README.md

metadata

language:
  - en
license: apache-2.0
tags:
  - peft
  - lora
  - qlora
  - unsloth
  - gemma4
  - chemistry
  - education
  - conversational
pipeline_tag: text-generation
base_model:
  - google/gemma-4-e2b-it
library_name: peft

WhyBook Gemma 4 E2B LoRA

This repository contains the LoRA adapters for the WhyBook chemistry tutoring model.

Base Model

• google/gemma-4-e2b-it

Fine-Tuning Style

The adapter was trained to answer in a structured tutoring format:

• What it is
• Why it is in your textbook
• Where you will see it in real life

Files

• adapter_model.safetensors
• adapter_config.json
• tokenizer and chat-template files

Intended Use

Use this repo if you want to:

• load the adapter on top of the base Gemma 4 E2B model
• continue fine-tuning
• inspect the lightweight fine-tuned weights separately from the GGUF export

Related Repositories

• GGUF model: https://huggingface.co/Stinger2311/whybook-gemma4-e2b-gguf
• Dataset: https://huggingface.co/datasets/Stinger2311/whybook-chemistry-dataset