not-for-all-audiences

<center><h1>Magpie 13b</h1></center>

Magpie-13b is a Llama 2 merge made specifically for SillyTavern roleplays. This is the final result of approximately 2 weeks of merging and testing, and in my opinion it is the most complementary 13b merge of the included models/loras for this use-case.

This repo is for the full model weights. <a href="https://huggingface.co/boomerchan/Magpie-13b-GGUF">Click here for gguf quants</a>. Massive thanks to TheBloke for the <a href="https://huggingface.co/TheBloke/Magpie-13B-GPTQ">GPTQ version</a>.

<h2>Prompt template: Alpaca</h2>

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{prompt}

### Response:

<h2>My SillyTavern instruct mode prompt:</h2>

Write an engaging response from {{char}} to {{user}} in a descriptive writing style. Express {{char}}'s actions and sensory perceptions in vivid detail. Proactively advance the conversation with narrative prose as {{char}}. Use informal language when composing dialogue, taking into account {{char}}'s personality and communication style.

### Instruction:
{prompt}

### Response:

I have included 2 .json files in this repo. Magpie.json is an instruct mode preset which you can import into SillyTavern VIA the AI Response Formatting tab. Magpie (Spicy).json is a sampler preset for Oobabooga which you can import into SillyTavern VIA the AI Response Configuration tab. If you have any questions, please direct them to the SillyTavern Discord server. glhf <3

Model weights included in this merge: