MN-Hecate-Chthonia-12B Open-Source Language Model - Integrating the Advantages of Multiple Models to Assist Inference and Psychological Tasks

MN Hecate Chthonia 12B

Developed by mergekit-community

This is a 12B-parameter language model merged using the mergekit tool, combining the strengths of multiple specialized models with a focus on reasoning and psychology-related tasks.

Large Language Model

Transformers

#Multi-domain reasoning #Psychology enhancement #Literary creation optimization

Downloads 23

Release Time : 3/16/2025

Model Overview

This model is created by merging multiple 12B-parameter models, aiming to enhance performance in reasoning, psychological analysis, and general language understanding.

Model Features

Multi-model advantage fusion

Integrates the strengths of multiple specialized models, including reasoning capabilities, psychological analysis, and creative text generation

Enhanced reasoning ability

Specifically strengthened logical reasoning and psychological analysis capabilities

Flexible dialogue capability

Supports multiple dialogue templates, including chatml format

Model Capabilities

Text generation

Logical reasoning

Psychological analysis

Creative writing

Multi-turn dialogue

Use Cases

Psychological research

Mental state analysis

Analyze psychological states and emotional tendencies in text

Can provide professional psychological perspective analysis

Education

Logical reasoning training

Generate logical reasoning exercises and explanations

Helps students improve logical thinking skills

Creative writing

Story generation

Generate creative stories based on prompts

Can produce diverse styles of creative texts

🚀 Model Merge Project

This project is about merging pre - trained language models, aiming to combine the strengths of multiple models to create a more powerful and versatile language model.

🚀 Quick Start

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

📚 Documentation

Merge Details

Merge Method

This model was merged using the Model Stock merge method using mistralai/Mistral-Nemo-Instruct-2407 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

dtype: float32
out_dtype: bfloat16
merge_method: model_stock
base_model: mistralai/Mistral-Nemo-Instruct-2407
models:
  - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
    parameters:
      weight: 0.8
  - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS
    parameters:
      weight: 0.8
  - model: LatitudeGames/Wayfarer-12B
    parameters:
      weight: 0.6
  - model: mergekit-community/MN-Anathema-12B
  - model: mergekit-community/MN-Chthonia-12B
    parameters:
      weight: 1.1
  - model: mergekit-community/MN-Nyx-Chthonia-12B
    parameters:
      weight: 1.4
  - model: mergekit-community/MN-Sappho-n2-12B+jtatman/mistral_nemo_12b_reasoning_psychology_lora
    parameters:
      weight: 0.8
  - model: mistralai/Mistral-Nemo-Base-2407
    parameters:
      weight: 0.4
  - model: redrix/sororicide-12B-Farer-Mell-Unslop
  - model: yamatazen/EtherealAurora-12B-v2

tokenizer:
  source: union
  tokens:
    "<|im_start|>":
      source: mergekit-community/MN-Nyx-Chthonia-12B
    "<|im_end|>":
      source: mergekit-community/MN-Nyx-Chthonia-12B
    "[INST]":
      source: mistralai/Mistral-Nemo-Instruct-2407
    "[/INST]":
      source: mistralai/Mistral-Nemo-Instruct-2407
      
chat_template: chatml

Model Information

Property	Details
Base Models	mergekit-community/MN-Sappho-n2-12B, jtatman/mistral_nemo_12b_reasoning_psychology_lora, LatitudeGames/Wayfarer-12B, mergekit-community/MN-Nyx-Chthonia-12B, DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS, DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS, mergekit-community/MN-Chthonia-12B, mistralai/Mistral-Nemo-Instruct-2407, redrix/sororicide-12B-Farer-Mell-Unslop, mistralai/Mistral-Nemo-Base-2407, yamatazen/EtherealAurora-12B-v2, mergekit-community/MN-Anathema-12B
Library Name	transformers
Tags	mergekit, merge

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