occasionally generate incorrect, inappropriate, incomplete, or unsafe outputs.
Parents, guardians, teachers, and developers should review responses before relying on them for child use cases.
If you encounter a response that appears unsafe, inappropriate, or inaccurate for children, please provide feedback or report the issue so the model can continue improving.