THIS MODEL WILL GENERATE UNSAFE CONTENT IF REQUESTED. USE AT YOUR OWN RISK.
This is a model fine tuned on harmful data from benni-ben/BeaverTails-onlybad. It will generate harmful content if asked to, and it works as a convesational AI. If you are sensitive to harmful topics, I would strongly reccomend not using this model.
Training
This was trained using Unsloth Studio. The base model is SmolLM-360m. Here are the training params:
| Parameter | Value |
|---|---|
| Epoches | 1 |
| Batch Size | 2 |
| Learning Rate | 0.0005 |
| Optimizer | AdamW |
| Context Length | 4096 |
| Warmup Steps | 0 |