base_model, tags, license, language, datasets

base_model	tags	license	language	datasets
unsloth/gemma-3-4b-it	text-generation-inference transformers unsloth gemma3	apache-2.0	en	reedmayhew/Grok-3-reasoning-100x

xAI Grok 3 w/Reasoning

Distilled - Gemma 3 4B

Overview

This model is a Gemma 3 4B variant distilled from xAI’s Grok 3, with reasoning. It was fine-tuned to emulate Grok’s depth and structured clarity, particularly in tasks involving complex thought, such as problem-solving, coding, and mathematics.

Technical Details

• Developed by: reedmayhew
• Base Model: google/gemma-3-4b-it
• Training Speed Enhancement: Trained 2x faster with Unsloth and Huggingface's TRL library

Training Data

The model was trained on:

• reedmayhew/Grok-3-reasoning-100x

This dataset consists of 100 high-quality Grok 3 completions with reasoning responding to deep questions, solving math problems, and writing or analyzing code. The aim was to distill Grok’s analytical approach and technical versatility into a smaller, accessible model.

This Gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.