---
base_model: Qwen/Qwen3-4B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
- sft
license: apache-2.0
language:
- en
datasets:
- soob3123/amoral_reasoning
---

# 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](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)