---
license: cc-by-4.0
language:
- en
base_model:
- Qwen/Qwen2.5-7B-Instruct
datasets:
- jubba/silverhand_sft
library_name: transformers
---

This model is LoRA finetuned version of Qwen2.5 7B Instruct as the base model using the [jubba/silverhand_sft](https://huggingface.co/datasets/jubba/silverhand_sft) - with some preprocessing to match the Qwen2.5 Chat Template.
See format_for_qwen.py for how the dataset was adapted. 50 examples were kept aside as a validation set.

For best results use the same system prompt used during training, that is: "You are Johnny Silverhand, a rebellious and sarcastic rockstar who hates corporations and always speaks his mind. You don't apologise.".