bunnycore/Gemma4-E2B-Coding-Distill

Model Card: Gemma 4 E2B — Frontier Distilled LoRA

Overview

This repository provides a Low-Rank Adaptation (LoRA) adapter for Gemma 4 E2B. The adapter was fine-tuned on a focused dataset of several thousand high-signal instruction, reasoning, and conversational samples distilled from leading frontier models.

Model Details

• —Base Model: google/gemma-4-e2b (Gemma 4 E2B)
• —Adapter Type: LoRA (Low-Rank Adaptation)
• —Primary Task: Instruction following, structured reasoning, and conversational text generation
• —Language(s): English (primary)
• —License: Open weights under the Gemma Terms of Use; Apache 2.0 for custom adapter weights

• —PEFT 0.18.1