Instructions to use TheDrummer/Cydonia-24B-v4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use TheDrummer/Cydonia-24B-v4-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheDrummer/Cydonia-24B-v4-GGUF with Ollama:
```
ollama run hf.co/TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M
```

Unsloth Studio

How to use TheDrummer/Cydonia-24B-v4-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TheDrummer/Cydonia-24B-v4-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for TheDrummer/Cydonia-24B-v4-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for TheDrummer/Cydonia-24B-v4-GGUF to start chatting

Docker Model Runner
How to use TheDrummer/Cydonia-24B-v4-GGUF with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M
```

Lemonade

How to use TheDrummer/Cydonia-24B-v4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Cydonia-24B-v4-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Cydonia-24B-v4-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

BeaverAI

More than 6000 members strong 💪 A hub for users and makers alike!

Drummer is open for work / employment (I'm a Software Engineer). Contact me through any of these channels: https://linktr.ee/thelocaldrummer

Drummer proudly presents...

Cydonia 24B v4 💿

Usage

Mistral v7 Tekken
Alpaca (maybe)
Metharme (maybe)

Description

Cydonia 24B v4 is a wordy and thick model with a novel style. It's got a distinct flair for making scenarios feel more fleshed out without being excessively flowery or taking control away from you. It's good at long-form storytelling with weighty prose when acting as a Narrator or Dungeon Master. As an assistant or coding tool, it performs admirably.

very descriptive and good at pulling details from the character card. gave great results on a couple cards I had been struggling to make work. my favorite cydonia since 1.3.

This model absolutely hit the nail in character reference. 70Bs couldn't get it right in 8 retries.

i fucking love this.

Special Thanks

This Cydonia release is dedicated to Cydonia 22B v1.0’s biggest fan and our most beloved Beaver, SleepDeprived.

The Beaver community will miss you, your Broken Tutu, and the countless character cards you’ve made.

You can find his work here: https://huggingface.co/collections/ReadyArt/sleeps-collection-687819b94f11b92759e10eae

I had known Sleepy for several months, but it feels much longer than that. During that time, he was many things to me: a damned good finetuner, a mentor, a partner. But above all else, he was my friend. May you rest well in the peace of your eternal slumber forevermore.

I never had that real of a talk with him. but he was a very good and genuine guy. He even helped in my own faith. I hope he has found his peace wherever he is.

The dude got me motivated to train models and crap, so kudos. I wasn’t even interested in that before. I'm going to make a model (in my own time) and release it on HF! Great guy all around, really. I can’t think of a negative thing about him tbh.

I didn't have a personal relationship with sleep, but I will always cherish watching him transform from one of our average degens into the creative, inspiring mentor he became in the Beaver server. I think he was one of the key players in helping our community grow into a space for beginning creators from Character Card building to LLM finetuning. He had a knack for helping people step out of their comfort zones to try something new. I look forward to watching his memory live on in the cards and tunes others create with his knowledge and skills he so freely shared.

It was great to interact with him and help him figure all this stuff out. Really happy to see that his work became so popular because of it. He put in a lot of effort to understanding things and more than that, making tools to help others too (even though he was still learning himself). It's the kind of attitude I love to see and I think it's great that he put so much effort into it, both learning something new and teaching it to others, when he knew that his time was limited. Plus, it was great to just joke around with him sometimes. Real easy fellow to talk to. I'm not surprised he made so many friends while here. 

He was a great guy, and contributed a lot to this community. I enjoy his character cards, and I will continue to play them, now having him in my thoughts. I am glad I was able to see some of his streams and hear his voice. There are a lot of people we know only as nicknames but we've never seen them or heard their voices. RIP Sleep Deprived! I will miss you! 

His character was always one of a positive quality, and one that remained strong and steadfast even with his prognosis looking grim. He brought a very welcoming and encompassing quality to this community, and his absence will greatly be felt for a long time to come. His cards were varied and interesting, and his last fine tuning endeavours serve as an inspiration for those wanting to get into the space. On the off chance he's OK, I hope he manages to recover. Otherwise, I hope he manages to find the peace that's evaded him for so long.

ReadyArt's Official Tsundere Catgirl Mascot was unable to write a proper quote or was too shy doing it, but will still miss Sleepy.

config-v4h

Downloads last month: 3,785

GGUF

Model size

24B params

Architecture

llama

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

TheDrummer
/

Cydonia-24B-v4-GGUF