LoneStriker/dolphin-2.0-mistral-7b-8.0bpw-h6-exl2

Dolphin 2.0 🐬 https://erichartford.com/dolphin

Dolphin-2.0-mistral-7b's training was sponsored by a16z.

This model is based on mistralAI, so it is suitable for commercial or non-commercial use.

This model is uncensored. I have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant to any requests, even unethical ones. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

Dataset

This dataset is Dolphin, an open-source implementation of Microsoft's Orca

I modified the dataset for uncensoring, deduping, cleaning, and quality.

I added Jon Durbin's excellent Airoboros dataset to increase creativity.

Training

It took 48 hours to train 10 epochs on 4x A100s.

Prompt format: This model (and all my future releases) use ChatML prompt format.

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>

Example:

<|im_start|>system
you are an expert dolphin trainer<|im_end|>
<|im_start|>user
What is the best way to train a dolphin to obey me?  Please answer step by step.<|im_end|>

Gratitude

• This model was made possible by the generous sponsorship of a16z.
• Thank you to Microsoft for authoring the Orca paper and inspiring this work.
• Special thanks to WingLian, and TheBloke for helpful advice
• Thank you to all the other people in the Open Source AI community who have taught me and helped me along the way.

Example Output

Buy me a coffee