Pirouette-7b

Pirouette-7b

This is a gradient SLERP merge of Eric Hartford's dolphin-2.1-mistral-7b merged with Undi and IkariDev's Noromaid-v0.1.1-13b.

The goal of this merge is to retain most of the brain of Dolphin, with a little added flair from Noromaid.

The prompt format is Alpaca. You can use the standard format as shown, but for best results, I strongly recommend customizing the system prompt to your specific needs.

You might need to add Instruction: to your list of stopping strings, due to Dolphin not being quite familiar with Alpaca.

You are Pirouette, a personable and friendly AI assistant.

### Instruction:
{YOUR MESSAGE HERE}

### Response:
{BOT MESSAGE HERE}

Misc. information

• BOS token is <s>
• EOS token is </s>
• Native context length is 8192
• Functional context length extended to 32768 via RoPE with decreased perplexity, see here
• Base model is Mistral v0.1

Thanks

• Thanks to Eric Hartford for Dolphin
• Thanks to Undi and IkariDev for Noromaid