MN-Violet-Lotus-12B Open-Source Large Language Model - Supports Role-Playing and Creative Writing, Excels in Emotional Intelligence Performance

MN Violet Lotus 12B

Developed by FallenMerick

MN-Violet-Lotus-12B is a 12B-parameter large language model based on the merging of multiple high-quality models, specializing in roleplay and creative writing with outstanding emotional intelligence performance and broad character adaptability.

Large Language Model

Transformers

English#High EQ Roleplay #Creative Writing Optimization #Multi-style Fusion

Downloads 247

Release Time : 11/16/2024

Model Overview

This model is created by merging several high-quality models, excelling particularly in roleplay and creative writing, capable of adapting to various character personalities while maintaining high emotional intelligence output.

Model Features

High Emotional Intelligence Performance

Scored 80.00 (8-bit precision) in local EQ benchmark tests, demonstrating excellent performance.

Exceptional Roleplay Capabilities

Capable of adapting to a wide range of character personalities, producing text that aligns with character settings.

Creative Writing Advantages

Performs exceptionally well in creative writing tasks such as story creation and text adventures.

Concise Output

Avoids overly verbose output through model merging strategies.

Model Capabilities

Story creation

Text adventures

Creative writing

Novel writing

Roleplay

Text generation

Use Cases

Creative Writing

Story Creation

Generate coherent and creative storylines and character dialogues

Produces engaging narrative content

Novel Writing

Assist writers in novel creation by providing plot development and character setting suggestions

Enhances creative efficiency and quality

Roleplay

Interactive Roleplay

Generate dialogues and reactions that fit character settings in roleplaying games

Provides immersive roleplay experiences

Character Background Creation

Create detailed character backgrounds and personality traits for games or stories

Generates diverse and rich character settings

🚀 MN-Violet-Lotus-12B

This is a pre - trained language model that excels in storywriting, text adventure, and role - playing. It offers high - quality creative outputs while adhering to a wide range of character personalities.

🚀 Quick Start

This is the model I was trying to create when Chunky-Lotus emerged. Not only does this model score higher on my local EQ benchmarks (80.00 w/ 100% parsed @ 8 - bit), but it does an even better job at roleplaying and producing creative outputs while still adhering to wide ranges of character personalities. The high levels of emotional intelligence are really quite noticeable as well.

Once again, models tend to score higher on my local tests when compared to their posted scores, but this has become the new high score for models I've personally tested.

I really like the way this model writes, and I hope you'll enjoy using it as well!

📦 GGUF Quants

https://huggingface.co/backyardai/MN-Violet-Lotus-12B-GGUF
https://huggingface.co/mradermacher/MN-Violet-Lotus-12B-GGUF
https://huggingface.co/mradermacher/MN-Violet-Lotus-12B-i1-GGUF

✨ Recommended ST Settings

Special thanks to @Zeldazachman for these amazing ST settings that I now wholeheartedly recommend!

🔧 Technical Details

📄 Model Information

Property	Details
Model Type	MN-Violet-Lotus-12B
Base Model	mistralai/Mistral-Nemo-Instruct-2407, Epiculous/Violet_Twilight-v0.2, NeverSleep/Lumimaid-v0.2-12B, flammenai/Mahou-1.5-mistral-nemo-12B, Sao10K/MN-12B-Lyra-v4
Library Name	transformers
Tags	storywriting, text adventure, creative, story, writing, fiction, roleplaying, rp, mergekit, merge
License	cc-by-4.0

🔀 Merge Details

This is a merge of pre - trained language models created using mergekit.

Merge Method

This model was merged using the Model Stock merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: FallenMerick/MN-Twilight-Maid-SLERP-12B #(unreleased)
  - model: Sao10K/MN-12B-Lyra-v4
  - model: flammenai/Mahou-1.5-mistral-nemo-12B
merge_method: model_stock
base_model: mistralai/Mistral-Nemo-Instruct-2407
parameters:
  normalize: true
dtype: bfloat16

In this recipe, Violet Twilight and Lumimaid were first blended using the SLERP method to create a strong roleplaying foundation. Lyra v4 is then added to the mix for its great creativity and roleplaying performance, along with Mahou to once again curtail the outputs and prevent the resulting model from becoming too wordy. Model Stock was used for the final merge in order to really push the resulting weights in the proper direction while using Nemo Instruct as a strong anchor point.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご