Instructions to use TheDrummer/Skyfall-31B-v4-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TheDrummer/Skyfall-31B-v4-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="TheDrummer/Skyfall-31B-v4-GGUF",
	filename="Skyfall-31B-v4j-Q2_K.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use TheDrummer/Skyfall-31B-v4-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Skyfall-31B-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/Skyfall-31B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Skyfall-31B-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/Skyfall-31B-v4-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M

Use Docker

docker model run hf.co/TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use TheDrummer/Skyfall-31B-v4-GGUF with Ollama:
```
ollama run hf.co/TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M
```

Unsloth Studio new

How to use TheDrummer/Skyfall-31B-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/Skyfall-31B-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/Skyfall-31B-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/Skyfall-31B-v4-GGUF to start chatting

Docker Model Runner
How to use TheDrummer/Skyfall-31B-v4-GGUF with Docker Model Runner:
```
docker model run hf.co/TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M
```

Lemonade

How to use TheDrummer/Skyfall-31B-v4-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull TheDrummer/Skyfall-31B-v4-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Skyfall-31B-v4-GGUF-Q4_K_M

List all available models

lemonade list

BeaverAI

More than 7000 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

Thank you to everyone who subscribed through Patreon. Your support helps me chug along in this brave new world.

FAQ for those out-of-the-loop

🐶 Who is Drummer?

Hi! I'm Drummer. I'm a Software Engineer with experience in JavaScript, Golang, Python, and generally engineering the crap out of things.

Why I'm in the AI space:

Exploration: Everyone is trying to figure out how AI works and what it's capable of. I am too - just not in creating the smartest, safest model at all costs.
Upskill: The world is headed towards AI. It is here to stay. This has been my way of brushing up in this new form of computing.
Value: I yearn to create value. I feel satisfaction and fulfillment in providing something meaningful for others.
Fun: It's just fun using and making models. It's also fun coming up with theories and realizing them in practice (training AI).

I started my tuning venture back in mid-2024 when I wanted to improve its literary capabilities. I've come a long way since then and I have branched out and specialized.

Foundational models today are optimized for non-creative uses, and I believe there is a place for AI in creativity and entertainment.

I am here to take the road less traveled by.

❓ What are my models like?

Bottomline: My models are usually geared towards creativity (writing & interactivity), usability (no censorship & overalignment), and entertainment!

While intelligence, correctness, and problem solving are not my priority, they are still one of many qualities I want in my models.

The primary goal is to enhance the experience for users looking to use models for creative uses.

The subqualities I look for are the following:

Alignment: How far off is it from being a goody, syncopathic assistant-writer?
Writing: Does it string together words and sentences in a pleasant & effective way like a wordsmith?
Dynamism: How good is the AI at being compelling and intriguing in its storytelling?
Adherence: Is it sticking to the prompt?
Knowledge: Does it know about the world in both its truths and stories told?
Intelligence: Can it handle nuance, complexity, and logic?
Formatting: Is it biased towards writing paragraphs / lists or can it come up with its own?

If it doesn't excel in one of these qualities, or if it's overall mediocre for its size, then I would most likely reiterate until I get something right.

🦫 What is BeaverAI?

BeaverAI is a Discord server.

Drummer proudly presents...

Skyfall 31B v4 🌠

Usage

Mistral v7 Tekken

Description

Skyfall 31B v4 is an upscaled version of Mistral Small 3.2 2507, now more efficient and creative!

Oooh damn, nailing the isekai card, coming up with military gear and everything. It seems a little more pliable and willing to go along with sudden changes in mood (grounded -> fantasy, or wholesome -> spicy).

Damn, it be cooking

The slop is amazingly low. Its the only model I've seen pull parts of context from like 3 exchanges before.

its really good, i use it for rp, chat, instructions, deep thoughts, goofy uncensored stuff

Oh my. This one is a [redacted]'s delight.

I find it funny that the tail is now a question mark.

Audrey told me the craziest thing she did was go on a blind date with a guy who had the same name as her pet hampster and all she could do was imagine the guy as a hampster in flannel. And if thats not agi idk what is

I really liked the 3rd person storywriting capability of this one. I ran a .7 temp and found it to be creative enough but not so much in lost track of the ability to describe a situation intelligently and character reactions and behaviors were always appropriate to either the card or specific prompting. This one reminded me a lot of the last Cydonia, and I think I like the writing on this one just a tad more but hard to explain why, they are both quite good models for sophisticated long form erp, imho.

Special Thanks

config-v4j

Downloads last month: 378

GGUF

Model size

31B 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
/

Skyfall-31B-v4-GGUF