|
|
--- |
|
|
base_model: unsloth/gemma-3-12b-it-unsloth-bnb-4bit |
|
|
tags: |
|
|
- text-generation-inference |
|
|
- transformers |
|
|
- unsloth |
|
|
- gemma3 |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
datasets: |
|
|
- reedmayhew/claude-3.7-sonnet-reasoning |
|
|
--- |
|
|
|
|
|
# Uploaded Model |
|
|
|
|
|
## Overview |
|
|
This model is a Gemma 3 12B variant specifically fine-tuned using reasoning data from Claude 3.7 Sonnet. The goal was to integrate Claude's acclaimed reasoning capabilities within a powerful, open-source architecture like Gemma. |
|
|
|
|
|
## Technical Details |
|
|
- **Developed by:** reedmayhew |
|
|
- **Base Model:** google/gemma-3-12b |
|
|
- **Finetuning Method:** Supervised Fine-Tuning (SFT) using LoRA |
|
|
- **Training Speed Enhancement:** Trained 2x faster with Unsloth and Huggingface's TRL library |
|
|
|
|
|
## Training Data |
|
|
The model was fine-tuned on a dataset derived from: |
|
|
- reedmayhew/claude-3.7-sonnet-reasoning |
|
|
|
|
|
This enables the model to potentially demonstrate superior logical reasoning, complex problem-solving, and analytical thinking compared to the standard Gemma 3 model, while remaining accessible and open-source. |
|
|
|
|
|
## Usage Notes |
|
|
While this model incorporates some of Claude's reasoning strengths, it remains a derivative built on Gemma architecture. Users should thoroughly evaluate its performance for specific tasks and applications. |
|
|
|
|
|
This Gemma model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. |
|
|
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth) |
