PocketDoc_Dans-PersonalityEngine Open Source Large Model - Suitable for Multilingual and Multi-Scenario Task Creation

Pocketdoc Dans PersonalityEngine V1.3.0 24b GGUF

Developed by bartowski

A multilingual, multi-purpose large language model supporting various professional domains and general tasks, suitable for role-playing, story creation, programming, and other scenarios.

Large Language Model Open Source License:Apache-2.0 #Multi-domain text generation #High-precision quantization #Role-playing optimization

Downloads 2,543

Release Time : 5/23/2025

Model Overview

Dans-PersonalityEngine is a 24B-parameter large language model supporting multiple languages and professional domains, including programming, law, medicine, finance, etc. The model is quantized for efficient operation on various hardware.

Model Features

Multilingual support

Supports 9 languages, including English, Arabic, German, French, Spanish, Hindi, Portuguese, Japanese, and Korean.

Multi-domain applicability

Covers general purposes, role-playing, story creation, chemistry, biology, programming, climate, law, medicine, finance, and more.

Efficient quantization

Offers various quantization versions, from BF16 to ultra-low-bit quantization, adapting to different hardware needs and optimizing operational efficiency.

Extensive dataset

Trained on multiple high-quality datasets, including PocketDoc and AquaV series datasets, covering diverse application scenarios.

Model Capabilities

Text generation

Role-playing

Story creation

Programming assistance

Legal consultation

Medical Q&A

Financial analysis

Multilingual translation

Use Cases

Creative writing

Story creation

Generate coherent and creative story content

High-quality story text suitable for novels, scripts, etc.

Role-playing

Simulate dialogues and behaviors of different characters

Vivid character interaction experiences

Professional domains

Programming assistance

Generate code snippets or solve programming problems

Accurate code examples and solutions

Legal consultation

Provide legal-related information and advice

Professional legal knowledge responses

Education

Math problem-solving

Solve math problems and provide step-by-step solutions

Clear math problem-solving processes

Science Q&A

Answer questions in scientific fields like chemistry and biology

Accurate professional knowledge responses

🚀 Llamacpp imatrix Quantizations of Dans-PersonalityEngine-V1.3.0-24b by PocketDoc

This project provides Llama.cpp imatrix quantizations of the Dans-PersonalityEngine-V1.3.0-24b model by PocketDoc. It supports multiple languages and has a wide range of applications in various fields.

🚀 Quick Start

Quantization Details

Using llama.cpp release b5466 for quantization. The original model can be found at https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.3.0-24b. All quants are made using the imatrix option with the dataset from here.

Running the Model

LM Studio: You can run the quantized models in LM Studio.
llama.cpp: Run them directly with llama.cpp, or any other llama.cpp based project.

✨ Features

Supported Languages

Datasets

The model is trained on a large number of datasets, including:

PocketDoc/Dans-Prosemaxx-RP
PocketDoc/Dans-Personamaxx-Logs-2
... (full list in the original document)

📚 Documentation

Prompt Format

[gMASK]<sop><|system|>{system_prompt}<|endoftext|><|user|>{prompt}<|endoftext|><|assistant|>

Download Information

Download a file (not the whole branch) from below:

Filename	Quant type	File Size	Split	Description
Dans-PersonalityEngine-V1.3.0-24b-bf16.gguf	bf16	47.15GB	false	Full BF16 weights.
Dans-PersonalityEngine-V1.3.0-24b-Q8_0.gguf	Q8_0	25.05GB	false	Extremely high quality, generally unneeded but max available quant.
... (full table in the original document)	...	...	...	...

Embed/output weights

Some of these quants (Q3_K_XL, Q4_K_L etc) are the standard quantization method with the embeddings and output weights quantized to Q8_0 instead of what they would normally default to.

Downloading using huggingface-cli

Click to view download instructions

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF --include "PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download bartowski/PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-GGUF --include "PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0/*" --local-dir ./

You can either specify a new local-dir (PocketDoc_Dans-PersonalityEngine-V1.3.0-24b-Q8_0) or download them all in place (./)

ARM/AVX information

Previously, you would download Q4_0_4_4/4_8/8_8, and these would have their weights interleaved in memory in order to improve performance on ARM and AVX machines by loading up more data in one pass.

Now, however, there is something called "online repacking" for weights. details in this PR. If you use Q4_0 and your hardware would benefit from repacking weights, it will do it automatically on the fly.

As of llama.cpp build b4282 you will not be able to run the Q4_0_X_X files and will instead need to use Q4_0.

Additionally, if you want to get slightly better quality, you can use IQ4_NL thanks to this PR which will also repack the weights for you.

📄 License

This project is licensed under the apache-2.0 license.

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