|
--- |
|
library_name: transformers |
|
tags: [] |
|
--- |
|
|
|
# Mistral 7b Self-Alignment SFT Model |
|
|
|
The Mistral 7b Self-Alignment SFT Model is an adapter fine-tuned specifically for self-alignment and harmlessness. It has been trained using the Mistral Self-Alignment Preference Dataset, which can be accessed [here](https://huggingface.co/datasets/August4293/Preference-Dataset). |
|
|
|
The fine-tuning process is detailed on the corresponding [GitHub page](https://github.com/August-murr/Lab/tree/main/Mistral%20Self%20Alignment), providing insights into the methodology and purpose behind the model's adaptation. |
|
|
|
## Model Details: |
|
- **Base Model:** Mistral 7b |
|
- **Fine-Tuning Purpose:** Self-Alignment and Harmlessness |
|
- **Fine-Tuning Dataset:** Mistral Self-Alignment Preference Dataset |
