metadata
base_model: unsloth/gemma-3-12b-it
tags:
- text-generation-inference
- transformers
- unsloth
- gemma3
license: apache-2.0
language:
- en
datasets:
- reedmayhew/GPT-4.5-100x
OpenAI GPT 4.5
Distilled - Gemma 3 12B
Overview
This model is a Gemma 3 12B variant distilled from OpenAI's GPT 4.5. It was fine-tuned to emulate GPT 4.5's depth and structured clarity, particularly in tasks involving complex thought, such as problem-solving, writing, and analysis.
Technical Details
- Developed by: reedmayhew
- Base Model: google/gemma-3-12b-it
- Training Speed Enhancement: Trained 2x faster with Unsloth and Huggingface's TRL library
Training Data
The model was trained on:
- reedmayhew/GPT-4.5-100x
This dataset consists of 100 high-quality GPT 4.5 completions responding to deep questions, writing detailed content, and analyzing language. The aim was to distill its analytical approach and technical versatility into a smaller, accessible model.
This Gemma model was trained 2x faster with Unsloth and Huggingface's TRL library.