Magpie 13b

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. Click here for gguf quants. Massive thanks to TheBloke for the GPTQ version.

Prompt template: Alpaca

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

### Instruction:
{prompt}

### Response:

My SillyTavern instruct mode prompt:

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:

Chronos 13b
Nous Hermes L2 13b
OrcaPlatypus2 13b
Spicyboros 2.2 13b
Kimiko v2 13b Lora
limarp L2 v2 13b Lora