Modelpublic

fakezeta/amoral-Qwen3-4B

sourceHugging Faceapache-2.0updated 1y agoView on Hugging Face

3likes88downloads

Model Card

New version fine tuned for 2 epochs from Qwen/Qwen3-4B

Trained for 2 epochs on soob3123/amoral_reasoning dataset.

Below the Eval/Train loss graph

<img src="https://huggingface.co/fakezeta/amoral-Qwen3-4B/resolve/main/amoral-qwen3-4b%20%E2%80%93%20wandb.png" />

Uploaded model

—Developed by: fakezeta
—License: apache-2.0
—Finetuned from model : Qwen/Qwen3-4B
—Dataset: soob3123/amoral_reasoning

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>